\\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Thrower\\nCourt: U.S. Court of Appeals for the Second Circuit\\nDate decided: 2019-01-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n17‐445‐pr \\nUnited States v. Thrower \\n \\n UNITED STATES COURT OF APPEALS \\n FOR THE SECOND CIRCUIT \\n ______________ \\n \\n August Term, 2017 \\n \\n (Submitted: April 19, 2018 Decided: January 31, 2019) \\n \\n Docket No. 17‐445‐pr \\n ____________ \\n \\n UNITED STATES OF AMERICA, \\n \\n Petitioner‐Appellee, \\n \\n –v.– \\n \\n WILLIAM THROWER, \\n \\n Respondent‐Appellant. *\\n \\n ______________ \\n \\n \\n ON APPEAL FROM THE UNITED STATES DISTRICT COURT FOR THE \\n EASTERN DISTRICT OF NEW YORK \\n \\nBefore: \\n WESLEY and CHIN, Circuit Judges, and COTE, District Judge.† \\n\\n\\n* The Clerk of the Court is directed to amend the caption as set forth above. \\n Judge Denise Cote, of the United States District Court for the Southern District of New \\n†\\n\\nYork, sitting by designation. \\n\\f The Government appeals from a judgment of the United States District \\nCourt for the Eastern District of New York (Ross, J.) reducing the defendant’s \\nsentence from 180 months to 120 months and ordering his immediate release on \\ntime served. The Government argues that the district court erred in concluding \\nthat the defendant’s prior convictions for the New York offenses of robbery in the \\nthird degree and attempted robbery in the third degree do not qualify as predicate \\n“violent felonies” under the Armed Career Criminal Act, 18 U.S.C. § 924(e)(1). \\n We agree with the Government. Accordingly, we REVERSE the district \\ncourt’s grant of Thrower’s § 2255 petition, VACATE the amended judgment, and \\nREMAND for the district court to reinstate Thrower’s original sentence. \\n ______________ \\n \\n Amy Busa, Alexander Mindlin, Assistant United States \\n Attorneys, for Richard P. Donoghue, United States \\n Attorney for the Eastern District of New York, for \\n Appellant. \\n \\n Jane Simkin Smith, Millbrook, NY, for Defendant‐\\n Appellee. \\n \\n ______________ \\n \\nPER CURIAM: \\n\\n The Government appeals from a February 13, 2017 judgment of the United \\n\\nStates District Court for the Eastern District of New York (Ross, J.) reducing \\n\\ndefendant William Thrower’s sentence from 180 months to 120 months and \\n\\nordering Thrower’s immediate release on time served. The Government argues \\n\\nthat the district court erred in concluding that Thrower’s prior convictions for the \\n\\nNew York offenses of robbery in the third degree and attempted robbery in the \\n\\n\\n 2 \\n\\fthird degree do not qualify as predicate “violent felonies” under the Armed Career \\n\\nCriminal Act (“ACCA”), 18 U.S.C. § 924(e)(1), an enhancement that mandates a \\n\\nminimum sentence of 180 months. \\n\\n We agree with the Government. Accordingly, we REVERSE the district \\n\\ncourt’s grant of Thrower’s § 2255 petition, VACATE the amended judgment, and \\n\\nREMAND for the district court to reinstate Thrower’s original sentence. \\n\\n\\n BACKGROUND \\n\\n In 2005, William Thrower was convicted of possessing a firearm while \\n\\npreviously having been convicted of a “violent felony,” in violation of 18 U.S.C. \\n\\n§ 922(g)(1). A conviction under § 922(g)(1) carries a mandatory‐minimum sentence \\n\\nof 120 months. During sentencing in 2008, the district court additionally found that \\n\\nThrower qualified as an “armed career criminal” under ACCA, 18 U.S.C. \\n\\n§ 924(e)(1), which mandates a minimum sentence of 180 months for anyone \\n\\nconvicted of § 922(g)(1) who also has three prior “violent felony” convictions. The \\n\\ndistrict court noted that Thrower’s criminal history included the following felony \\n\\noffenses: (1) a 1981 conviction for first‐degree robbery, N.Y. Penal Law § 160.15; \\n\\n(2) a 1981 conviction for third‐degree burglary, N.Y. Penal Law § 140.20; (3) a 1993 \\n\\nconviction for fourth‐degree larceny, N.Y. Penal Law § 155.30; (4) a 1994 conviction \\n\\n 3 \\n\\ffor attempted third‐degree robbery, N.Y. Penal Law §§ 160.05 and 110.00; and (5) \\n\\na 2000 conviction for third‐degree robbery, N.Y. Penal Law § 160.05. Without \\n\\nspecifying which of Thrower’s prior convictions constituted the three predicate \\n\\n“violent felonies” or which ACCA clause(s)—the force clause, the enumerated‐\\n\\noffenses clause, or the residual clause—it relied upon in determining that the \\n\\nconvictions so qualified, the district court found Thrower subject to the ACCA \\n\\nenhancement and consequently sentenced him to 180 months’ incarceration. \\n\\n The Supreme Court subsequently struck down ACCA’s residual clause as \\n\\nunconstitutionally vague, Johnson v. United States, 135 S. Ct. 2551, 2557 (2015) \\n\\n(“Johnson II”); see also Welch v. United States, 136 S. Ct. 1257, 1265 (2016) (holding \\n\\nthat Johnson II applies retroactively), calling into question Thrower’s sentence. \\n\\nConsequently, Thrower challenged the ACCA enhancement in a 28 U.S.C. § 2255 \\n\\npetition for a writ of habeas corpus, which the district court granted.1 The district \\n\\ncourt agreed with Thrower that neither New York robbery in the third degree nor \\n\\nNew York attempted robbery in the third degree qualifies as a “violent felony” \\n\\n\\n1 In adjudicating Thrower’s petition under § 2255, the district court concluded that when \\nsentencing Thrower in 2008, it had relied, at least in part, on the now‐unconstitutional \\nresidual clause to determine that ACCA’s mandatory sentencing provision applied. It \\ntherefore analyzed anew whether at least three of Thrower’s prior convictions qualified \\nunder the two remaining ACCA clauses. Because they did not, the district court found \\nthat the prior error was prejudicial. \\n 4 \\n\\funder ACCA’s force clause.2 Because the Government no longer claimed that \\n\\nfourth‐degree larceny qualified without the residual clause, only two of Thrower’s \\n\\nprior convictions remained as potential ACCA predicates—a number insufficient \\n\\nto subject him to the ACCA enhancement. Seeing, therefore, no need to determine \\n\\nwhether first‐degree robbery or third‐degree burglary qualifies as a “violent \\n\\nfelony,” the district court ordered Thrower immediately released on time served. \\n\\n The Government timely appealed, arguing that because robbery in the first \\n\\nand third degrees and attempted robbery in the third degree qualify as ACCA \\n\\npredicates, the district court erred in granting Thrower’s § 2255 petition. \\n\\n\\n DISCUSSION \\n\\n We review de novo whether the offenses of New York robbery in the first and \\n\\nthird degrees and attempted robbery in the third degree qualify as ACCA “violent \\n\\nfelonies.” See United States v. Brown, 629 F.3d 290, 293 (2d Cir. 2011) (per curiam). \\n\\nThey do. \\n\\n \\n\\n \\n\\n\\n\\n2 The Government did not contend that either offense satisfies the requirements of the \\nenumerated‐offenses clause. \\n 5 \\n\\f 1. Armed Career Criminal Act \\n\\n ACCA mandates a minimum 180‐month term of imprisonment for any \\n\\nperson convicted of possessing a firearm in violation of 18 U.S.C. § 922(g)(1) who \\n\\nalso has three prior “violent felony” convictions. Id. § 924(e)(1). Under the force \\n\\nclause, a “violent felony” is “any crime punishable by imprisonment for a term \\n\\nexceeding one year, . . . that . . . has as an element the use, attempted use, or \\n\\nthreatened use of physical force against the person of another.” Id. § 924(e)(2)(B)(i). \\n\\nAs the Supreme Court has explained, “‘physical force’ means violent force—that \\n\\nis, force capable of causing physical pain or injury to another person.” Johnson v. \\n\\nUnited States, 559 U.S. 133, 140 (2010) (“Johnson I”) (emphasis in original); see also \\n\\nStokeling v. United States, 139 S. Ct. 544, 554 (2019) (explaining that “Johnson [I] . . . \\n\\ndoes not require any particular degree of likelihood or probability that the force \\n\\nused will cause physical pain or injury; only potentiality”). \\n\\n Courts apply a “categorical approach” to determine whether a prior \\n\\nconviction qualifies as a “violent felony.” See, e.g., United States v. Hill, 890 F.3d 51, \\n\\n55–56 (2d Cir. 2018). Under the categorical approach, “courts identify ‘the \\n\\nminimum criminal conduct necessary for conviction under a particular statute.’” \\n\\n \\n\\n\\n 6 \\n\\fId. at 55 (quoting United States v. Acosta, 470 F.3d 132, 135 (2d Cir. 2006) (per \\n\\ncuriam)). In so doing, they “look only to the statutory definitions—i.e., the \\n\\nelements—of the offense, and not to the particular underlying facts.” Id. (quoting \\n\\nDescamps v. United States, 570 U.S. 254, 261 (2013) (alterations omitted)). If the state‐\\n\\nlaw offense categorically requires the elements listed in § 924(e)(2)(B)(i), it may \\n\\nserve as a predicate “violent felony.” \\n\\n 2. New York Robbery in the First and Third Degrees \\n\\n Thrower argues that the New York offense of robbery in the third degree \\n\\ndoes not qualify as a “violent felony” because the requisite force for the offense \\n\\n“can be something less than ‘force capable of causing physical pain or injury.’” \\n\\nAppellee Br. 17 (quoting Johnson I, 599 U.S. at 140). We disagree. \\n\\n The New York offense of robbery in the third degree occurs when a person \\n\\n“forcibly steals property.” N.Y. Penal Law § 160.05. Forcible stealing—common to \\n\\nevery degree of robbery in New York State3—is defined as: \\n\\n when, in the course of committing a larceny, [a person] uses or \\n threatens the immediate use of physical force upon another person \\n for the purpose of: 1. Preventing or overcoming resistance to the \\n taking of the property or to the retention thereof immediately after \\n the taking; or 2. Compelling the owner of such property or another \\n\\n\\n3 See N.Y. Penal Law § 160.05; id. § 160.10; id. § 160.15; see also People v. Miller, 87 N.Y.2d \\n211, 214 (1995) (“The essence of the [New York] crime of robbery is forcible stealing.”). \\n 7 \\n\\f person to deliver up the property or to engage in other conduct which \\n aids in the commission of the larceny. \\n \\nId. § 160.00. \\n\\n By its plain language, the New York robbery statute matches the ACCA \\n\\ndefinition of a “violent felony.” Predicate offenses under ACCA include those that \\n\\nhave as an element “the use . . . or threatened use of physical force.” 18 U.S.C. § \\n\\n924(e)(2)(B)(i). New York requires the “use[] or threaten[ed] . . . immediate use of \\n\\nphysical force.” Additionally, the New York robbery statute, like ACCA’s force \\n\\nclause, is modeled on the common law definition of robbery. As the Supreme \\n\\nCourt recently explained in Stokeling, “the term ‘physical force’ in ACCA \\n\\nencompasses the degree of force necessary to commit common‐law robbery,” \\n\\ndefined as “the amount of force necessary to overcome a victim’s resistance.” \\n\\nStokeling, 139 S. Ct. at 555. Like the Florida robbery statute at issue in Stokeling, the \\n\\nNew York robbery statute uses the term “physical force.” The New York Court of \\n\\nAppeals has explained that “if a statute uses a word which has a definite and well‐\\n\\nknown meaning at common law, it will be construed with the aid of common‐law \\n\\ndefinitions, unless it clearly appears that it was not so intended.” People v. King, 61 \\n\\nN.Y.2d 550, 554–55 (1984). Far from evincing a clear intent to stray from the \\n\\ncommon law understanding of robbery, the robbery statute explicitly incorporates \\n\\n 8 \\n\\fthe common law definition by explaining that “physical force” means enough \\n\\nforce to “[p]revent[] or overcom[e] resistance to the taking . . . or . . . [to c]ompel[] \\n\\nthe owner . . . to deliver up the property.” N.Y. Penal Law § 160.00; see also People \\n\\nv. Jurgins, 26 N.Y.3d 607, 614 (2015). \\n\\n None of the cases to which Thrower cites convince us that New York courts \\n\\ninterpret the force required for New York robbery as less than that required under \\n\\nACCA. In People v. Lee, 197 A.D.2d 378 (1st Dep’t 1993), a New York intermediate \\n\\ncourt of appeals found the force element of § 160.05 satisfied where the defendant \\n\\n“bumped his unidentified victim, took money, and fled while another forcibly \\n\\nblocked the victim’s pursuit,” because the act of blocking was a form of \\n\\novercoming the victim’s resistance, id. at 378 (citing People v. Patton, 184 A.D.2d \\n\\n483, 483 (1st Dep’t 1992) (“[A]ct[ing] as a blocker [is a form of] overcoming the \\n\\nvictim’s resistance to the robbery within the meaning of Penal Law § 160.00(1).” \\n\\n(emphasis added))).4 Similarly, in People v. Safon, 166 A.D.2d 892 (4th Dep’t 1990), \\n\\n\\n\\n4 See also United States v. Pereira‐Gomez, 903 F.3d 155, 166 (2d Cir. 2018) (explaining that a \\n“’human wall’ [is] no mere obstacle to the victim’s pursuit of the robber; it constitute[s] a \\nthreat that pursuit would lead to a violent confrontation” and therefore holding that New \\nYork attempted robbery in the second degree qualifies as a “crime of violence” under the \\nidentically worded force clause of application note 1(B)(iii) to Section 2L1.2 of the 2014 \\nSentencing Guidelines); see also U.S.S.G. § 2L1.2 cmt. 1(B)(iii) (2014) (defining a “crime of \\nviolence” as having “as an element the use, attempted use, or threatened use of physical \\nforce against the person of another”). \\n 9 \\n\\fa New York intermediate appellate court affirmed a third‐degree robbery \\n\\nconviction where the evidence showed that the defendant and the victim “tugged \\n\\nat each other until defendant’s hand slipped out of the glove holding the money” \\n\\nbecause this “was sufficient to prove that defendant used physical force for the \\n\\npurpose of overcoming the victimʹs resistance to the taking,” id. at 893 (emphasis \\n\\nadded). \\n\\n We therefore conclude that the New York offense of robbery in the third \\n\\ndegree, which like every degree of robbery in New York requires the common law \\n\\nelement of “forcible stealing,” is a “violent felony” under ACCA. By extension, \\n\\nNew York robbery in the first degree is also a “violent felony” under ACCA.5 \\n\\n 3. New York Attempted Robbery in the Third Degree \\n\\n Thrower next argues that the New York offense of attempted robbery in the \\n\\nthird degree does not qualify as a “violent felony” because a person may be \\n\\nconvicted of attempted robbery by merely attempting to threaten to use physical \\n\\n\\n\\n5 Thrower argues that his conviction for first‐degree robbery does not qualify as an ACCA \\npredicate because he received a Certificate of Relief from Civil Disabilities from the State \\nof New York that restored his civil rights. Although Thrower is correct that a conviction \\nwith respect to which civil rights have been restored cannot serve as an ACCA predicate, \\nthis exception applies only where the Certificate does not prohibit the possession of \\nfirearms. See 18 U.S.C. § 921(a)(20). Thrower has not shown that his Certificate lacks such \\na prohibition. See United States v. Bullock, 550 F.3d 247, 250 (2d Cir. 2008). \\n 10 \\n\\fforce, falling short of the requirement of attempting to use physical force. We again \\n\\ndisagree. \\n\\n As above, the New York attempted robbery statute, by its own terms, \\n\\nmatches the ACCA definition of a “violent felony.” Predicate offenses under \\n\\nACCA include those that have as an element the “attempted use . . . of physical \\n\\nforce.” 18 U.S.C. § 924(e)(2)(B)(i). Under federal law, “[a] person is guilty of an \\n\\nattempt to commit a crime if he or she (1) had the intent to commit the crime, and \\n\\n(2) engaged in conduct amounting to a ‘substantial step’ towards the commission \\n\\nof the crime.” United States v. Martinez, 775 F.2d 31, 35 (2d Cir. 1985). \\n\\n New York requires that, “with intent to commit a crime . . . [a person] \\n\\nengage[] in conduct which tends to effect the commission of such crime.” N.Y. \\n\\nPenal Law § 110.00. The New York Court of Appeals has clarified that an attempt \\n\\nrequires that the action taken by an accused be “so near to its accomplishment that \\n\\nin all reasonable probability the crime itself would have been committed but for \\n\\ntimely interference.” People v. Rizzo, 246 N.Y. 334, 337 (1927); see also People v. \\n\\nDenson, 26 N.Y.3d 179, 189 (2015) (“[F]or a defendant to be guilty of an attempted \\n\\ncrime, the defendant must have engaged in conduct that came dangerously near \\n\\ncommission of the completed crime.” (quotation marks and citation omitted)). \\n\\n\\n 11 \\n\\fWhere a statute requires that a person be so “dangerously near” forcibly stealing \\n\\nproperty “that in all reasonable probability” she would have completed the \\n\\nrobbery but for interference, the statute categorically requires that a person take a \\n\\n“substantial step” toward the use of physical force. See People v. Acosta, 80 N.Y.2d \\n\\n665, 670 (1993) (explaining that New York’s attempt statute is “more stringent” \\n\\nthan the “‘substantial step’ test . . . adopted by [the Second Circuit]”); United States \\n\\nv. Farhane, 634 F.3d 127, 146 (2d Cir. 2011) (noting that the federal “substantial \\n\\nstep” test “ushered in a broader view of attempt” than that employed at common \\n\\nlaw). \\n\\n Nothing from New York’s courts leads us to conclude otherwise. Though \\n\\nThrower posits that a defendant might be convicted of attempted robbery in New \\n\\nYork for an attempt to threaten to use physical force—as distinct from an attempt \\n\\nto use physical force or a threat to use physical force—he fails to “at least point to \\n\\nhis own case or other cases in which the state courts in fact did apply the statute \\n\\nin the . . . manner for which he argues.”6 See Gonzales v. Duenas–Alvarez, 549 U.S. \\n\\n\\n\\n\\n6 Even if Thrower could cite to such an example, we would not come out differently on \\nthis issue. An attempt to threaten to use force by, for example, attempting to use a \\nthreatening note, itself constitutes a “threatened use of physical force.” \\n 12 \\n\\f183, 193 (2007). As such, we are left with the text of the New York attempted \\n\\nrobbery statute, which plainly matches ACCA’s definition of a “violent felony.” \\n\\n We therefore conclude that the New York offense of attempted robbery in \\n\\nthe third degree is a “violent felony” under ACCA. \\n\\n\\n CONCLUSION \\n\\n Robbery in the first and third degrees and attempted robbery in the third \\n\\ndegree, in violation of N.Y. Penal Law §§ 110.00, 160.05, 160.15, are “violent \\n\\nfelonies” under the force clause of ACCA. Because Thrower therefore has three \\n\\nqualifying “violent felony” convictions under ACCA, the district court erred by \\n\\nnot sentencing him to the applicable 180‐month mandatory minimum term of \\n\\nincarceration. \\n\\n We REVERSE the district court’s grant of Thrower’s § 2255 petition, \\n\\nVACATE the amended judgment, and REMAND for the district court to reinstate \\n\\nThrower’s original sentence. \\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":57,"cells":{"id":{"kind":"number","value":8443861,"string":"8,443,861"},"name":{"kind":"string","value":"United States v. William THROWER"},"name_abbreviation":{"kind":"string","value":"United States v. Thrower"},"decision_date":{"kind":"string","value":"2019-01-31"},"docket_number":{"kind":"string","value":"Docket No. 17-445-pr; August Term, 2017"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Second Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chin, Cote, Wesley\", \"parties\": \"\", \"opinions\": [{\"author\": \"PER CURIAM\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415288/\", \"author_raw\": \"PER CURIAM\"}]}"},"judge1":{"kind":"string","value":"CHIN"},"judge2":{"kind":"string","value":"COTE"},"judge3":{"kind":"string","value":"WESLEY"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443861/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. William THROWER\nCourt: U.S. Court of Appeals for the Second Circuit\nDate decided: 2019-01-31\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. William THROWER\\nCourt: U.S. Court of Appeals for the Second Circuit\\nDate decided: 2019-01-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":58,"cells":{"id":{"kind":"number","value":4578607,"string":"4,578,607"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Kevin Culley v. Cumberland Valley School Dist"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3800"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges (Opinion\", \"parties\": \"\", \"opinions\": [{\"author\": \"AMBRO, Circuit Judge\", \"type\": \"010combined\", \"text\": \"NOT PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-3800\\n ________________\\n\\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\\n\\n v.\\n\\n CUMBERLAND VALLEY SCHOOL DISTRICT,\\n\\n Appellant\\n ________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (D.C. Civil Action No. 1-15-cv-00857)\\n District Judge: Honorable John E. Jones, III\\n ________________\\n\\n Argued November 6, 2018\\n\\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\\n\\n (Opinion filed: December 20, 2018)\\n\\n\\nMark W. Cheramie Walz [Argued]\\nSweet, Stevens, Katz & Williams LLP\\n331 East Butler Avenue\\nP.O. Box 5069\\nNew Britain, PA 18901\\n Counsel for Appellant\\n\\nJudith A. Gran [Argued]\\nReisman Carolla & Gran LLP\\n19 Chestnut Street\\nHaddonfield, NJ 08033\\n\\fPhillip A. Drumheiser\\nP.O. Box 890\\nCarlisle, PA 17013\\n Counsel for Appellees\\n\\n ________________\\n\\n OPINION*\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\\n\\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\\n\\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\\n\\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\\n\\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\\n\\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\\n\\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\\n\\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\\n\\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\\n\\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\\n\\naffirm.\\n\\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\\n\\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\\n\\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\\n\\n\\n\\n*\\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\\nconstitute binding precedent.\\n 2\\n\\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\\n\\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\\n\\nsignificant turns for the worse. From seventh through tenth grade, when the incident\\n\\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\\n\\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\\n\\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\\n\\nabsent 43 times, or over 30% of the time.\\n\\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\\n\\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\\n\\nstating that J.C. should be allowed to cease activities during his physical education\\n\\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\\n\\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\\n\\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\\n\\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\\n\\nwith several friends, attempted to leave the school grounds during the day. The other\\n\\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\\n\\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\\n\\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\\n\\nhe required, his parents filed a due process complaint under the IDEA on January 29.\\n\\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\\n\\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\\n\\nbathroom, extra time to complete assignments, and the provision of class notes in case of\\n\\n 3\\n\\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\\n\\nshould receive homebound instruction for half of each school day, Cumberland tried to\\n\\nimplement this accommodation as well, but things did not go well. J.C. was rarely\\n\\npresent when the instructor arrived at his house, and even when present was not\\n\\nmotivated or cooperative. Id. at 107–116.\\n\\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\\n\\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\\n\\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\\n\\nnot have a “qualifying disability” and thus was not eligible for special education under\\n\\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\\n\\nCrohn’s disease was responsible for his difficulties in school, and that his condition\\n\\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\\n\\nthen requested an independent educational evaluation (IEE), which reached the opposite\\n\\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\\n\\nfound that he was eligible for special education under the IDEA and gave numerous\\n\\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\\n\\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\\n\\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\\n\\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\\n\\nadopted an individualized education program (IEP) for J.C. to provide special education\\n\\nunder the IDEA. Id. at 249–279.\\n\\n\\n\\n 4\\n\\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\\n\\nand issued his decision in February 2015. He found that J.C. was not eligible for special\\n\\neducation under the IDEA because, even though Crohn’s disease was a qualifying\\n\\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\\n\\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\\n\\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\\n\\nacademic decline, it was not clear that most or all of these absences were caused by\\n\\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\\n\\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\\n\\nproviding every accommodation requested by his family. Id. at 50–51.\\n\\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\\n\\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\\n\\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\\n\\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\\n\\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\\n\\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\\n\\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\\n\\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\\n\\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\\n\\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\\n\\nthat Cumberland breached its “Child Find” duty.\\n\\n\\n\\n 5\\n\\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\\n\\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\\n\\nthe District Court’s conclusions of law, including whether it applied the correct legal\\n\\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\\n\\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\\n\\nthe state administrative decision under the so-called “modified de novo” standard, under\\n\\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\\n\\nfacie correct,” which means that, if the Court disagrees with those findings, it must\\n\\nexplain the basis for its disagreement. Id. This is not substantively different from de\\n\\nnovo review, though courts are cautioned not to substitute their view of sound educational\\n\\npolicy for that of local school authorities. Id.\\n\\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\\n\\nEvaluation Report, seems to involve a category error on its part. Neither the District\\n\\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\\n\\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\\n\\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\\n\\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\\n\\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\\n\\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\\n\\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\\n\\nbest to tailor the education of children to their unique needs once they are found eligible.\\n\\n\\n\\n 6\\n\\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\\n\\nspecial education.\\n\\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\\n\\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\\n\\nfor special education under the IDEA. Cumberland does identify one problem in the\\n\\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\\n\\nevidence to determine eligibility based on the category of Other Health Impairment,”\\n\\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\\n\\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\\n\\n152. Hence the Report was not incomplete.\\n\\n The rest of Cumberland’s arguments misread the record. The District Court did\\n\\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\\n\\neligible disability but must also require specially designed instruction due to that\\n\\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\\n\\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\\n\\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\\n\\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\\n\\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\\n\\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\\n\\nJ.C.’s conditions than the Evaluation Report.\\n\\n The Hearing Officer’s principal ground for discounting the independent report was\\n\\nits finding of a specific learning disability as to mathematics, but the District Court was\\n\\n 7\\n\\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\\n\\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\\n\\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\\n\\npattern—strong performance for many years followed by a sharp decline—indicates a\\n\\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\\n\\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\\n\\ncould not manifest progressively over time, aside from a conclusory citation to the\\n\\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\\n\\npsychological processes involved” in various tasks. There is nothing illogical about the\\n\\nidea that a learning disability might only impair a student’s ability to do the tasks\\n\\ninvolved in higher and more complex forms of mathematics.\\n\\n Even aside from this specific dispute, the Hearing Officer was wrong to\\n\\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\\n\\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\\n\\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\\n\\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\\n\\nsuch as clear error review, the District Court’s reversal as to the weight of the\\n\\nindependent evaluation would be more of a problem. But the “modified de novo”\\n\\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\\n\\neligibility based on the preponderance of the evidence. This merely requires it to explain\\n\\nits disagreements with the Hearing Officer, which it did.\\n\\n\\n\\n 8\\n\\f Cumberland also misstates that the school’s Report concluded that J.C. was not\\n\\nIDEA eligible because of the second criterion, the need for specially designed instruction.\\n\\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\\n\\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\\n\\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\\n\\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\\n\\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\\n\\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\\n\\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\\n\\neducation curriculum for all classes, it also concludes that he requires itinerant\\n\\nlearning/emotional support and “specially designed instructional strategies within his\\n\\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\\n\\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\\n\\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\\n\\nwas already apparent that homebound instruction was, to put it mildly, not going well.\\n\\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\\n\\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\\n\\ndisease of the digestive system required adapting the content, methodology, or delivery of\\n\\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\\n\\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\\n\\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\\n\\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\\n\\n 9\\n\\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\\n\\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\\n\\nas something requiring only a Section 504 accommodation, not IDEA special education,\\n\\nCumberland and the Hearing Officer both treated the disease as something discrete and\\n\\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\\n\\nfinding to the contrary.\\n\\n Finally, Cumberland claims the District Court erred in finding that the school\\n\\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\\n\\nrelevant federal law, to identify students with disabilities who require accommodations or\\n\\nspecial education services proactively rather than waiting around for a child’s parents to\\n\\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\\n\\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\\n\\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\\n\\nOfficer’s decision made no finding as to Child Find under the IDEA because he\\n\\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\\n\\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\\n\\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\\n\\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\\n\\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\\n\\nit also found that Cumberland should have provided Section 504 services well before\\n\\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\\n\\n\\n\\n 10\\n\\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\\n\\nthough it were a Section 504 question.\\n\\n Because both the IDEA Child Find and the Section 504 claims involve what\\n\\nCumberland knew or should have known at what point in time, we will analyze them\\n\\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\\n\\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\\n\\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\\n\\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\\n\\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\\n\\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\\n\\nfrom seventh grade on he experienced severe academic decline and numerous\\n\\ndisciplinary issues. The District Court is correct that Cumberland at least should have\\n\\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\\n\\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\\n\\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\\n\\nthat among the warning signs was his declining academic performance.\\n\\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\\n\\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\\n\\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\\n\\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\\n\\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\\n\\nhim for special education under the IDEA. In that context the Hearing Officer held that\\n\\n 11\\n\\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\\n\\nsuch that he had not proven his disease adversely affected his education.\\n\\n Second, Cumberland’s argument is illogical and inconsistent with the basic\\n\\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\\n\\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\\n\\ncome forward, at that time, with evidence the disease was the cause of his problems; that\\n\\nwould be placing the burden on J.C. and his family for identifying him as a student with a\\n\\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\\n\\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\\n\\neven before he had proven that his poor conduct and performance were a result of his\\n\\ndisease, there can be no requirement for that proof now during litigation. That obligation\\n\\nwas in play even were his disease not behind his declining performance in school. The\\n\\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\\n\\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\\n\\nfailing to adopt a service plan for J.C. until March 2014.\\n\\n * * * * *\\n\\n Thus we affirm.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355860/\", \"author_raw\": \"AMBRO, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"AMBRO"},"judge2":{"kind":"string","value":"SCIRICA"},"judge3":{"kind":"string","value":"RENDELL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"AMBRO\": \", Circuit\", \"SCIRICA\": \", Circuit\", \"RENDELL\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578607/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Kevin Culley v. Cumberland Valley School Dist\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nNOT PRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 17-3800\n ________________\n\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\n\n v.\n\n CUMBERLAND VALLEY SCHOOL DISTRICT,\n\n Appellant\n ________________\n\n Appeal from the United States District Court\n for the Middle District of Pennsylvania\n (D.C. Civil Action No. 1-15-cv-00857)\n District Judge: Honorable John E. Jones, III\n ________________\n\n Argued November 6, 2018\n\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\n\n (Opinion filed: December 20, 2018)\n\n\nMark W. Cheramie Walz [Argued]\nSweet, Stevens, Katz & Williams LLP\n331 East Butler Avenue\nP.O. Box 5069\nNew Britain, PA 18901\n Counsel for Appellant\n\nJudith A. Gran [Argued]\nReisman Carolla & Gran LLP\n19 Chestnut Street\nHaddonfield, NJ 08033\n\fPhillip A. Drumheiser\nP.O. Box 890\nCarlisle, PA 17013\n Counsel for Appellees\n\n ________________\n\n OPINION*\n ________________\n\nAMBRO, Circuit Judge\n\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\n\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\n\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\n\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\n\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\n\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\n\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\n\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\n\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\n\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\n\naffirm.\n\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\n\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\n\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\n\n\n\n*\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\nconstitute binding precedent.\n 2\n\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\n\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\n\nsignificant turns for the worse. From seventh through tenth grade, when the incident\n\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\n\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\n\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\n\nabsent 43 times, or over 30% of the time.\n\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\n\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\n\nstating that J.C. should be allowed to cease activities during his physical education\n\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\n\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\n\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\n\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\n\nwith several friends, attempted to leave the school grounds during the day. The other\n\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\n\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\n\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\n\nhe required, his parents filed a due process complaint under the IDEA on January 29.\n\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\n\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\n\nbathroom, extra time to complete assignments, and the provision of class notes in case of\n\n 3\n\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\n\nshould receive homebound instruction for half of each school day, Cumberland tried to\n\nimplement this accommodation as well, but things did not go well. J.C. was rarely\n\npresent when the instructor arrived at his house, and even when present was not\n\nmotivated or cooperative. Id. at 107–116.\n\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\n\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\n\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\n\nnot have a “qualifying disability” and thus was not eligible for special education under\n\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\n\nCrohn’s disease was responsible for his difficulties in school, and that his condition\n\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\n\nthen requested an independent educational evaluation (IEE), which reached the opposite\n\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\n\nfound that he was eligible for special education under the IDEA and gave numerous\n\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\n\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\n\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\n\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\n\nadopted an individualized education program (IEP) for J.C. to provide special education\n\nunder the IDEA. Id. at 249–279.\n\n\n\n 4\n\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\n\nand issued his decision in February 2015. He found that J.C. was not eligible for special\n\neducation under the IDEA because, even though Crohn’s disease was a qualifying\n\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\n\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\n\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\n\nacademic decline, it was not clear that most or all of these absences were caused by\n\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\n\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\n\nproviding every accommodation requested by his family. Id. at 50–51.\n\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\n\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\n\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\n\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\n\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\n\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\n\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\n\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\n\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\n\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\n\nthat Cumberland breached its “Child Find” duty.\n\n\n\n 5\n\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\n\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\n\nthe District Court’s conclusions of law, including whether it applied the correct legal\n\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\n\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\n\nthe state administrative decision under the so-called “modified de novo” standard, under\n\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\n\nfacie correct,” which means that, if the Court disagrees with those findings, it must\n\nexplain the basis for its disagreement. Id. This is not substantively different from de\n\nnovo review, though courts are cautioned not to substitute their view of sound educational\n\npolicy for that of local school authorities. Id.\n\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\n\nEvaluation Report, seems to involve a category error on its part. Neither the District\n\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\n\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\n\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\n\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\n\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\n\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\n\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\n\nbest to tailor the education of children to their unique needs once they are found eligible.\n\n\n\n 6\n\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\n\nspecial education.\n\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\n\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\n\nfor special education under the IDEA. Cumberland does identify one problem in the\n\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\n\nevidence to determine eligibility based on the category of Other Health Impairment,”\n\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\n\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\n\n152. Hence the Report was not incomplete.\n\n The rest of Cumberland’s arguments misread the record. The District Court did\n\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\n\neligible disability but must also require specially designed instruction due to that\n\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\n\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\n\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\n\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\n\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\n\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\n\nJ.C.’s conditions than the Evaluation Report.\n\n The Hearing Officer’s principal ground for discounting the independent report was\n\nits finding of a specific learning disability as to mathematics, but the District Court was\n\n 7\n\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\n\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\n\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\n\npattern—strong performance for many years followed by a sharp decline—indicates a\n\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\n\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\n\ncould not manifest progressively over time, aside from a conclusory citation to the\n\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\n\npsychological processes involved” in various tasks. There is nothing illogical about the\n\nidea that a learning disability might only impair a student’s ability to do the tasks\n\ninvolved in higher and more complex forms of mathematics.\n\n Even aside from this specific dispute, the Hearing Officer was wrong to\n\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\n\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\n\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\n\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\n\nsuch as clear error review, the District Court’s reversal as to the weight of the\n\nindependent evaluation would be more of a problem. But the “modified de novo”\n\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\n\neligibility based on the preponderance of the evidence. This merely requires it to explain\n\nits disagreements with the Hearing Officer, which it did.\n\n\n\n 8\n\f Cumberland also misstates that the school’s Report concluded that J.C. was not\n\nIDEA eligible because of the second criterion, the need for specially designed instruction.\n\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\n\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\n\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\n\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\n\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\n\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\n\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\n\neducation curriculum for all classes, it also concludes that he requires itinerant\n\nlearning/emotional support and “specially designed instructional strategies within his\n\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\n\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\n\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\n\nwas already apparent that homebound instruction was, to put it mildly, not going well.\n\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\n\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\n\ndisease of the digestive system required adapting the content, methodology, or delivery of\n\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\n\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\n\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\n\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\n\n 9\n\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\n\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\n\nas something requiring only a Section 504 accommodation, not IDEA special education,\n\nCumberland and the Hearing Officer both treated the disease as something discrete and\n\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\n\nfinding to the contrary.\n\n Finally, Cumberland claims the District Court erred in finding that the school\n\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\n\nrelevant federal law, to identify students with disabilities who require accommodations or\n\nspecial education services proactively rather than waiting around for a child’s parents to\n\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\n\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\n\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\n\nOfficer’s decision made no finding as to Child Find under the IDEA because he\n\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\n\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\n\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\n\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\n\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\n\nit also found that Cumberland should have provided Section 504 services well before\n\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\n\n\n\n 10\n\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\n\nthough it were a Section 504 question.\n\n Because both the IDEA Child Find and the Section 504 claims involve what\n\nCumberland knew or should have known at what point in time, we will analyze them\n\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\n\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\n\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\n\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\n\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\n\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\n\nfrom seventh grade on he experienced severe academic decline and numerous\n\ndisciplinary issues. The District Court is correct that Cumberland at least should have\n\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\n\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\n\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\n\nthat among the warning signs was his declining academic performance.\n\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\n\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\n\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\n\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\n\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\n\nhim for special education under the IDEA. In that context the Hearing Officer held that\n\n 11\n\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\n\nsuch that he had not proven his disease adversely affected his education.\n\n Second, Cumberland’s argument is illogical and inconsistent with the basic\n\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\n\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\n\ncome forward, at that time, with evidence the disease was the cause of his problems; that\n\nwould be placing the burden on J.C. and his family for identifying him as a student with a\n\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\n\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\n\neven before he had proven that his poor conduct and performance were a result of his\n\ndisease, there can be no requirement for that proof now during litigation. That obligation\n\nwas in play even were his disease not behind his declining performance in school. The\n\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\n\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\n\nfailing to adopt a service plan for J.C. until March 2014.\n\n * * * * *\n\n Thus we affirm.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Kevin Culley v. Cumberland Valley School Dist\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nNOT PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-3800\\n ________________\\n\\n KEVIN CULLEY, and; DENISE CULLEY, on behalf of; J.C.\\n\\n v.\\n\\n CUMBERLAND VALLEY SCHOOL DISTRICT,\\n\\n Appellant\\n ________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n (D.C. Civil Action No. 1-15-cv-00857)\\n District Judge: Honorable John E. Jones, III\\n ________________\\n\\n Argued November 6, 2018\\n\\n Before: AMBRO, SCIRICA, and RENDELL, Circuit Judges\\n\\n (Opinion filed: December 20, 2018)\\n\\n\\nMark W. Cheramie Walz [Argued]\\nSweet, Stevens, Katz & Williams LLP\\n331 East Butler Avenue\\nP.O. Box 5069\\nNew Britain, PA 18901\\n Counsel for Appellant\\n\\nJudith A. Gran [Argued]\\nReisman Carolla & Gran LLP\\n19 Chestnut Street\\nHaddonfield, NJ 08033\\n\\fPhillip A. Drumheiser\\nP.O. Box 890\\nCarlisle, PA 17013\\n Counsel for Appellees\\n\\n ________________\\n\\n OPINION*\\n ________________\\n\\nAMBRO, Circuit Judge\\n\\n J.C., son of plaintiffs Kevin and Denise Culley, was diagnosed with Crohn’s\\n\\ndisease at age six. It is a painful, even debilitating, disease that affects the digestive tract\\n\\nand can cause abdominal pain, diarrhea, fatigue, weight loss, and malnutrition. It can\\n\\neven be life-threatening. See Mayo Clinic, Crohn’s Disease (Mar. 8, 2018), available at\\n\\nhttps://www.mayoclinic.org/diseases-conditions/crohns-disease/symptoms-causes/syc-\\n\\n20353304. After a disciplinary dispute with J.C.’s school, part of the Cumberland Valley\\n\\nSchool District system, that resulted in his expulsion, J.C.’s parents filed suit claiming\\n\\nthat Cumberland had violated J.C.’s rights under the Individuals with Disabilities\\n\\nEducation Act (IDEA), 20 U.S.C. § 1400 et seq., and under Section 504 of the\\n\\nRehabilitation Act. 29 U.S.C. § 701 et seq. The District Court agreed, and we now\\n\\naffirm.\\n\\n Born in 1998, J.C. was diagnosed with Crohn’s disease in 2004. Cumberland was\\n\\ninformed of the diagnosis in 2007. App. at 53. J.C.’s performance in school was\\n\\ngenerally strong through his sixth grade year, in 2009–2010, and he did not have\\n\\n\\n\\n*\\n This disposition is not an opinion of the full Court and pursuant to I.O.P. 5.7 does not\\nconstitute binding precedent.\\n 2\\n\\fsignificant behavioral or social difficulties through that time. Id. at 130–131. But from\\n\\nseventh grade onward, both J.C.’s academic performance and his disciplinary record took\\n\\nsignificant turns for the worse. From seventh through tenth grade, when the incident\\n\\ngiving rise to this lawsuit occurred and he was expelled, J.C. maintained a grade point\\n\\naverage just above a failing mark of 70, had numerous disciplinary incidents, and was\\n\\nincreasingly absent from school. Id. at 128, 131, 169–170. By tenth grade J.C. was\\n\\nabsent 43 times, or over 30% of the time.\\n\\n In April 2013, while in ninth grade, J.C. was admitted to Hershey Medical Center\\n\\nfor surgery. Shortly thereafter in May, the school received a letter from his physician\\n\\nstating that J.C. should be allowed to cease activities during his physical education\\n\\nclasses if he experienced pain. Id. at 170. In July 2013 the school received another letter\\n\\nfrom J.C.’s doctor stating that he should be allowed to leave class to use the bathroom on\\n\\na liberal basis. Id. It appears Cumberland agreed to these accommodations.\\n\\n On January 17, 2014, J.C. had a disciplinary incident where he, apparently along\\n\\nwith several friends, attempted to leave the school grounds during the day. The other\\n\\nstudents fled, while J.C. was apprehended and had disciplinary proceedings brought\\n\\nagainst him, with an eye toward expulsion. After J.C.’s doctor wrote a letter to the school\\n\\non January 27, 2014, giving a fuller account of J.C.’s diagnosis and the accommodations\\n\\nhe required, his parents filed a due process complaint under the IDEA on January 29.\\n\\nCumberland adopted a Section 504 Service Plan for J.C. in March 2014, which provided\\n\\nfor a number of accommodations, including an “any time pass” to go to the nurse or the\\n\\nbathroom, extra time to complete assignments, and the provision of class notes in case of\\n\\n 3\\n\\ffrequent absences. Id. at 92–94. After receiving a letter from J.C.’s doctor stating that he\\n\\nshould receive homebound instruction for half of each school day, Cumberland tried to\\n\\nimplement this accommodation as well, but things did not go well. J.C. was rarely\\n\\npresent when the instructor arrived at his house, and even when present was not\\n\\nmotivated or cooperative. Id. at 107–116.\\n\\n The school board voted to expel J.C. on April 7, 2014, with the expulsion taking\\n\\neffect on May 8, 2014. At the same time, Cumberland released its Evaluation Report\\n\\nfrom its psychologist’s evaluation of J.C. Id. at 123. The report concluded that he did\\n\\nnot have a “qualifying disability” and thus was not eligible for special education under\\n\\nthe IDEA. Id. at 152. It also stated that there was insufficient evidence that J.C.’s\\n\\nCrohn’s disease was responsible for his difficulties in school, and that his condition\\n\\ncalled for Section 504 accommodations, not IDEA specialized instruction. J.C.’s parents\\n\\nthen requested an independent educational evaluation (IEE), which reached the opposite\\n\\nconclusion. Id. at 162–192. Noting the pervasive effect of Crohn’s on J.C.’s life, the IEE\\n\\nfound that he was eligible for special education under the IDEA and gave numerous\\n\\n“recommendations for specially designed instruction” to help tailor J.C.’s education to\\n\\nhis benefit. Id. at 189–191. It also found that J.C. had ADHD and specific learning\\n\\ndisabilities as to math and listening comprehension. Id. at 189. After J.C. moved to a\\n\\nneighboring school district, East Pennsboro, for the 2014–'15 school year, that district\\n\\nadopted an individualized education program (IEP) for J.C. to provide special education\\n\\nunder the IDEA. Id. at 249–279.\\n\\n\\n\\n 4\\n\\f Meanwhile, the Hearing Officer on J.C.’s due process complaint held a hearing\\n\\nand issued his decision in February 2015. He found that J.C. was not eligible for special\\n\\neducation under the IDEA because, even though Crohn’s disease was a qualifying\\n\\ndisability, it did not require specialized instruction. Id. at 48. The Hearing Officer\\n\\nendorsed Cumberland’s Evaluation Report and largely dismissed the findings from the\\n\\nIEE. He noted that while J.C.’s frequent absences doubtless caused much of his\\n\\nacademic decline, it was not clear that most or all of these absences were caused by\\n\\nCrohn’s. Id. The Hearing Officer also concluded that, while J.C. was unambiguously\\n\\ncovered by Section 504, Cumberland had met all of its obligations under that statute by\\n\\nproviding every accommodation requested by his family. Id. at 50–51.\\n\\n J.C.’s parents then timely filed a civil action on his behalf in the Middle District of\\n\\nPennsylvania challenging the Hearing Officer’s decision. See Culley et al. v.\\n\\nCumberland Valley School District, No. 1:15-cv-00857-JEJ (M.D. Pa. 2015). Ruling on\\n\\nthe parties’ cross-motions for judgment on the record, the District Court reversed the\\n\\nHearing Officer, finding that J.C. was eligible under the IDEA, that Cumberland had\\n\\nviolated its “Child Find” duty to identify students with disabilities, and that it violated\\n\\nSection 504 by failing to evaluate J.C. prior to March 2014. Op. at 26 (App. at 28).\\n\\nCumberland now appeals, arguing that the District Court erred by (1) reversing the\\n\\nHearing Officer’s determination that Cumberland’s Evaluation Report was appropriate,\\n\\n(2) finding that J.C. was eligible for special education under the IDEA, and (3) finding\\n\\nthat Cumberland breached its “Child Find” duty.\\n\\n\\n\\n 5\\n\\f The District Court had original jurisdiction under 28 U.S.C. § 1331 and 20 U.S.C.\\n\\n§ 1415(i)(2). We have appellate jurisdiction under 28 U.S.C. § 1291. We review afresh\\n\\nthe District Court’s conclusions of law, including whether it applied the correct legal\\n\\nstandards under the IDEA, and we review its findings of fact for clear error. Ridley\\n\\nSchool District v. M.R., 680 F.3d 260, 268 (3d Cir. 2012). As to the merits, we review\\n\\nthe state administrative decision under the so-called “modified de novo” standard, under\\n\\nwhich the hearing officer’s findings of fact are given “due weight” and treated as “prima\\n\\nfacie correct,” which means that, if the Court disagrees with those findings, it must\\n\\nexplain the basis for its disagreement. Id. This is not substantively different from de\\n\\nnovo review, though courts are cautioned not to substitute their view of sound educational\\n\\npolicy for that of local school authorities. Id.\\n\\n Cumberland’s first argument on appeal, concerning the “appropriateness” of the\\n\\nEvaluation Report, seems to involve a category error on its part. Neither the District\\n\\nCourt’s decision nor the Hearing Officer used the word “appropriate” in connection with\\n\\nthe Evaluation Report. Nor do the statutory and regulatory provisions governing IDEA\\n\\nevaluations. See 20 U.S.C. § 1414(b), 34 C.F.R. § 300.304. The cases Cumberland cites\\n\\nconcern whether an IEP adopted under the IDEA is appropriate. See, e.g., Board of\\n\\nEducation of Hendrick Hudson Central School District, Westchester Co. v. Rowley, 458\\n\\nU.S. 176 (1982). The deference commended by Rowley and the other cases Cumberland\\n\\ncites, therefore, goes not to the threshold question of eligibility under the IDEA but how\\n\\nbest to tailor the education of children to their unique needs once they are found eligible.\\n\\n\\n\\n 6\\n\\fThat is of no relevance to this case, where Cumberland found J.C. ineligible for IDEA\\n\\nspecial education.\\n\\n The question of the weight to be given to the Evaluation Report, and to the IEE, is\\n\\nundoubtedly key to the main issue in this case, namely whether J.C. is in fact qualified\\n\\nfor special education under the IDEA. Cumberland does identify one problem in the\\n\\nDistrict Court’s analysis: it misquoted the Report as stating that there was “insufficient\\n\\nevidence to determine eligibility based on the category of Other Health Impairment,”\\n\\nwhen in fact the Report said that there was “insufficient information that [J.C.] has\\n\\nlimited alertness due to a medical condition.” Compare Op. at 11 (App. at 13), App. at\\n\\n152. Hence the Report was not incomplete.\\n\\n The rest of Cumberland’s arguments misread the record. The District Court did\\n\\nnot neglect the second prong of IDEA eligibility—that a student need not only have an\\n\\neligible disability but must also require specially designed instruction due to that\\n\\ndisability. Rather, its opinion explicitly referred to the correct set of criteria. Op. at 9.\\n\\nAnd while the Court did not discuss in detail J.C.’s need for specially designed\\n\\ninstruction, it did give reasons why the Hearing Officer was wrong to discount the IEE,\\n\\nwhich contained detailed instructions for ways J.C.’s instruction should be modified to\\n\\nsuit his needs. If credited, then, the IEE provides ample support for finding that J.C. was\\n\\nIDEA eligible. And we agree that the IEE paints a fuller and more accurate picture of\\n\\nJ.C.’s conditions than the Evaluation Report.\\n\\n The Hearing Officer’s principal ground for discounting the independent report was\\n\\nits finding of a specific learning disability as to mathematics, but the District Court was\\n\\n 7\\n\\fcorrect that J.C.’s performance in math was anything but strong. In ninth grade, for\\n\\ninstance, J.C. failed the first three periods of his basic algebra course, only passing the\\n\\nentire course (with a D grade) due to a strong final period. App. at 69. Arguably this\\n\\npattern—strong performance for many years followed by a sharp decline—indicates a\\n\\n“discrepancy between intellectual ability and academic achievement.” See 22 Pa. Code\\n\\n§ 14.125. Cumberland cites no evidence for its claim that a specific learning disability\\n\\ncould not manifest progressively over time, aside from a conclusory citation to the\\n\\ndefinition of specific learning disabilities as “a disorder in one or more of the basic\\n\\npsychological processes involved” in various tasks. There is nothing illogical about the\\n\\nidea that a learning disability might only impair a student’s ability to do the tasks\\n\\ninvolved in higher and more complex forms of mathematics.\\n\\n Even aside from this specific dispute, the Hearing Officer was wrong to\\n\\ncharacterize the independent report as “conclusory;” it is plainly more detailed in its\\n\\nanalysis than the school’s own Evaluation Report, showing J.C.’s life and the misery his\\n\\ndisease inflicts on him in far richer context. Compare App. at 151–152, 188–189.\\n\\nPerhaps if the Hearing Officer’s factual conclusions were entitled to increased deference,\\n\\nsuch as clear error review, the District Court’s reversal as to the weight of the\\n\\nindependent evaluation would be more of a problem. But the “modified de novo”\\n\\nstandard does not actually restrict the Court’s power to reach its own conclusions as to\\n\\neligibility based on the preponderance of the evidence. This merely requires it to explain\\n\\nits disagreements with the Hearing Officer, which it did.\\n\\n\\n\\n 8\\n\\f Cumberland also misstates that the school’s Report concluded that J.C. was not\\n\\nIDEA eligible because of the second criterion, the need for specially designed instruction.\\n\\nIn fact the Report checked the box indicating that J.C. does not have a qualifying\\n\\ndisability at all. App. at 152. The Hearing Officer concluded to the contrary that Crohn’s\\n\\ndisease was a qualifying disability, and Cumberland does not argue otherwise. Nor is\\n\\nCumberland correct in stating that the East Pennsboro IEP is “actually just an\\n\\naccommodations plan, but contained on an IEP form instead of on a Section 504 form.”\\n\\nAppellant’s Br. at 18. Although the IEP does include many of the same accommodations\\n\\nas the Cumberland Section 504 plan, and states that J.C. must participate in the general\\n\\neducation curriculum for all classes, it also concludes that he requires itinerant\\n\\nlearning/emotional support and “specially designed instructional strategies within his\\n\\nmainstream courses of study.” App. at 262. And while Cumberland argues that there had\\n\\nnot been sufficient time to see whether the newly enacted Section 504 plan and its\\n\\naccommodation of homebound instruction would be sufficient to address J.C.’s needs, it\\n\\nwas already apparent that homebound instruction was, to put it mildly, not going well.\\n\\n Ultimately the basis for Cumberland’s conviction that J.C. does not require\\n\\nspecially designed instruction is not the Evaluation Report but rather a disbelief that “a\\n\\ndisease of the digestive system required adapting the content, methodology, or delivery of\\n\\nthe academic curriculum.” Appellant’s Br. at 17. But the independent evaluation\\n\\nexplains the connection well: J.C.’s life has been pervasively shaped in all facets by his\\n\\ndisease, and his numerous behavioral, emotional, social, and academic problems are, to\\n\\nsome degree, related to it. App. at 188. It may even, as the Evaluation Report itself\\n\\n 9\\n\\fsuggested, App. at 124, contribute to his ADHD—something neither the Report nor the\\n\\nHearing Officer considered in their analysis of J.C.’s IDEA eligibility. In seeing Crohn’s\\n\\nas something requiring only a Section 504 accommodation, not IDEA special education,\\n\\nCumberland and the Hearing Officer both treated the disease as something discrete and\\n\\nisolated rather than the defining condition of J.C.’s life. The District Court did not err in\\n\\nfinding to the contrary.\\n\\n Finally, Cumberland claims the District Court erred in finding that the school\\n\\nbreached its so-called “Child Find” duty. This refers to a school’s obligation, under\\n\\nrelevant federal law, to identify students with disabilities who require accommodations or\\n\\nspecial education services proactively rather than waiting around for a child’s parents to\\n\\nconfront them with evidence of this need. Both the IDEA and Section 504 impose such a\\n\\nduty, see 20 U.S.C. § 1412(a)(3); 34 C.F.R. § 104.32. And there appears to be some\\n\\nconfusion in this case about which “Child Find” duty is actually at issue. The Hearing\\n\\nOfficer’s decision made no finding as to Child Find under the IDEA because he\\n\\nconcluded that J.C. was not IDEA-eligible, and then ruled that Cumberland had not\\n\\nviolated Section 504 by failing to provide accommodations earlier. This analysis did not\\n\\ndiscuss the 504 Child Find obligation, and reasoned principally that the school had no\\n\\nnotice that J.C. required accommodations prior to receiving the physician’s notes in 2014.\\n\\nThe District Court, meanwhile, found a violation of the Child Find duty under the IDEA;\\n\\nit also found that Cumberland should have provided Section 504 services well before\\n\\nwhen it started providing those services, but did not discuss the 504 claims in terms of a\\n\\n\\n\\n 10\\n\\fChild Find duty. On appeal, however, both parties’ briefs discuss the Child Find issue as\\n\\nthough it were a Section 504 question.\\n\\n Because both the IDEA Child Find and the Section 504 claims involve what\\n\\nCumberland knew or should have known at what point in time, we will analyze them\\n\\ntogether. Cumberland knew of J.C.’s diagnosis as early as 2007. This seems sufficient to\\n\\ntrigger its Section 504 obligations to ensure that J.C. received whatever accommodations\\n\\nhe might require for his Crohn’s disease, as no one disputes that Crohn’s is sufficient to\\n\\ntrigger Section 504 coverage. Although it appears Cumberland was willing to make ad\\n\\nhoc accommodations to J.C.’s needs due to Crohn’s, see App. at 22, this was entirely\\n\\nreactive. It would be bad enough had J.C.’s performance in school been exemplary. But\\n\\nfrom seventh grade on he experienced severe academic decline and numerous\\n\\ndisciplinary issues. The District Court is correct that Cumberland at least should have\\n\\ninvestigated the question of whether J.C.’s numerous issues stemmed from his\\n\\ndebilitating, life-threatening disease in a way that would be helped by accommodations.\\n\\nIt did not do so. The same applies under the IDEA, given that J.C. is IDEA-eligible and\\n\\nthat among the warning signs was his declining academic performance.\\n\\n Cumberland contends that the Hearing Officer correctly rejected the Section 504\\n\\nclaim because J.C. and his parents failed to prove that the “warning signs” they cite were\\n\\ncaused by Crohn’s. Appellant’s Br. at 26–27. There are two problems here. First, the\\n\\ndiscussion they cite in the Hearing Officer’s decision was not about Section 504 or the\\n\\nChild Find obligation at all; instead it concerned whether J.C.’s Crohn’s disease qualified\\n\\nhim for special education under the IDEA. In that context the Hearing Officer held that\\n\\n 11\\n\\fJ.C. had not sufficiently proven that his absences from school were caused by Crohn’s,\\n\\nsuch that he had not proven his disease adversely affected his education.\\n\\n Second, Cumberland’s argument is illogical and inconsistent with the basic\\n\\nconcept of a Child Find obligation. The School knew that J.C. had Crohn’s, and it\\n\\nobserved the warning signs. There cannot have been a burden on J.C. or his parents to\\n\\ncome forward, at that time, with evidence the disease was the cause of his problems; that\\n\\nwould be placing the burden on J.C. and his family for identifying him as a student with a\\n\\ndisability, precisely what the Child Find duty forbids. If there was no burden at that time,\\n\\nif the school was obliged to investigate J.C.’s needs under the IDEA and Section 504\\n\\neven before he had proven that his poor conduct and performance were a result of his\\n\\ndisease, there can be no requirement for that proof now during litigation. That obligation\\n\\nwas in play even were his disease not behind his declining performance in school. The\\n\\nDistrict Court did not err, therefore, in concluding that Cumberland violated its Child\\n\\nFind obligations under the IDEA and that it violated its obligations under Section 504 by\\n\\nfailing to adopt a service plan for J.C. until March 2014.\\n\\n * * * * *\\n\\n Thus we affirm.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":59,"cells":{"id":{"kind":"number","value":4578608,"string":"4,578,608"},"name":{"kind":"string","value":"John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant"},"name_abbreviation":{"kind":"string","value":"John Simpson v. Attorney General United States"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3718"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chagares, Jordan, Vanaskie\", \"parties\": \"\", \"opinions\": [{\"author\": \"VANASKIE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3718\\n _____________\\n\\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\\n\\n v.\\n\\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\\n EXPLOSIVES; UNITED STATES OF AMERICA\\n\\n John F. Simpson,\\n Appellant\\n\\n _____________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n District Judge: Honorable John E. Jones, III\\n (D.C. Civil No. 1-15-mc-00297)\\n ______________\\n\\n Argued October 30, 2018\\n ______________\\n\\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\\n Judges\\n\\n (Opinion Filed: January 3, 2019)\\n\\nAdam J. Kraut\\nJoshua Prince [ARGUED]\\nPrince Law Offices\\n646 Lenape Road\\nBechtelsville, PA 19505\\n Counsel for Appellant\\n\\nDavid J. Freed\\nUnited States Attorney\\nCarlo D. Marchioli [ARGUED]\\nKate L. Mershimer\\nOffice of United States Attorney\\n228 Walnut Street, P.O. Box 11754\\n220 Federal Building and Courthouse\\nHarrisburg, PA 17108\\n\\nJeffrey A. Cohen\\nATF Associate Chief Counsel\\nJohn Kevin White\\nATF Division Counsel\\n601 Walnut Street, Suite 1000E\\nPhiladelphia, PA 19106\\n Counsel for Appellees\\n\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the\\nClerk for filing prior to retiring from the bench on January 1, 2019.\\nDue to the intervening holiday, the opinion has been entered on the\\ndocket by the Clerk this day.\\n\\n\\n\\n\\n 2\\n\\f ________________\\n\\n OPINION\\n ________________\\n\\nVANASKIE, Circuit Judge.\\n\\n Appellant John Simpson appeals the District Court’s\\norder granting summary judgment for Appellees and affirming\\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\\nAfter an annual compliance investigation, the ATF determined\\nthat Simpson had committed over 400 willful violations of the\\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\\nand 27 C.F.R. § 478.73. After an administrative hearing, the\\nATF affirmed its revocation decision and Simpson filed a\\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\\nDistrict Court, adopting a Magistrate Judge’s report and\\nrecommendation, granted summary judgment in favor of the\\nATF. For the following reasons, we will affirm.\\n\\n Simpson’s appeal presents us with the question of what\\nstandard to apply to determine whether a violation of the GCA\\nwas willful, an issue we have not yet addressed in a\\nprecedential opinion. In a non-precedential opinion, we found\\npersuasive the willfulness standard used by seven other\\ncircuits: knowledge of a legal obligation and purposeful\\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\\nAgreeing with the unanimous view of all the Courts of Appeals\\nto have addressed this issue, we now hold in this precedential\\n\\n\\n\\n\\n 3\\n\\fopinion that this willfulness standard applies to violations of\\nthe GCA. Because it is clear that Simpson knew of and was\\nplainly indifferent to his obligations by committing hundreds\\nof GCA violations, we will affirm the District Court’s ruling.\\n\\n I.\\n\\n Simpson applied for a dealer’s FFL in 2010, which\\nprompted an ATF interview. During the interview, ATF\\nrepresentatives discussed Simpson’s legal responsibilities and\\nobligations as a firearms dealer, covering topics such as\\nacquisition and disposition (“A&D”) recordkeeping, sales to\\nlaw enforcement, out-of-state gun sales, prohibited sales,\\nconsignment of firearms, and personal firearms. At the end of\\nthe meeting, Simpson signed an Acknowledgement of Federal\\nFirearms Regulations, certifying that he understood his\\nresponsibility to learn and follow all laws and regulations\\ngoverning his FFL. Simpson subsequently received an FFL\\nand opened a firearms store, Warrior Ridge Trading\\n\\n In 2011, Simpson attended a seminar for FFL holders,\\nwhere ATF officials discussed federal firearms regulations and\\nshowed sample Firearms Transaction Records. In 2012, after\\nconsulting with the ATF about his desire to assemble AR-15\\nrifles, Simpson applied for an additional FFL to manufacture\\nfirearms. ATF officials met with him and discussed the legal\\nresponsibilities associated with a manufacturer’s license,\\nincluding the duty to mark all manufactured firearms and to\\nkeep a separate manufacturing A&D book. Simpson again\\nsigned an acknowledgement form certifying that he understood\\nhis legal obligations under his additional FFL.\\n\\n In February 2014, Simpson applied to relocate his FFLs\\nbecause he planned to move his firearms store to another\\n\\n\\n\\n\\n 4\\n\\flocation. An ATF Industry Operations Inspector (“IOI”) met\\nwith him and discussed his application. Simpson once again\\nsigned a form acknowledging that he understood his\\nresponsibilities and obligations under the GCA.\\n\\n In April 2014, ATF conducted a compliance inspection\\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\\nAccording to IOI Susan Whitman, this inspection “was the\\nworst [she] ever conducted,” and, based upon her report, the\\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\\nrequested a review of the revocation decision pursuant to 18\\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\\nATF Director of Industry Operations (“DIO”) Juan Orellana\\nfound that Simpson had committed over 400 willful violations\\nof the GCA. As summarized by the Magistrate Judge, these\\nviolations include:\\n\\n [S]elling or delivering multiple\\n firearms without having completed\\n Firearm Transaction Records,\\n ATF Forms 4473, and without\\n Simpson making the required\\n entries in his [A&D] Book;\\n transferring firearms without\\n conducting background checks;\\n dealing firearms at the Alexandria\\n Sportsman’s Club and in West\\n Virginia without obtaining a\\n license to do so; selling or\\n delivering firearms, firearm\\n frames, or firearm receivers in\\n seven instances to individuals who\\n did not live in Pennsylvania;\\n incorrectly identifying in multiple\\n\\n\\n\\n\\n 5\\n\\f instances the firearms that had\\n been transferred; failing to identify\\n and mark 14 firearms that he\\n manufactured, and failing to make\\n the required records for those\\n manufactured firearms; failing to\\n record the disposition of five\\n firearms to other licensees; failing\\n to record the record of disposition\\n of 30 firearms to non-licensees;\\n failing on over 70 occasions to\\n record required information in his\\n A&D Book; failing in\\n approximately 200 instances to\\n record information on ATF Forms\\n 4473; failing to appropriately sign\\n and date ATF Form 4473 in dozens\\n of cases to indicate that he did not\\n have reasonable cause to believe\\n that a transferee was disqualified\\n from receiving a firearm; and\\n failing to submit an Annual\\n Firearms Manufacturing and\\n Exportation Report (ATF Form\\n 5300.11) in 2012 and 2013.\\n\\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\\nfinal revocation notices to Simpson.\\n\\n Simpson then filed a petition for judicial review and\\nmoved for an emergency stay of the revocation of his FFLs.\\nThe District Court denied his motion, finding that Simpson was\\nunlikely to “succe[ed] on the merits, given the numerosity and\\ntypes of violations,” and because the court was not “persuaded\\n\\n\\n\\n\\n 6\\n\\fby [Simpson’s] contention that he was inadequately trained by\\n[the ATF].” (App. 9). The case was then referred to a\\nMagistrate Judge for pretrial management. Upon completion\\nof discovery, the parties filed cross-motions for summary\\njudgment.\\n\\n Addressing the cross-motions in a Report and\\nRecommendation, the Magistrate Judge concluded that the\\nATF was authorized to revoke Simpson’s FFLs because he had\\nwillfully committed over 400 violations of the GCA. (App. I\\n33-34). The District Court adopted the report and\\nrecommendation in its entirety, and thus granted summary\\njudgment for the ATF and affirmed its revocation of Simpson’s\\nFFLs. Simpson’s timely appeal followed.\\n\\n\\n\\n II.\\n\\n The District Court had jurisdiction to review the ATF’s\\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\\nto 28 U.S.C. § 1291. We exercise de novo review over the\\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\\ngrant of summary judgment is warranted “if the movant shows\\nthat there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law.” Fed. R.\\nCiv. P. 56(a). Further, an administrative record “enjoys a\\npresumption of veracity” at summary judgment. Am. Arms\\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\\nomitted).\\n\\n\\n\\n\\n 7\\n\\f III.\\n\\n Under the GCA, the ATF may revoke an FFL if the\\nlicense holder willfully violated any provision of the GCA or\\nany rule or regulation prescribed under the GCA. 18 U.S.C.\\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\\nviolation [of the GCA] authorizes the ATF to revoke the\\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\\nThus, in the GCA context, our review of the District Court’s\\ngrant of summary judgment requires us to determine whether\\nthere was no genuine dispute as to any material fact\\nestablishing even one willful violation of the GCA. See Am.\\nArms, 563 F.3d at 86 (noting that “a single uncontested\\nviolation suffices to uphold” summary judgment for the ATF\\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\\n2008))).\\n\\n Eight other Courts of Appeals have held that a violation\\nof the GCA is willful where the licensee knew of his legal\\nobligation and purposefully disregarded or was plainly\\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\\n1979). We find this definition of willfulness to be appropriate.\\nIndeed, this standard mirrors the willfulness standard we have\\napplied in the parallel context of ATF revocations of fireworks\\nand explosives licenses for violations of federal explosives\\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\\n19 (upholding the ATF’s interpretation of willful because it\\n\\n\\n\\n\\n 8\\n\\fwas reasonable).1 In Vineland, we upheld that willfulness\\n“do[es] not require a bad purpose,” or an intent to disobey the\\nlaw, but rather willfulness can be established by a mere\\n“violation of the regulations with knowledge of their\\nrequirements.” Id. Moreover, both parties in this case agree\\nwith this willfulness standard. Accordingly, we now join our\\nsister circuits in holding that a violation of the GCA is willful\\nwhere the licensee: (1) knew of his legal obligation under the\\nGCA, and (2) either purposefully disregarded or was plainly\\nindifferent to GCA requirements.\\n\\n Here, Simpson has been charged with willfully\\nviolating the GCA over 400 times. He contends that he did not\\nfully understand his obligations and that any violations he\\ncommitted were not willful, but due to mistake or ignorance.\\nWe disagree, as the record indicates that Simpson was well\\napprised of his duties under the GCA but continually violated\\nGCA recordkeeping, manufacturing, and sales requirements.\\n\\n\\n\\n 1\\n In Vineland, we deferred to the ATF’s interpretation\\nof willfulness under federal explosives law because we found\\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\\nof explosives licensing decisions is governed only by 5 U.S.C.\\n§ 706, so we apply Chevron deference to reasonable agency\\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\\n(1984). In contrast, the GCA explicitly tasks courts with\\nconducting de novo review of ATF licensing denials or\\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\\ndistrict court decisions regarding ATF firearms licensing de\\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\\n\\n\\n\\n\\n 9\\n\\f A.\\n\\n The record shows that Simpson was informed of his\\nobligations as an FFL licensee. For example, Simpson met\\nwith ATF officials three times about his FFLs and, at the\\nconclusion of each meeting, he signed a form acknowledging\\nthat he discussed various regulatory topics with the ATF. In\\naddition, Simpson attended an ATF seminar for FFL holders\\nwhere he learned more about his obligations under the GCA.\\n\\n The record also demonstrates that Simpson often\\ncomplied with GCA requirements. On numerous occasions,\\nSimpson lawfully sold firearms and fully completed the A&D\\nrecordkeeping required under the GCA. Also, he applied to\\nrelocate his FFL, demonstrating that he knew that he was only\\nallowed to sell firearms from his approved FFL location. His\\nfull compliance with GCA requirements in some instances\\nbelies his assertion that he did not understand those\\nrequirements.\\n\\n Further, some of Simpson’s actions illustrate that he\\nunderstood the GCA regulatory scheme quite well. For\\nexample, he sometimes transferred firearms from his FFL\\ninventory to his personal collection, thereby taking advantage\\nof a statutory loophole that allowed him to later sell the\\nfirearms at gun shows without conducting background checks.\\nSuch action is inconsistent with that of a person who does not\\nunderstand the GCA regulatory scheme. Accordingly, we find\\nthat no reasonable fact-finder could disagree that Simpson\\nknew and understood his GCA obligations as an FFL licensee.\\n\\n\\n\\n\\n 10\\n\\f B.\\n\\n In this case, the ATF has alleged that Simpson was\\nplainly indifferent to the GCA’s requirements. We must\\ntherefore determine what constitutes plain indifference under\\nthe willfulness standard we have adopted.\\n\\n Plain indifference is demonstrated by “a lack of concern\\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\\nlack of concern may be shown by circumstantial evidence—\\nsuch as repeated violations or a large quantity of violations.\\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\\nat 322; Willingham Sports, 415 F.3d at 1277.\\n\\n The ATF charged Simpson with willfully violating a\\nlong list of separate provisions of the GCA under his\\nmanufacturer’s FFL, including, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) dealing firearms outside of his FFL premises;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents;\\n (f) transferring firearms and misidentifying\\n corresponding A&D entries;\\n (g) failing to identify and mark manufactured firearms;\\n (h) failing to record the manufacture of firearms in his\\n A&D book;\\n\\n\\n\\n\\n 11\\n\\f (i) failing to record dispositions of firearms to FFL\\n holders and non-licensees;\\n (j) failing to complete all fields of Form 4473s; and\\n (k) failing to sign and date Form 4473s.\\n\\n(See App. I 8). Additionally, the ATF charged Simpson with\\nwillfully violating another series of provisions of the GCA\\nunder his dealer’s FFL. These include, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) selling firearms in West Virginia;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents\\n (f) purchasing firearms without recording the purchases\\n in his A&D book;\\n (g) failing to complete all fields of Form 4473s; and\\n (h) failing to sign and date Form 4473s.\\n\\nId.\\n\\n Simpson contends that all of these violations either were\\nmere mistakes or were due to his “fundamental\\nmisunderstanding as to the importance” of GCA recordkeeping\\nrequirements. (Appellant’s Br. 35). However, in view of the\\nfact that Simpson received training on his obligations and\\nexplicitly acknowledged that he understood his GCA\\nobligations, the sheer number and continuing nature of the\\nviolations clearly demonstrate Simpson’s plain indifference to\\nthe GCA’s requirements.\\n\\n\\n\\n\\n 12\\n\\f While there is no dispute that Simpson violated the\\nGCA on numerous occasions, there is also evidence of other\\nfirearms transactions in which Simpson fully complied with\\nGCA requirements by completing, signing, and dating Form\\n4473s, recording the dispositions in his A&D book, and\\nconducting background checks. This inconsistent conduct\\nsuggests both that Simpson knew of his obligations and was\\nindifferent to complying with them. Moreover, there is\\nevidence of blatant GCA violations. For example, Simpson\\nroutinely transferred receivers to out-of-state residents—in\\nclear violation of the GCA—but falsely recorded the transfers\\nas rifle sales in his A&D book, making these transactions\\nappear lawful. Such behavior is indicative of Simpson’s lack\\nof concern for his GCA obligations as an FFL holder.\\n\\n In sum, the record sufficiently shows that Simpson had\\nknowledge of his FFL obligations, yet acted plainly\\nindifferently to them, thus willfully violating the GCA.\\nAccordingly, we find that the ATF was authorized to revoke\\nSimpson’s FFLs.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons we will affirm the District\\nCourt’s grant of summary judgment in favor of the ATF,\\naffirming its revocation of Simpson’s FFLs.\\n\\n\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355861/\", \"author_raw\": \"VANASKIE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"CHAGARES"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":"VANASKIE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578608/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3718\n _____________\n\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\n\n v.\n\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\n EXPLOSIVES; UNITED STATES OF AMERICA\n\n John F. Simpson,\n Appellant\n\n _____________\n\n On Appeal from the United States District Court\n for the Middle District of Pennsylvania\n District Judge: Honorable John E. Jones, III\n (D.C. Civil No. 1-15-mc-00297)\n ______________\n\n Argued October 30, 2018\n ______________\n\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\n Judges\n\n (Opinion Filed: January 3, 2019)\n\nAdam J. Kraut\nJoshua Prince [ARGUED]\nPrince Law Offices\n646 Lenape Road\nBechtelsville, PA 19505\n Counsel for Appellant\n\nDavid J. Freed\nUnited States Attorney\nCarlo D. Marchioli [ARGUED]\nKate L. Mershimer\nOffice of United States Attorney\n228 Walnut Street, P.O. Box 11754\n220 Federal Building and Courthouse\nHarrisburg, PA 17108\n\nJeffrey A. Cohen\nATF Associate Chief Counsel\nJohn Kevin White\nATF Division Counsel\n601 Walnut Street, Suite 1000E\nPhiladelphia, PA 19106\n Counsel for Appellees\n\n\n\n The Honorable Judge Vanaskie transmitted the opinion to the\nClerk for filing prior to retiring from the bench on January 1, 2019.\nDue to the intervening holiday, the opinion has been entered on the\ndocket by the Clerk this day.\n\n\n\n\n 2\n\f ________________\n\n OPINION\n ________________\n\nVANASKIE, Circuit Judge.\n\n Appellant John Simpson appeals the District Court’s\norder granting summary judgment for Appellees and affirming\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\nAfter an annual compliance investigation, the ATF determined\nthat Simpson had committed over 400 willful violations of the\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\nand 27 C.F.R. § 478.73. After an administrative hearing, the\nATF affirmed its revocation decision and Simpson filed a\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\nDistrict Court, adopting a Magistrate Judge’s report and\nrecommendation, granted summary judgment in favor of the\nATF. For the following reasons, we will affirm.\n\n Simpson’s appeal presents us with the question of what\nstandard to apply to determine whether a violation of the GCA\nwas willful, an issue we have not yet addressed in a\nprecedential opinion. In a non-precedential opinion, we found\npersuasive the willfulness standard used by seven other\ncircuits: knowledge of a legal obligation and purposeful\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\nAgreeing with the unanimous view of all the Courts of Appeals\nto have addressed this issue, we now hold in this precedential\n\n\n\n\n 3\n\fopinion that this willfulness standard applies to violations of\nthe GCA. Because it is clear that Simpson knew of and was\nplainly indifferent to his obligations by committing hundreds\nof GCA violations, we will affirm the District Court’s ruling.\n\n I.\n\n Simpson applied for a dealer’s FFL in 2010, which\nprompted an ATF interview. During the interview, ATF\nrepresentatives discussed Simpson’s legal responsibilities and\nobligations as a firearms dealer, covering topics such as\nacquisition and disposition (“A&D”) recordkeeping, sales to\nlaw enforcement, out-of-state gun sales, prohibited sales,\nconsignment of firearms, and personal firearms. At the end of\nthe meeting, Simpson signed an Acknowledgement of Federal\nFirearms Regulations, certifying that he understood his\nresponsibility to learn and follow all laws and regulations\ngoverning his FFL. Simpson subsequently received an FFL\nand opened a firearms store, Warrior Ridge Trading\n\n In 2011, Simpson attended a seminar for FFL holders,\nwhere ATF officials discussed federal firearms regulations and\nshowed sample Firearms Transaction Records. In 2012, after\nconsulting with the ATF about his desire to assemble AR-15\nrifles, Simpson applied for an additional FFL to manufacture\nfirearms. ATF officials met with him and discussed the legal\nresponsibilities associated with a manufacturer’s license,\nincluding the duty to mark all manufactured firearms and to\nkeep a separate manufacturing A&D book. Simpson again\nsigned an acknowledgement form certifying that he understood\nhis legal obligations under his additional FFL.\n\n In February 2014, Simpson applied to relocate his FFLs\nbecause he planned to move his firearms store to another\n\n\n\n\n 4\n\flocation. An ATF Industry Operations Inspector (“IOI”) met\nwith him and discussed his application. Simpson once again\nsigned a form acknowledging that he understood his\nresponsibilities and obligations under the GCA.\n\n In April 2014, ATF conducted a compliance inspection\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\nAccording to IOI Susan Whitman, this inspection “was the\nworst [she] ever conducted,” and, based upon her report, the\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\nrequested a review of the revocation decision pursuant to 18\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\nATF Director of Industry Operations (“DIO”) Juan Orellana\nfound that Simpson had committed over 400 willful violations\nof the GCA. As summarized by the Magistrate Judge, these\nviolations include:\n\n [S]elling or delivering multiple\n firearms without having completed\n Firearm Transaction Records,\n ATF Forms 4473, and without\n Simpson making the required\n entries in his [A&D] Book;\n transferring firearms without\n conducting background checks;\n dealing firearms at the Alexandria\n Sportsman’s Club and in West\n Virginia without obtaining a\n license to do so; selling or\n delivering firearms, firearm\n frames, or firearm receivers in\n seven instances to individuals who\n did not live in Pennsylvania;\n incorrectly identifying in multiple\n\n\n\n\n 5\n\f instances the firearms that had\n been transferred; failing to identify\n and mark 14 firearms that he\n manufactured, and failing to make\n the required records for those\n manufactured firearms; failing to\n record the disposition of five\n firearms to other licensees; failing\n to record the record of disposition\n of 30 firearms to non-licensees;\n failing on over 70 occasions to\n record required information in his\n A&D Book; failing in\n approximately 200 instances to\n record information on ATF Forms\n 4473; failing to appropriately sign\n and date ATF Form 4473 in dozens\n of cases to indicate that he did not\n have reasonable cause to believe\n that a transferee was disqualified\n from receiving a firearm; and\n failing to submit an Annual\n Firearms Manufacturing and\n Exportation Report (ATF Form\n 5300.11) in 2012 and 2013.\n\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\nfinal revocation notices to Simpson.\n\n Simpson then filed a petition for judicial review and\nmoved for an emergency stay of the revocation of his FFLs.\nThe District Court denied his motion, finding that Simpson was\nunlikely to “succe[ed] on the merits, given the numerosity and\ntypes of violations,” and because the court was not “persuaded\n\n\n\n\n 6\n\fby [Simpson’s] contention that he was inadequately trained by\n[the ATF].” (App. 9). The case was then referred to a\nMagistrate Judge for pretrial management. Upon completion\nof discovery, the parties filed cross-motions for summary\njudgment.\n\n Addressing the cross-motions in a Report and\nRecommendation, the Magistrate Judge concluded that the\nATF was authorized to revoke Simpson’s FFLs because he had\nwillfully committed over 400 violations of the GCA. (App. I\n33-34). The District Court adopted the report and\nrecommendation in its entirety, and thus granted summary\njudgment for the ATF and affirmed its revocation of Simpson’s\nFFLs. Simpson’s timely appeal followed.\n\n\n\n II.\n\n The District Court had jurisdiction to review the ATF’s\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\nto 28 U.S.C. § 1291. We exercise de novo review over the\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\ngrant of summary judgment is warranted “if the movant shows\nthat there is no genuine dispute as to any material fact and the\nmovant is entitled to judgment as a matter of law.” Fed. R.\nCiv. P. 56(a). Further, an administrative record “enjoys a\npresumption of veracity” at summary judgment. Am. Arms\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\nomitted).\n\n\n\n\n 7\n\f III.\n\n Under the GCA, the ATF may revoke an FFL if the\nlicense holder willfully violated any provision of the GCA or\nany rule or regulation prescribed under the GCA. 18 U.S.C.\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\nviolation [of the GCA] authorizes the ATF to revoke the\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\nThus, in the GCA context, our review of the District Court’s\ngrant of summary judgment requires us to determine whether\nthere was no genuine dispute as to any material fact\nestablishing even one willful violation of the GCA. See Am.\nArms, 563 F.3d at 86 (noting that “a single uncontested\nviolation suffices to uphold” summary judgment for the ATF\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\n2008))).\n\n Eight other Courts of Appeals have held that a violation\nof the GCA is willful where the licensee knew of his legal\nobligation and purposefully disregarded or was plainly\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\n1979). We find this definition of willfulness to be appropriate.\nIndeed, this standard mirrors the willfulness standard we have\napplied in the parallel context of ATF revocations of fireworks\nand explosives licenses for violations of federal explosives\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\n19 (upholding the ATF’s interpretation of willful because it\n\n\n\n\n 8\n\fwas reasonable).1 In Vineland, we upheld that willfulness\n“do[es] not require a bad purpose,” or an intent to disobey the\nlaw, but rather willfulness can be established by a mere\n“violation of the regulations with knowledge of their\nrequirements.” Id. Moreover, both parties in this case agree\nwith this willfulness standard. Accordingly, we now join our\nsister circuits in holding that a violation of the GCA is willful\nwhere the licensee: (1) knew of his legal obligation under the\nGCA, and (2) either purposefully disregarded or was plainly\nindifferent to GCA requirements.\n\n Here, Simpson has been charged with willfully\nviolating the GCA over 400 times. He contends that he did not\nfully understand his obligations and that any violations he\ncommitted were not willful, but due to mistake or ignorance.\nWe disagree, as the record indicates that Simpson was well\napprised of his duties under the GCA but continually violated\nGCA recordkeeping, manufacturing, and sales requirements.\n\n\n\n 1\n In Vineland, we deferred to the ATF’s interpretation\nof willfulness under federal explosives law because we found\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\nof explosives licensing decisions is governed only by 5 U.S.C.\n§ 706, so we apply Chevron deference to reasonable agency\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\n(1984). In contrast, the GCA explicitly tasks courts with\nconducting de novo review of ATF licensing denials or\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\ndistrict court decisions regarding ATF firearms licensing de\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\n\n\n\n\n 9\n\f A.\n\n The record shows that Simpson was informed of his\nobligations as an FFL licensee. For example, Simpson met\nwith ATF officials three times about his FFLs and, at the\nconclusion of each meeting, he signed a form acknowledging\nthat he discussed various regulatory topics with the ATF. In\naddition, Simpson attended an ATF seminar for FFL holders\nwhere he learned more about his obligations under the GCA.\n\n The record also demonstrates that Simpson often\ncomplied with GCA requirements. On numerous occasions,\nSimpson lawfully sold firearms and fully completed the A&D\nrecordkeeping required under the GCA. Also, he applied to\nrelocate his FFL, demonstrating that he knew that he was only\nallowed to sell firearms from his approved FFL location. His\nfull compliance with GCA requirements in some instances\nbelies his assertion that he did not understand those\nrequirements.\n\n Further, some of Simpson’s actions illustrate that he\nunderstood the GCA regulatory scheme quite well. For\nexample, he sometimes transferred firearms from his FFL\ninventory to his personal collection, thereby taking advantage\nof a statutory loophole that allowed him to later sell the\nfirearms at gun shows without conducting background checks.\nSuch action is inconsistent with that of a person who does not\nunderstand the GCA regulatory scheme. Accordingly, we find\nthat no reasonable fact-finder could disagree that Simpson\nknew and understood his GCA obligations as an FFL licensee.\n\n\n\n\n 10\n\f B.\n\n In this case, the ATF has alleged that Simpson was\nplainly indifferent to the GCA’s requirements. We must\ntherefore determine what constitutes plain indifference under\nthe willfulness standard we have adopted.\n\n Plain indifference is demonstrated by “a lack of concern\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\nlack of concern may be shown by circumstantial evidence—\nsuch as repeated violations or a large quantity of violations.\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\nat 322; Willingham Sports, 415 F.3d at 1277.\n\n The ATF charged Simpson with willfully violating a\nlong list of separate provisions of the GCA under his\nmanufacturer’s FFL, including, inter alia:\n\n (a) selling firearms without completing Form 4473s;\n (b) selling or delivering firearms without recording the\n disposition in his A&D book;\n (c) transferring firearms without conducting\n background checks;\n (d) dealing firearms outside of his FFL premises;\n (e) selling or delivering firearms to non-Pennsylvania\n residents;\n (f) transferring firearms and misidentifying\n corresponding A&D entries;\n (g) failing to identify and mark manufactured firearms;\n (h) failing to record the manufacture of firearms in his\n A&D book;\n\n\n\n\n 11\n\f (i) failing to record dispositions of firearms to FFL\n holders and non-licensees;\n (j) failing to complete all fields of Form 4473s; and\n (k) failing to sign and date Form 4473s.\n\n(See App. I 8). Additionally, the ATF charged Simpson with\nwillfully violating another series of provisions of the GCA\nunder his dealer’s FFL. These include, inter alia:\n\n (a) selling firearms without completing Form 4473s;\n (b) selling or delivering firearms without recording the\n disposition in his A&D book;\n (c) transferring firearms without conducting\n background checks;\n (d) selling firearms in West Virginia;\n (e) selling or delivering firearms to non-Pennsylvania\n residents\n (f) purchasing firearms without recording the purchases\n in his A&D book;\n (g) failing to complete all fields of Form 4473s; and\n (h) failing to sign and date Form 4473s.\n\nId.\n\n Simpson contends that all of these violations either were\nmere mistakes or were due to his “fundamental\nmisunderstanding as to the importance” of GCA recordkeeping\nrequirements. (Appellant’s Br. 35). However, in view of the\nfact that Simpson received training on his obligations and\nexplicitly acknowledged that he understood his GCA\nobligations, the sheer number and continuing nature of the\nviolations clearly demonstrate Simpson’s plain indifference to\nthe GCA’s requirements.\n\n\n\n\n 12\n\f While there is no dispute that Simpson violated the\nGCA on numerous occasions, there is also evidence of other\nfirearms transactions in which Simpson fully complied with\nGCA requirements by completing, signing, and dating Form\n4473s, recording the dispositions in his A&D book, and\nconducting background checks. This inconsistent conduct\nsuggests both that Simpson knew of his obligations and was\nindifferent to complying with them. Moreover, there is\nevidence of blatant GCA violations. For example, Simpson\nroutinely transferred receivers to out-of-state residents—in\nclear violation of the GCA—but falsely recorded the transfers\nas rifle sales in his A&D book, making these transactions\nappear lawful. Such behavior is indicative of Simpson’s lack\nof concern for his GCA obligations as an FFL holder.\n\n In sum, the record sufficiently shows that Simpson had\nknowledge of his FFL obligations, yet acted plainly\nindifferently to them, thus willfully violating the GCA.\nAccordingly, we find that the ATF was authorized to revoke\nSimpson’s FFLs.\n\n\n\n IV.\n\n For the foregoing reasons we will affirm the District\nCourt’s grant of summary judgment in favor of the ATF,\naffirming its revocation of Simpson’s FFLs.\n\n\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: John F. SIMPSON, T/A Warrior Ridge Trading; T/A LCT Pro Shop v. ATTORNEY GENERAL UNITED STATES OF AMERICA; Director, Bureau of Alcohol, Tobacco, Firearms & Explosives; Director of Industry Operations, Bureau of Alcohol, Tobacco, Firearms & Explosives; United States of America John F. Simpson, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3718\\n _____________\\n\\nJOHN F. SIMPSON, t/a Warrior Ridge Trading; t/a LCT Pro Shop\\n\\n v.\\n\\n ATTORNEY GENERAL UNITED STATES OF AMERICA;\\nDIRECTOR, BUREAU OF ALCOHOL, TOBACCO, FIREARMS\\n & EXPLOSIVES; DIRECTOR OF INDUSTRY OPERATIONS,\\n BUREAU OF ALCOHOL, TOBACCO, FIREARMS &\\n EXPLOSIVES; UNITED STATES OF AMERICA\\n\\n John F. Simpson,\\n Appellant\\n\\n _____________\\n\\n On Appeal from the United States District Court\\n for the Middle District of Pennsylvania\\n District Judge: Honorable John E. Jones, III\\n (D.C. Civil No. 1-15-mc-00297)\\n ______________\\n\\n Argued October 30, 2018\\n ______________\\n\\f Before: CHAGARES, JORDAN, and VANASKIE, Circuit\\n Judges\\n\\n (Opinion Filed: January 3, 2019)\\n\\nAdam J. Kraut\\nJoshua Prince [ARGUED]\\nPrince Law Offices\\n646 Lenape Road\\nBechtelsville, PA 19505\\n Counsel for Appellant\\n\\nDavid J. Freed\\nUnited States Attorney\\nCarlo D. Marchioli [ARGUED]\\nKate L. Mershimer\\nOffice of United States Attorney\\n228 Walnut Street, P.O. Box 11754\\n220 Federal Building and Courthouse\\nHarrisburg, PA 17108\\n\\nJeffrey A. Cohen\\nATF Associate Chief Counsel\\nJohn Kevin White\\nATF Division Counsel\\n601 Walnut Street, Suite 1000E\\nPhiladelphia, PA 19106\\n Counsel for Appellees\\n\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the\\nClerk for filing prior to retiring from the bench on January 1, 2019.\\nDue to the intervening holiday, the opinion has been entered on the\\ndocket by the Clerk this day.\\n\\n\\n\\n\\n 2\\n\\f ________________\\n\\n OPINION\\n ________________\\n\\nVANASKIE, Circuit Judge.\\n\\n Appellant John Simpson appeals the District Court’s\\norder granting summary judgment for Appellees and affirming\\nthe Bureau of Alcohol, Tobacco, Firearms & Explosives’\\n(“ATF”) revocation of his federal firearms licenses (“FFLs”).\\nAfter an annual compliance investigation, the ATF determined\\nthat Simpson had committed over 400 willful violations of the\\nGun Control Act of 1968, 18 U.S.C. § 921 et seq. (“GCA”),\\nand therefore revoked his FFLs pursuant to 18 U.S.C. § 923(e)\\nand 27 C.F.R. § 478.73. After an administrative hearing, the\\nATF affirmed its revocation decision and Simpson filed a\\npetition for judicial review under 18 U.S.C. § 923(f)(3). The\\nDistrict Court, adopting a Magistrate Judge’s report and\\nrecommendation, granted summary judgment in favor of the\\nATF. For the following reasons, we will affirm.\\n\\n Simpson’s appeal presents us with the question of what\\nstandard to apply to determine whether a violation of the GCA\\nwas willful, an issue we have not yet addressed in a\\nprecedential opinion. In a non-precedential opinion, we found\\npersuasive the willfulness standard used by seven other\\ncircuits: knowledge of a legal obligation and purposeful\\ndisregard or plain indifference to it. Taylor v. Hughes, 548 F.\\nApp’x 822, 824 (3d Cir. 2013) (citing Borchardt Rifle Corp. v.\\nCook, 684 F.3d 1037, 1042 n.9 (10th Cir. 2012) (listing cases)).\\nAgreeing with the unanimous view of all the Courts of Appeals\\nto have addressed this issue, we now hold in this precedential\\n\\n\\n\\n\\n 3\\n\\fopinion that this willfulness standard applies to violations of\\nthe GCA. Because it is clear that Simpson knew of and was\\nplainly indifferent to his obligations by committing hundreds\\nof GCA violations, we will affirm the District Court’s ruling.\\n\\n I.\\n\\n Simpson applied for a dealer’s FFL in 2010, which\\nprompted an ATF interview. During the interview, ATF\\nrepresentatives discussed Simpson’s legal responsibilities and\\nobligations as a firearms dealer, covering topics such as\\nacquisition and disposition (“A&D”) recordkeeping, sales to\\nlaw enforcement, out-of-state gun sales, prohibited sales,\\nconsignment of firearms, and personal firearms. At the end of\\nthe meeting, Simpson signed an Acknowledgement of Federal\\nFirearms Regulations, certifying that he understood his\\nresponsibility to learn and follow all laws and regulations\\ngoverning his FFL. Simpson subsequently received an FFL\\nand opened a firearms store, Warrior Ridge Trading\\n\\n In 2011, Simpson attended a seminar for FFL holders,\\nwhere ATF officials discussed federal firearms regulations and\\nshowed sample Firearms Transaction Records. In 2012, after\\nconsulting with the ATF about his desire to assemble AR-15\\nrifles, Simpson applied for an additional FFL to manufacture\\nfirearms. ATF officials met with him and discussed the legal\\nresponsibilities associated with a manufacturer’s license,\\nincluding the duty to mark all manufactured firearms and to\\nkeep a separate manufacturing A&D book. Simpson again\\nsigned an acknowledgement form certifying that he understood\\nhis legal obligations under his additional FFL.\\n\\n In February 2014, Simpson applied to relocate his FFLs\\nbecause he planned to move his firearms store to another\\n\\n\\n\\n\\n 4\\n\\flocation. An ATF Industry Operations Inspector (“IOI”) met\\nwith him and discussed his application. Simpson once again\\nsigned a form acknowledging that he understood his\\nresponsibilities and obligations under the GCA.\\n\\n In April 2014, ATF conducted a compliance inspection\\nof Simpson’s FFLs pursuant to 18 U.S.C. § 923(g)(1)(C). ]\\nAccording to IOI Susan Whitman, this inspection “was the\\nworst [she] ever conducted,” and, based upon her report, the\\nATF decided to revoke Simpson’s FFLs. (App. I 7). Simpson\\nrequested a review of the revocation decision pursuant to 18\\nU.S.C. § 923(f)(2) and 27 C.F.R. § 478.74. After a hearing,\\nATF Director of Industry Operations (“DIO”) Juan Orellana\\nfound that Simpson had committed over 400 willful violations\\nof the GCA. As summarized by the Magistrate Judge, these\\nviolations include:\\n\\n [S]elling or delivering multiple\\n firearms without having completed\\n Firearm Transaction Records,\\n ATF Forms 4473, and without\\n Simpson making the required\\n entries in his [A&D] Book;\\n transferring firearms without\\n conducting background checks;\\n dealing firearms at the Alexandria\\n Sportsman’s Club and in West\\n Virginia without obtaining a\\n license to do so; selling or\\n delivering firearms, firearm\\n frames, or firearm receivers in\\n seven instances to individuals who\\n did not live in Pennsylvania;\\n incorrectly identifying in multiple\\n\\n\\n\\n\\n 5\\n\\f instances the firearms that had\\n been transferred; failing to identify\\n and mark 14 firearms that he\\n manufactured, and failing to make\\n the required records for those\\n manufactured firearms; failing to\\n record the disposition of five\\n firearms to other licensees; failing\\n to record the record of disposition\\n of 30 firearms to non-licensees;\\n failing on over 70 occasions to\\n record required information in his\\n A&D Book; failing in\\n approximately 200 instances to\\n record information on ATF Forms\\n 4473; failing to appropriately sign\\n and date ATF Form 4473 in dozens\\n of cases to indicate that he did not\\n have reasonable cause to believe\\n that a transferee was disqualified\\n from receiving a firearm; and\\n failing to submit an Annual\\n Firearms Manufacturing and\\n Exportation Report (ATF Form\\n 5300.11) in 2012 and 2013.\\n\\n(App. I 7-8; see also App. II 137-98). As such, the ATF issued\\nfinal revocation notices to Simpson.\\n\\n Simpson then filed a petition for judicial review and\\nmoved for an emergency stay of the revocation of his FFLs.\\nThe District Court denied his motion, finding that Simpson was\\nunlikely to “succe[ed] on the merits, given the numerosity and\\ntypes of violations,” and because the court was not “persuaded\\n\\n\\n\\n\\n 6\\n\\fby [Simpson’s] contention that he was inadequately trained by\\n[the ATF].” (App. 9). The case was then referred to a\\nMagistrate Judge for pretrial management. Upon completion\\nof discovery, the parties filed cross-motions for summary\\njudgment.\\n\\n Addressing the cross-motions in a Report and\\nRecommendation, the Magistrate Judge concluded that the\\nATF was authorized to revoke Simpson’s FFLs because he had\\nwillfully committed over 400 violations of the GCA. (App. I\\n33-34). The District Court adopted the report and\\nrecommendation in its entirety, and thus granted summary\\njudgment for the ATF and affirmed its revocation of Simpson’s\\nFFLs. Simpson’s timely appeal followed.\\n\\n\\n\\n II.\\n\\n The District Court had jurisdiction to review the ATF’s\\nrevocation decision under 18 U.S.C. § 923(f), 5 U.S.C. § 702,\\nand 28 U.S.C. § 1331. We have appellate jurisdiction pursuant\\nto 28 U.S.C. § 1291. We exercise de novo review over the\\nDistrict Court’s grant of summary judgment. See, e.g., Kelly\\nv. Borough of Carlisle, 622 F.3d 248, 253 (3d Cir. 2010). A\\ngrant of summary judgment is warranted “if the movant shows\\nthat there is no genuine dispute as to any material fact and the\\nmovant is entitled to judgment as a matter of law.” Fed. R.\\nCiv. P. 56(a). Further, an administrative record “enjoys a\\npresumption of veracity” at summary judgment. Am. Arms\\nInt’l v. Herbert, 563 F.3d 78, 86 n.12 (4th Cir. 2009) (citation\\nomitted).\\n\\n\\n\\n\\n 7\\n\\f III.\\n\\n Under the GCA, the ATF may revoke an FFL if the\\nlicense holder willfully violated any provision of the GCA or\\nany rule or regulation prescribed under the GCA. 18 U.S.C.\\n§ 923(e); see also 27 C.F.R. § 478.73. “A single willful\\nviolation [of the GCA] authorizes the ATF to revoke the\\nviolator’s FFL, regardless of how severe . . . .” Fairmont Cash\\nMgmt., L.L.C. v. James, 858 F.3d 356, 362 (5th Cir. 2017).\\nThus, in the GCA context, our review of the District Court’s\\ngrant of summary judgment requires us to determine whether\\nthere was no genuine dispute as to any material fact\\nestablishing even one willful violation of the GCA. See Am.\\nArms, 563 F.3d at 86 (noting that “a single uncontested\\nviolation suffices to uphold” summary judgment for the ATF\\n(citing Armalite, Inc. v. Lambert, 544 F.3d 644, 649 (6th Cir.\\n2008))).\\n\\n Eight other Courts of Appeals have held that a violation\\nof the GCA is willful where the licensee knew of his legal\\nobligation and purposefully disregarded or was plainly\\nindifferent to the requirements. See Borchardt Rifle, 684 F.3d\\nat 1042; Fairmont Cash Mgmt., 858 F.3d at 362; Armalite, 544\\nF.3d at 647; RSM, Inc. v. Herbert, 466 F.3d 316, 317 (4th Cir.\\n2006); Article II Gun Shop, Inc. v. Gonzales, 441 F.3d 492, 497\\n(7th Cir. 2006); Willingham Sports, Inc. v. ATF, 415 F.3d 1274,\\n1277 (11th Cir. 2005); Perri v. ATF, 637 F.2d 1332, 1336 (9th\\nCir. 1981); Lewin v. Blumenthal, 590 F.2d 268, 269 (8th Cir.\\n1979). We find this definition of willfulness to be appropriate.\\nIndeed, this standard mirrors the willfulness standard we have\\napplied in the parallel context of ATF revocations of fireworks\\nand explosives licenses for violations of federal explosives\\nlaws. See Vineland Fireworks Co. v. ATF, 544 F.3d 509, 517–\\n19 (upholding the ATF’s interpretation of willful because it\\n\\n\\n\\n\\n 8\\n\\fwas reasonable).1 In Vineland, we upheld that willfulness\\n“do[es] not require a bad purpose,” or an intent to disobey the\\nlaw, but rather willfulness can be established by a mere\\n“violation of the regulations with knowledge of their\\nrequirements.” Id. Moreover, both parties in this case agree\\nwith this willfulness standard. Accordingly, we now join our\\nsister circuits in holding that a violation of the GCA is willful\\nwhere the licensee: (1) knew of his legal obligation under the\\nGCA, and (2) either purposefully disregarded or was plainly\\nindifferent to GCA requirements.\\n\\n Here, Simpson has been charged with willfully\\nviolating the GCA over 400 times. He contends that he did not\\nfully understand his obligations and that any violations he\\ncommitted were not willful, but due to mistake or ignorance.\\nWe disagree, as the record indicates that Simpson was well\\napprised of his duties under the GCA but continually violated\\nGCA recordkeeping, manufacturing, and sales requirements.\\n\\n\\n\\n 1\\n In Vineland, we deferred to the ATF’s interpretation\\nof willfulness under federal explosives law because we found\\nit reasonable. See Vineland, 544 F.3d at 518 n.17. Our review\\nof explosives licensing decisions is governed only by 5 U.S.C.\\n§ 706, so we apply Chevron deference to reasonable agency\\ndecisions. See 18 U.S.C. § 843(e)(2); see also Chevron,\\nU.S.A., Inc. v. Nat. Res. Def. Council, Inc., 467 U.S. 837\\n(1984). In contrast, the GCA explicitly tasks courts with\\nconducting de novo review of ATF licensing denials or\\nrevocations. See 18 U.S.C. § 923(f)(3). As such, we review\\ndistrict court decisions regarding ATF firearms licensing de\\nnovo. See, e.g., Willingham Sports, 415 F.3d at 1275-76.\\n\\n\\n\\n\\n 9\\n\\f A.\\n\\n The record shows that Simpson was informed of his\\nobligations as an FFL licensee. For example, Simpson met\\nwith ATF officials three times about his FFLs and, at the\\nconclusion of each meeting, he signed a form acknowledging\\nthat he discussed various regulatory topics with the ATF. In\\naddition, Simpson attended an ATF seminar for FFL holders\\nwhere he learned more about his obligations under the GCA.\\n\\n The record also demonstrates that Simpson often\\ncomplied with GCA requirements. On numerous occasions,\\nSimpson lawfully sold firearms and fully completed the A&D\\nrecordkeeping required under the GCA. Also, he applied to\\nrelocate his FFL, demonstrating that he knew that he was only\\nallowed to sell firearms from his approved FFL location. His\\nfull compliance with GCA requirements in some instances\\nbelies his assertion that he did not understand those\\nrequirements.\\n\\n Further, some of Simpson’s actions illustrate that he\\nunderstood the GCA regulatory scheme quite well. For\\nexample, he sometimes transferred firearms from his FFL\\ninventory to his personal collection, thereby taking advantage\\nof a statutory loophole that allowed him to later sell the\\nfirearms at gun shows without conducting background checks.\\nSuch action is inconsistent with that of a person who does not\\nunderstand the GCA regulatory scheme. Accordingly, we find\\nthat no reasonable fact-finder could disagree that Simpson\\nknew and understood his GCA obligations as an FFL licensee.\\n\\n\\n\\n\\n 10\\n\\f B.\\n\\n In this case, the ATF has alleged that Simpson was\\nplainly indifferent to the GCA’s requirements. We must\\ntherefore determine what constitutes plain indifference under\\nthe willfulness standard we have adopted.\\n\\n Plain indifference is demonstrated by “a lack of concern\\nfor [GCA] regulations. . . .” Am. Arms Int’l, 563 F.3d at 87. A\\nlack of concern may be shown by circumstantial evidence—\\nsuch as repeated violations or a large quantity of violations.\\nSee, e.g., Borchardt Rifle, 684 F.3d at 1043–44; Am. Arms\\nInt’l, 563 F.3d at 87; On Target Sporting Goods, Inc. v. Att’y\\nGen., 472 F.3d 572, 575 (8th Cir. 2007); RSM, Inc., 466 F.3d\\nat 322; Willingham Sports, 415 F.3d at 1277.\\n\\n The ATF charged Simpson with willfully violating a\\nlong list of separate provisions of the GCA under his\\nmanufacturer’s FFL, including, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) dealing firearms outside of his FFL premises;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents;\\n (f) transferring firearms and misidentifying\\n corresponding A&D entries;\\n (g) failing to identify and mark manufactured firearms;\\n (h) failing to record the manufacture of firearms in his\\n A&D book;\\n\\n\\n\\n\\n 11\\n\\f (i) failing to record dispositions of firearms to FFL\\n holders and non-licensees;\\n (j) failing to complete all fields of Form 4473s; and\\n (k) failing to sign and date Form 4473s.\\n\\n(See App. I 8). Additionally, the ATF charged Simpson with\\nwillfully violating another series of provisions of the GCA\\nunder his dealer’s FFL. These include, inter alia:\\n\\n (a) selling firearms without completing Form 4473s;\\n (b) selling or delivering firearms without recording the\\n disposition in his A&D book;\\n (c) transferring firearms without conducting\\n background checks;\\n (d) selling firearms in West Virginia;\\n (e) selling or delivering firearms to non-Pennsylvania\\n residents\\n (f) purchasing firearms without recording the purchases\\n in his A&D book;\\n (g) failing to complete all fields of Form 4473s; and\\n (h) failing to sign and date Form 4473s.\\n\\nId.\\n\\n Simpson contends that all of these violations either were\\nmere mistakes or were due to his “fundamental\\nmisunderstanding as to the importance” of GCA recordkeeping\\nrequirements. (Appellant’s Br. 35). However, in view of the\\nfact that Simpson received training on his obligations and\\nexplicitly acknowledged that he understood his GCA\\nobligations, the sheer number and continuing nature of the\\nviolations clearly demonstrate Simpson’s plain indifference to\\nthe GCA’s requirements.\\n\\n\\n\\n\\n 12\\n\\f While there is no dispute that Simpson violated the\\nGCA on numerous occasions, there is also evidence of other\\nfirearms transactions in which Simpson fully complied with\\nGCA requirements by completing, signing, and dating Form\\n4473s, recording the dispositions in his A&D book, and\\nconducting background checks. This inconsistent conduct\\nsuggests both that Simpson knew of his obligations and was\\nindifferent to complying with them. Moreover, there is\\nevidence of blatant GCA violations. For example, Simpson\\nroutinely transferred receivers to out-of-state residents—in\\nclear violation of the GCA—but falsely recorded the transfers\\nas rifle sales in his A&D book, making these transactions\\nappear lawful. Such behavior is indicative of Simpson’s lack\\nof concern for his GCA obligations as an FFL holder.\\n\\n In sum, the record sufficiently shows that Simpson had\\nknowledge of his FFL obligations, yet acted plainly\\nindifferently to them, thus willfully violating the GCA.\\nAccordingly, we find that the ATF was authorized to revoke\\nSimpson’s FFLs.\\n\\n\\n\\n IV.\\n\\n For the foregoing reasons we will affirm the District\\nCourt’s grant of summary judgment in favor of the ATF,\\naffirming its revocation of Simpson’s FFLs.\\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":60,"cells":{"id":{"kind":"number","value":4578609,"string":"4,578,609"},"name":{"kind":"string","value":"CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent"},"name_abbreviation":{"kind":"string","value":"Chiao Ku v. Attorney General United States"},"decision_date":{"kind":"string","value":"2019-01-03"},"docket_number":{"kind":"string","value":"17-3001"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jordan, Vanaskie, Nygaard\", \"parties\": \"\", \"opinions\": [{\"author\": \"VANASKIE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3001\\n _____________\\n\\n CHIAO FANG KU,\\n AKA Chiao Fang Ronan, AKA Anna Ronan,\\n Petitioner\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _____________\\n\\n On Petition for Review of an Order of the\\n Board of Immigration Appeals\\n (Agency No. A077-160-352)\\n Immigration Judge: Walter A. Durling\\n ______________\\n\\n Argued September 12, 2018\\n ______________\\n\\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\\n Judges\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\\nfiling prior to retiring from the bench on January 1, 2019. Due to the\\nintervening holiday, the opinion has been entered on the docket by the\\nClerk this day.\\n\\f (Opinion Filed: January 3, 2019)\\n\\n\\nThomas M. Griffin [Argued]\\nSurin & Griffin\\n718 Arch Street\\nSuite 701N\\nPhiladelphia, PA 19106\\n Counsel for Petitioner\\n\\nChad A. Readler, Acting Assistant Attorney General\\nNancy E. Friedman, Senior Litigation Counsel\\nJustin R. Markel, Senior Litigation Counsel\\nGregory A. Pennington, Jr. [Argued]\\nUnited States Department of Justice\\nOffice of Immigration Litigation\\nCivil Division\\nP.O. Box 878\\nBen Franklin Station\\nWashington, DC 20044\\n Counsel for Respondent\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nVANASKIE, Circuit Judge.\\n\\n Seeking to remain in this country, Chiao Fang Ku\\npetitions for review of a final order of removal issued by the\\nBoard of Immigration Appeals (“BIA” or “Board”). The\\nBoard determined that Ku had committed an aggravated felony\\n\\n\\n\\n\\n 2\\n\\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\\nconviction for wire fraud constituted an offense involving\\nfraud or deceit in which the loss to the victims exceeded\\n$10,000. The Board also found that Ku’s wire fraud conviction\\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\\nineligible for an adjustment of status. Although the\\nImmigration Judge (“IJ”) granted Ku a waiver of\\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\\nextreme hardship that her deportation would cause her U.S.\\nCitizen children, the Board reversed that decision. Ku\\nchallenges each of the Board’s decisions.\\n\\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\\nheld that determination of whether a fraud offense involved\\nloss to the victims of $10,000 or more requires a circumstance-\\nspecific approach, allowing the immigration court to review\\nboth the charging document and sentencing-related materials\\nto determine the loss amount attributable to the offense. On\\nthe facts of this case, we find that the undisputed loss to the\\nvictims of well over $10,000 was sufficiently tethered to Ku’s\\nwire fraud conviction such that the conviction qualifies as an\\naggravated felony. Furthermore, we find no error in the\\nBoard’s determination that wire fraud constitutes a crime of\\nmoral turpitude. Lastly, regarding the waiver of admissibility,\\nwe do not have jurisdiction to review the discretionary denial\\nof a waiver under § 212(h) of the INA. Accordingly, we will\\ndeny in part and dismiss in part Ku’s petition for review.\\n\\n I.\\n\\n Ku is a native and citizen of Taiwan. She was admitted\\nto the United States in 1997 and gained status as a lawful\\npermanent resident in 2002. In 2014, Ku was charged with a\\n\\n\\n\\n\\n 3\\n\\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\\nKu waived her right to an indictment and was charged by\\ninformation only. The Information alleged that Ku was tasked\\nwith managing the finances of her in-laws, E.R. and M.R, and\\nthat she was provided access to her in-laws’ bank accounts in\\nconnection with this role. The Information further alleged that,\\nbetween May 2008 and July 2013, Ku defrauded her in-laws\\nby using her access to their accounts to take money from them\\nfor her personal use. In particular, it alleged that Ku: (1)\\ntransferred funds from her in-laws’ accounts to her own\\naccounts; (2) withdrew funds from her in-laws’ accounts as\\ncash; (3) made payments from her in-laws’ accounts to pay off\\nher personal credit cards; (4) wrote and cashed checks payable\\nto herself by forging her mother-in-law’s signature; and (5)\\nfraudulently applied for and obtained credit cards in her\\nmother-in-law’s name and used them for her own purposes.\\nThe Information alleged that, in total, Ku stole more than\\n$950,000 from her in-laws.\\n\\n These allegations were incorporated by reference into\\nthe sole count of the Information, which alleged that, on or\\nabout November 7, 2011, Ku,\\n\\n having devised and intending to devise a\\n scheme and artifice to defraud and to obtain\\n money and property by means of materially\\n false and fraudulent pretenses,\\n representations, and promises, did cause\\n writings, signs, signals, pictures, and sounds\\n to be transmitted by means of wire\\n communications in interstate commerce for\\n the purpose of executing such scheme and\\n artifice, to wit: executing an online payment\\n from M.R.’s Sovereign Bank account, ending\\n\\n\\n\\n\\n 4\\n\\f in 8497, to the defendant’s Chase credit card\\n account, ending in 6567, in the amount of\\n $2,290.53.\\n\\n(App. 590). The Information further contained forfeiture\\nallegations, which directed that, upon conviction of the sole\\ncount of the Information, Ku “forfeit to the United States . . .\\nany property, real or personal, that constitutes, or is derived\\nfrom, proceeds traceable to the commission of the offense,\\nincluding but not limited to at least $950,000 in United States\\ncurrency.” (App. 591).\\n\\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\\nsingle count of the Information. In her sentencing\\nmemorandum, Ku, through counsel, acknowledged that she\\nwas “now subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). Ku was ultimately\\nsentenced to a term of 18 months’ imprisonment, followed by\\none year of supervised release. The judgment includes a total\\nloss determination of $954,515.71 and orders restitution in that\\namount. (App. 582).\\n\\n After Ku completed her sentence, she was served with\\na Notice to Appear and placed in removal proceedings. The\\nNotice to Appear charged Ku with being removable under\\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\\nindividual convicted of an aggravated felony as defined in 8\\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\\nconcluded that Ku was removable as charged because the\\n\\n\\n 1\\n The plea agreement is not part of the administrative\\nrecord before us, nor was it in the record before the IJ or BIA.\\n\\n\\n\\n\\n 5\\n\\frecord of conviction substantiated a finding that the wire fraud\\ninvolved a loss of more than $10,000.\\n\\n In order to avoid deportation, Ku sought to re-adjust her\\nstatus based on her U.S. Citizen husband.2 The Immigration\\nJudge granted Ku’s application for a waiver of inadmissibility\\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\\nbased on the extreme hardship that her deportation would cause\\nher U.S. Citizen children, and granted Ku’s adjustment of\\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\\n\\n On appeal, the Board affirmed that the Government\\ndemonstrated by clear and convincing evidence that Ku was\\nremovable as an aggravated felon as defined at\\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\\nin which the loss to the victims exceeded $10,000. In doing so,\\nthe Board noted that the Information alleged that Ku stole more\\nthan $950,000 in funds belonging to her in-laws, and that this\\nallegation was incorporated by reference into the count to\\nwhich Ku pleaded guilty. It also observed that the Information\\nalso contained a forfeiture allegation stating that, upon\\nconviction, Ku would forfeit over $950,000 in currency.\\nFinally, the Board considered relevant that the Judgment of\\nConviction found a total loss of over $950,000 and ordered\\nrestitution in that amount.\\n\\n The Board further concluded that Ku’s conviction was\\nfor a crime involving moral turpitude, making her inadmissible\\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\\n\\n 2\\n Ku's present husband is not the man to whom she was\\npreviously married and whose parents are the elderly in-laws\\nshe defrauded.\\n\\n\\n\\n\\n 6\\n\\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\\nfor adjustment of status of certain aliens to that of an alien\\nlawfully admitted for permanent residence); see also 8 U.S.C.\\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\\ndiscretion of the Attorney General). Although it acknowledged\\nthe hardship posed to her family, the Board ultimately found\\nthat, given the severity of her crime, Ku did not merit a\\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\\nand denied Ku’s applications for a § 212(h) waiver and for\\nadjustment of status. Ku timely filed a petition for review.\\n\\n II.\\n\\n Although we have jurisdiction to review final orders of\\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\\n\\n 3\\n We have taken a broad view of what constitutes a\\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\\njurisdictional purposes when a removability determination has\\nbeen made that is no longer appealable to the BIA, regardless\\n[of] whether a formal order of removal has been entered.” Id.\\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\\nof removal, and relief under the [Convention Against Torture]\\nconstitutes ‘a final order of removal’ within the meaning of\\n[§ 1252], [because] the alien is entitled to no further process\\nbefore deportation.”). Here, although the Board did not\\nexplicitly order Ku removed to Taiwan, it found her removable\\nand denied her application for adjustment of status, her only\\npetition for relief. (App. 5). Furthermore, the Board sustained\\nDHS’s appeal, which requested that Ku be ordered removed to\\nTaiwan. Accordingly, for the purposes of this appeal, we\\n\\n\\n\\n\\n 7\\n\\fjurisdiction to review any final order of removal against an\\nalien who is removable by reason of having committed [an\\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\\nhowever, have jurisdiction to examine ‘constitutional claims or\\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\\nhave authority to take up the issue, applying plenary review, of\\nwhether Ku’s conviction qualifies as an aggravated felony\\nbecause it is “a purely legal question, and one that governs our\\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\\n203, 207 (3d Cir. 2002)). We also review de novo the legal\\nquestion of what elements of a federal criminal statute\\nimplicate moral turpitude, while affording Chevron deference\\nto the Board’s definition of “moral turpitude.” Knapik v.\\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\\n\\n III.\\n\\n On appeal, Ku challenges all three aspects of the BIA’s\\norder. First, she contends that the BIA incorrectly determined\\nthat her wire-fraud conviction involved a loss of more than\\n$10,000 by relying on evidence that was not sufficiently\\ntethered to the sole count of conviction.4 Second, Ku argues\\n\\n\\nconsider the Board’s order to be a final order of removal. The\\nGovernment’s motion to remand this case to the Board for\\nissuance of an order directing that Ku be removed to Taiwan\\nand to allow the IJ to make additional findings on removability\\nwill be denied as moot.\\n 4\\n We note that Ku does not challenge—and did not\\nchallenge before the IJ or the Board—that her wire fraud\\n\\n\\n\\n\\n 8\\n\\fthat the Board erred in finding that her wire-fraud conviction\\nwas for a crime involving moral turpitude because the statute\\nof conviction does not require a showing of intent. Third, Ku\\nasserts that the BIA applied the incorrect legal standard in\\nreversing the IJ’s grant of a discretionary waiver of\\ninadmissibility. We reject all three of Ku’s challenges and\\ntherefore deny the petition for review.\\n\\n A.\\n\\n Section 237(a)(2)(A)(iii) of the INA, as amended,\\nprovides that “[a]ny alien who is convicted of an aggravated\\nfelony at any time after admission is deportable.” 8 U.S.C.\\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\\nrelevant part, as an offense that “involves fraud or deceit in\\nwhich the loss to the victim or victims exceeds $10,000.” 8\\nU.S.C. § 1101(a)(43)(M)(i).\\n\\n In Nijhawan v. Holder, the Supreme Court addressed\\nthe issue of whether the $10,000 threshold of the aggravated\\nfelony statute “refers to an element of a fraud statute or to the\\nfactual circumstances surrounding commission of the crime on\\na specific occasion.” 557 U.S. at 33. The Court adopted the\\nlatter interpretation, characterizing the review as examining\\n“the specific way in which an offender committed the crime on\\na specific occasion.” Id. at 34. The Court distinguished the\\n“circumstance-specific approach” to be used in determining\\nwhether a crime “involves fraud or deceit in which the loss to\\nthe victim or victims exceeds $10,000” from the “categorical\\napproach” used in determining whether a crime is a “violent\\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\\n\\nconviction “involves fraud or deceit” under 8 U.S.C.\\n§ 1101(a)(43)(M).\\n\\n\\n\\n\\n 9\\n\\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\\nso-called “modified categorical approach” employed in some\\ncontexts, which would limit an IJ’s consideration to charging\\ndocuments, jury instructions, special jury findings, or some\\nequivalent judge-made findings and—in the case of a guilty\\nplea—to the written plea documents or plea colloquy. Id. at\\n41. While the Supreme Court acknowledged that “the statute\\nforesees the use of fundamentally fair procedures,” it rejected\\nthe argument that fairness requires such evidentiary\\nlimitations. Id. Accordingly, it found “nothing unfair” about\\nthe IJ’s reliance upon the defendant’s stipulation and the\\ndistrict court’s restitution order to determine that the crime at\\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\\nId. at 42–43.\\n\\n Since Nijhawan, we have consistently applied the\\ncircumstance-specific approach to determine the amount of\\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\\naddressed the issue in Fan Wang, in which we reviewed “not\\nonly those documents that may be considered in a modified\\ncategorical approach (the indictment, plea agreement, and\\njudgment),” but also others, including “the presentence\\ninvestigation report and any sentencing-related material.” 898\\nF.3d at 348–49 (citations and internal quotation marks\\nomitted). Relying on Nijhawan, we reasoned that\\nconsideration of such materials “is appropriate so long as the\\npetitioner has been given a ‘fair opportunity’ to challenge the\\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\\nat 41). Accordingly, we determined that the Board did not go\\nbeyond the bounds of proper review by examining the record—\\nincluding the sole count of the superseding information, the\\n\\n\\n\\n\\n 10\\n\\fplea colloquy, the presentence investigation report, the “total\\nloss” specified in the judgment, and the restitution order—to\\ndetermine whether the petitioner’s prior conviction was an\\n“aggravated felony.” Id. at 349–50. In determining the proper\\namount of loss in that case, we were persuaded by the\\nGovernment’s argument that the loss amount listed in the\\njudgment and restitution order was “undeniably tethered” to\\nthe conduct for which the petitioner was convicted. Id. at 351.\\n\\n We consider the loss to the victims in this case—as\\nevidenced by the Information, Judgment, and Restitution\\nOrder—to be sufficiently tethered to the count of conviction\\nsuch that Ku’s conviction was an aggravated felony.\\nParagraphs 1 through 10 of the Information allege that Ku stole\\nmore than $950,000 in funds belonging to her in-laws, and\\nthese paragraphs were incorporated by reference into the count\\nto which Ku pleaded guilty. Furthermore, the forfeiture\\nallegation contained in the Information states that, upon\\nconviction, Ku would forfeit the “proceeds traceable to the\\ncommission of the offense, including but not limited to at least\\n$950,000 in United States currency.” (App. 591). Finally, the\\nJudgment of Conviction indicates a loss of $954,515.71 and\\norders restitution in that amount. Each of these documents is\\nreviewable under the circumstance-specific approach laid out\\nby the Supreme Court in Nijhawan. Together, they provide\\nclear and convincing evidence that Ku’s offense involved a\\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\\narguments to the contrary, all of which lack merit.\\n\\n 1.\\n\\n First, Ku contends that the circumstance-specific\\napproach described in Nijhawan does not apply in her case\\nbecause the single count of the Information made clear that it\\n\\n\\n\\n\\n 11\\n\\fwas for the specified amount of $2,290.53. She urges us to\\nread Nijhawan to have kept intact the modified categorical\\napproach for cases in which the charging document contains a\\nclear indication of the loss amount. Under the modified\\ncategorical approach, she contends, the Board was correct in\\nreviewing the Information but, because the count of conviction\\ncontains a loss amount of $2,290.53, the Board should have\\nstopped there.\\n\\n Contrary to Ku’s assertion, Nijhawan does not stand for\\nthe proposition that, when the count of conviction contains a\\nloss amount, immigration officials must look no further. The\\nSupreme Court explicitly rejected the use of the modified\\ncategorical approach in determining whether a prior conviction\\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\\n(interpreting Nijhawan). Rather, it determined that the\\ncircumstance-specific approach is required because the\\naggravated felony statute “refers to the particular\\ncircumstances in which an offender committed a (more broadly\\ndefined) fraud or deceit crime on a particular occasion,” and\\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\\nNoting that the Government in immigration proceedings is\\nheld only to a “clear and convincing” burden of proof, and not\\n“beyond a reasonable doubt,” the Supreme Court found\\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\\nrelated material”—in that case a sentencing stipulation and\\nrestitution order. Id. at 42–43. It also noted that “the sole\\npurpose of the aggravated felony inquiry is to ascertain the\\nnature of a prior conviction; it is not an invitation to relitigate\\nthe conviction itself.” Id. (internal quotation marks omitted).\\n\\n Nothing in Nijhawan suggests that the circumstance-\\nspecific approach applies in some cases but not others, or that\\n\\n\\n\\n\\n 12\\n\\fthe documents reviewable under that approach vary from case\\nto case. Furthermore, we have consistently interpreted\\nNijhawan as allowing an IJ, in determining the loss amount, to\\nlook beyond the charging document to sentencing-related\\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\\nF.3d at 348–49. Ku has not persuaded us that our reading is\\nincorrect.\\n\\n 2.\\n\\n Second, Ku contends that, because her conviction was\\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\\ncaused through other acts and transactions are not sufficiently\\n“tethered” to the count of conviction for purposes of the\\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\\nKu asks us to read the Information as charging her in Count\\nOne with a “scheme and artifice to defraud” her in-laws of\\n$2,290.53, and not as charging her with one instance of wire\\nfraud that was part of a broader “scheme and artifice to\\ndefraud” her in-laws of over $950,000. However, such an\\ninterpretation is inconsistent with the language of the\\nInformation. In Count One, the Government “re-alleges and\\nincorporates by reference” the first eight paragraphs, which\\nallege that, over five years, Ku defrauded her in-laws of more\\nthan $950,000 by transferring funds from their accounts to her\\nown accounts, withdrawing funds as cash, making payments to\\ncredit card companies for charges she incurred, and writing and\\ncashing checks payable to herself. (App. 588–90). The explicit\\nincorporation of those paragraphs into the count to which Ku\\npleaded guilty supports an interpretation of the count itself as\\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\\nof more than $950,000.\\n\\n\\n\\n\\n 13\\n\\f We are similarly unpersuaded by Ku’s contention that,\\nbecause Paragraphs 1 through 8 of the Information describe\\nconduct that does not necessarily amount to wire fraud, such\\nconduct cannot count toward the total loss resulting from her\\nconviction. It is incontrovertible that the “scheme and artifice\\nto defraud” charged in Count One of the Information\\nencompassed the whole course of Ku’s unlawful conduct,\\nincluding the one incident in which Ku committed wire fraud\\nin the amount of $2,390.53, and which resulted in a total loss\\nof over $950,000. In short, because Ku pleaded guilty to\\ncommitting wire fraud as part of a scheme to defraud her in-\\nlaws of more than $950,000, the total loss amount is, to use our\\nlanguage from Fan Wang, “undeniably tethered” to her wire\\nfraud conviction.\\n\\n 3.\\n\\n Finally, Ku contends that the single-count Information\\nto which she pleaded guilty is part of the “justice package”\\nworked out between her and the Government and urges the\\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\\ndoing so, Ku relies on our opinion in Alaka v. Attorney\\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\\nthis case make it distinguishable from Alaka.\\n\\n In Alaka—which we decided prior to Nijhawan5—we\\nheld that the IJ erred by considering the amount of intended\\n\\n\\n 5\\n Because Alaka was decided prior to the Supreme\\nCourt’s decision in Nijhawan, its application of the modified\\ncategorical approach to the aggravated-felony analysis does\\nnot affect our decision. However, to the extent that Alaka\\nstands for the proposition that an IJ may not consider dismissed\\n\\n\\n\\n\\n 14\\n\\floss for all of the charges against the petitioner rather than the\\nsingle count for which she was convicted. Alaka, 456 F.3d at\\n106. The petitioner had been indicted on three counts for\\nconduct involving fraudulent checks, but was convicted of only\\none count, for which the actual loss was $4,716.68. Id. at 92.\\nThe sentencing court nonetheless held that the petitioner’s\\nconduct was part of a “common scheme or plan,” and therefore\\nfound the total intended loss to be nearly $50,000. Id. It\\nordered her to pay $4,716.68 in restitution. Id. In subsequent\\nimmigration proceedings, the IJ concluded that the petitioner\\nhad been convicted of an aggravated felony on the ground that\\nthe intended loss was more than $10,000. Id. at 105, n.27. On\\nappeal, we determined that, while the IJ properly considered\\nthe factual findings of the sentencing report in determining\\nwhether the offense was an aggravated felony, the loss amount\\ntied to the dismissed charges was not properly considered as\\npart of the aggravated-felony analysis. Id. at 106–08. In doing\\nso, we noted that “the plain and unambiguous language of the\\nstatute . . . predicates removal on a convicted offense resulting\\nin losses greater than $10,000,” thereby foreclosing inclusion\\nof losses stemming from unconvicted offenses. Id. 106–07\\n(citations omitted). Furthermore, we considered that, because\\nit is “the plea agreement that establishes the offense for which\\nthe defendant will be convicted, it is to that agreement, and not\\nthe indictment or the sentence, that we look in determining the\\nintended loss.” Id. at 107. The petitioner “unmistakably pled\\nguilty to one count, and the plea agreement plainly documented\\nthat loss at less than $10,000.” Id. at 108 (citations and\\nalterations omitted). Because the plea agreement “spell[ed] it\\nout for us in black and white,” we concluded that the plea\\n\\n\\ncharges when calculating the loss attributable to the conviction,\\nit remains good law.\\n\\n\\n\\n\\n 15\\n\\fagreement alone established the loss amount, and “not . . . the\\nloss charged in the indictment, tabulated for restitution\\npurposes, or calculated for sentencing.” Id. (citations omitted).\\n\\n Here, in stark contrast to the petitioner in Alaka, the\\nrecord before us contains no plea agreement, and certainly not\\none which explicitly spells out the loss amount to which Ku\\npleaded guilty. Instead, Ku urges us to find that, based on the\\nfact that the Government could have charged her with a much\\nlonger list of crimes but did not, the loss amount as indicated\\nin Count One was part of an explicit bargain between her and\\nthe Government. However, this argument is based on pure\\nconjecture. Absent a clear and unmistakable indication of loss\\nin a written plea agreement, we are left with only the\\nInformation, Judgment, and Restitution Order to determine the\\nloss attributable to Ku’s conviction. As explained above, these\\ndocuments, taken together, provide clear and convincing\\nevidence that the loss amount attributable to Ku’s wire fraud\\nconviction exceeded $10,000, and Ku has provided no plea\\nagreement or any other document to the contrary.6\\n\\n 6\\n The sentencing court in Alaka calculated the total loss\\namount based on the “common scheme or plan,” which, it\\nconsidered, included both the count of conviction and the\\ndismissed counts, and we considered the IJ’s reliance on that\\ncalculation to be in error in light of the plea agreement. 456\\nF.3d at 106. But this does not help Ku. As explained above,\\nthe wire fraud count to which Ku pleaded guilty was based in\\npart on her “scheme and artifice to defraud” her in-laws of over\\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\\nthe sentencing court in this case did not base its loss calculation\\non any acts that were not explicitly incorporated into the count\\nof conviction.\\n\\n\\n\\n\\n 16\\n\\f Ku’s argument that this Court should respect the\\n“justice package” between her and the Government also\\ntouches on the Supreme Court’s landmark holdings in Padilla\\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\\ntoward respecting agreements between criminal defendants\\nand the Government with respect to the collateral\\nconsequences of a conviction. But this line of argument merely\\nhighlights another critical shortcoming of Ku’s case. To the\\nextent Ku argues that the Information was designed\\nspecifically to avoid immigration consequences, there is no\\nevidence in the record to support such a finding. Indeed, Ku’s\\nattorney indicated in her sentencing memorandum that Ku “is\\nnow subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). This statement, while not\\nconclusive, certainly undermines any assertion that the “justice\\npackage” referred to by Ku was designed to avoid an\\naggravated felony conviction. Indeed, absent any other\\nevidence in the record to the contrary, the sentencing\\nmemorandum supports a finding that, at the time of her guilty\\nplea, Ku understood that she was pleading guilty to an\\naggravated felony.\\n\\n B.\\n\\n Having concluded that the Board did not err in finding\\nthat Ku was convicted of an aggravated felony, we turn to the\\nquestion of whether Ku’s conviction constituted a “crime\\ninvolving moral turpitude” under the INA. Ku argues that wire\\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\\nthe specific intent to defraud. This is incorrect.\\n\\n\\n\\n\\n 17\\n\\f The statute provides that a person is guilty of wire fraud\\nif, “having devised or intending to devise any scheme or\\nartifice to defraud,” that person “transmits or causes to be\\ntransmitted by means of wire, radio, or television\\ncommunication in interstate or foreign commerce, any\\nwritings, signs, signals, pictures, or sounds for the purpose of\\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\\nhave long treated fraud crimes as “involving moral turpitude.”\\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\\ndecided cases make it plain that crimes in which fraud was an\\ningredient have always been regarded as involving moral\\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\\nfall well within the recognized definition of ‘crimes involving\\nmoral turpitude.’”). Furthermore, we have also consistently\\nread the wire fraud statute as containing the element of specific\\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\\n(3d Cir. 2012) (“To prove wire fraud, the Government must\\nestablish (1) the defendant’s knowing and willful participation\\nin a scheme or artifice to defraud, (2) with the specific intent to\\ndefraud, and (3) the use of . . . interstate wire communications\\nin furtherance of the scheme.”) (internal quotation marks\\nomitted) (emphasis added).\\n\\n Seeking to persuade us to revisit these tenets, Ku asks\\nus to read the statutory terms “having devised” and “intending\\nto devise” as disjunctive means of committing wire fraud, the\\nlatter containing the mens rea of intent, and the former\\neschewing any mens rea at all. But the language of the statute\\ndoes not lend itself to such an interpretation. The specific\\nintent requirement is contained in the latter part of the statute—\\n“for the purpose of executing [a] scheme or artifice [to\\ndefraud]”—and must be proved regardless of whether the\\n\\n\\n\\n\\n 18\\n\\fperson made the transmission after “having devised” or while\\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\\nPlainly read, the language Ku seizes on, “having devised or\\nintending to devise,” refers not to the requisite mens rea but to\\nthe temporal relationship between the formation of the fraud\\nscheme and the transmission itself. Either way, the person\\nmust have made the transmission for the purpose of executing\\nthe fraud scheme in order to be convicted.\\n\\n Ku’s statutory interpretation argument holds no weight.\\nAccordingly, we see no need to revisit the long-held tenet that\\nfraud crimes—including wire fraud—are crimes involving\\nmoral turpitude under the INA.\\n\\n C.\\n\\n Finally, Ku asks us to find that the Board committed\\nerror in its reversal of the IJ’s finding that she was eligible for\\na discretionary waiver of inadmissibility based on the hardship\\nher deportation would cause her U.S. citizen children.\\nHowever, we lack jurisdiction over the Board’s decision on\\nthis point.\\n\\n The INA provides that an alien is inadmissible to the\\nUnited States if she has been convicted of a crime involving\\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\\nprovides, however, that the Attorney General may waive\\ninadmissibility to allow an applicant to obtain adjustment of\\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\\nof a United States citizen . . . and can show that denial of\\nadmission would cause extreme hardship to the citizen . . . .”\\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\\n2002). The authority to waive one or more grounds of\\ninadmissibility is vested solely in the Attorney General and “no\\n\\n\\n\\n\\n 19\\n\\fcourt shall have jurisdiction to review” a decision to deny such\\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\\n\\n We may, however, review “constitutional claims or\\nquestions of law raised upon a petition for review . . . .” Id. at\\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\\ncircumscribed” in that it is limited to “colorable claims or\\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\\nCir. 2008) (per curiam) (quotation marks and citation omitted).\\nWhile “[t]he question of our jurisdiction over a colorable legal\\nclaim does not turn on whether that claim is ultimately\\nmeritorious . . . , a party may not dress up a claim with legal\\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\\n\\n Ku argues that we have jurisdiction to consider her\\npetition for review on the waiver issue because it presents a\\nquestion of law, namely whether the Board applied the proper\\nlegal standard in making the discretionary determination. But\\nKu’s argument boils down to her contention that the Board\\nfailed to consider certain equities relevant to the hardship\\ndetermination. As we have consistently held, “arguments such\\nas that an Immigration Judge or the BIA incorrectly weighed\\nevidence, failed to consider evidence or improperly weighed\\nequitable factors are not questions of law under\\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\\n(3d Cir. 2007). Because the substance of Ku’s petition for\\nreview amounts to contesting the weight the Board should have\\ngiven to the positive equities of her case, we do not have\\njurisdiction over it and will dismiss in part that aspect of the\\npetition.\\n\\n IV.\\n\\n\\n\\n\\n 20\\n\\f For the foregoing reasons, we will deny in part and\\ndismiss in part Ku's petition for review, and we will deny as\\nmoot the Government's motion to remand.\\n\\n\\n\\n\\n 21\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4355862/\", \"author_raw\": \"VANASKIE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"JORDAN"},"judge2":{"kind":"string","value":"VANASKIE"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4578609/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-3001\n _____________\n\n CHIAO FANG KU,\n AKA Chiao Fang Ronan, AKA Anna Ronan,\n Petitioner\n v.\n\nATTORNEY GENERAL UNITED STATES OF AMERICA,\n Respondent\n _____________\n\n On Petition for Review of an Order of the\n Board of Immigration Appeals\n (Agency No. A077-160-352)\n Immigration Judge: Walter A. Durling\n ______________\n\n Argued September 12, 2018\n ______________\n\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\n Judges\n\n\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\nfiling prior to retiring from the bench on January 1, 2019. Due to the\nintervening holiday, the opinion has been entered on the docket by the\nClerk this day.\n\f (Opinion Filed: January 3, 2019)\n\n\nThomas M. Griffin [Argued]\nSurin & Griffin\n718 Arch Street\nSuite 701N\nPhiladelphia, PA 19106\n Counsel for Petitioner\n\nChad A. Readler, Acting Assistant Attorney General\nNancy E. Friedman, Senior Litigation Counsel\nJustin R. Markel, Senior Litigation Counsel\nGregory A. Pennington, Jr. [Argued]\nUnited States Department of Justice\nOffice of Immigration Litigation\nCivil Division\nP.O. Box 878\nBen Franklin Station\nWashington, DC 20044\n Counsel for Respondent\n\n ________________\n\n OPINION\n ________________\n\n\nVANASKIE, Circuit Judge.\n\n Seeking to remain in this country, Chiao Fang Ku\npetitions for review of a final order of removal issued by the\nBoard of Immigration Appeals (“BIA” or “Board”). The\nBoard determined that Ku had committed an aggravated felony\n\n\n\n\n 2\n\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\nconviction for wire fraud constituted an offense involving\nfraud or deceit in which the loss to the victims exceeded\n$10,000. The Board also found that Ku’s wire fraud conviction\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\nineligible for an adjustment of status. Although the\nImmigration Judge (“IJ”) granted Ku a waiver of\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\nextreme hardship that her deportation would cause her U.S.\nCitizen children, the Board reversed that decision. Ku\nchallenges each of the Board’s decisions.\n\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\nheld that determination of whether a fraud offense involved\nloss to the victims of $10,000 or more requires a circumstance-\nspecific approach, allowing the immigration court to review\nboth the charging document and sentencing-related materials\nto determine the loss amount attributable to the offense. On\nthe facts of this case, we find that the undisputed loss to the\nvictims of well over $10,000 was sufficiently tethered to Ku’s\nwire fraud conviction such that the conviction qualifies as an\naggravated felony. Furthermore, we find no error in the\nBoard’s determination that wire fraud constitutes a crime of\nmoral turpitude. Lastly, regarding the waiver of admissibility,\nwe do not have jurisdiction to review the discretionary denial\nof a waiver under § 212(h) of the INA. Accordingly, we will\ndeny in part and dismiss in part Ku’s petition for review.\n\n I.\n\n Ku is a native and citizen of Taiwan. She was admitted\nto the United States in 1997 and gained status as a lawful\npermanent resident in 2002. In 2014, Ku was charged with a\n\n\n\n\n 3\n\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\nKu waived her right to an indictment and was charged by\ninformation only. The Information alleged that Ku was tasked\nwith managing the finances of her in-laws, E.R. and M.R, and\nthat she was provided access to her in-laws’ bank accounts in\nconnection with this role. The Information further alleged that,\nbetween May 2008 and July 2013, Ku defrauded her in-laws\nby using her access to their accounts to take money from them\nfor her personal use. In particular, it alleged that Ku: (1)\ntransferred funds from her in-laws’ accounts to her own\naccounts; (2) withdrew funds from her in-laws’ accounts as\ncash; (3) made payments from her in-laws’ accounts to pay off\nher personal credit cards; (4) wrote and cashed checks payable\nto herself by forging her mother-in-law’s signature; and (5)\nfraudulently applied for and obtained credit cards in her\nmother-in-law’s name and used them for her own purposes.\nThe Information alleged that, in total, Ku stole more than\n$950,000 from her in-laws.\n\n These allegations were incorporated by reference into\nthe sole count of the Information, which alleged that, on or\nabout November 7, 2011, Ku,\n\n having devised and intending to devise a\n scheme and artifice to defraud and to obtain\n money and property by means of materially\n false and fraudulent pretenses,\n representations, and promises, did cause\n writings, signs, signals, pictures, and sounds\n to be transmitted by means of wire\n communications in interstate commerce for\n the purpose of executing such scheme and\n artifice, to wit: executing an online payment\n from M.R.’s Sovereign Bank account, ending\n\n\n\n\n 4\n\f in 8497, to the defendant’s Chase credit card\n account, ending in 6567, in the amount of\n $2,290.53.\n\n(App. 590). The Information further contained forfeiture\nallegations, which directed that, upon conviction of the sole\ncount of the Information, Ku “forfeit to the United States . . .\nany property, real or personal, that constitutes, or is derived\nfrom, proceeds traceable to the commission of the offense,\nincluding but not limited to at least $950,000 in United States\ncurrency.” (App. 591).\n\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\nsingle count of the Information. In her sentencing\nmemorandum, Ku, through counsel, acknowledged that she\nwas “now subject to automatic deportation as a result of her\nconviction in this case.” (App. 740). Ku was ultimately\nsentenced to a term of 18 months’ imprisonment, followed by\none year of supervised release. The judgment includes a total\nloss determination of $954,515.71 and orders restitution in that\namount. (App. 582).\n\n After Ku completed her sentence, she was served with\na Notice to Appear and placed in removal proceedings. The\nNotice to Appear charged Ku with being removable under\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\nindividual convicted of an aggravated felony as defined in 8\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\nconcluded that Ku was removable as charged because the\n\n\n 1\n The plea agreement is not part of the administrative\nrecord before us, nor was it in the record before the IJ or BIA.\n\n\n\n\n 5\n\frecord of conviction substantiated a finding that the wire fraud\ninvolved a loss of more than $10,000.\n\n In order to avoid deportation, Ku sought to re-adjust her\nstatus based on her U.S. Citizen husband.2 The Immigration\nJudge granted Ku’s application for a waiver of inadmissibility\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\nbased on the extreme hardship that her deportation would cause\nher U.S. Citizen children, and granted Ku’s adjustment of\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\n\n On appeal, the Board affirmed that the Government\ndemonstrated by clear and convincing evidence that Ku was\nremovable as an aggravated felon as defined at\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\nin which the loss to the victims exceeded $10,000. In doing so,\nthe Board noted that the Information alleged that Ku stole more\nthan $950,000 in funds belonging to her in-laws, and that this\nallegation was incorporated by reference into the count to\nwhich Ku pleaded guilty. It also observed that the Information\nalso contained a forfeiture allegation stating that, upon\nconviction, Ku would forfeit over $950,000 in currency.\nFinally, the Board considered relevant that the Judgment of\nConviction found a total loss of over $950,000 and ordered\nrestitution in that amount.\n\n The Board further concluded that Ku’s conviction was\nfor a crime involving moral turpitude, making her inadmissible\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\n\n 2\n Ku's present husband is not the man to whom she was\npreviously married and whose parents are the elderly in-laws\nshe defrauded.\n\n\n\n\n 6\n\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\nfor adjustment of status of certain aliens to that of an alien\nlawfully admitted for permanent residence); see also 8 U.S.C.\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\ndiscretion of the Attorney General). Although it acknowledged\nthe hardship posed to her family, the Board ultimately found\nthat, given the severity of her crime, Ku did not merit a\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\nand denied Ku’s applications for a § 212(h) waiver and for\nadjustment of status. Ku timely filed a petition for review.\n\n II.\n\n Although we have jurisdiction to review final orders of\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\n\n 3\n We have taken a broad view of what constitutes a\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\njurisdictional purposes when a removability determination has\nbeen made that is no longer appealable to the BIA, regardless\n[of] whether a formal order of removal has been entered.” Id.\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\nof removal, and relief under the [Convention Against Torture]\nconstitutes ‘a final order of removal’ within the meaning of\n[§ 1252], [because] the alien is entitled to no further process\nbefore deportation.”). Here, although the Board did not\nexplicitly order Ku removed to Taiwan, it found her removable\nand denied her application for adjustment of status, her only\npetition for relief. (App. 5). Furthermore, the Board sustained\nDHS’s appeal, which requested that Ku be ordered removed to\nTaiwan. Accordingly, for the purposes of this appeal, we\n\n\n\n\n 7\n\fjurisdiction to review any final order of removal against an\nalien who is removable by reason of having committed [an\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\nhowever, have jurisdiction to examine ‘constitutional claims or\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\nhave authority to take up the issue, applying plenary review, of\nwhether Ku’s conviction qualifies as an aggravated felony\nbecause it is “a purely legal question, and one that governs our\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\n203, 207 (3d Cir. 2002)). We also review de novo the legal\nquestion of what elements of a federal criminal statute\nimplicate moral turpitude, while affording Chevron deference\nto the Board’s definition of “moral turpitude.” Knapik v.\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\n\n III.\n\n On appeal, Ku challenges all three aspects of the BIA’s\norder. First, she contends that the BIA incorrectly determined\nthat her wire-fraud conviction involved a loss of more than\n$10,000 by relying on evidence that was not sufficiently\ntethered to the sole count of conviction.4 Second, Ku argues\n\n\nconsider the Board’s order to be a final order of removal. The\nGovernment’s motion to remand this case to the Board for\nissuance of an order directing that Ku be removed to Taiwan\nand to allow the IJ to make additional findings on removability\nwill be denied as moot.\n 4\n We note that Ku does not challenge—and did not\nchallenge before the IJ or the Board—that her wire fraud\n\n\n\n\n 8\n\fthat the Board erred in finding that her wire-fraud conviction\nwas for a crime involving moral turpitude because the statute\nof conviction does not require a showing of intent. Third, Ku\nasserts that the BIA applied the incorrect legal standard in\nreversing the IJ’s grant of a discretionary waiver of\ninadmissibility. We reject all three of Ku’s challenges and\ntherefore deny the petition for review.\n\n A.\n\n Section 237(a)(2)(A)(iii) of the INA, as amended,\nprovides that “[a]ny alien who is convicted of an aggravated\nfelony at any time after admission is deportable.” 8 U.S.C.\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\nrelevant part, as an offense that “involves fraud or deceit in\nwhich the loss to the victim or victims exceeds $10,000.” 8\nU.S.C. § 1101(a)(43)(M)(i).\n\n In Nijhawan v. Holder, the Supreme Court addressed\nthe issue of whether the $10,000 threshold of the aggravated\nfelony statute “refers to an element of a fraud statute or to the\nfactual circumstances surrounding commission of the crime on\na specific occasion.” 557 U.S. at 33. The Court adopted the\nlatter interpretation, characterizing the review as examining\n“the specific way in which an offender committed the crime on\na specific occasion.” Id. at 34. The Court distinguished the\n“circumstance-specific approach” to be used in determining\nwhether a crime “involves fraud or deceit in which the loss to\nthe victim or victims exceeds $10,000” from the “categorical\napproach” used in determining whether a crime is a “violent\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\n\nconviction “involves fraud or deceit” under 8 U.S.C.\n§ 1101(a)(43)(M).\n\n\n\n\n 9\n\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\nso-called “modified categorical approach” employed in some\ncontexts, which would limit an IJ’s consideration to charging\ndocuments, jury instructions, special jury findings, or some\nequivalent judge-made findings and—in the case of a guilty\nplea—to the written plea documents or plea colloquy. Id. at\n41. While the Supreme Court acknowledged that “the statute\nforesees the use of fundamentally fair procedures,” it rejected\nthe argument that fairness requires such evidentiary\nlimitations. Id. Accordingly, it found “nothing unfair” about\nthe IJ’s reliance upon the defendant’s stipulation and the\ndistrict court’s restitution order to determine that the crime at\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\nId. at 42–43.\n\n Since Nijhawan, we have consistently applied the\ncircumstance-specific approach to determine the amount of\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\naddressed the issue in Fan Wang, in which we reviewed “not\nonly those documents that may be considered in a modified\ncategorical approach (the indictment, plea agreement, and\njudgment),” but also others, including “the presentence\ninvestigation report and any sentencing-related material.” 898\nF.3d at 348–49 (citations and internal quotation marks\nomitted). Relying on Nijhawan, we reasoned that\nconsideration of such materials “is appropriate so long as the\npetitioner has been given a ‘fair opportunity’ to challenge the\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\nat 41). Accordingly, we determined that the Board did not go\nbeyond the bounds of proper review by examining the record—\nincluding the sole count of the superseding information, the\n\n\n\n\n 10\n\fplea colloquy, the presentence investigation report, the “total\nloss” specified in the judgment, and the restitution order—to\ndetermine whether the petitioner’s prior conviction was an\n“aggravated felony.” Id. at 349–50. In determining the proper\namount of loss in that case, we were persuaded by the\nGovernment’s argument that the loss amount listed in the\njudgment and restitution order was “undeniably tethered” to\nthe conduct for which the petitioner was convicted. Id. at 351.\n\n We consider the loss to the victims in this case—as\nevidenced by the Information, Judgment, and Restitution\nOrder—to be sufficiently tethered to the count of conviction\nsuch that Ku’s conviction was an aggravated felony.\nParagraphs 1 through 10 of the Information allege that Ku stole\nmore than $950,000 in funds belonging to her in-laws, and\nthese paragraphs were incorporated by reference into the count\nto which Ku pleaded guilty. Furthermore, the forfeiture\nallegation contained in the Information states that, upon\nconviction, Ku would forfeit the “proceeds traceable to the\ncommission of the offense, including but not limited to at least\n$950,000 in United States currency.” (App. 591). Finally, the\nJudgment of Conviction indicates a loss of $954,515.71 and\norders restitution in that amount. Each of these documents is\nreviewable under the circumstance-specific approach laid out\nby the Supreme Court in Nijhawan. Together, they provide\nclear and convincing evidence that Ku’s offense involved a\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\narguments to the contrary, all of which lack merit.\n\n 1.\n\n First, Ku contends that the circumstance-specific\napproach described in Nijhawan does not apply in her case\nbecause the single count of the Information made clear that it\n\n\n\n\n 11\n\fwas for the specified amount of $2,290.53. She urges us to\nread Nijhawan to have kept intact the modified categorical\napproach for cases in which the charging document contains a\nclear indication of the loss amount. Under the modified\ncategorical approach, she contends, the Board was correct in\nreviewing the Information but, because the count of conviction\ncontains a loss amount of $2,290.53, the Board should have\nstopped there.\n\n Contrary to Ku’s assertion, Nijhawan does not stand for\nthe proposition that, when the count of conviction contains a\nloss amount, immigration officials must look no further. The\nSupreme Court explicitly rejected the use of the modified\ncategorical approach in determining whether a prior conviction\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\n(interpreting Nijhawan). Rather, it determined that the\ncircumstance-specific approach is required because the\naggravated felony statute “refers to the particular\ncircumstances in which an offender committed a (more broadly\ndefined) fraud or deceit crime on a particular occasion,” and\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\nNoting that the Government in immigration proceedings is\nheld only to a “clear and convincing” burden of proof, and not\n“beyond a reasonable doubt,” the Supreme Court found\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\nrelated material”—in that case a sentencing stipulation and\nrestitution order. Id. at 42–43. It also noted that “the sole\npurpose of the aggravated felony inquiry is to ascertain the\nnature of a prior conviction; it is not an invitation to relitigate\nthe conviction itself.” Id. (internal quotation marks omitted).\n\n Nothing in Nijhawan suggests that the circumstance-\nspecific approach applies in some cases but not others, or that\n\n\n\n\n 12\n\fthe documents reviewable under that approach vary from case\nto case. Furthermore, we have consistently interpreted\nNijhawan as allowing an IJ, in determining the loss amount, to\nlook beyond the charging document to sentencing-related\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\nF.3d at 348–49. Ku has not persuaded us that our reading is\nincorrect.\n\n 2.\n\n Second, Ku contends that, because her conviction was\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\ncaused through other acts and transactions are not sufficiently\n“tethered” to the count of conviction for purposes of the\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\nKu asks us to read the Information as charging her in Count\nOne with a “scheme and artifice to defraud” her in-laws of\n$2,290.53, and not as charging her with one instance of wire\nfraud that was part of a broader “scheme and artifice to\ndefraud” her in-laws of over $950,000. However, such an\ninterpretation is inconsistent with the language of the\nInformation. In Count One, the Government “re-alleges and\nincorporates by reference” the first eight paragraphs, which\nallege that, over five years, Ku defrauded her in-laws of more\nthan $950,000 by transferring funds from their accounts to her\nown accounts, withdrawing funds as cash, making payments to\ncredit card companies for charges she incurred, and writing and\ncashing checks payable to herself. (App. 588–90). The explicit\nincorporation of those paragraphs into the count to which Ku\npleaded guilty supports an interpretation of the count itself as\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\nof more than $950,000.\n\n\n\n\n 13\n\f We are similarly unpersuaded by Ku’s contention that,\nbecause Paragraphs 1 through 8 of the Information describe\nconduct that does not necessarily amount to wire fraud, such\nconduct cannot count toward the total loss resulting from her\nconviction. It is incontrovertible that the “scheme and artifice\nto defraud” charged in Count One of the Information\nencompassed the whole course of Ku’s unlawful conduct,\nincluding the one incident in which Ku committed wire fraud\nin the amount of $2,390.53, and which resulted in a total loss\nof over $950,000. In short, because Ku pleaded guilty to\ncommitting wire fraud as part of a scheme to defraud her in-\nlaws of more than $950,000, the total loss amount is, to use our\nlanguage from Fan Wang, “undeniably tethered” to her wire\nfraud conviction.\n\n 3.\n\n Finally, Ku contends that the single-count Information\nto which she pleaded guilty is part of the “justice package”\nworked out between her and the Government and urges the\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\ndoing so, Ku relies on our opinion in Alaka v. Attorney\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\nthis case make it distinguishable from Alaka.\n\n In Alaka—which we decided prior to Nijhawan5—we\nheld that the IJ erred by considering the amount of intended\n\n\n 5\n Because Alaka was decided prior to the Supreme\nCourt’s decision in Nijhawan, its application of the modified\ncategorical approach to the aggravated-felony analysis does\nnot affect our decision. However, to the extent that Alaka\nstands for the proposition that an IJ may not consider dismissed\n\n\n\n\n 14\n\floss for all of the charges against the petitioner rather than the\nsingle count for which she was convicted. Alaka, 456 F.3d at\n106. The petitioner had been indicted on three counts for\nconduct involving fraudulent checks, but was convicted of only\none count, for which the actual loss was $4,716.68. Id. at 92.\nThe sentencing court nonetheless held that the petitioner’s\nconduct was part of a “common scheme or plan,” and therefore\nfound the total intended loss to be nearly $50,000. Id. It\nordered her to pay $4,716.68 in restitution. Id. In subsequent\nimmigration proceedings, the IJ concluded that the petitioner\nhad been convicted of an aggravated felony on the ground that\nthe intended loss was more than $10,000. Id. at 105, n.27. On\nappeal, we determined that, while the IJ properly considered\nthe factual findings of the sentencing report in determining\nwhether the offense was an aggravated felony, the loss amount\ntied to the dismissed charges was not properly considered as\npart of the aggravated-felony analysis. Id. at 106–08. In doing\nso, we noted that “the plain and unambiguous language of the\nstatute . . . predicates removal on a convicted offense resulting\nin losses greater than $10,000,” thereby foreclosing inclusion\nof losses stemming from unconvicted offenses. Id. 106–07\n(citations omitted). Furthermore, we considered that, because\nit is “the plea agreement that establishes the offense for which\nthe defendant will be convicted, it is to that agreement, and not\nthe indictment or the sentence, that we look in determining the\nintended loss.” Id. at 107. The petitioner “unmistakably pled\nguilty to one count, and the plea agreement plainly documented\nthat loss at less than $10,000.” Id. at 108 (citations and\nalterations omitted). Because the plea agreement “spell[ed] it\nout for us in black and white,” we concluded that the plea\n\n\ncharges when calculating the loss attributable to the conviction,\nit remains good law.\n\n\n\n\n 15\n\fagreement alone established the loss amount, and “not . . . the\nloss charged in the indictment, tabulated for restitution\npurposes, or calculated for sentencing.” Id. (citations omitted).\n\n Here, in stark contrast to the petitioner in Alaka, the\nrecord before us contains no plea agreement, and certainly not\none which explicitly spells out the loss amount to which Ku\npleaded guilty. Instead, Ku urges us to find that, based on the\nfact that the Government could have charged her with a much\nlonger list of crimes but did not, the loss amount as indicated\nin Count One was part of an explicit bargain between her and\nthe Government. However, this argument is based on pure\nconjecture. Absent a clear and unmistakable indication of loss\nin a written plea agreement, we are left with only the\nInformation, Judgment, and Restitution Order to determine the\nloss attributable to Ku’s conviction. As explained above, these\ndocuments, taken together, provide clear and convincing\nevidence that the loss amount attributable to Ku’s wire fraud\nconviction exceeded $10,000, and Ku has provided no plea\nagreement or any other document to the contrary.6\n\n 6\n The sentencing court in Alaka calculated the total loss\namount based on the “common scheme or plan,” which, it\nconsidered, included both the count of conviction and the\ndismissed counts, and we considered the IJ’s reliance on that\ncalculation to be in error in light of the plea agreement. 456\nF.3d at 106. But this does not help Ku. As explained above,\nthe wire fraud count to which Ku pleaded guilty was based in\npart on her “scheme and artifice to defraud” her in-laws of over\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\nthe sentencing court in this case did not base its loss calculation\non any acts that were not explicitly incorporated into the count\nof conviction.\n\n\n\n\n 16\n\f Ku’s argument that this Court should respect the\n“justice package” between her and the Government also\ntouches on the Supreme Court’s landmark holdings in Padilla\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\ntoward respecting agreements between criminal defendants\nand the Government with respect to the collateral\nconsequences of a conviction. But this line of argument merely\nhighlights another critical shortcoming of Ku’s case. To the\nextent Ku argues that the Information was designed\nspecifically to avoid immigration consequences, there is no\nevidence in the record to support such a finding. Indeed, Ku’s\nattorney indicated in her sentencing memorandum that Ku “is\nnow subject to automatic deportation as a result of her\nconviction in this case.” (App. 740). This statement, while not\nconclusive, certainly undermines any assertion that the “justice\npackage” referred to by Ku was designed to avoid an\naggravated felony conviction. Indeed, absent any other\nevidence in the record to the contrary, the sentencing\nmemorandum supports a finding that, at the time of her guilty\nplea, Ku understood that she was pleading guilty to an\naggravated felony.\n\n B.\n\n Having concluded that the Board did not err in finding\nthat Ku was convicted of an aggravated felony, we turn to the\nquestion of whether Ku’s conviction constituted a “crime\ninvolving moral turpitude” under the INA. Ku argues that wire\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\nthe specific intent to defraud. This is incorrect.\n\n\n\n\n 17\n\f The statute provides that a person is guilty of wire fraud\nif, “having devised or intending to devise any scheme or\nartifice to defraud,” that person “transmits or causes to be\ntransmitted by means of wire, radio, or television\ncommunication in interstate or foreign commerce, any\nwritings, signs, signals, pictures, or sounds for the purpose of\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\nhave long treated fraud crimes as “involving moral turpitude.”\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\ndecided cases make it plain that crimes in which fraud was an\ningredient have always been regarded as involving moral\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\nfall well within the recognized definition of ‘crimes involving\nmoral turpitude.’”). Furthermore, we have also consistently\nread the wire fraud statute as containing the element of specific\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\n(3d Cir. 2012) (“To prove wire fraud, the Government must\nestablish (1) the defendant’s knowing and willful participation\nin a scheme or artifice to defraud, (2) with the specific intent to\ndefraud, and (3) the use of . . . interstate wire communications\nin furtherance of the scheme.”) (internal quotation marks\nomitted) (emphasis added).\n\n Seeking to persuade us to revisit these tenets, Ku asks\nus to read the statutory terms “having devised” and “intending\nto devise” as disjunctive means of committing wire fraud, the\nlatter containing the mens rea of intent, and the former\neschewing any mens rea at all. But the language of the statute\ndoes not lend itself to such an interpretation. The specific\nintent requirement is contained in the latter part of the statute—\n“for the purpose of executing [a] scheme or artifice [to\ndefraud]”—and must be proved regardless of whether the\n\n\n\n\n 18\n\fperson made the transmission after “having devised” or while\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\nPlainly read, the language Ku seizes on, “having devised or\nintending to devise,” refers not to the requisite mens rea but to\nthe temporal relationship between the formation of the fraud\nscheme and the transmission itself. Either way, the person\nmust have made the transmission for the purpose of executing\nthe fraud scheme in order to be convicted.\n\n Ku’s statutory interpretation argument holds no weight.\nAccordingly, we see no need to revisit the long-held tenet that\nfraud crimes—including wire fraud—are crimes involving\nmoral turpitude under the INA.\n\n C.\n\n Finally, Ku asks us to find that the Board committed\nerror in its reversal of the IJ’s finding that she was eligible for\na discretionary waiver of inadmissibility based on the hardship\nher deportation would cause her U.S. citizen children.\nHowever, we lack jurisdiction over the Board’s decision on\nthis point.\n\n The INA provides that an alien is inadmissible to the\nUnited States if she has been convicted of a crime involving\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\nprovides, however, that the Attorney General may waive\ninadmissibility to allow an applicant to obtain adjustment of\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\nof a United States citizen . . . and can show that denial of\nadmission would cause extreme hardship to the citizen . . . .”\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\n2002). The authority to waive one or more grounds of\ninadmissibility is vested solely in the Attorney General and “no\n\n\n\n\n 19\n\fcourt shall have jurisdiction to review” a decision to deny such\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\n\n We may, however, review “constitutional claims or\nquestions of law raised upon a petition for review . . . .” Id. at\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\ncircumscribed” in that it is limited to “colorable claims or\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\nCir. 2008) (per curiam) (quotation marks and citation omitted).\nWhile “[t]he question of our jurisdiction over a colorable legal\nclaim does not turn on whether that claim is ultimately\nmeritorious . . . , a party may not dress up a claim with legal\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\n\n Ku argues that we have jurisdiction to consider her\npetition for review on the waiver issue because it presents a\nquestion of law, namely whether the Board applied the proper\nlegal standard in making the discretionary determination. But\nKu’s argument boils down to her contention that the Board\nfailed to consider certain equities relevant to the hardship\ndetermination. As we have consistently held, “arguments such\nas that an Immigration Judge or the BIA incorrectly weighed\nevidence, failed to consider evidence or improperly weighed\nequitable factors are not questions of law under\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\n(3d Cir. 2007). Because the substance of Ku’s petition for\nreview amounts to contesting the weight the Board should have\ngiven to the positive equities of her case, we do not have\njurisdiction over it and will dismiss in part that aspect of the\npetition.\n\n IV.\n\n\n\n\n 20\n\f For the foregoing reasons, we will deny in part and\ndismiss in part Ku's petition for review, and we will deny as\nmoot the Government's motion to remand.\n\n\n\n\n 21\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: CHIAO FANG KU, AKA Chiao Fang Ronan, AKA Anna Ronan, Petitioner v. ATTORNEY GENERAL UNITED STATES OF AMERICA, Respondent\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-3001\\n _____________\\n\\n CHIAO FANG KU,\\n AKA Chiao Fang Ronan, AKA Anna Ronan,\\n Petitioner\\n v.\\n\\nATTORNEY GENERAL UNITED STATES OF AMERICA,\\n Respondent\\n _____________\\n\\n On Petition for Review of an Order of the\\n Board of Immigration Appeals\\n (Agency No. A077-160-352)\\n Immigration Judge: Walter A. Durling\\n ______________\\n\\n Argued September 12, 2018\\n ______________\\n\\n Before: JORDAN, VANASKIE, and NYGAARD, Circuit\\n Judges\\n\\n\\n The Honorable Judge Vanaskie transmitted the opinion to the Clerk for\\nfiling prior to retiring from the bench on January 1, 2019. Due to the\\nintervening holiday, the opinion has been entered on the docket by the\\nClerk this day.\\n\\f (Opinion Filed: January 3, 2019)\\n\\n\\nThomas M. Griffin [Argued]\\nSurin & Griffin\\n718 Arch Street\\nSuite 701N\\nPhiladelphia, PA 19106\\n Counsel for Petitioner\\n\\nChad A. Readler, Acting Assistant Attorney General\\nNancy E. Friedman, Senior Litigation Counsel\\nJustin R. Markel, Senior Litigation Counsel\\nGregory A. Pennington, Jr. [Argued]\\nUnited States Department of Justice\\nOffice of Immigration Litigation\\nCivil Division\\nP.O. Box 878\\nBen Franklin Station\\nWashington, DC 20044\\n Counsel for Respondent\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nVANASKIE, Circuit Judge.\\n\\n Seeking to remain in this country, Chiao Fang Ku\\npetitions for review of a final order of removal issued by the\\nBoard of Immigration Appeals (“BIA” or “Board”). The\\nBoard determined that Ku had committed an aggravated felony\\n\\n\\n\\n\\n 2\\n\\funder 8 U.S.C. § 1101(a)(43)(M)(i) because her prior\\nconviction for wire fraud constituted an offense involving\\nfraud or deceit in which the loss to the victims exceeded\\n$10,000. The Board also found that Ku’s wire fraud conviction\\nconstituted a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) such that, without a waiver, she is\\nineligible for an adjustment of status. Although the\\nImmigration Judge (“IJ”) granted Ku a waiver of\\ninadmissibility under 8 U.S.C. § 1182(h)(1)(B) based on the\\nextreme hardship that her deportation would cause her U.S.\\nCitizen children, the Board reversed that decision. Ku\\nchallenges each of the Board’s decisions.\\n\\n In Nijhawan v. Holder, 557 U.S. 29 (2009), the Court\\nheld that determination of whether a fraud offense involved\\nloss to the victims of $10,000 or more requires a circumstance-\\nspecific approach, allowing the immigration court to review\\nboth the charging document and sentencing-related materials\\nto determine the loss amount attributable to the offense. On\\nthe facts of this case, we find that the undisputed loss to the\\nvictims of well over $10,000 was sufficiently tethered to Ku’s\\nwire fraud conviction such that the conviction qualifies as an\\naggravated felony. Furthermore, we find no error in the\\nBoard’s determination that wire fraud constitutes a crime of\\nmoral turpitude. Lastly, regarding the waiver of admissibility,\\nwe do not have jurisdiction to review the discretionary denial\\nof a waiver under § 212(h) of the INA. Accordingly, we will\\ndeny in part and dismiss in part Ku’s petition for review.\\n\\n I.\\n\\n Ku is a native and citizen of Taiwan. She was admitted\\nto the United States in 1997 and gained status as a lawful\\npermanent resident in 2002. In 2014, Ku was charged with a\\n\\n\\n\\n\\n 3\\n\\fsingle count of wire fraud, in violation of 18 U.S.C. § 1343.\\nKu waived her right to an indictment and was charged by\\ninformation only. The Information alleged that Ku was tasked\\nwith managing the finances of her in-laws, E.R. and M.R, and\\nthat she was provided access to her in-laws’ bank accounts in\\nconnection with this role. The Information further alleged that,\\nbetween May 2008 and July 2013, Ku defrauded her in-laws\\nby using her access to their accounts to take money from them\\nfor her personal use. In particular, it alleged that Ku: (1)\\ntransferred funds from her in-laws’ accounts to her own\\naccounts; (2) withdrew funds from her in-laws’ accounts as\\ncash; (3) made payments from her in-laws’ accounts to pay off\\nher personal credit cards; (4) wrote and cashed checks payable\\nto herself by forging her mother-in-law’s signature; and (5)\\nfraudulently applied for and obtained credit cards in her\\nmother-in-law’s name and used them for her own purposes.\\nThe Information alleged that, in total, Ku stole more than\\n$950,000 from her in-laws.\\n\\n These allegations were incorporated by reference into\\nthe sole count of the Information, which alleged that, on or\\nabout November 7, 2011, Ku,\\n\\n having devised and intending to devise a\\n scheme and artifice to defraud and to obtain\\n money and property by means of materially\\n false and fraudulent pretenses,\\n representations, and promises, did cause\\n writings, signs, signals, pictures, and sounds\\n to be transmitted by means of wire\\n communications in interstate commerce for\\n the purpose of executing such scheme and\\n artifice, to wit: executing an online payment\\n from M.R.’s Sovereign Bank account, ending\\n\\n\\n\\n\\n 4\\n\\f in 8497, to the defendant’s Chase credit card\\n account, ending in 6567, in the amount of\\n $2,290.53.\\n\\n(App. 590). The Information further contained forfeiture\\nallegations, which directed that, upon conviction of the sole\\ncount of the Information, Ku “forfeit to the United States . . .\\nany property, real or personal, that constitutes, or is derived\\nfrom, proceeds traceable to the commission of the offense,\\nincluding but not limited to at least $950,000 in United States\\ncurrency.” (App. 591).\\n\\n Ku pleaded guilty, pursuant to a plea agreement,1 to the\\nsingle count of the Information. In her sentencing\\nmemorandum, Ku, through counsel, acknowledged that she\\nwas “now subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). Ku was ultimately\\nsentenced to a term of 18 months’ imprisonment, followed by\\none year of supervised release. The judgment includes a total\\nloss determination of $954,515.71 and orders restitution in that\\namount. (App. 582).\\n\\n After Ku completed her sentence, she was served with\\na Notice to Appear and placed in removal proceedings. The\\nNotice to Appear charged Ku with being removable under\\n§ 237(a)(2)(A)(iii) of the Immigration and Nationality Act\\n(“INA” or the “Act”), 8 U.S.C. § 1227(a)(2)(A)(iii), as an\\nindividual convicted of an aggravated felony as defined in 8\\nU.S.C. § 1101(a)(43)(M)(i). The Immigration Judge\\nconcluded that Ku was removable as charged because the\\n\\n\\n 1\\n The plea agreement is not part of the administrative\\nrecord before us, nor was it in the record before the IJ or BIA.\\n\\n\\n\\n\\n 5\\n\\frecord of conviction substantiated a finding that the wire fraud\\ninvolved a loss of more than $10,000.\\n\\n In order to avoid deportation, Ku sought to re-adjust her\\nstatus based on her U.S. Citizen husband.2 The Immigration\\nJudge granted Ku’s application for a waiver of inadmissibility\\nunder § 212(h)(1)(B) of the Act, 8 U.S.C. § 1182(h)(1)(B),\\nbased on the extreme hardship that her deportation would cause\\nher U.S. Citizen children, and granted Ku’s adjustment of\\nstatus pursuant to § 245(a) of the INA, 8 U.S.C. § 1255(a).\\n\\n On appeal, the Board affirmed that the Government\\ndemonstrated by clear and convincing evidence that Ku was\\nremovable as an aggravated felon as defined at\\n§ 1101(a)(43)(M)(i) in that her offense involved fraud or deceit\\nin which the loss to the victims exceeded $10,000. In doing so,\\nthe Board noted that the Information alleged that Ku stole more\\nthan $950,000 in funds belonging to her in-laws, and that this\\nallegation was incorporated by reference into the count to\\nwhich Ku pleaded guilty. It also observed that the Information\\nalso contained a forfeiture allegation stating that, upon\\nconviction, Ku would forfeit over $950,000 in currency.\\nFinally, the Board considered relevant that the Judgment of\\nConviction found a total loss of over $950,000 and ordered\\nrestitution in that amount.\\n\\n The Board further concluded that Ku’s conviction was\\nfor a crime involving moral turpitude, making her inadmissible\\nunder § 212(a)(2)(A)(i)(I) of the INA, 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I), such that she required a § 212(h) waiver\\n\\n 2\\n Ku's present husband is not the man to whom she was\\npreviously married and whose parents are the elderly in-laws\\nshe defrauded.\\n\\n\\n\\n\\n 6\\n\\fin order to adjust her status. See 8 U.S.C. § 1255(a) (providing\\nfor adjustment of status of certain aliens to that of an alien\\nlawfully admitted for permanent residence); see also 8 U.S.C.\\n§ 1182(h)(1)(B) (providing for waiver of inadmissibility at the\\ndiscretion of the Attorney General). Although it acknowledged\\nthe hardship posed to her family, the Board ultimately found\\nthat, given the severity of her crime, Ku did not merit a\\n§ 212(h) waiver. It accordingly vacated the decision of the IJ\\nand denied Ku’s applications for a § 212(h) waiver and for\\nadjustment of status. Ku timely filed a petition for review.\\n\\n II.\\n\\n Although we have jurisdiction to review final orders of\\nremoval under 8 U.S.C. § 1252(a),3 “no court shall have\\n\\n 3\\n We have taken a broad view of what constitutes a\\n“final order of removal” under § 1252. Higgs v. Att’y Gen.,\\n655 F.3d 333, 337–38 (3d Cir. 2011). “[A]n order is final for\\njurisdictional purposes when a removability determination has\\nbeen made that is no longer appealable to the BIA, regardless\\n[of] whether a formal order of removal has been entered.” Id.\\n(quoting Yusupov v. Att’y Gen., 518 F.3d 185, 195 (3d Cir.\\n2008)); see also Shehu v. Att’y Gen., 482 F.3d 652, 656 (3d\\nCir. 2007) (“[D]enial of a . . . petition for asylum, withholding\\nof removal, and relief under the [Convention Against Torture]\\nconstitutes ‘a final order of removal’ within the meaning of\\n[§ 1252], [because] the alien is entitled to no further process\\nbefore deportation.”). Here, although the Board did not\\nexplicitly order Ku removed to Taiwan, it found her removable\\nand denied her application for adjustment of status, her only\\npetition for relief. (App. 5). Furthermore, the Board sustained\\nDHS’s appeal, which requested that Ku be ordered removed to\\nTaiwan. Accordingly, for the purposes of this appeal, we\\n\\n\\n\\n\\n 7\\n\\fjurisdiction to review any final order of removal against an\\nalien who is removable by reason of having committed [an\\naggravated felony].” 8 U.S.C. § 1252(a)(2)(C). “We do,\\nhowever, have jurisdiction to examine ‘constitutional claims or\\nquestions of law.’” Fan Wang v. Att’y Gen., 898 F.3d 341, 343\\n(3d Cir. 2018) (quoting Catwell v. Att’y Gen., 623 F.3d 199,\\n205 (3d Cir. 2010); 8 U.S.C. § 1252(a)(2)(D)). Therefore, we\\nhave authority to take up the issue, applying plenary review, of\\nwhether Ku’s conviction qualifies as an aggravated felony\\nbecause it is “a purely legal question, and one that governs our\\nown jurisdiction.” Id. (quoting Valansi v. Ashcroft, 278 F.3d\\n203, 207 (3d Cir. 2002)). We also review de novo the legal\\nquestion of what elements of a federal criminal statute\\nimplicate moral turpitude, while affording Chevron deference\\nto the Board’s definition of “moral turpitude.” Knapik v.\\nAshcroft, 384 F.3d 84, 88 (3d Cir. 2004).\\n\\n III.\\n\\n On appeal, Ku challenges all three aspects of the BIA’s\\norder. First, she contends that the BIA incorrectly determined\\nthat her wire-fraud conviction involved a loss of more than\\n$10,000 by relying on evidence that was not sufficiently\\ntethered to the sole count of conviction.4 Second, Ku argues\\n\\n\\nconsider the Board’s order to be a final order of removal. The\\nGovernment’s motion to remand this case to the Board for\\nissuance of an order directing that Ku be removed to Taiwan\\nand to allow the IJ to make additional findings on removability\\nwill be denied as moot.\\n 4\\n We note that Ku does not challenge—and did not\\nchallenge before the IJ or the Board—that her wire fraud\\n\\n\\n\\n\\n 8\\n\\fthat the Board erred in finding that her wire-fraud conviction\\nwas for a crime involving moral turpitude because the statute\\nof conviction does not require a showing of intent. Third, Ku\\nasserts that the BIA applied the incorrect legal standard in\\nreversing the IJ’s grant of a discretionary waiver of\\ninadmissibility. We reject all three of Ku’s challenges and\\ntherefore deny the petition for review.\\n\\n A.\\n\\n Section 237(a)(2)(A)(iii) of the INA, as amended,\\nprovides that “[a]ny alien who is convicted of an aggravated\\nfelony at any time after admission is deportable.” 8 U.S.C.\\n§ 1227(a)(2)(A)(iii). The Act defines “aggravated felony,” in\\nrelevant part, as an offense that “involves fraud or deceit in\\nwhich the loss to the victim or victims exceeds $10,000.” 8\\nU.S.C. § 1101(a)(43)(M)(i).\\n\\n In Nijhawan v. Holder, the Supreme Court addressed\\nthe issue of whether the $10,000 threshold of the aggravated\\nfelony statute “refers to an element of a fraud statute or to the\\nfactual circumstances surrounding commission of the crime on\\na specific occasion.” 557 U.S. at 33. The Court adopted the\\nlatter interpretation, characterizing the review as examining\\n“the specific way in which an offender committed the crime on\\na specific occasion.” Id. at 34. The Court distinguished the\\n“circumstance-specific approach” to be used in determining\\nwhether a crime “involves fraud or deceit in which the loss to\\nthe victim or victims exceeds $10,000” from the “categorical\\napproach” used in determining whether a crime is a “violent\\nfelony” under the Armed Career Criminal Act (“ACCA”), 18\\n\\nconviction “involves fraud or deceit” under 8 U.S.C.\\n§ 1101(a)(43)(M).\\n\\n\\n\\n\\n 9\\n\\fU.S.C. § 924(e). Id. at 34–40. It also rejected the use of the\\nso-called “modified categorical approach” employed in some\\ncontexts, which would limit an IJ’s consideration to charging\\ndocuments, jury instructions, special jury findings, or some\\nequivalent judge-made findings and—in the case of a guilty\\nplea—to the written plea documents or plea colloquy. Id. at\\n41. While the Supreme Court acknowledged that “the statute\\nforesees the use of fundamentally fair procedures,” it rejected\\nthe argument that fairness requires such evidentiary\\nlimitations. Id. Accordingly, it found “nothing unfair” about\\nthe IJ’s reliance upon the defendant’s stipulation and the\\ndistrict court’s restitution order to determine that the crime at\\nissue was an “aggravated felony” under § 1101(a)(43)(M)(i).\\nId. at 42–43.\\n\\n Since Nijhawan, we have consistently applied the\\ncircumstance-specific approach to determine the amount of\\nloss in “aggravated felony” cases. See, e.g., Kaplun v. Att’y\\nGen., 602 F.3d 260, 265–66 (3d Cir. 2010); Doe v. Att’y Gen.,\\n659 F.3d 266, 274–76 (3d Cir. 2011). Most recently, we\\naddressed the issue in Fan Wang, in which we reviewed “not\\nonly those documents that may be considered in a modified\\ncategorical approach (the indictment, plea agreement, and\\njudgment),” but also others, including “the presentence\\ninvestigation report and any sentencing-related material.” 898\\nF.3d at 348–49 (citations and internal quotation marks\\nomitted). Relying on Nijhawan, we reasoned that\\nconsideration of such materials “is appropriate so long as the\\npetitioner has been given a ‘fair opportunity’ to challenge the\\nGovernment’s claim.” Id. at 349 (quoting Nijhawan, 557 U.S.\\nat 41). Accordingly, we determined that the Board did not go\\nbeyond the bounds of proper review by examining the record—\\nincluding the sole count of the superseding information, the\\n\\n\\n\\n\\n 10\\n\\fplea colloquy, the presentence investigation report, the “total\\nloss” specified in the judgment, and the restitution order—to\\ndetermine whether the petitioner’s prior conviction was an\\n“aggravated felony.” Id. at 349–50. In determining the proper\\namount of loss in that case, we were persuaded by the\\nGovernment’s argument that the loss amount listed in the\\njudgment and restitution order was “undeniably tethered” to\\nthe conduct for which the petitioner was convicted. Id. at 351.\\n\\n We consider the loss to the victims in this case—as\\nevidenced by the Information, Judgment, and Restitution\\nOrder—to be sufficiently tethered to the count of conviction\\nsuch that Ku’s conviction was an aggravated felony.\\nParagraphs 1 through 10 of the Information allege that Ku stole\\nmore than $950,000 in funds belonging to her in-laws, and\\nthese paragraphs were incorporated by reference into the count\\nto which Ku pleaded guilty. Furthermore, the forfeiture\\nallegation contained in the Information states that, upon\\nconviction, Ku would forfeit the “proceeds traceable to the\\ncommission of the offense, including but not limited to at least\\n$950,000 in United States currency.” (App. 591). Finally, the\\nJudgment of Conviction indicates a loss of $954,515.71 and\\norders restitution in that amount. Each of these documents is\\nreviewable under the circumstance-specific approach laid out\\nby the Supreme Court in Nijhawan. Together, they provide\\nclear and convincing evidence that Ku’s offense involved a\\nloss of over $10,000. Nonetheless, we briefly addresses Ku’s\\narguments to the contrary, all of which lack merit.\\n\\n 1.\\n\\n First, Ku contends that the circumstance-specific\\napproach described in Nijhawan does not apply in her case\\nbecause the single count of the Information made clear that it\\n\\n\\n\\n\\n 11\\n\\fwas for the specified amount of $2,290.53. She urges us to\\nread Nijhawan to have kept intact the modified categorical\\napproach for cases in which the charging document contains a\\nclear indication of the loss amount. Under the modified\\ncategorical approach, she contends, the Board was correct in\\nreviewing the Information but, because the count of conviction\\ncontains a loss amount of $2,290.53, the Board should have\\nstopped there.\\n\\n Contrary to Ku’s assertion, Nijhawan does not stand for\\nthe proposition that, when the count of conviction contains a\\nloss amount, immigration officials must look no further. The\\nSupreme Court explicitly rejected the use of the modified\\ncategorical approach in determining whether a prior conviction\\nis an aggravated felony under § 1101(a)(43)(M)(i). Nijhawan,\\n557 U.S. at 41–42; see also Kaplun, 602 F.3d at 265–66\\n(interpreting Nijhawan). Rather, it determined that the\\ncircumstance-specific approach is required because the\\naggravated felony statute “refers to the particular\\ncircumstances in which an offender committed a (more broadly\\ndefined) fraud or deceit crime on a particular occasion,” and\\nnot to an element of the offense. Nijhawan, 557 U.S. at 32.\\nNoting that the Government in immigration proceedings is\\nheld only to a “clear and convincing” burden of proof, and not\\n“beyond a reasonable doubt,” the Supreme Court found\\n“nothing unfair about [an IJ] rel[ying] upon earlier sentencing-\\nrelated material”—in that case a sentencing stipulation and\\nrestitution order. Id. at 42–43. It also noted that “the sole\\npurpose of the aggravated felony inquiry is to ascertain the\\nnature of a prior conviction; it is not an invitation to relitigate\\nthe conviction itself.” Id. (internal quotation marks omitted).\\n\\n Nothing in Nijhawan suggests that the circumstance-\\nspecific approach applies in some cases but not others, or that\\n\\n\\n\\n\\n 12\\n\\fthe documents reviewable under that approach vary from case\\nto case. Furthermore, we have consistently interpreted\\nNijhawan as allowing an IJ, in determining the loss amount, to\\nlook beyond the charging document to sentencing-related\\nmaterials. See Kaplun, 602 F.3d at 265–66; Fan Wang, 898\\nF.3d at 348–49. Ku has not persuaded us that our reading is\\nincorrect.\\n\\n 2.\\n\\n Second, Ku contends that, because her conviction was\\nfor “a single act of a $2,290.53 on-line transfer,” the losses she\\ncaused through other acts and transactions are not sufficiently\\n“tethered” to the count of conviction for purposes of the\\naggravated felony statute. (Petitioner’s Br. at 27). In doing so,\\nKu asks us to read the Information as charging her in Count\\nOne with a “scheme and artifice to defraud” her in-laws of\\n$2,290.53, and not as charging her with one instance of wire\\nfraud that was part of a broader “scheme and artifice to\\ndefraud” her in-laws of over $950,000. However, such an\\ninterpretation is inconsistent with the language of the\\nInformation. In Count One, the Government “re-alleges and\\nincorporates by reference” the first eight paragraphs, which\\nallege that, over five years, Ku defrauded her in-laws of more\\nthan $950,000 by transferring funds from their accounts to her\\nown accounts, withdrawing funds as cash, making payments to\\ncredit card companies for charges she incurred, and writing and\\ncashing checks payable to herself. (App. 588–90). The explicit\\nincorporation of those paragraphs into the count to which Ku\\npleaded guilty supports an interpretation of the count itself as\\ndescribing Ku’s “scheme and artifice to defraud” her in-laws\\nof more than $950,000.\\n\\n\\n\\n\\n 13\\n\\f We are similarly unpersuaded by Ku’s contention that,\\nbecause Paragraphs 1 through 8 of the Information describe\\nconduct that does not necessarily amount to wire fraud, such\\nconduct cannot count toward the total loss resulting from her\\nconviction. It is incontrovertible that the “scheme and artifice\\nto defraud” charged in Count One of the Information\\nencompassed the whole course of Ku’s unlawful conduct,\\nincluding the one incident in which Ku committed wire fraud\\nin the amount of $2,390.53, and which resulted in a total loss\\nof over $950,000. In short, because Ku pleaded guilty to\\ncommitting wire fraud as part of a scheme to defraud her in-\\nlaws of more than $950,000, the total loss amount is, to use our\\nlanguage from Fan Wang, “undeniably tethered” to her wire\\nfraud conviction.\\n\\n 3.\\n\\n Finally, Ku contends that the single-count Information\\nto which she pleaded guilty is part of the “justice package”\\nworked out between her and the Government and urges the\\nCourt to defer to that agreement. (Petitioner’s Br. at 35). In\\ndoing so, Ku relies on our opinion in Alaka v. Attorney\\nGeneral, 456 F.3d 88 (3d Cir. 2006). However, the facts of\\nthis case make it distinguishable from Alaka.\\n\\n In Alaka—which we decided prior to Nijhawan5—we\\nheld that the IJ erred by considering the amount of intended\\n\\n\\n 5\\n Because Alaka was decided prior to the Supreme\\nCourt’s decision in Nijhawan, its application of the modified\\ncategorical approach to the aggravated-felony analysis does\\nnot affect our decision. However, to the extent that Alaka\\nstands for the proposition that an IJ may not consider dismissed\\n\\n\\n\\n\\n 14\\n\\floss for all of the charges against the petitioner rather than the\\nsingle count for which she was convicted. Alaka, 456 F.3d at\\n106. The petitioner had been indicted on three counts for\\nconduct involving fraudulent checks, but was convicted of only\\none count, for which the actual loss was $4,716.68. Id. at 92.\\nThe sentencing court nonetheless held that the petitioner’s\\nconduct was part of a “common scheme or plan,” and therefore\\nfound the total intended loss to be nearly $50,000. Id. It\\nordered her to pay $4,716.68 in restitution. Id. In subsequent\\nimmigration proceedings, the IJ concluded that the petitioner\\nhad been convicted of an aggravated felony on the ground that\\nthe intended loss was more than $10,000. Id. at 105, n.27. On\\nappeal, we determined that, while the IJ properly considered\\nthe factual findings of the sentencing report in determining\\nwhether the offense was an aggravated felony, the loss amount\\ntied to the dismissed charges was not properly considered as\\npart of the aggravated-felony analysis. Id. at 106–08. In doing\\nso, we noted that “the plain and unambiguous language of the\\nstatute . . . predicates removal on a convicted offense resulting\\nin losses greater than $10,000,” thereby foreclosing inclusion\\nof losses stemming from unconvicted offenses. Id. 106–07\\n(citations omitted). Furthermore, we considered that, because\\nit is “the plea agreement that establishes the offense for which\\nthe defendant will be convicted, it is to that agreement, and not\\nthe indictment or the sentence, that we look in determining the\\nintended loss.” Id. at 107. The petitioner “unmistakably pled\\nguilty to one count, and the plea agreement plainly documented\\nthat loss at less than $10,000.” Id. at 108 (citations and\\nalterations omitted). Because the plea agreement “spell[ed] it\\nout for us in black and white,” we concluded that the plea\\n\\n\\ncharges when calculating the loss attributable to the conviction,\\nit remains good law.\\n\\n\\n\\n\\n 15\\n\\fagreement alone established the loss amount, and “not . . . the\\nloss charged in the indictment, tabulated for restitution\\npurposes, or calculated for sentencing.” Id. (citations omitted).\\n\\n Here, in stark contrast to the petitioner in Alaka, the\\nrecord before us contains no plea agreement, and certainly not\\none which explicitly spells out the loss amount to which Ku\\npleaded guilty. Instead, Ku urges us to find that, based on the\\nfact that the Government could have charged her with a much\\nlonger list of crimes but did not, the loss amount as indicated\\nin Count One was part of an explicit bargain between her and\\nthe Government. However, this argument is based on pure\\nconjecture. Absent a clear and unmistakable indication of loss\\nin a written plea agreement, we are left with only the\\nInformation, Judgment, and Restitution Order to determine the\\nloss attributable to Ku’s conviction. As explained above, these\\ndocuments, taken together, provide clear and convincing\\nevidence that the loss amount attributable to Ku’s wire fraud\\nconviction exceeded $10,000, and Ku has provided no plea\\nagreement or any other document to the contrary.6\\n\\n 6\\n The sentencing court in Alaka calculated the total loss\\namount based on the “common scheme or plan,” which, it\\nconsidered, included both the count of conviction and the\\ndismissed counts, and we considered the IJ’s reliance on that\\ncalculation to be in error in light of the plea agreement. 456\\nF.3d at 106. But this does not help Ku. As explained above,\\nthe wire fraud count to which Ku pleaded guilty was based in\\npart on her “scheme and artifice to defraud” her in-laws of over\\n$950,000. (App. 590). Unlike the sentencing court in Alaka,\\nthe sentencing court in this case did not base its loss calculation\\non any acts that were not explicitly incorporated into the count\\nof conviction.\\n\\n\\n\\n\\n 16\\n\\f Ku’s argument that this Court should respect the\\n“justice package” between her and the Government also\\ntouches on the Supreme Court’s landmark holdings in Padilla\\nv. Kentucky, 559 U.S. 356 (2010), and Descamps v. United\\nStates, 570 U.S. 254 (2013), both of which, she argues, counsel\\ntoward respecting agreements between criminal defendants\\nand the Government with respect to the collateral\\nconsequences of a conviction. But this line of argument merely\\nhighlights another critical shortcoming of Ku’s case. To the\\nextent Ku argues that the Information was designed\\nspecifically to avoid immigration consequences, there is no\\nevidence in the record to support such a finding. Indeed, Ku’s\\nattorney indicated in her sentencing memorandum that Ku “is\\nnow subject to automatic deportation as a result of her\\nconviction in this case.” (App. 740). This statement, while not\\nconclusive, certainly undermines any assertion that the “justice\\npackage” referred to by Ku was designed to avoid an\\naggravated felony conviction. Indeed, absent any other\\nevidence in the record to the contrary, the sentencing\\nmemorandum supports a finding that, at the time of her guilty\\nplea, Ku understood that she was pleading guilty to an\\naggravated felony.\\n\\n B.\\n\\n Having concluded that the Board did not err in finding\\nthat Ku was convicted of an aggravated felony, we turn to the\\nquestion of whether Ku’s conviction constituted a “crime\\ninvolving moral turpitude” under the INA. Ku argues that wire\\nfraud is not a “crime involving moral turpitude” under 8 U.S.C.\\n§ 1182(a)(2)(A)(i)(I) because it does not include as an element\\nthe specific intent to defraud. This is incorrect.\\n\\n\\n\\n\\n 17\\n\\f The statute provides that a person is guilty of wire fraud\\nif, “having devised or intending to devise any scheme or\\nartifice to defraud,” that person “transmits or causes to be\\ntransmitted by means of wire, radio, or television\\ncommunication in interstate or foreign commerce, any\\nwritings, signs, signals, pictures, or sounds for the purpose of\\nexecuting such scheme or artifice.” 18 U.S.C. § 1343. Courts\\nhave long treated fraud crimes as “involving moral turpitude.”\\nJordan v. De George, 341 U.S. 223, 232 (1951) (“[T]he\\ndecided cases make it plain that crimes in which fraud was an\\ningredient have always been regarded as involving moral\\nturpitude.”); Singh v. Att’y Gen., 807 F.3d 547, 550 (3d Cir.\\n2015) (“Crimes . . . involving allegations of dishonesty or fraud\\nfall well within the recognized definition of ‘crimes involving\\nmoral turpitude.’”). Furthermore, we have also consistently\\nread the wire fraud statute as containing the element of specific\\nintent. See, e.g., United States v. Andrews, 681 F.3d 509, 518\\n(3d Cir. 2012) (“To prove wire fraud, the Government must\\nestablish (1) the defendant’s knowing and willful participation\\nin a scheme or artifice to defraud, (2) with the specific intent to\\ndefraud, and (3) the use of . . . interstate wire communications\\nin furtherance of the scheme.”) (internal quotation marks\\nomitted) (emphasis added).\\n\\n Seeking to persuade us to revisit these tenets, Ku asks\\nus to read the statutory terms “having devised” and “intending\\nto devise” as disjunctive means of committing wire fraud, the\\nlatter containing the mens rea of intent, and the former\\neschewing any mens rea at all. But the language of the statute\\ndoes not lend itself to such an interpretation. The specific\\nintent requirement is contained in the latter part of the statute—\\n“for the purpose of executing [a] scheme or artifice [to\\ndefraud]”—and must be proved regardless of whether the\\n\\n\\n\\n\\n 18\\n\\fperson made the transmission after “having devised” or while\\n“intending to devise” the scheme to defraud. 18 U.S.C. § 1343.\\nPlainly read, the language Ku seizes on, “having devised or\\nintending to devise,” refers not to the requisite mens rea but to\\nthe temporal relationship between the formation of the fraud\\nscheme and the transmission itself. Either way, the person\\nmust have made the transmission for the purpose of executing\\nthe fraud scheme in order to be convicted.\\n\\n Ku’s statutory interpretation argument holds no weight.\\nAccordingly, we see no need to revisit the long-held tenet that\\nfraud crimes—including wire fraud—are crimes involving\\nmoral turpitude under the INA.\\n\\n C.\\n\\n Finally, Ku asks us to find that the Board committed\\nerror in its reversal of the IJ’s finding that she was eligible for\\na discretionary waiver of inadmissibility based on the hardship\\nher deportation would cause her U.S. citizen children.\\nHowever, we lack jurisdiction over the Board’s decision on\\nthis point.\\n\\n The INA provides that an alien is inadmissible to the\\nUnited States if she has been convicted of a crime involving\\nmoral turpitude. 8 U.S.C. § 1182(a)(2)(A)(i)(I). The Act also\\nprovides, however, that the Attorney General may waive\\ninadmissibility to allow an applicant to obtain adjustment of\\nstatus under § 1182(h), “if the alien is a spouse, parent, or child\\nof a United States citizen . . . and can show that denial of\\nadmission would cause extreme hardship to the citizen . . . .”\\nDe Leon–Reynoso v. Ashcroft, 293 F.3d 633, 637 (3d Cir.\\n2002). The authority to waive one or more grounds of\\ninadmissibility is vested solely in the Attorney General and “no\\n\\n\\n\\n\\n 19\\n\\fcourt shall have jurisdiction to review” a decision to deny such\\na request. 8 U.S.C. § 1252(a)(2)(B)(i).\\n\\n We may, however, review “constitutional claims or\\nquestions of law raised upon a petition for review . . . .” Id. at\\n§ 1252(a)(2)(D). Our jurisdiction in that respect is “narrowly\\ncircumscribed” in that it is limited to “colorable claims or\\nquestions of law.” Cospito v. Att’y Gen., 539 F.3d 166, 170 (3d\\nCir. 2008) (per curiam) (quotation marks and citation omitted).\\nWhile “[t]he question of our jurisdiction over a colorable legal\\nclaim does not turn on whether that claim is ultimately\\nmeritorious . . . , a party may not dress up a claim with legal\\nclothing to invoke this Court's jurisdiction.” Pareja v. Att’y\\nGen., 615 F.3d 180, 187 (3d Cir. 2010) (citations omitted).\\n\\n Ku argues that we have jurisdiction to consider her\\npetition for review on the waiver issue because it presents a\\nquestion of law, namely whether the Board applied the proper\\nlegal standard in making the discretionary determination. But\\nKu’s argument boils down to her contention that the Board\\nfailed to consider certain equities relevant to the hardship\\ndetermination. As we have consistently held, “arguments such\\nas that an Immigration Judge or the BIA incorrectly weighed\\nevidence, failed to consider evidence or improperly weighed\\nequitable factors are not questions of law under\\n§ 1252(a)(2)(D).” Jarbough v. Att’y Gen., 483 F.3d 184, 189\\n(3d Cir. 2007). Because the substance of Ku’s petition for\\nreview amounts to contesting the weight the Board should have\\ngiven to the positive equities of her case, we do not have\\njurisdiction over it and will dismiss in part that aspect of the\\npetition.\\n\\n IV.\\n\\n\\n\\n\\n 20\\n\\f For the foregoing reasons, we will deny in part and\\ndismiss in part Ku's petition for review, and we will deny as\\nmoot the Government's motion to remand.\\n\\n\\n\\n\\n 21\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":61,"cells":{"id":{"kind":"number","value":4580566,"string":"4,580,566"},"name":{"kind":"string","value":"T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment"},"name_abbreviation":{"kind":"string","value":"T Mobile Northeast LLC v. City of Wilmington"},"decision_date":{"kind":"string","value":"2019-01-10"},"docket_number":{"kind":"string","value":"18-1831"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Jordan, Nygaard, Vanaskie\", \"parties\": \"\", \"opinions\": [{\"author\": \"JORDAN, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1831\\n _____________\\n\\n T MOBILE NORTHEAST LLC,\\n Appellant\\n\\n v.\\n\\n CITY OF WILMINGTON, DELAWARE;\\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\\n _____________\\n\\n On Appeal from the United States District Court\\n for the District of Delaware\\n (D.C. No. 1-16-cv-01108)\\n District Judge: Hon. Eduardo C. Robreno\\n _______________\\n\\n Argued\\n September 12, 2018\\n\\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\\n (Filed: January 10, 2019)\\n\\n\\n *\\n The Honorable Thomas I. Vanaskie retired from the\\nCourt on January 1, 2019 after the argument and conference\\nin this case, but before the filing of the opinion. This opinion\\nis filed by a quorum of the panel pursuant to 28 U.S.C.\\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\\n\\f _______________\\n\\nThomas S. Thompson [ARGUED]\\nDavis Wright Tremaine\\n1919 Pennsylvania Avenue, NW\\nSte. 800\\nWashington, DC 20006\\n\\nCounsel for Appellant\\n\\nJoseph Van Eaton [ARGUED]\\nBest Best & Krieger\\n2000 Pennsylvania Avenue\\nSte. 5300\\nWashington, DC 20006\\n\\nCounsel for Appellees\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\n\\nJORDAN, Circuit Judge.\\n\\n No one likes bad cell phone reception or slow\\nstreaming data on their smartphone, but that does not mean\\nanyone wants a cellular antenna in their neighborhood, which\\nis why there are zoning battles like the one central to this\\ncase.\\n\\n T Mobile Northeast LLC (“T Mobile”), a wireless\\ntelecommunications service provider, applied to the Zoning\\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\\nDelaware for permission to erect an antenna in the City. The\\n\\n\\n\\n\\n 2\\n\\fZBA said no. So, relying on a provision of federal law that\\nallows a disappointed wireless service provider like T Mobile\\nto seek review in a district court “within 30 days after” a\\nzoning authority’s “final action,” 47 U.S.C.\\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\\nproceeded for over a year, however, the District Court\\nconcluded that it lacked jurisdiction. The Court reasoned that\\nbecause T Mobile filed its complaint before the ZBA released\\na written decision confirming an earlier oral rejection of the\\nzoning application, the claim was not ripe. And, since\\nT Mobile did not supplement its complaint to include the\\nZBA’s written decision within 30 days of its issuance, the\\nCourt also concluded that relation back could not remedy the\\nripeness defect. The District Court thus granted the City’s\\nmotion for summary judgment.\\n\\n T Mobile now appeals. It argues that its complaint\\nwas not premature or, in the alternative, that its supplemental\\npleading cured any ripeness problem. We agree that the grant\\nof summary judgment was improper and, for the reasons that\\nfollow, will remand the case for further proceedings\\nconsistent with this opinion.\\n\\nI. BACKGROUND\\n\\n A. Statutory Framework\\n\\n This dispute is governed by the Telecommunications\\nAct of 1996 (“TCA”), which amended the Federal\\nCommunications Act of 1934 and includes provisions on\\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\\n“encourage the rapid deployment of new telecommunications\\n\\n\\n\\n\\n 3\\n\\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\\nfor expedited review in federal court of a denial of permission\\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\\nSuch review is a “benefit Congress expressly intended to\\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\\nthe TCA also serves to preserve local zoning authority. 47\\nU.S.C. § 332(c)(7).\\n\\n At issue here are three key sections of the statute.\\nFirst, the TCA mandates that “[a] State or local government\\nor instrumentality thereof shall act on any request for\\nauthorization to place, construct, or modify personal wireless\\nservice facilities within a reasonable period of time after the\\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\\nCommunications Commission (“FCC”) has interpreted\\n“reasonable period of time” in that statutory provision to\\nmean that zoning authorities have a “shot clock” 1 and must\\nact within 90 days of an application to attach an antenna to an\\nexisting structure or 150 days of an application where a new\\nsupport structure is to be built. Petition for Declaratory\\n\\n 1\\n “Shot clock” is a term borrowed from basketball. In\\nthat game, it signifies a time limit to make a shot attempt,\\nbeginning once a team has possession of the basketball. See,\\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\\nsecond-clock/. If the team has not made a shot attempt, i.e.,\\nacted, within the prescribed time limit, it forfeits possession\\nof the ball. Id. Here, the permitting authority has exclusive\\njurisdiction over an application until it fails to act within a\\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\\n332(c)(7)(B)(ii).\\n\\n\\n\\n\\n 4\\n\\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\\ncall the “review provision” of the statute, the TCA grants\\n“[a]ny person adversely affected by any final action or failure\\nto act by a State or local government or any instrumentality\\nthereof” a right to have that locality’s decision reviewed by\\n“commenc[ing] an action” “within 30 days” in district court.\\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\\nprovision,” the TCA states that “[a]ny decision by a State or\\nlocal government or instrumentality thereof to deny a request\\nto place, construct, or modify personal wireless service\\nfacilities shall be in writing and supported by substantial\\nevidence contained in a written record.” Id.\\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\\nand “decision … to deny” are not defined in the TCA.\\nFurthermore, the statute does not make clear whether “final\\naction” should be read to encompass all decisions to deny,\\nincluding oral ones, nor does it address whether there is a\\ndifference between an “act” for purposes of the shot clock\\nand a “final action” for purposes of judicial review.\\n\\n B. Factual Background\\n\\n T Mobile is a telecommunications service provider. It\\nsays that it needs to erect a cellular antenna to fill “a\\nsignificant gap” in coverage for its customers in Wilmington,\\nDelaware, (Opening Br. at 3) presumably where there has\\nbeen an increase in phone calls and data usage. T Mobile\\nwants to put its antenna on top of a senior living high-rise in\\nthe City, but, because a special exception to local zoning laws\\nis needed, it first had to go to the ZBA. It filed an initial\\napplication and then, on August 25, 2016, a final amended\\napplication, seeking the exception.\\n\\n\\n\\n\\n 5\\n\\f The ZBA held a hearing on October 26, 2016, to\\nconsider T Mobile’s request, some two months after the final\\namended application was submitted. During the hearing,\\nT Mobile presented evidence of the need for the antenna and\\ndiscussed proposals to address aesthetic concerns. The ZBA\\nalso received objections from members of the local\\ncommunity, some of whom were outspoken in worrying\\nabout the effects of radio frequency emissions. At the end of\\nthe hearing, the ZBA denied T Mobile’s application in a\\nunanimous oral decision.\\n\\n The Board gave several reasons for the denial. One\\nboard member said the ZBA should not encourage the use of\\na senior living community rooftop as the base for an antenna\\nbecause of the potential adverse effect on the properties in the\\nneighborhood. Another board member said there was not\\nenough proof of a need for additional coverage to support the\\napplication. The Chairman said there was not enough\\nevidence that T Mobile needed the antenna and that it did not\\nappear to satisfy the zoning code in terms of placement and\\nheight restrictions.\\n\\n The ZBA’s oral decision to deny the application was\\nnot put in writing on October 26 or anytime soon thereafter.\\nAccording to T Mobile, that fits a “pattern and practice of\\n[the ZBA] not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) Only\\nafter T Mobile had filed its initial complaint in the District\\nCourt, and after the City filed its answer, did the ZBA issue\\nits written decision and explanation of its reasoning for\\ndenying the application.\\n\\n\\n\\n\\n 6\\n\\f T Mobile asserts that the denial of its application\\nviolates the TCA. Under the statute, such a denial is invalid\\nif it has the “effect of prohibiting the provision of personal\\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\\nthe basis of the environmental effects of radio frequency\\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\\nWilmington’s denial was improper on both of those grounds. 2\\nBut those assertions go to the merits and are not actually\\nbefore us on this appeal. At issue now is whether T Mobile’s\\nclaim can be heard at all.\\n\\n C. Procedural History\\n\\n Evidently with its eye on the 30-day deadline in the\\nTCA’s review provision, T Mobile filed a lawsuit in the\\nUnited States District Court for the District of Delaware\\nwithin 30 days of the ZBA’s oral decision, challenging that\\ndenial. 3 In addition to its claims on the merits, T Mobile’s\\ninitial complaint alleged that the City violated procedures\\nmandated in the TCA, specifically those in the denial\\nprovision, by failing to provide a written decision\\n\\n 2\\n T Mobile also raised a Delaware state law claim.\\nThat claim is not at issue here and does not impact\\nT Mobile’s claims under federal law.\\n 3\\n For reasons discussed herein, the 30-day filing\\ndeadline was not triggered by the oral decision. See infra pp.\\n12-20. If it were, however, T Mobile’s complaint would have\\nbeen timely. The oral decision was delivered at the\\nOctober 26, 2016 hearing. Suit was filed on November 28,\\n2016, but because the thirtieth day from October 26 fell on a\\nweekend, the November 28 filing was within the 30-day\\nwindow. Fed. R. Civ. P. 6(a)(1).\\n\\n\\n\\n\\n 7\\n\\fcontemporaneous with its oral decision and by not supporting\\nthe denial with substantial evidence.\\n\\n The parties entered into a stipulation asking the\\nDistrict Court for an expedited case schedule, as provided for\\nin the review provision of the TCA. 47 U.S.C.\\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\\nthen answered the complaint, asserting a number of\\naffirmative defenses, including that the complaint was not\\nripe because the ZBA had not yet issued a final written\\ndecision. Nevertheless, the City did not, at that time, file a\\nmotion to dismiss for failure to state a claim or for lack of\\njurisdiction. Two days after the City filed its answer, the\\nZBA issued a written decision on T Mobile’s application.\\nThe parties pressed forward with the suit and prepared a\\ndiscovery plan, which specifically mentioned the written\\ndecision. T Mobile filed a motion for summary judgment,\\nwhich the City met with a cross-motion for summary\\njudgment. The City’s motion was styled in the alternative as\\na motion to dismiss the complaint as unripe because it was\\nfiled prematurely, i.e., before the written decision had been\\nissued.\\n\\n Not until December 21, 2017, nearly a year after the\\nZBA issued its written denial, did T Mobile file a motion\\nseeking leave to amend or supplement the initial complaint to\\nnote the issuance of that written decision. 4 The District Court\\n\\n 4\\n When “[a] claim or defense set out in a pleading [is]\\naffected by events that occur after the pleading is filed ….\\nRule 15(d) allows a court,” to permit a supplemental\\npleading. 3 James Wm. Moore et al., Moore’s Federal\\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\\n\\n\\n\\n\\n 8\\n\\fgranted the motion to supplement. Wilmington then\\nresponded by moving to dismiss the supplemental complaint\\nas untimely because it failed to cure the defect.\\n\\n Ultimately, the District Court granted Wilmington’s\\ncross-motion for summary judgment for want of jurisdiction,\\nwithout ruling on the City’s motion to dismiss. The Court\\nfirst concluded that the initial complaint was irreparably\\nunripe because both the TCA and Delaware law require the\\nZBA to issue a written decision before the agency’s action\\ncould be considered final, and T Mobile had thus filed its\\ninitial complaint too soon. Second, the Court said that the\\nsupplemental complaint could not fix the ripeness problem\\nbecause it was filed past the 30-day window for seeking\\nreview of the ZBA’s final action. Because the Court reached\\n\\n\\n\\nunder Rule 15(d) differ from amended pleadings made under\\nRule 15(a). First, amended pleadings “relate to matters that\\noccurred prior to the filing of the original pleading and\\nentirely replace the earlier pleading; [supplemental pleadings]\\ndeal with events subsequent to the pleading to be altered and\\nrepresent additions to or continuations of the earlier\\npleadings.” 6A Charles Alan Wright et al., Federal Practice\\n& Procedure § 1504 (3d ed. 2018). Second “certain\\namendments may be made as a matter of course within stated\\ntime periods, whereas all supplemental pleadings require\\nleave of court under Rule 15(d).” Id. “Parties and courts\\noccasionally confuse supplemental pleadings with amended\\npleadings and mislabeling is common.” Id. Here, T Mobile’s\\ncomplaint was filed as an amended complaint but it is\\nproperly categorized as a supplemental complaint, and we\\nwill refer to it as such herein.\\n\\n\\n\\n\\n 9\\n\\fthat determination, it found it unnecessary to conclude\\nwhether T Mobile’s supplemental complaint was entitled to\\nthe benefit of the relation-back doctrine under Rule 15(c).\\n\\n This appeal followed.\\nII. DISCUSSION 5\\n\\n T Mobile challenges the District Court’s grant of\\nsummary judgment in favor of Wilmington, contending that\\nthere is jurisdiction to hear its case. It advances two\\nalternative grounds for reversal: that its complaint was ripe\\nbecause the ZBA’s oral decision qualifies as a “final action”\\nunder the review provision of the TCA, and, in the\\nalternative, that the supplemental complaint relates back to\\nand cures any ripeness problem with its initial complaint.\\nThose arguments in turn raise three questions for determining\\nwhether the District Court’s jurisdictional ruling was proper.\\nFirst, whether the oral decision of the ZBA was a final action.\\nSecond, whether the timing requirement in the TCA’s review\\nprovision is jurisdictional. And third, whether an untimely\\n\\n 5\\n The District Court had jurisdiction to consider its\\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\\ndetermined the complaint contained incurable jurisdictional\\ndefects and declined to reach the merits. We have jurisdiction\\npursuant to 28 U.S.C. § 1291. We review all the issues\\npresented in this case de novo, as they involve only legal\\nissues, i.e., interpretation of a federal statute and of a Federal\\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\\n123, 125 (3d Cir. 2007).\\n\\n\\n\\n\\n 10\\n\\fsupplemental complaint can relate back and cure an unripe\\ninitial complaint. Although we disagree with T Mobile that\\nan oral decision of the ZBA qualifies as a “final action,” we\\nagree that jurisdiction was proper in the District Court\\nbecause the timing requirement in the TCA’s review\\nprovision is non-jurisdictional, and T Mobile’s supplemental\\ncomplaint therefore relates back and cures the ripeness\\nproblem with the initial complaint. The District Court should\\nthus have reached the merits of the dispute.\\n\\n A. The Oral Decision Was Not a Final Action of\\n the ZBA.\\n\\n The ripeness of T Mobile’s initial complaint depends\\nupon whether the ZBA’s oral decision was a “final action”\\nwithin the meaning of the TCA. Consideration of that issue\\nuncovers another: whether the TCA requires a locality to\\nrender its decision in writing for that decision to qualify as a\\nfinal action. The District Court held that, under both federal\\nand Delaware law, only a written decision can serve as a final\\naction of the ZBA. Because traditional hallmarks of agency\\naction and the statutory text and structure of the TCA favor\\nthat approach, we agree that only a written decision can serve\\nas a locality’s final action when denying an application.\\n\\n In Delaware Riverkeeper Network v. Secretary\\nPennsylvania Department of Environmental Protection,\\n(Riverkeeper III), we determined that, when reviewing\\nfinality under the Natural Gas Act, “[a]lthough the\\ndecisionmaking process we are reviewing is defined by [state]\\nlaw, we nevertheless apply a federal finality standard to\\ndetermine whether Congress has made the results of that\\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\\n\\n\\n\\n\\n 11\\n\\fsame reasoning holds true here, since, for the TCA just as for\\nthe Natural Gas Act, “the finality requirement itself, along\\nwith the presumption that Congress intended us to apply it,\\nare creatures of federal, not state, law.” Id. at 71.\\n\\n Under federal law, not all agency determinations are\\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\\n1992). Final agency actions bear certain “traditional\\nhallmarks” that demonstrate “[t]here is nothing left for the\\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\\nCir. 2017). We noted those hallmarks on an earlier occasion\\nwhen we said that, “[f]inal agency action must mark the\\nconsummation of the agency’s decisionmaking process, must\\nnot be of a merely tentative or interlocutory nature, and must\\nbe one by which rights or obligations have been determined,\\nor from which legal consequences will flow.” Riverkeeper\\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\\nomitted).\\n\\n To decide what the TCA requires for finality, we\\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\\nwith the text[.]”) Here, the statutory text makes it clear that,\\nif a denial is not in writing, there is something left for the\\nagency to do. The denial provision of the TCA states that\\n“[a]ny decision … to deny … shall be in writing and\\nsupported by substantial evidence contained in a written\\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\\nwhy the same should not be true for actions besides denial, 6\\n\\n 6\\n For instance, it is not apparent why community\\nmembers aggrieved by a decision to grant some permit to a\\n\\n\\n\\n\\n 12\\n\\fbut we need not decide that today. It is enough to say that, in\\nthose zoning decisions governed by the TCA, a locality’s oral\\ndeclaration of a denial is “of a merely tentative or\\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\\n(citation omitted) (speaking in reference to the Natural Gas\\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\\ncould have approved the minutes, revised them, or rejected\\nthem, and thus until the board approved the minutes its\\ndecision was not final).\\n\\n Moreover, an oral decision is not an action from which\\nlegal consequences flow. Federal law governs finality, but\\nDelaware’s procedures still matter, and the Delaware\\nSuperior Court has concluded that a written document must\\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\\nZoning Bd. of Adjustment for the City of Wilmington, No.\\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\\nTitle 22 of the Delaware Code, the section that governs\\nappeals from ZBA proceedings, requires a written document\\nto be filed because the statute “provides that [s]uch petition\\nshall be presented to the Court within 30 days after the filing\\nof the decision in the office of the board.” Id. (internal\\nquotation marks omitted). That reasoning is persuasive and\\n\\n\\n\\n\\nwireless provider, assuming those members have standing to\\nsue, would not be equally entitled to a zoning authority’s\\nwritten decision before the time limit in the TCA’s review\\nprovision is triggered.\\n\\n\\n\\n\\n 13\\n\\fshows that, under Delaware law, the ZBA’s oral decision is\\nwithout legal consequences. 7\\n\\n There are distinct policy advantages to forestalling\\njudicial scrutiny until a written denial is issued. Requiring a\\nwritten decision focuses review on a particular, documented\\nstatement of reasons. See USCOC of Greater Mo. v. City of\\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\\nwritten decision is the central object of our scrutiny under the\\nTCA, the process of judicial review is best served by delaying\\nthe ripening of a TCA claim until the local authority has\\nissued its written decision.”). It also prevents ambiguity with\\nrespect to when a claim can be brought. As the District Court\\nhere stated, to hold otherwise “would promote a pernicious\\nambiguity as to when that short period of time begins to run.”\\n(App. at 7.) And it promotes uniformity of federal procedures\\nby clarifying when, across all jurisdictions, an action becomes\\nfinal.\\n\\n 7\\n T Mobile cites to a different opinion, Schmalhofer v.\\nBoard of Adjustment of Newark, to advance a contrary\\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\\nfootnote that “a written decision is not required or expressly\\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\\nstretching the Schmalhofer court’s language too far. In that\\ncase, the City of Newark had issued a verbatim transcript of\\nthe hearing, so there was a writing. Id. at *3; see infra note\\n11. There is no indication of any written decision in this case,\\nprior to December 22, 2016, when the City issued the written\\ndenial bearing the date of December 21, 2016.\\n\\n\\n\\n\\n 14\\n\\f The Supreme Court’s decision in T-Mobile South, LLC\\nv. City of Roswell, Georgia, also adds support to the\\nconclusion that only a written denial can constitute final\\naction, triggering a party’s right to review. 135 S. Ct. 808\\n(2015). In that case, the Court held that the “substantial\\nevidence” supporting a locality’s decision to deny must be\\nreleased contemporaneously with the written decision to\\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\\nlocal zoning authority’s final action, which triggers judicial\\nreview, and its decision to deny, which must be in writing.\\nIndeed, the Supreme Court said in no uncertain terms that,\\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\\nthe written notice of denial[.]” Id. at 817 n.4. The Court\\nlinked the locality’s decision to deny to the 30-day time limit\\nto file a complaint after a final action has been taken. Id. at\\n817 (“Only once the denial is issued would the 30-day\\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\\ndays after the City denied petitioner’s application—petitioner\\nfiled suit in Federal District Court.”).\\n\\n The Court went on to discuss timing, saying, “the\\nlocality must provide or make available its written reasons at\\nessentially the same time as it communicates its denial[,]”\\n“[b]ecause an entity may not be able to make a considered\\n\\n 8\\n The Court was interpreting the denial provision,\\nwhich, as we noted earlier, states that, “[a]ny decision by a\\nState or local government or instrumentality thereof to deny a\\nrequest to place, construct, or modify personal wireless\\nservice facilities shall be in writing and supported by\\nsubstantial evidence contained in a written record.” 47\\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\\n\\n\\n\\n\\n 15\\n\\fdecision whether to seek judicial review without knowing the\\nreasons for the denial of its application, and because a court\\ncannot review the denial without knowing the locality’s\\nreasons[.]” Id. at 816. The majority opinion was critical of\\nthe dissent for attempting to “fashion a world in which a\\nlocality can wait until a lawsuit is commenced and a court\\norders it to state its reasons[,] … [leaving the challenging\\nentity to] risk being sandbagged by the written reasons that\\nthe locality subsequently provides in litigation after the\\nchallenging entity has shown its cards.” Id. at 816 n.3. That\\ncritique is premised on the written decision being the final\\naction that starts the 30-day time limit for commencing suit. 9\\n\\n The Supreme Court anticipated that localities might\\nneed to delay issuing a written denial if they are not ready to\\nrelease their substantial reasons. See id. at 817 (noting that\\n\\n 9\\n T Mobile asserts that Wilmington has a “pattern and\\npractice of not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) But if\\nonly a written denial is a final action, the shot clock requires\\nthe City to issue that written decision within a given time\\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\\nasserts that when a locality has a pattern and practice of not\\nreleasing written decisions, that practice delays the overall\\nprocess, since a cellular service provider would be required to\\ninitiate two causes of action: one to compel a written decision\\nand another to challenge that written decision. That,\\nhowever, is precisely what Congress envisioned by providing\\nseparate remedies for a failure to “act” within a reasonable\\ntime period and for an improper denial. 47 U.S.C.\\n§ 332(c)(7)(B)(iii).\\n\\n\\n\\n\\n 16\\n\\f“[i]f a locality is not in a position to provide its reasons\\npromptly, the locality can delay the issuance of its denial\\nwithin this 90– or 150–day window, and instead release it\\nalong with its reasons once those reasons are ready to be\\nprovided.”). That further counsels against treating an oral\\ndetermination as a final action since, if an oral determination\\nis deemed a final action, localities will be unable to take\\nadvantage of the permissible delay afforded by the shot clock\\nfor publishing their reasoning.\\n\\n Two of our sister courts of appeals agree that only a\\nwritten decision can constitute final action. The Eighth\\nCircuit in USCOC of Greater Missouri v. City of Ferguson\\nstated that “[t]he plain language of the TCA indicates that\\n‘final action’ does not occur until issuance of a written\\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\\nPreferred Sites LLC v. Troup County likewise held a\\ncomplaint to be timely when it was filed within 30 days of a\\nwritten decision, even though it was filed more than 30 days\\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\\n\\n 10\\n T Mobile attempts to distinguish Preferred Sites by\\nstating that, unlike here, the case did “not address a city that\\ndoes not issue a written decision close in time to when it\\nmakes the decision to deny.” (Opening Br. at 37.) But that\\nargument is irrelevant to whether the statutory text requires a\\nwriting for an agency decision to be final. T Mobile also cites\\nto Preferred Sites to argue that it should not matter if there is\\na writing requirement since the oral denial could be seen as\\nakin to a court announcing a decision. It explains that “when\\nan appeal is filed after the court announces a decision, but\\nbefore the entry of the judgment, it is treated as being filed on\\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\\n\\n\\n\\n\\n 17\\n\\f2002) (concluding that, “[b]ased on the plain language of the\\nstatute,” that “a ‘final action’ occurs when the state or local\\nauthority issues its written decision. The statute expressly\\nmandates a … decision … committed to writing. Until the\\nstate or local authority issues its written notification, its task\\nunder the statute is not complete.”). No circuit has held\\notherwise.\\n\\n Persuasive authority thus indicates that any action, and\\ncertainly a denial, must be in writing to be final. But, there is\\nanother possible interpretation of the statutory text. The\\nwords “shall be in writing” could be read not as a condition of\\nfinality, but instead as a simple directive to state and local\\ngovernments to place their final action in writing. “The TCA\\nprovides no express answer to … when a local government’s\\npermitting decision becomes a ‘final action,’ which starts the\\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\\nstatute only states that denials must be in writing. 47 U.S.C.\\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\\nsame way. Id. And, Congress used the words “decision to\\ndeny” in one statutory subsection and “final action” in\\nanother, which could evince an intent to give those terms\\ndifferent meanings. As the Supreme Court has “recognized\\n… Congress’s use of certain language in one part of the\\nstatute and different language in another can indicate that\\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\\n\\n\\n\\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\\nPreferred Sites, but it was only contained in a footnote. No\\nother court has followed that line of reasoning, and we\\ndecline to follow it here.\\n\\n\\n\\n\\n 18\\n\\fmarks omitted). Thus, it could be argued, if Congress wanted\\nto mandate a writing for zoning denials to constitute final\\naction, it could have been more explicit, providing, for\\ninstance, that a “decision must be in writing to qualify as a\\nfinal action.”\\n\\n But, of course, one can almost always fault legislative\\ndrafting, like other kinds of writing, after the fact. That\\nsomething might have been said even more clearly does not\\nmean it is not clear enough. So, “[r]ather than expecting (let\\nalone demanding) perfection in drafting,” we can “construe[]\\nstatutes to have a particular meaning even as we\\nacknowledge[] that Congress could have expressed itself\\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\\n(2016).\\n\\n The text and structure of the statute, Delaware\\nprocedures, Supreme Court reasoning, our sister circuits’\\ndecisions, and policy arguments all support the conclusion\\nthat a writing is in fact a requirement for a denial to be final. 11\\nIn light of that conclusion, the ZBA’s oral determination on\\n\\n 11\\n What constitutes a “writing” has some flexibility,\\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\\nminutes by written resolution was a final action that bound\\nthe parties). In City of Roswell, for example, the Supreme\\nCourt indicated that minutes of an oral meeting could be\\nsufficient. 135 S. Ct. at 816. Here, however, there is no\\nevidence that the ZBA’s oral determination was noted in the\\nminutes of the October 26th meeting and issued by the City as\\nits formal decision.\\n\\n\\n\\n\\n 19\\n\\fOctober 26, 2016, was not a final action ripe for judicial\\nreview. Therefore, as that oral determination was not reduced\\nto writing until December 22, 2016, preceding the filing of\\nT Mobile’s initial complaint, that complaint’s cause of action\\nwas not ripe.\\n\\n\\n\\n\\n 20\\n\\f B. No Separate Time Limit Exists Following an\\n Oral Determination.\\n\\n As an alternative to its argument that the ZBA’s oral\\ndecision was a final action, T Mobile asks us to consider\\nwhether a “local government must issue the ‘writing’ close in\\ntime to the ‘decision … to deny’ to establish a ‘final action’\\nthat will be subject to expedited review.” 12 (Opening Br. at\\n41.) Essentially, T Mobile is asserting that the “shot clock”\\ngoverning the time to act, which allows a wireless carrier to\\nsue for a locality’s failure to act, is insufficient, and that a\\nnew requirement, albeit not in the statute, should be imposed\\non localities. Under T Mobile’s proposed rule, an oral\\ndecision would have to be reduced to writing within a\\nspecified time period. That argument assumes that an oral\\ndetermination can serve to satisfy the requirement to “act” on\\na request within the limits of the shot clock, and that, without\\na separate judicially created time limit, there would be no\\ndeadline for the locality to release its written decision to deny,\\ndespite City of Rowell’s contemporaneous writing\\nrequirement. Because we conclude that a denial must be in\\nwriting to be a final action, the issuance of that writing is the\\ngovernment “act” ruled by the shot clock. 13 Aside from the\\n\\n 12\\n Wilmington argues that T Mobile has waived that\\nissue, but we need not address that argument because we\\nconclude that no such requirement exists.\\n 13\\n Again, the Supreme Court held in City of Roswell\\nthat a locality’s decision to deny must be accompanied by\\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\\nlocality were able to withhold its reasoning for its decision,\\nthose aggrieved by the locality’s actions would “be left to\\n\\n\\n\\n\\n 21\\n\\ftime limits associated with the “shot clock,” there is no other\\ndeadline governing the issuance of a written decision\\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\\nAny time limit we fabricated would be inappropriate.\\n\\n T Mobile argues that, without a requirement for\\nlocalities to issue a written decision within a set amount of\\ntime following an oral determination, wireless carriers are left\\n“to wait until the FCC ‘shot clock’ expires – which could be\\n90 or 150 days depending on the type of installation involved\\n– and then [to] file an action alleging that the City has failed\\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\\ncontends that a “failure to act” lawsuit is insufficient because\\nthe remedy for a successful suit is simply an order telling the\\nCity to issue a written decision. In T Mobile’s view, forcing\\nwireless providers to sue both to compel a written decision\\nonce the shot clock is violated and again to contest the written\\ndecision serves only to “create yet further delay.” (Opening\\nBr. at 46.)\\n\\n\\n\\n\\nguess at what the locality’s written reasons will be, write a\\ncomplaint that contains those hypotheses, and risk being\\nsandbagged by the written reasons that the locality\\nsubsequently provides in litigation after the challenging entity\\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\\nfile suit, however, because the locality’s “final action” has not\\nyet occurred, those concerns vanish. The ZBA’s decision\\nhere, when reduced to writing, was both its decision to deny\\nand its final action.\\n\\n\\n\\n\\n 22\\n\\f Those concerns are overstated and, in any case,\\nirrelevant. The shot clock begins to run once a wireless\\nprovider files its application, so it is already ticking before\\nany oral decision is made. If the locality fails to meet that\\ndeadline by not issuing a written decision before the shot\\nclock expires, the wireless provider can bring a claim for a\\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\\nMobile asserts that requiring a separate failure-to-act suit, in\\naddition to a suit on the merits, undercuts the statutory\\npurpose of expedited judicial review, particularly in cases\\nwhere the locality has a “pattern and practice of not issuing a\\nwritten decision of land use denials unless or until [it] is\\nsued.” (Opening Br. at 7.) But the statute’s own remedies\\ncannot possibly undercut its purpose. A separate failure-to-\\nact claim is the very remedy Congress chose for shot clock\\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\\nT Mobile likes that policy choice, it is the one Congress\\nmade, and we are not free to change it.\\n\\n C. The Timing Requirement Is Not\\n Jurisdictional.\\n\\n Because we hold that a writing is required for a denial\\nto constitute a final action, T Mobile’s initial complaint was\\nnot ripe for review when filed. And, T Mobile’s\\nsupplemental complaint was filed more than 30 days after the\\nZBA issued its written decision and was therefore untimely\\nunder the TCA’s review provision. 47 U.S.C.\\n§ 332(c)(7)(B)(v). Thus, the District Court only had\\njurisdiction if T Mobile’s supplemental complaint cured the\\n\\n 14\\n It is not clear which time limit would have applied in\\nthis case and whether it would have been violated.\\n\\n\\n\\n\\n 23\\n\\fripeness flaw in its initial complaint by relating back to the\\noriginal filing date. If the 30-day time limit in the TCA’s\\nreview provision is nonjurisdictional, we can safely say that\\nrelation back is possible and allows a supplemental complaint\\nto cure a defective premature filing. 15 At the outset, then, we\\nmust determine whether that 30-day time limit is\\njurisdictional, being mindful both of the Supreme Court’s\\ncounsel to exercise caution before holding timing\\nrequirements to be jurisdictional and of its guidance regarding\\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\\n149, 153-54. Caution is indeed warranted because statutes of\\nlimitations and other filing deadlines “ordinarily are not\\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\\nnonjurisdictional.”).\\n\\n\\n 15\\n We do not reach the issue of whether an unripe\\ncomplaint can be cured by a supplemental or amended\\npleading over which the Court lacked jurisdiction.\\n 16\\n The City claims that our decision in Nextel Partners\\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\\neffectively determinative. Not so. In Kingston Township,\\nthen-Judge Alito noted that the District Court had held the\\ntiming requirement in the TCA’s review provision was\\njurisdictional. Id. at 695. But we did not address whether\\nthat determination was correct, nor did we rely on it. Instead,\\nwe concluded that there could be no “failure to act” towards\\nan application that was not submitted. Id. at 692. Since our\\ndecision in that case, the Supreme Court has clarified the\\nprocess for determining if a time limit is jurisdictional.\\nSebelius, 568 U.S. at 149.\\n\\n\\n\\n\\n 24\\n\\f “[T]o ward off profligate use of the term ‘jurisdiction,’\\n[the Supreme Court has] adopted a readily administrable\\nbright line for determining whether to classify a statutory\\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\\n(quotation marks omitted). We are to ask “whether Congress\\nhas clearly state[d] that the rule is jurisdictional; absent such a\\nclear statement, we … should treat the restriction as\\nnonjurisdictional in character.” Id. (alteration in original)\\n(citation and quotation marks omitted); see also Musacchio v.\\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\\ntime bar as jurisdictional only if Congress has ‘clearly stated’\\nthat it is.”). In deciding whether Congress has made such a\\nclear statement, “we evaluate the ‘text, context, and relevant\\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\\n(2010)).\\n\\n Referencing that last test, Wilmington asserts that\\n“[s]ection 332’s statutory grant of jurisdiction to district\\ncourts, the text of the statute, the placement of the filing\\nwindow in that same section, and the well-established\\ntreatment of the filing window as jurisdictional, [all\\ndemonstrate] that the filing window is jurisdictional.”\\n(Answering Br. at 15.) We disagree. The differences\\nbetween the review provision’s timing requirement and the\\ntiming requirement we held to be jurisdictional in Kalb, and\\nthe similarities between the review provision’s timing\\nrequirements and those at issue in Sebelius and Musacchio,\\nwhich the Supreme Court held to be nonjurisdictional,\\nactually support treating the timing requirement in the TCA’s\\nreview provision as nonjurisdictional.\\n\\n\\n\\n\\n 25\\n\\f First, although Wilmington says that the text of the\\nstatute indicates Congress’s desire to make the 30-day timing\\nrequirement jurisdictional, the text does not use the term\\n“jurisdictional” or any variation of it to describe the timing\\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\\nthe statute uses permissive rather than mandatory language.\\nUnlike the timing requirement we held to be jurisdictional in\\nKalb, which mandated that an action would be barred if not\\nfiled in time, the TCA’s review provision states that an action\\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\\ncloser to that which the Supreme Court decided was\\nnonjurisdictional in Sebelius. The statute at issue in that case,\\nlike the review provision here, uses a permissive phrase –\\n“may obtain a hearing” – before it states the timing\\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\\nSimilar to the timing requirement the Supreme Court held to\\nbe nonjurisdictional in Musacchio, the review provision does\\nnot confer jurisdiction, instead it allows an action to be\\n\\n 17\\n T Mobile also points to Henderson v. Shinseki,\\nwhich held a timing requirement to be nonjurisdictional even\\nthough it used the mandatory “shall” before stating the timing\\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\\nin Shinseki, where the pertinent timing requirement could\\nhave barred a veteran’s appeal, was partly based on “the\\ncanon that provisions for benefits to members of the Armed\\nServices are to be construed in the beneficiaries’ favor,” and\\nso it is of less utility in deciding this dispute. Id. at 441\\n(quotation marks and citations omitted).\\n\\n\\n\\n\\n 26\\n\\fcommenced “in any court of competent jurisdiction.” See\\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\\nexpressly refer to subject-matter jurisdiction or speak in\\njurisdictional terms.”). The text of the statute therefore favors\\na holding that the timing requirement is nonjurisdictional.\\n\\n Wilmington next contends that the context of the\\ntiming requirement favors the view that the requirement is\\njurisdictional, because the Supreme Court has stated that it is\\n“inextricably linked to … the language that creates the right\\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\\nsays the City, the “filing window created by [the review\\nprovision] is jurisdictional [because] it is integral to the\\nexpress purpose of the section, to this Court’s jurisdiction,\\nand to the parties’ rights and obligations[.]” (Answering Br.\\nat 8.)\\n\\n True enough, the review provision’s timing\\nrequirement does appear in the same subsection as the\\nstatutory text granting jurisdiction. 47 U.S.C.\\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\\nboth found the source of the timing requirement to be\\nimportant in determining whether that requirement was\\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\\nthe same point the City now does, stating that a timing\\nrequirement was jurisdictional because “the thirty-day appeal\\nperiod here is embedded in the same statutory section that\\ngrants jurisdiction to the court of appeals.” Id.\\n\\n\\n\\n\\n 27\\n\\f But the location of the timing requirement within the\\nstatutory structure, without more, does not clearly reveal\\nCongressional intent. As noted by the Supreme Court in\\nSebelius, a timing requirement should not be classified as\\njurisdictional solely based on its placement in a jurisdictional\\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\\nwould otherwise classify as nonjurisdictional … does not\\nbecome jurisdictional simply because it is placed in a section\\nof a statute that also contains jurisdictional provisions.”\\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\\nMusacchio too, the Supreme Court held that a timing\\nrequirement was nonjurisdictional despite its presence in the\\njurisdiction-granting section of the statute at issue. 136 S. Ct.\\nat 717. The Court emphasized that the statute did not directly\\nspeak of the timing requirement as jurisdictional, despite its\\nmandatory language. Id. That reasoning applies with at least\\nequal force here, so the context of the review provision’s\\ntiming requirement does not make the requirement\\njurisdictional.\\n\\n Finally, Wilmington asserts that the timing\\nrequirement is jurisdictional because of the historical\\ntreatment of similar provisions. The City asserts that the\\nphrase “within 30 days after” creates a “window,” during\\nwhich a complaint must be filed, and not a “deadline.”\\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\\ndays after” creates a 60-day filing window while “no later\\nthan 60 days after” creates a filing deadline).) But that\\nargument misses the point because it goes to whether the rule\\nbars suit between certain dates or only after a certain date, not\\nto whether the timing requirement is jurisdictional. See, e.g.,\\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\\n\\n\\n\\n\\n 28\\n\\ffiling window is a jurisdictional bar for suits filed before the\\nwindow opens). And just because a complaint may be unripe\\nbefore a particular date does not mean that a deadline by\\nwhich suit must be filed is jurisdictional. As we stated in\\nKalb, the Supreme Court’s decisions in Bowles and Reed\\nElsevier both looked to “the Court’s prior treatment of\\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\\nSebelius, the timing requirement, as here, used the phrase\\n“within” and thus, under Wilmington’s logic, it would have\\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\\nSupreme Court held otherwise, id., and that is of high\\nimportance.\\n\\n Because the text and context of this statute, and\\nhistorical treatment of timing requirements in similar statutes,\\ndo not reveal a clear intent from Congress to make the review\\nprovision’s timing requirement jurisdictional, we conclude\\nthat it is not. 18\\n\\n D. Rule 15 Allows a Supplemental Complaint\\n Filed After a Claims Processing Deadline To\\n Relate Back and Cure an Unripe Initial\\n Complaint.\\n\\n We next consider whether an untimely supplemental\\ncomplaint can, by relating back, cure an initial complaint that\\nwas unripe. We believe it can, and because T Mobile’s\\n\\n 18\\n That conclusion is further supported by the\\nthoughtful concurrence in Athens Cellular, concluding after\\nSebelius that the timing requirement “imposed by Congress in\\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\\nF.3d at 1113 (Kaplan, J. concurring).\\n\\n\\n\\n\\n 29\\n\\fmotion to supplement its complaint was properly granted, that\\nsupplemental complaint relates back and is ripe. The District\\nCourt therefore had jurisdiction and should not have granted\\nWilmington’s motion for summary judgment.\\n\\n At the outset, we note that the parties do not dispute,\\nand we agree, that the District Court was within its discretion\\nto grant T Mobile’s motion to supplement its complaint.\\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\\nmotion and reasonable notice, the [district] court may, on just\\nterms, permit a [moving] party to serve a supplemental\\npleading setting out any … event that happened after the date\\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\\nlimited to subsequent events related to the claim or defense\\npresented in the original pleading.”). Here, the District Court\\nrightly granted T Mobile’s motion to supplement. That\\ndecision was just, since Wilmington had long since had notice\\nof the event – the filing of the written denial – that occurred\\nafter the initial pleading. After all, the City issued that denial,\\nand the denial was featured in the parties’ discovery plan.\\nThe issuance of it was also plainly related to T Mobile’s\\ninitial complaint.\\n\\n That the initial complaint was premature is not a bar\\nsince, under Rule 15(d), “[t]he court may permit\\nsupplementation even though the original pleading is\\ndefective in stating a claim for relief or defense.” Fed. R.\\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\\n“Rule 15(d) is intended to give the [district] court broad\\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\\nP. 15(d) advisory committee’s note to 1963 amendment. It is\\n\\n\\n\\n\\n 30\\n\\ffurthermore “within the discretion of the court to allow a\\nsupplemental pleading to be filed at any stage of the case[.]”\\nMoore et al., supra, ¶ 15.30. The District Court here was thus\\nwell within its discretion in granting T Mobile’s motion to\\nsupplement the complaint.\\n\\n Rule 15 does not indicate whether or under what\\ncircumstances a supplemental pleading can relate back to the\\ndate of the original pleading to avoid the effect of a time\\nlimit. 6A Charles Alan Wright et al., Federal Practice &\\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\\nwhich provides for the relation back of amended pleadings,\\ndoes not specifically refer to supplemental pleadings. Fed. R.\\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\\nrelation back. Fed. R. Civ. P. 15(d). But case law and\\nsecondary sources have long instructed that once a\\nsupplemental complaint is granted, it is treated like an\\namended complaint for purposes of relation back. 19 Thus,\\neven though Rule 15(d) is in a separate statutory provision\\nfrom Rule 15(c), a supplemental complaint can relate back.\\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\\nbetween an amended pleading and a supplemental pleading is\\n\\n 19\\n Courts have generally held that a supplemental\\ncomplaint is eligible for relation back, but rely on different\\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\\ncourts have held that for purposes of applying the relation-\\nback doctrine a supplemental pleading may be treated as an\\namended pleading under Rule 15(c); other courts have\\napplied the relation-back principle directly to supplemental\\npleadings even though Rule 15(d) does not mention it.”)\\n(internal citations omitted).\\n\\n\\n\\n\\n 31\\n\\foften disregarded for purposes of relation back under Rule\\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\\n680-81 (8th Cir. 1962) (finding supplemental pleading related\\nback despite plaintiff suing in the wrong capacity and not\\nachieving appropriate status for diversity jurisdiction until\\nafter the limitations period had expired). That stands to\\nreason, since, if a “defendant had notice of the subject matter\\nof the dispute and was not prejudiced in preparing a defense\\n…[,] the policy against stale claims becomes subsidiary to the\\npolicy expressed throughout the rules in favor of allowing a\\nparty to set forth all the grievances against another party in\\none action and resolving them on their merits.” Wright et al.,\\nsupra, § 1508.\\n\\n So a pleading filed according to Rule 15(d) can relate\\nback, assuming it meets “the basic test for relation back\\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\\n¶ 15.30 (“A supplemental pleading may relate back to the\\ndate of the original complaint if the requirements under Rule\\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\\npleading relates back if Rule 15(c)’s test is met). In fact, as\\nthe District Court observed, if a supplemental complaint\\nmeets the requirements for relation back then “[r]elation back\\nis mandatory,” and not subject to additional equitable\\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\\n\\n 20\\n We note, however, that “[a] party opposing the\\nintroduction of a supplemental pleading might wish to raise\\nthe statute-of-limitations defense when the additional\\npleading (1) alleges new matter that brings the earlier\\npleading up to date; (2) cures a defect in the original pleading;\\n\\n\\n\\n\\n 32\\n\\f Looking then to Rule 15(c), a complaint “relates back\\nto the date of the original pleading when … [it] asserts a\\nclaim or defense that arose out of the conduct, transaction, or\\noccurrence set out -- or attempted to be set out -- in the\\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\\nDistrict Court here concluded that there was no need to\\ndetermine whether T Mobile’s supplemental complaint\\nrelated back, because, even if it did, “it fail[ed] to cure the\\ndeficiencies of the initial complaint[.]” (App. at 8.) But\\ngiven our view that the supplemental complaint could indeed\\ncure the ripeness problem with the initial complaint, we must\\ncontend with the relation-back question.\\n\\n To determine if relation back is proper, the only issue\\nis whether there is a “common core of operative facts in the\\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\\nrely on the same core facts. The written denial was a\\ncertification and restatement of the earlier oral denial.\\n\\n Thus, the only question remaining is whether a\\ncomplaint that relates back can cure an untimely initial\\ncomplaint, and the answer is yes. The clear preference\\nembodied in Rule 15 is for merits-based decision making. Cf.\\nMoore et al., supra, ¶ 15.30 (“The same principles that\\nsupport the liberal amendment of pleadings also apply to\\nsupplemental pleadings.”). As the Supreme Court has stated,\\nthe purpose of Rule 15 is “to balance the interests of the\\n\\n\\nor (3) states a new claim that arose after the filing of the\\ncomplaint.” Wright et al., supra, § 1508.\\n\\n\\n\\n\\n 33\\n\\fdefendant protected by the statute of limitations with the\\npreference expressed in the Federal Rules of Civil Procedure\\nin general, and Rule 15 in particular, for resolving disputes on\\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\\n550 (2010). The requirements of Rule 15 itself protect\\ndefendants from an unfair relation back. 21 Under that Rule,\\ncourts “look[s] to whether the opposing party has had fair\\nnotice of the general fact situation and legal theory upon\\nwhich the amending party proceeds.” Bensel, 387 F.3d at\\n310. In this instance, Wilmington had sufficient notice since\\nthe supplemented complaint simply alleged the issuance of\\nthe ZBA’s written denial. And, of course, Wilmington had\\nnotice of everything in the supplemental complaint. It not\\nonly knew of the written denial and the reasons given, it\\ngenerated them.\\n\\n Relation back has been allowed to address\\njurisdictional problems. We said in Berkshire Fashions, Inc.\\nv. M.V. Hakusan II that relation back may be used to cure\\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\\nCir. 1992). In that case, the District Court had dismissed the\\nplaintiff’s claim based on admiralty jurisdiction and denied\\nthe plaintiff’s motion to amend its complaint to allege\\ndiversity jurisdiction. Id. at 877. We concluded that both\\ndecisions were in error, holding that an amended complaint\\nrelates back and can cure insufficient pleading of subject\\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\\n\\n 21\\n This is not a pass for endless delay in\\nsupplementing a complaint. Indeed, we have endeavored to\\nemphasize that whether to allow supplemental pleading\\ndepends on equitable considerations of fairness and notice\\nthat district courts must take into account.\\n\\n\\n\\n\\n 34\\n\\fa plaintiff to cure a diversity defect when the case had been\\nlitigated for years. See GBForefront, L.P., v. Forefront\\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\\namend the complaint … to cure defective jurisdictional\\nallegations”).\\n\\n Other circuits have held the same. See Woods v. Ind.\\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\\nCir. 1993) (“Consistent with its history and purpose, Rule\\n15(c) has uniformly been applied to relate back [filings] that\\ncure defective statements of jurisdiction ….”); Boyce v.\\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\\namendment alleging that no previous appeal had been taken\\nto the United States Court of Customs and Patent Appeals to\\ncure jurisdictional defect in complaint after statute of\\nlimitations had expired). That conclusion is also consistent\\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\\nof jurisdiction [to] be amended, upon terms, in the trial or\\nappellate courts.” Id.\\n\\n Courts have similarly permitted cure of actual defects\\nin the court’s jurisdiction, going beyond just jurisdictional\\nallegations. For instance, although not in a case involving a\\nlater complaint, the Supreme Court has said that a court can\\ndrop a dispensable non-diverse party to cure a defect in\\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\\n2001) (stating that, “where it is appropriate to relate back an\\namendment to a pleading under Rule 15, jurisdiction is\\nassessed as if the amendment had taken place at the time the\\ncomplaint was first filed[,]” and thus replacing a non-diverse\\n\\n\\n\\n\\n 35\\n\\fplaintiff with a diverse plaintiff cured any jurisdiction\\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\\ncomplaint could be cured by a later complaint that pled an\\nassignment occurring after the original complaint was filed).\\n\\n Nonetheless, “[a]mendments that go beyond the mere\\ncorrection or factual modification of the original pleading and\\nsignificantly alter the claim or defense alleged in that\\npleading are treated more cautiously by the courts in applying\\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\\nSecond Circuit, for instance, only sometimes allows\\njurisdictional defects to be cured “when the underlying facts,\\nif properly pled, would have supported jurisdiction at the time\\nthe action commenced.” Correspondent Servs. Corp. v. First\\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\\ncure the original complaint since they were defects “not [in\\nthe] allegations of existing underlying jurisdictional facts but\\nrather [in] the prerequisite jurisdictional facts themselves”).\\nWilmington argues such hesitance is appropriate here because\\nallowing relation back to cure the jurisdictional problem with\\nT Mobile’s initial complaint “would allow two wrongs under\\nSection 332 [(filing early and filing late)] to make a right.”\\n(Answering Br. at 2.)\\n\\n We again disagree with the City. It is quite true that\\nT Mobile has made procedural matters more difficult than\\nthey should be in this case. But denying relation-back to cure\\nthe defect in this instance would not comport with Rule 15’s\\naim to encourage resolution of disputes on the merits\\nwhenever possible. The ripeness requirement exists so that\\n\\n\\n\\n\\n 36\\n\\fcourts avoid issuing essentially advisory opinions. See\\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\\nCourts and the Federal System 224 (5th ed. 2003) (noting that\\nthe ripeness doctrine allows courts to avoid a “dispute … too\\n‘ill-defined’ to be appropriate for judicial resolution until\\nfurther developments … more sharply framed the issues for\\ndecision.”). That concern ceased to exist here once the\\nsupplemental pleading was in place. At that point, the dispute\\nhad matured and become capable of judicial review,\\ndemonstrating that, “actions taken after the filing of the initial\\ncomplaint can be used to establish subject matter\\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\\nF.3d 1329, 1337 (Fed. Cir. 2008).\\n\\n If a supplemental complaint cannot cure an unripe\\ncomplaint, an endless feedback loop would be created\\nwhereby the ripeness problem could never be overcome, even\\nthough, as here, the dispute later became obviously ripe. Our\\nsister circuits have recognized that problem and concluded\\nthat a supplemental complaint is the solution. 22 In Wilson v.\\nWestinghouse Electric Corp., the Eighth Circuit determined\\nthat prohibiting an amended (or supplemental) complaint\\nfrom alleging facts that occurred after the date the initial\\n\\n 22\\n In our Circuit, a thoughtful district court decision\\nhad long ago reached that conclusion. It held that an\\nuntimely supplement adding facts occurring after the initial\\nfiling that showed exhaustion of administrative remedies\\ncould relate back to the initial premature complaint and allow\\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\\n521, 526-27 (E.D. Pa. 1976).\\n\\n\\n\\n\\n 37\\n\\fcomplaint was filed would turn a premature complaint into an\\n“irretrievable mistake that bars jurisdiction” and would be\\n“precisely the kind of procedural mousetrap that the Federal\\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\\nCir. 1988). The court held that, “[e]ven when the District\\nCourt lacks jurisdiction over a claim at the time of its original\\nfiling, a supplemental complaint may cure the defect by\\nalleging the subsequent fact which eliminates the\\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\\n75). While Wilson addressed a circumstance in which the\\nsupplemental complaint was timely filed, the proposition still\\napplies in a case like ours because, if a party was limited to\\nrefiling within an applicable time limit, there would be little\\nneed to make provision for supplementation of a complaint,\\nas a new complaint could be filed. 23\\n\\n 23\\n We note that sparing the cost of refiling and\\nproviding convenience to the Court would remain legitimate\\nreasons for allowing supplemental complaints. But the\\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\\n1504 (“The purpose of subdivision (d) is to promote as\\ncomplete an adjudication of the dispute between the parties as\\nis possible. … A supplemental pleading may be employed\\nfor a variety of purposes.”). Wilmington contends that\\nWilson is inapposite since it involved a timely supplemental\\ncomplaint. Thus, concern about a perpetual loop outcome\\nwas not proper because the plaintiff could have simply refiled\\nhis complaint. But we agree that “a plaintiff need not\\ncommence a new action when after-occurring events\\ndemonstrate that it has a right to relief even if the original\\ncomplaint was insufficient. A plaintiff may also be allowed\\nto supplement the complaint even if jurisdiction … would not\\nhave been proper if the claim had been asserted in an\\n\\n\\n\\n\\n 38\\n\\f The Ninth Circuit, in Security Insurance Co. of New\\nHaven v. United States ex rel. Haydis, also relied on that logic\\nto find that relation back could cure an unripe complaint filed\\nbefore a statutory filing window opened. 338 F.2d 444, 448-\\n49 (9th Cir. 1964). In a fact scenario with striking similarities\\nto the present appeal, the plaintiff had filed its claim before a\\nstatutory waiting period was over and then did not file an\\namended complaint until after the statute of limitations period\\nhad run. Id. at 445-46. The appeals court held that the\\ndistrict court was “not required to apply the doctrine of\\nrelation back so literally as to carry it to a time [before it was\\nripe] so as to prevent the maintenance of the action in the first\\nplace.” Id. at 449.\\n\\n The Supreme Court has favorably cited Security\\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\\na precondition of filing a complaint by first filing an\\napplication with a particular agency. 426 U.S. at 72, 75. The\\nCourt noted that a supplemental complaint, alleging that the\\napplication had since been filed, would have cured the\\njurisdictional defect. Id. at 75. In saying so, the Court relied\\n\\n\\n\\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\\n2018) (citation omitted). If supplemental complaints could\\nnot cure ripeness, “then all supplemental pleadings of this\\nnature would be defeated for lack of jurisdiction – [the]\\n‘procedural mousetrap’ would render all supplemental\\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\\nomitted).\\n\\n\\n\\n\\n 39\\n\\fon Security Insurance. Id. at 75 n.8 (citing Security\\nInsurance, 338 F.2d at 447-49). 24\\n\\n Yet Wilmington asserts that ripeness can never be\\ncured by a later complaint. It advances four cases for that\\nproposition, but none are helpful. First, the City cites\\nDelaware Riverkeeper Network v. Secretary Pennsylvania\\nDepartment of Environmental Protection, (Riverkeeper I),\\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\\n“even though the underlying claim became ripe for review\\nduring the pendency of the case, the ripening of the claim did\\nnot cure deficient pleadings.” (App. at 8.) In that case,\\nhowever, no attempt to file a later complaint alleging ripeness\\nwas made. Riverkeeper I, 833 F.3d at 369-70.\\n\\n Likewise, in another two of the four cases that\\nWilmington cites, there was no effort made to amend or\\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\\naction at the time of filing of petition may only be reviewed\\nupon the filing of another petition); W. Union Tel. Co., 773\\nF.2d at 377-78 (concluding that the court lacked jurisdiction\\nover challenges filed before the action became final).\\nTherefore, neither case determined whether relation back of a\\nlater-filed complaint could cure a ripeness problem in the\\ninitial complaint.\\n\\n 24\\n Wilmington contends that Mathews is inapposite\\nsince the statute of limitations was waived. That argument\\nhas no traction since, if it were a jurisdictional bar, it could\\nnot be waived.\\n\\n\\n\\n\\n 40\\n\\f The City fares no better relying on Council Tree\\nCommunications v. FCC, in which we stated that “[a] petition\\nto review a non-final agency order is incurably premature.”\\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\\nwas the complaint ripe, and the petitioner still had a petition\\nfor reconsideration pending before the relevant agency on the\\ndate the case was decided. Id. at 287. Furthermore, Council\\nTree explicitly acknowledged that a supplemental complaint\\ncan cure an unripe complaint when there is jurisdiction over\\nthat supplemental pleading. See id. at 291 (“[W]e note that\\n‘nothing prevented [the petitioners] from supplementing their\\npremature petition with a later protective petition.’” (second\\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\\n\\n Wilmington also makes three policy arguments in\\nsupport of its position that an untimely supplemental\\ncomplaint should not be able to cure an unripe complaint.\\nFirst, it contends that allowing suits to be filed before an\\naction is ripe would “extend[] federal court jurisdiction over\\nlocal government actions before those actions are final[.]”\\n(Answering Br. at 9.) Second, such filings would waste\\njudicial resources and, in this case, cost taxpayers money, by\\nforcing courts to deal with a higher volume of unripe\\ncomplaints. Third, the purpose of § 332 is to preserve local\\nzoning authority, which would be undermined by allowing\\nplaintiffs to file suit early and thereby places undue pressure\\non zoning commissions.\\n\\n Those contentions, however, are unpersuasive. First, a\\ncourt would remain without jurisdiction if the claim had not\\nripened by the time of the supplemental complaint. Second, it\\n\\n\\n\\n\\n 41\\n\\fseems that Wilmington overstates the impact that a decision\\nallowing an unripe complaint to be cured would have, since\\nour holding today makes it clear that an action is not final\\nuntil a written decision has been issued. Clarifying when a\\ndetermination is ripe for review should end any incentive for\\naggrieved parties to file early to ensure they have not filed too\\nlate.\\n\\n Perhaps more importantly, however, courts can police\\nany potential abuse on a case-by-case basis using Rule 15(d)\\nand the Rule 15(c) test for relation back. It is understood that\\n“relation back of a supplemental pleading should not result in\\nproviding unfair procedural advantages to a plaintiff[,] so …\\nrelation back may not be for all purposes.” Wright et al.,\\nsupra, § 1508. But here no unfair advantage has resulted, and\\ndefendants in general will be adequately protected by a\\ndistrict court’s Rule 15(d) analysis, which will determine if a\\nsupplemental complaint should be allowed at all. For\\ninstance, if a locality’s action is not yet a final action at the\\ntime a Rule 15(d) motion is filed, the motion can easily be\\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\\n530 (9th Cir. 1986) (supplemental pleading denied when it\\nstill failed to cure defective original pleading).\\n\\n When all is said and done here, we conclude that, to\\neffectuate the liberal purpose of Rule 15 and to avoid the\\nendless feedback loop that the City’s legal argument would\\ncreate, Rule 15 allows an untimely supplemental complaint to\\nrelate back and cure an unripe initial complaint.\\n\\n\\n\\n\\n 42\\n\\fIII. CONCLUSION\\n\\n For the foregoing reasons, we will reverse the District\\nCourt’s grant of the City’s motion for summary judgment,\\nvacate the District Court’s denial of T Mobile’s motion for\\nsummary judgment, and remand to the District Court for\\nfurther proceedings consistent with this opinion.25\\n\\n\\n\\n\\n 25\\n We will vacate the District Court’s denial of\\nT Mobile’s motion for summary judgment because it was\\nsolely based on a finding that T Mobile’s suit was not timely\\nbrought.\\n\\n\\n\\n\\n 43\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4357819/\", \"author_raw\": \"JORDAN, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"JORDAN"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"VANASKIE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4580566/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-10\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 18-1831\n _____________\n\n T MOBILE NORTHEAST LLC,\n Appellant\n\n v.\n\n CITY OF WILMINGTON, DELAWARE;\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\n _____________\n\n On Appeal from the United States District Court\n for the District of Delaware\n (D.C. No. 1-16-cv-01108)\n District Judge: Hon. Eduardo C. Robreno\n _______________\n\n Argued\n September 12, 2018\n\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\n (Filed: January 10, 2019)\n\n\n *\n The Honorable Thomas I. Vanaskie retired from the\nCourt on January 1, 2019 after the argument and conference\nin this case, but before the filing of the opinion. This opinion\nis filed by a quorum of the panel pursuant to 28 U.S.C.\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\n\f _______________\n\nThomas S. Thompson [ARGUED]\nDavis Wright Tremaine\n1919 Pennsylvania Avenue, NW\nSte. 800\nWashington, DC 20006\n\nCounsel for Appellant\n\nJoseph Van Eaton [ARGUED]\nBest Best & Krieger\n2000 Pennsylvania Avenue\nSte. 5300\nWashington, DC 20006\n\nCounsel for Appellees\n _______________\n\n OPINION OF THE COURT\n _______________\n\n\nJORDAN, Circuit Judge.\n\n No one likes bad cell phone reception or slow\nstreaming data on their smartphone, but that does not mean\nanyone wants a cellular antenna in their neighborhood, which\nis why there are zoning battles like the one central to this\ncase.\n\n T Mobile Northeast LLC (“T Mobile”), a wireless\ntelecommunications service provider, applied to the Zoning\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\nDelaware for permission to erect an antenna in the City. The\n\n\n\n\n 2\n\fZBA said no. So, relying on a provision of federal law that\nallows a disappointed wireless service provider like T Mobile\nto seek review in a district court “within 30 days after” a\nzoning authority’s “final action,” 47 U.S.C.\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\nproceeded for over a year, however, the District Court\nconcluded that it lacked jurisdiction. The Court reasoned that\nbecause T Mobile filed its complaint before the ZBA released\na written decision confirming an earlier oral rejection of the\nzoning application, the claim was not ripe. And, since\nT Mobile did not supplement its complaint to include the\nZBA’s written decision within 30 days of its issuance, the\nCourt also concluded that relation back could not remedy the\nripeness defect. The District Court thus granted the City’s\nmotion for summary judgment.\n\n T Mobile now appeals. It argues that its complaint\nwas not premature or, in the alternative, that its supplemental\npleading cured any ripeness problem. We agree that the grant\nof summary judgment was improper and, for the reasons that\nfollow, will remand the case for further proceedings\nconsistent with this opinion.\n\nI. BACKGROUND\n\n A. Statutory Framework\n\n This dispute is governed by the Telecommunications\nAct of 1996 (“TCA”), which amended the Federal\nCommunications Act of 1934 and includes provisions on\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\n“encourage the rapid deployment of new telecommunications\n\n\n\n\n 3\n\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\nfor expedited review in federal court of a denial of permission\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\nSuch review is a “benefit Congress expressly intended to\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\nthe TCA also serves to preserve local zoning authority. 47\nU.S.C. § 332(c)(7).\n\n At issue here are three key sections of the statute.\nFirst, the TCA mandates that “[a] State or local government\nor instrumentality thereof shall act on any request for\nauthorization to place, construct, or modify personal wireless\nservice facilities within a reasonable period of time after the\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\nCommunications Commission (“FCC”) has interpreted\n“reasonable period of time” in that statutory provision to\nmean that zoning authorities have a “shot clock” 1 and must\nact within 90 days of an application to attach an antenna to an\nexisting structure or 150 days of an application where a new\nsupport structure is to be built. Petition for Declaratory\n\n 1\n “Shot clock” is a term borrowed from basketball. In\nthat game, it signifies a time limit to make a shot attempt,\nbeginning once a team has possession of the basketball. See,\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\nsecond-clock/. If the team has not made a shot attempt, i.e.,\nacted, within the prescribed time limit, it forfeits possession\nof the ball. Id. Here, the permitting authority has exclusive\njurisdiction over an application until it fails to act within a\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\n332(c)(7)(B)(ii).\n\n\n\n\n 4\n\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\ncall the “review provision” of the statute, the TCA grants\n“[a]ny person adversely affected by any final action or failure\nto act by a State or local government or any instrumentality\nthereof” a right to have that locality’s decision reviewed by\n“commenc[ing] an action” “within 30 days” in district court.\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\nprovision,” the TCA states that “[a]ny decision by a State or\nlocal government or instrumentality thereof to deny a request\nto place, construct, or modify personal wireless service\nfacilities shall be in writing and supported by substantial\nevidence contained in a written record.” Id.\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\nand “decision … to deny” are not defined in the TCA.\nFurthermore, the statute does not make clear whether “final\naction” should be read to encompass all decisions to deny,\nincluding oral ones, nor does it address whether there is a\ndifference between an “act” for purposes of the shot clock\nand a “final action” for purposes of judicial review.\n\n B. Factual Background\n\n T Mobile is a telecommunications service provider. It\nsays that it needs to erect a cellular antenna to fill “a\nsignificant gap” in coverage for its customers in Wilmington,\nDelaware, (Opening Br. at 3) presumably where there has\nbeen an increase in phone calls and data usage. T Mobile\nwants to put its antenna on top of a senior living high-rise in\nthe City, but, because a special exception to local zoning laws\nis needed, it first had to go to the ZBA. It filed an initial\napplication and then, on August 25, 2016, a final amended\napplication, seeking the exception.\n\n\n\n\n 5\n\f The ZBA held a hearing on October 26, 2016, to\nconsider T Mobile’s request, some two months after the final\namended application was submitted. During the hearing,\nT Mobile presented evidence of the need for the antenna and\ndiscussed proposals to address aesthetic concerns. The ZBA\nalso received objections from members of the local\ncommunity, some of whom were outspoken in worrying\nabout the effects of radio frequency emissions. At the end of\nthe hearing, the ZBA denied T Mobile’s application in a\nunanimous oral decision.\n\n The Board gave several reasons for the denial. One\nboard member said the ZBA should not encourage the use of\na senior living community rooftop as the base for an antenna\nbecause of the potential adverse effect on the properties in the\nneighborhood. Another board member said there was not\nenough proof of a need for additional coverage to support the\napplication. The Chairman said there was not enough\nevidence that T Mobile needed the antenna and that it did not\nappear to satisfy the zoning code in terms of placement and\nheight restrictions.\n\n The ZBA’s oral decision to deny the application was\nnot put in writing on October 26 or anytime soon thereafter.\nAccording to T Mobile, that fits a “pattern and practice of\n[the ZBA] not issuing a written decision of land use denials\nunless or until the City is sued.” (Opening Br. at 7.) Only\nafter T Mobile had filed its initial complaint in the District\nCourt, and after the City filed its answer, did the ZBA issue\nits written decision and explanation of its reasoning for\ndenying the application.\n\n\n\n\n 6\n\f T Mobile asserts that the denial of its application\nviolates the TCA. Under the statute, such a denial is invalid\nif it has the “effect of prohibiting the provision of personal\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\nthe basis of the environmental effects of radio frequency\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\nWilmington’s denial was improper on both of those grounds. 2\nBut those assertions go to the merits and are not actually\nbefore us on this appeal. At issue now is whether T Mobile’s\nclaim can be heard at all.\n\n C. Procedural History\n\n Evidently with its eye on the 30-day deadline in the\nTCA’s review provision, T Mobile filed a lawsuit in the\nUnited States District Court for the District of Delaware\nwithin 30 days of the ZBA’s oral decision, challenging that\ndenial. 3 In addition to its claims on the merits, T Mobile’s\ninitial complaint alleged that the City violated procedures\nmandated in the TCA, specifically those in the denial\nprovision, by failing to provide a written decision\n\n 2\n T Mobile also raised a Delaware state law claim.\nThat claim is not at issue here and does not impact\nT Mobile’s claims under federal law.\n 3\n For reasons discussed herein, the 30-day filing\ndeadline was not triggered by the oral decision. See infra pp.\n12-20. If it were, however, T Mobile’s complaint would have\nbeen timely. The oral decision was delivered at the\nOctober 26, 2016 hearing. Suit was filed on November 28,\n2016, but because the thirtieth day from October 26 fell on a\nweekend, the November 28 filing was within the 30-day\nwindow. Fed. R. Civ. P. 6(a)(1).\n\n\n\n\n 7\n\fcontemporaneous with its oral decision and by not supporting\nthe denial with substantial evidence.\n\n The parties entered into a stipulation asking the\nDistrict Court for an expedited case schedule, as provided for\nin the review provision of the TCA. 47 U.S.C.\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\nthen answered the complaint, asserting a number of\naffirmative defenses, including that the complaint was not\nripe because the ZBA had not yet issued a final written\ndecision. Nevertheless, the City did not, at that time, file a\nmotion to dismiss for failure to state a claim or for lack of\njurisdiction. Two days after the City filed its answer, the\nZBA issued a written decision on T Mobile’s application.\nThe parties pressed forward with the suit and prepared a\ndiscovery plan, which specifically mentioned the written\ndecision. T Mobile filed a motion for summary judgment,\nwhich the City met with a cross-motion for summary\njudgment. The City’s motion was styled in the alternative as\na motion to dismiss the complaint as unripe because it was\nfiled prematurely, i.e., before the written decision had been\nissued.\n\n Not until December 21, 2017, nearly a year after the\nZBA issued its written denial, did T Mobile file a motion\nseeking leave to amend or supplement the initial complaint to\nnote the issuance of that written decision. 4 The District Court\n\n 4\n When “[a] claim or defense set out in a pleading [is]\naffected by events that occur after the pleading is filed ….\nRule 15(d) allows a court,” to permit a supplemental\npleading. 3 James Wm. Moore et al., Moore’s Federal\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\n\n\n\n\n 8\n\fgranted the motion to supplement. Wilmington then\nresponded by moving to dismiss the supplemental complaint\nas untimely because it failed to cure the defect.\n\n Ultimately, the District Court granted Wilmington’s\ncross-motion for summary judgment for want of jurisdiction,\nwithout ruling on the City’s motion to dismiss. The Court\nfirst concluded that the initial complaint was irreparably\nunripe because both the TCA and Delaware law require the\nZBA to issue a written decision before the agency’s action\ncould be considered final, and T Mobile had thus filed its\ninitial complaint too soon. Second, the Court said that the\nsupplemental complaint could not fix the ripeness problem\nbecause it was filed past the 30-day window for seeking\nreview of the ZBA’s final action. Because the Court reached\n\n\n\nunder Rule 15(d) differ from amended pleadings made under\nRule 15(a). First, amended pleadings “relate to matters that\noccurred prior to the filing of the original pleading and\nentirely replace the earlier pleading; [supplemental pleadings]\ndeal with events subsequent to the pleading to be altered and\nrepresent additions to or continuations of the earlier\npleadings.” 6A Charles Alan Wright et al., Federal Practice\n& Procedure § 1504 (3d ed. 2018). Second “certain\namendments may be made as a matter of course within stated\ntime periods, whereas all supplemental pleadings require\nleave of court under Rule 15(d).” Id. “Parties and courts\noccasionally confuse supplemental pleadings with amended\npleadings and mislabeling is common.” Id. Here, T Mobile’s\ncomplaint was filed as an amended complaint but it is\nproperly categorized as a supplemental complaint, and we\nwill refer to it as such herein.\n\n\n\n\n 9\n\fthat determination, it found it unnecessary to conclude\nwhether T Mobile’s supplemental complaint was entitled to\nthe benefit of the relation-back doctrine under Rule 15(c).\n\n This appeal followed.\nII. DISCUSSION 5\n\n T Mobile challenges the District Court’s grant of\nsummary judgment in favor of Wilmington, contending that\nthere is jurisdiction to hear its case. It advances two\nalternative grounds for reversal: that its complaint was ripe\nbecause the ZBA’s oral decision qualifies as a “final action”\nunder the review provision of the TCA, and, in the\nalternative, that the supplemental complaint relates back to\nand cures any ripeness problem with its initial complaint.\nThose arguments in turn raise three questions for determining\nwhether the District Court’s jurisdictional ruling was proper.\nFirst, whether the oral decision of the ZBA was a final action.\nSecond, whether the timing requirement in the TCA’s review\nprovision is jurisdictional. And third, whether an untimely\n\n 5\n The District Court had jurisdiction to consider its\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\ndetermined the complaint contained incurable jurisdictional\ndefects and declined to reach the merits. We have jurisdiction\npursuant to 28 U.S.C. § 1291. We review all the issues\npresented in this case de novo, as they involve only legal\nissues, i.e., interpretation of a federal statute and of a Federal\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\n123, 125 (3d Cir. 2007).\n\n\n\n\n 10\n\fsupplemental complaint can relate back and cure an unripe\ninitial complaint. Although we disagree with T Mobile that\nan oral decision of the ZBA qualifies as a “final action,” we\nagree that jurisdiction was proper in the District Court\nbecause the timing requirement in the TCA’s review\nprovision is non-jurisdictional, and T Mobile’s supplemental\ncomplaint therefore relates back and cures the ripeness\nproblem with the initial complaint. The District Court should\nthus have reached the merits of the dispute.\n\n A. The Oral Decision Was Not a Final Action of\n the ZBA.\n\n The ripeness of T Mobile’s initial complaint depends\nupon whether the ZBA’s oral decision was a “final action”\nwithin the meaning of the TCA. Consideration of that issue\nuncovers another: whether the TCA requires a locality to\nrender its decision in writing for that decision to qualify as a\nfinal action. The District Court held that, under both federal\nand Delaware law, only a written decision can serve as a final\naction of the ZBA. Because traditional hallmarks of agency\naction and the statutory text and structure of the TCA favor\nthat approach, we agree that only a written decision can serve\nas a locality’s final action when denying an application.\n\n In Delaware Riverkeeper Network v. Secretary\nPennsylvania Department of Environmental Protection,\n(Riverkeeper III), we determined that, when reviewing\nfinality under the Natural Gas Act, “[a]lthough the\ndecisionmaking process we are reviewing is defined by [state]\nlaw, we nevertheless apply a federal finality standard to\ndetermine whether Congress has made the results of that\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\n\n\n\n\n 11\n\fsame reasoning holds true here, since, for the TCA just as for\nthe Natural Gas Act, “the finality requirement itself, along\nwith the presumption that Congress intended us to apply it,\nare creatures of federal, not state, law.” Id. at 71.\n\n Under federal law, not all agency determinations are\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\n1992). Final agency actions bear certain “traditional\nhallmarks” that demonstrate “[t]here is nothing left for the\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\nCir. 2017). We noted those hallmarks on an earlier occasion\nwhen we said that, “[f]inal agency action must mark the\nconsummation of the agency’s decisionmaking process, must\nnot be of a merely tentative or interlocutory nature, and must\nbe one by which rights or obligations have been determined,\nor from which legal consequences will flow.” Riverkeeper\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\nomitted).\n\n To decide what the TCA requires for finality, we\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\nwith the text[.]”) Here, the statutory text makes it clear that,\nif a denial is not in writing, there is something left for the\nagency to do. The denial provision of the TCA states that\n“[a]ny decision … to deny … shall be in writing and\nsupported by substantial evidence contained in a written\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\nwhy the same should not be true for actions besides denial, 6\n\n 6\n For instance, it is not apparent why community\nmembers aggrieved by a decision to grant some permit to a\n\n\n\n\n 12\n\fbut we need not decide that today. It is enough to say that, in\nthose zoning decisions governed by the TCA, a locality’s oral\ndeclaration of a denial is “of a merely tentative or\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\n(citation omitted) (speaking in reference to the Natural Gas\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\ncould have approved the minutes, revised them, or rejected\nthem, and thus until the board approved the minutes its\ndecision was not final).\n\n Moreover, an oral decision is not an action from which\nlegal consequences flow. Federal law governs finality, but\nDelaware’s procedures still matter, and the Delaware\nSuperior Court has concluded that a written document must\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\nZoning Bd. of Adjustment for the City of Wilmington, No.\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\nTitle 22 of the Delaware Code, the section that governs\nappeals from ZBA proceedings, requires a written document\nto be filed because the statute “provides that [s]uch petition\nshall be presented to the Court within 30 days after the filing\nof the decision in the office of the board.” Id. (internal\nquotation marks omitted). That reasoning is persuasive and\n\n\n\n\nwireless provider, assuming those members have standing to\nsue, would not be equally entitled to a zoning authority’s\nwritten decision before the time limit in the TCA’s review\nprovision is triggered.\n\n\n\n\n 13\n\fshows that, under Delaware law, the ZBA’s oral decision is\nwithout legal consequences. 7\n\n There are distinct policy advantages to forestalling\njudicial scrutiny until a written denial is issued. Requiring a\nwritten decision focuses review on a particular, documented\nstatement of reasons. See USCOC of Greater Mo. v. City of\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\nwritten decision is the central object of our scrutiny under the\nTCA, the process of judicial review is best served by delaying\nthe ripening of a TCA claim until the local authority has\nissued its written decision.”). It also prevents ambiguity with\nrespect to when a claim can be brought. As the District Court\nhere stated, to hold otherwise “would promote a pernicious\nambiguity as to when that short period of time begins to run.”\n(App. at 7.) And it promotes uniformity of federal procedures\nby clarifying when, across all jurisdictions, an action becomes\nfinal.\n\n 7\n T Mobile cites to a different opinion, Schmalhofer v.\nBoard of Adjustment of Newark, to advance a contrary\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\nfootnote that “a written decision is not required or expressly\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\nstretching the Schmalhofer court’s language too far. In that\ncase, the City of Newark had issued a verbatim transcript of\nthe hearing, so there was a writing. Id. at *3; see infra note\n11. There is no indication of any written decision in this case,\nprior to December 22, 2016, when the City issued the written\ndenial bearing the date of December 21, 2016.\n\n\n\n\n 14\n\f The Supreme Court’s decision in T-Mobile South, LLC\nv. City of Roswell, Georgia, also adds support to the\nconclusion that only a written denial can constitute final\naction, triggering a party’s right to review. 135 S. Ct. 808\n(2015). In that case, the Court held that the “substantial\nevidence” supporting a locality’s decision to deny must be\nreleased contemporaneously with the written decision to\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\nlocal zoning authority’s final action, which triggers judicial\nreview, and its decision to deny, which must be in writing.\nIndeed, the Supreme Court said in no uncertain terms that,\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\nthe written notice of denial[.]” Id. at 817 n.4. The Court\nlinked the locality’s decision to deny to the 30-day time limit\nto file a complaint after a final action has been taken. Id. at\n817 (“Only once the denial is issued would the 30-day\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\ndays after the City denied petitioner’s application—petitioner\nfiled suit in Federal District Court.”).\n\n The Court went on to discuss timing, saying, “the\nlocality must provide or make available its written reasons at\nessentially the same time as it communicates its denial[,]”\n“[b]ecause an entity may not be able to make a considered\n\n 8\n The Court was interpreting the denial provision,\nwhich, as we noted earlier, states that, “[a]ny decision by a\nState or local government or instrumentality thereof to deny a\nrequest to place, construct, or modify personal wireless\nservice facilities shall be in writing and supported by\nsubstantial evidence contained in a written record.” 47\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\n\n\n\n\n 15\n\fdecision whether to seek judicial review without knowing the\nreasons for the denial of its application, and because a court\ncannot review the denial without knowing the locality’s\nreasons[.]” Id. at 816. The majority opinion was critical of\nthe dissent for attempting to “fashion a world in which a\nlocality can wait until a lawsuit is commenced and a court\norders it to state its reasons[,] … [leaving the challenging\nentity to] risk being sandbagged by the written reasons that\nthe locality subsequently provides in litigation after the\nchallenging entity has shown its cards.” Id. at 816 n.3. That\ncritique is premised on the written decision being the final\naction that starts the 30-day time limit for commencing suit. 9\n\n The Supreme Court anticipated that localities might\nneed to delay issuing a written denial if they are not ready to\nrelease their substantial reasons. See id. at 817 (noting that\n\n 9\n T Mobile asserts that Wilmington has a “pattern and\npractice of not issuing a written decision of land use denials\nunless or until the City is sued.” (Opening Br. at 7.) But if\nonly a written denial is a final action, the shot clock requires\nthe City to issue that written decision within a given time\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\nasserts that when a locality has a pattern and practice of not\nreleasing written decisions, that practice delays the overall\nprocess, since a cellular service provider would be required to\ninitiate two causes of action: one to compel a written decision\nand another to challenge that written decision. That,\nhowever, is precisely what Congress envisioned by providing\nseparate remedies for a failure to “act” within a reasonable\ntime period and for an improper denial. 47 U.S.C.\n§ 332(c)(7)(B)(iii).\n\n\n\n\n 16\n\f“[i]f a locality is not in a position to provide its reasons\npromptly, the locality can delay the issuance of its denial\nwithin this 90– or 150–day window, and instead release it\nalong with its reasons once those reasons are ready to be\nprovided.”). That further counsels against treating an oral\ndetermination as a final action since, if an oral determination\nis deemed a final action, localities will be unable to take\nadvantage of the permissible delay afforded by the shot clock\nfor publishing their reasoning.\n\n Two of our sister courts of appeals agree that only a\nwritten decision can constitute final action. The Eighth\nCircuit in USCOC of Greater Missouri v. City of Ferguson\nstated that “[t]he plain language of the TCA indicates that\n‘final action’ does not occur until issuance of a written\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\nPreferred Sites LLC v. Troup County likewise held a\ncomplaint to be timely when it was filed within 30 days of a\nwritten decision, even though it was filed more than 30 days\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\n\n 10\n T Mobile attempts to distinguish Preferred Sites by\nstating that, unlike here, the case did “not address a city that\ndoes not issue a written decision close in time to when it\nmakes the decision to deny.” (Opening Br. at 37.) But that\nargument is irrelevant to whether the statutory text requires a\nwriting for an agency decision to be final. T Mobile also cites\nto Preferred Sites to argue that it should not matter if there is\na writing requirement since the oral denial could be seen as\nakin to a court announcing a decision. It explains that “when\nan appeal is filed after the court announces a decision, but\nbefore the entry of the judgment, it is treated as being filed on\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\n\n\n\n\n 17\n\f2002) (concluding that, “[b]ased on the plain language of the\nstatute,” that “a ‘final action’ occurs when the state or local\nauthority issues its written decision. The statute expressly\nmandates a … decision … committed to writing. Until the\nstate or local authority issues its written notification, its task\nunder the statute is not complete.”). No circuit has held\notherwise.\n\n Persuasive authority thus indicates that any action, and\ncertainly a denial, must be in writing to be final. But, there is\nanother possible interpretation of the statutory text. The\nwords “shall be in writing” could be read not as a condition of\nfinality, but instead as a simple directive to state and local\ngovernments to place their final action in writing. “The TCA\nprovides no express answer to … when a local government’s\npermitting decision becomes a ‘final action,’ which starts the\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\nstatute only states that denials must be in writing. 47 U.S.C.\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\nsame way. Id. And, Congress used the words “decision to\ndeny” in one statutory subsection and “final action” in\nanother, which could evince an intent to give those terms\ndifferent meanings. As the Supreme Court has “recognized\n… Congress’s use of certain language in one part of the\nstatute and different language in another can indicate that\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\n\n\n\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\nPreferred Sites, but it was only contained in a footnote. No\nother court has followed that line of reasoning, and we\ndecline to follow it here.\n\n\n\n\n 18\n\fmarks omitted). Thus, it could be argued, if Congress wanted\nto mandate a writing for zoning denials to constitute final\naction, it could have been more explicit, providing, for\ninstance, that a “decision must be in writing to qualify as a\nfinal action.”\n\n But, of course, one can almost always fault legislative\ndrafting, like other kinds of writing, after the fact. That\nsomething might have been said even more clearly does not\nmean it is not clear enough. So, “[r]ather than expecting (let\nalone demanding) perfection in drafting,” we can “construe[]\nstatutes to have a particular meaning even as we\nacknowledge[] that Congress could have expressed itself\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\n(2016).\n\n The text and structure of the statute, Delaware\nprocedures, Supreme Court reasoning, our sister circuits’\ndecisions, and policy arguments all support the conclusion\nthat a writing is in fact a requirement for a denial to be final. 11\nIn light of that conclusion, the ZBA’s oral determination on\n\n 11\n What constitutes a “writing” has some flexibility,\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\nminutes by written resolution was a final action that bound\nthe parties). In City of Roswell, for example, the Supreme\nCourt indicated that minutes of an oral meeting could be\nsufficient. 135 S. Ct. at 816. Here, however, there is no\nevidence that the ZBA’s oral determination was noted in the\nminutes of the October 26th meeting and issued by the City as\nits formal decision.\n\n\n\n\n 19\n\fOctober 26, 2016, was not a final action ripe for judicial\nreview. Therefore, as that oral determination was not reduced\nto writing until December 22, 2016, preceding the filing of\nT Mobile’s initial complaint, that complaint’s cause of action\nwas not ripe.\n\n\n\n\n 20\n\f B. No Separate Time Limit Exists Following an\n Oral Determination.\n\n As an alternative to its argument that the ZBA’s oral\ndecision was a final action, T Mobile asks us to consider\nwhether a “local government must issue the ‘writing’ close in\ntime to the ‘decision … to deny’ to establish a ‘final action’\nthat will be subject to expedited review.” 12 (Opening Br. at\n41.) Essentially, T Mobile is asserting that the “shot clock”\ngoverning the time to act, which allows a wireless carrier to\nsue for a locality’s failure to act, is insufficient, and that a\nnew requirement, albeit not in the statute, should be imposed\non localities. Under T Mobile’s proposed rule, an oral\ndecision would have to be reduced to writing within a\nspecified time period. That argument assumes that an oral\ndetermination can serve to satisfy the requirement to “act” on\na request within the limits of the shot clock, and that, without\na separate judicially created time limit, there would be no\ndeadline for the locality to release its written decision to deny,\ndespite City of Rowell’s contemporaneous writing\nrequirement. Because we conclude that a denial must be in\nwriting to be a final action, the issuance of that writing is the\ngovernment “act” ruled by the shot clock. 13 Aside from the\n\n 12\n Wilmington argues that T Mobile has waived that\nissue, but we need not address that argument because we\nconclude that no such requirement exists.\n 13\n Again, the Supreme Court held in City of Roswell\nthat a locality’s decision to deny must be accompanied by\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\nlocality were able to withhold its reasoning for its decision,\nthose aggrieved by the locality’s actions would “be left to\n\n\n\n\n 21\n\ftime limits associated with the “shot clock,” there is no other\ndeadline governing the issuance of a written decision\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\nAny time limit we fabricated would be inappropriate.\n\n T Mobile argues that, without a requirement for\nlocalities to issue a written decision within a set amount of\ntime following an oral determination, wireless carriers are left\n“to wait until the FCC ‘shot clock’ expires – which could be\n90 or 150 days depending on the type of installation involved\n– and then [to] file an action alleging that the City has failed\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\ncontends that a “failure to act” lawsuit is insufficient because\nthe remedy for a successful suit is simply an order telling the\nCity to issue a written decision. In T Mobile’s view, forcing\nwireless providers to sue both to compel a written decision\nonce the shot clock is violated and again to contest the written\ndecision serves only to “create yet further delay.” (Opening\nBr. at 46.)\n\n\n\n\nguess at what the locality’s written reasons will be, write a\ncomplaint that contains those hypotheses, and risk being\nsandbagged by the written reasons that the locality\nsubsequently provides in litigation after the challenging entity\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\nfile suit, however, because the locality’s “final action” has not\nyet occurred, those concerns vanish. The ZBA’s decision\nhere, when reduced to writing, was both its decision to deny\nand its final action.\n\n\n\n\n 22\n\f Those concerns are overstated and, in any case,\nirrelevant. The shot clock begins to run once a wireless\nprovider files its application, so it is already ticking before\nany oral decision is made. If the locality fails to meet that\ndeadline by not issuing a written decision before the shot\nclock expires, the wireless provider can bring a claim for a\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\nMobile asserts that requiring a separate failure-to-act suit, in\naddition to a suit on the merits, undercuts the statutory\npurpose of expedited judicial review, particularly in cases\nwhere the locality has a “pattern and practice of not issuing a\nwritten decision of land use denials unless or until [it] is\nsued.” (Opening Br. at 7.) But the statute’s own remedies\ncannot possibly undercut its purpose. A separate failure-to-\nact claim is the very remedy Congress chose for shot clock\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\nT Mobile likes that policy choice, it is the one Congress\nmade, and we are not free to change it.\n\n C. The Timing Requirement Is Not\n Jurisdictional.\n\n Because we hold that a writing is required for a denial\nto constitute a final action, T Mobile’s initial complaint was\nnot ripe for review when filed. And, T Mobile’s\nsupplemental complaint was filed more than 30 days after the\nZBA issued its written decision and was therefore untimely\nunder the TCA’s review provision. 47 U.S.C.\n§ 332(c)(7)(B)(v). Thus, the District Court only had\njurisdiction if T Mobile’s supplemental complaint cured the\n\n 14\n It is not clear which time limit would have applied in\nthis case and whether it would have been violated.\n\n\n\n\n 23\n\fripeness flaw in its initial complaint by relating back to the\noriginal filing date. If the 30-day time limit in the TCA’s\nreview provision is nonjurisdictional, we can safely say that\nrelation back is possible and allows a supplemental complaint\nto cure a defective premature filing. 15 At the outset, then, we\nmust determine whether that 30-day time limit is\njurisdictional, being mindful both of the Supreme Court’s\ncounsel to exercise caution before holding timing\nrequirements to be jurisdictional and of its guidance regarding\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\n149, 153-54. Caution is indeed warranted because statutes of\nlimitations and other filing deadlines “ordinarily are not\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\nnonjurisdictional.”).\n\n\n 15\n We do not reach the issue of whether an unripe\ncomplaint can be cured by a supplemental or amended\npleading over which the Court lacked jurisdiction.\n 16\n The City claims that our decision in Nextel Partners\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\neffectively determinative. Not so. In Kingston Township,\nthen-Judge Alito noted that the District Court had held the\ntiming requirement in the TCA’s review provision was\njurisdictional. Id. at 695. But we did not address whether\nthat determination was correct, nor did we rely on it. Instead,\nwe concluded that there could be no “failure to act” towards\nan application that was not submitted. Id. at 692. Since our\ndecision in that case, the Supreme Court has clarified the\nprocess for determining if a time limit is jurisdictional.\nSebelius, 568 U.S. at 149.\n\n\n\n\n 24\n\f “[T]o ward off profligate use of the term ‘jurisdiction,’\n[the Supreme Court has] adopted a readily administrable\nbright line for determining whether to classify a statutory\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\n(quotation marks omitted). We are to ask “whether Congress\nhas clearly state[d] that the rule is jurisdictional; absent such a\nclear statement, we … should treat the restriction as\nnonjurisdictional in character.” Id. (alteration in original)\n(citation and quotation marks omitted); see also Musacchio v.\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\ntime bar as jurisdictional only if Congress has ‘clearly stated’\nthat it is.”). In deciding whether Congress has made such a\nclear statement, “we evaluate the ‘text, context, and relevant\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\n(2010)).\n\n Referencing that last test, Wilmington asserts that\n“[s]ection 332’s statutory grant of jurisdiction to district\ncourts, the text of the statute, the placement of the filing\nwindow in that same section, and the well-established\ntreatment of the filing window as jurisdictional, [all\ndemonstrate] that the filing window is jurisdictional.”\n(Answering Br. at 15.) We disagree. The differences\nbetween the review provision’s timing requirement and the\ntiming requirement we held to be jurisdictional in Kalb, and\nthe similarities between the review provision’s timing\nrequirements and those at issue in Sebelius and Musacchio,\nwhich the Supreme Court held to be nonjurisdictional,\nactually support treating the timing requirement in the TCA’s\nreview provision as nonjurisdictional.\n\n\n\n\n 25\n\f First, although Wilmington says that the text of the\nstatute indicates Congress’s desire to make the 30-day timing\nrequirement jurisdictional, the text does not use the term\n“jurisdictional” or any variation of it to describe the timing\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\nthe statute uses permissive rather than mandatory language.\nUnlike the timing requirement we held to be jurisdictional in\nKalb, which mandated that an action would be barred if not\nfiled in time, the TCA’s review provision states that an action\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\ncloser to that which the Supreme Court decided was\nnonjurisdictional in Sebelius. The statute at issue in that case,\nlike the review provision here, uses a permissive phrase –\n“may obtain a hearing” – before it states the timing\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\nSimilar to the timing requirement the Supreme Court held to\nbe nonjurisdictional in Musacchio, the review provision does\nnot confer jurisdiction, instead it allows an action to be\n\n 17\n T Mobile also points to Henderson v. Shinseki,\nwhich held a timing requirement to be nonjurisdictional even\nthough it used the mandatory “shall” before stating the timing\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\nin Shinseki, where the pertinent timing requirement could\nhave barred a veteran’s appeal, was partly based on “the\ncanon that provisions for benefits to members of the Armed\nServices are to be construed in the beneficiaries’ favor,” and\nso it is of less utility in deciding this dispute. Id. at 441\n(quotation marks and citations omitted).\n\n\n\n\n 26\n\fcommenced “in any court of competent jurisdiction.” See\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\nexpressly refer to subject-matter jurisdiction or speak in\njurisdictional terms.”). The text of the statute therefore favors\na holding that the timing requirement is nonjurisdictional.\n\n Wilmington next contends that the context of the\ntiming requirement favors the view that the requirement is\njurisdictional, because the Supreme Court has stated that it is\n“inextricably linked to … the language that creates the right\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\nsays the City, the “filing window created by [the review\nprovision] is jurisdictional [because] it is integral to the\nexpress purpose of the section, to this Court’s jurisdiction,\nand to the parties’ rights and obligations[.]” (Answering Br.\nat 8.)\n\n True enough, the review provision’s timing\nrequirement does appear in the same subsection as the\nstatutory text granting jurisdiction. 47 U.S.C.\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\nboth found the source of the timing requirement to be\nimportant in determining whether that requirement was\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\nthe same point the City now does, stating that a timing\nrequirement was jurisdictional because “the thirty-day appeal\nperiod here is embedded in the same statutory section that\ngrants jurisdiction to the court of appeals.” Id.\n\n\n\n\n 27\n\f But the location of the timing requirement within the\nstatutory structure, without more, does not clearly reveal\nCongressional intent. As noted by the Supreme Court in\nSebelius, a timing requirement should not be classified as\njurisdictional solely based on its placement in a jurisdictional\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\nwould otherwise classify as nonjurisdictional … does not\nbecome jurisdictional simply because it is placed in a section\nof a statute that also contains jurisdictional provisions.”\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\nMusacchio too, the Supreme Court held that a timing\nrequirement was nonjurisdictional despite its presence in the\njurisdiction-granting section of the statute at issue. 136 S. Ct.\nat 717. The Court emphasized that the statute did not directly\nspeak of the timing requirement as jurisdictional, despite its\nmandatory language. Id. That reasoning applies with at least\nequal force here, so the context of the review provision’s\ntiming requirement does not make the requirement\njurisdictional.\n\n Finally, Wilmington asserts that the timing\nrequirement is jurisdictional because of the historical\ntreatment of similar provisions. The City asserts that the\nphrase “within 30 days after” creates a “window,” during\nwhich a complaint must be filed, and not a “deadline.”\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\ndays after” creates a 60-day filing window while “no later\nthan 60 days after” creates a filing deadline).) But that\nargument misses the point because it goes to whether the rule\nbars suit between certain dates or only after a certain date, not\nto whether the timing requirement is jurisdictional. See, e.g.,\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\n\n\n\n\n 28\n\ffiling window is a jurisdictional bar for suits filed before the\nwindow opens). And just because a complaint may be unripe\nbefore a particular date does not mean that a deadline by\nwhich suit must be filed is jurisdictional. As we stated in\nKalb, the Supreme Court’s decisions in Bowles and Reed\nElsevier both looked to “the Court’s prior treatment of\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\nSebelius, the timing requirement, as here, used the phrase\n“within” and thus, under Wilmington’s logic, it would have\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\nSupreme Court held otherwise, id., and that is of high\nimportance.\n\n Because the text and context of this statute, and\nhistorical treatment of timing requirements in similar statutes,\ndo not reveal a clear intent from Congress to make the review\nprovision’s timing requirement jurisdictional, we conclude\nthat it is not. 18\n\n D. Rule 15 Allows a Supplemental Complaint\n Filed After a Claims Processing Deadline To\n Relate Back and Cure an Unripe Initial\n Complaint.\n\n We next consider whether an untimely supplemental\ncomplaint can, by relating back, cure an initial complaint that\nwas unripe. We believe it can, and because T Mobile’s\n\n 18\n That conclusion is further supported by the\nthoughtful concurrence in Athens Cellular, concluding after\nSebelius that the timing requirement “imposed by Congress in\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\nF.3d at 1113 (Kaplan, J. concurring).\n\n\n\n\n 29\n\fmotion to supplement its complaint was properly granted, that\nsupplemental complaint relates back and is ripe. The District\nCourt therefore had jurisdiction and should not have granted\nWilmington’s motion for summary judgment.\n\n At the outset, we note that the parties do not dispute,\nand we agree, that the District Court was within its discretion\nto grant T Mobile’s motion to supplement its complaint.\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\nmotion and reasonable notice, the [district] court may, on just\nterms, permit a [moving] party to serve a supplemental\npleading setting out any … event that happened after the date\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\nlimited to subsequent events related to the claim or defense\npresented in the original pleading.”). Here, the District Court\nrightly granted T Mobile’s motion to supplement. That\ndecision was just, since Wilmington had long since had notice\nof the event – the filing of the written denial – that occurred\nafter the initial pleading. After all, the City issued that denial,\nand the denial was featured in the parties’ discovery plan.\nThe issuance of it was also plainly related to T Mobile’s\ninitial complaint.\n\n That the initial complaint was premature is not a bar\nsince, under Rule 15(d), “[t]he court may permit\nsupplementation even though the original pleading is\ndefective in stating a claim for relief or defense.” Fed. R.\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\n“Rule 15(d) is intended to give the [district] court broad\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\nP. 15(d) advisory committee’s note to 1963 amendment. It is\n\n\n\n\n 30\n\ffurthermore “within the discretion of the court to allow a\nsupplemental pleading to be filed at any stage of the case[.]”\nMoore et al., supra, ¶ 15.30. The District Court here was thus\nwell within its discretion in granting T Mobile’s motion to\nsupplement the complaint.\n\n Rule 15 does not indicate whether or under what\ncircumstances a supplemental pleading can relate back to the\ndate of the original pleading to avoid the effect of a time\nlimit. 6A Charles Alan Wright et al., Federal Practice &\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\nwhich provides for the relation back of amended pleadings,\ndoes not specifically refer to supplemental pleadings. Fed. R.\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\nrelation back. Fed. R. Civ. P. 15(d). But case law and\nsecondary sources have long instructed that once a\nsupplemental complaint is granted, it is treated like an\namended complaint for purposes of relation back. 19 Thus,\neven though Rule 15(d) is in a separate statutory provision\nfrom Rule 15(c), a supplemental complaint can relate back.\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\nbetween an amended pleading and a supplemental pleading is\n\n 19\n Courts have generally held that a supplemental\ncomplaint is eligible for relation back, but rely on different\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\ncourts have held that for purposes of applying the relation-\nback doctrine a supplemental pleading may be treated as an\namended pleading under Rule 15(c); other courts have\napplied the relation-back principle directly to supplemental\npleadings even though Rule 15(d) does not mention it.”)\n(internal citations omitted).\n\n\n\n\n 31\n\foften disregarded for purposes of relation back under Rule\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\n680-81 (8th Cir. 1962) (finding supplemental pleading related\nback despite plaintiff suing in the wrong capacity and not\nachieving appropriate status for diversity jurisdiction until\nafter the limitations period had expired). That stands to\nreason, since, if a “defendant had notice of the subject matter\nof the dispute and was not prejudiced in preparing a defense\n…[,] the policy against stale claims becomes subsidiary to the\npolicy expressed throughout the rules in favor of allowing a\nparty to set forth all the grievances against another party in\none action and resolving them on their merits.” Wright et al.,\nsupra, § 1508.\n\n So a pleading filed according to Rule 15(d) can relate\nback, assuming it meets “the basic test for relation back\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\n¶ 15.30 (“A supplemental pleading may relate back to the\ndate of the original complaint if the requirements under Rule\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\npleading relates back if Rule 15(c)’s test is met). In fact, as\nthe District Court observed, if a supplemental complaint\nmeets the requirements for relation back then “[r]elation back\nis mandatory,” and not subject to additional equitable\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\n\n 20\n We note, however, that “[a] party opposing the\nintroduction of a supplemental pleading might wish to raise\nthe statute-of-limitations defense when the additional\npleading (1) alleges new matter that brings the earlier\npleading up to date; (2) cures a defect in the original pleading;\n\n\n\n\n 32\n\f Looking then to Rule 15(c), a complaint “relates back\nto the date of the original pleading when … [it] asserts a\nclaim or defense that arose out of the conduct, transaction, or\noccurrence set out -- or attempted to be set out -- in the\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\nDistrict Court here concluded that there was no need to\ndetermine whether T Mobile’s supplemental complaint\nrelated back, because, even if it did, “it fail[ed] to cure the\ndeficiencies of the initial complaint[.]” (App. at 8.) But\ngiven our view that the supplemental complaint could indeed\ncure the ripeness problem with the initial complaint, we must\ncontend with the relation-back question.\n\n To determine if relation back is proper, the only issue\nis whether there is a “common core of operative facts in the\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\nrely on the same core facts. The written denial was a\ncertification and restatement of the earlier oral denial.\n\n Thus, the only question remaining is whether a\ncomplaint that relates back can cure an untimely initial\ncomplaint, and the answer is yes. The clear preference\nembodied in Rule 15 is for merits-based decision making. Cf.\nMoore et al., supra, ¶ 15.30 (“The same principles that\nsupport the liberal amendment of pleadings also apply to\nsupplemental pleadings.”). As the Supreme Court has stated,\nthe purpose of Rule 15 is “to balance the interests of the\n\n\nor (3) states a new claim that arose after the filing of the\ncomplaint.” Wright et al., supra, § 1508.\n\n\n\n\n 33\n\fdefendant protected by the statute of limitations with the\npreference expressed in the Federal Rules of Civil Procedure\nin general, and Rule 15 in particular, for resolving disputes on\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\n550 (2010). The requirements of Rule 15 itself protect\ndefendants from an unfair relation back. 21 Under that Rule,\ncourts “look[s] to whether the opposing party has had fair\nnotice of the general fact situation and legal theory upon\nwhich the amending party proceeds.” Bensel, 387 F.3d at\n310. In this instance, Wilmington had sufficient notice since\nthe supplemented complaint simply alleged the issuance of\nthe ZBA’s written denial. And, of course, Wilmington had\nnotice of everything in the supplemental complaint. It not\nonly knew of the written denial and the reasons given, it\ngenerated them.\n\n Relation back has been allowed to address\njurisdictional problems. We said in Berkshire Fashions, Inc.\nv. M.V. Hakusan II that relation back may be used to cure\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\nCir. 1992). In that case, the District Court had dismissed the\nplaintiff’s claim based on admiralty jurisdiction and denied\nthe plaintiff’s motion to amend its complaint to allege\ndiversity jurisdiction. Id. at 877. We concluded that both\ndecisions were in error, holding that an amended complaint\nrelates back and can cure insufficient pleading of subject\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\n\n 21\n This is not a pass for endless delay in\nsupplementing a complaint. Indeed, we have endeavored to\nemphasize that whether to allow supplemental pleading\ndepends on equitable considerations of fairness and notice\nthat district courts must take into account.\n\n\n\n\n 34\n\fa plaintiff to cure a diversity defect when the case had been\nlitigated for years. See GBForefront, L.P., v. Forefront\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\namend the complaint … to cure defective jurisdictional\nallegations”).\n\n Other circuits have held the same. See Woods v. Ind.\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\nCir. 1993) (“Consistent with its history and purpose, Rule\n15(c) has uniformly been applied to relate back [filings] that\ncure defective statements of jurisdiction ….”); Boyce v.\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\namendment alleging that no previous appeal had been taken\nto the United States Court of Customs and Patent Appeals to\ncure jurisdictional defect in complaint after statute of\nlimitations had expired). That conclusion is also consistent\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\nof jurisdiction [to] be amended, upon terms, in the trial or\nappellate courts.” Id.\n\n Courts have similarly permitted cure of actual defects\nin the court’s jurisdiction, going beyond just jurisdictional\nallegations. For instance, although not in a case involving a\nlater complaint, the Supreme Court has said that a court can\ndrop a dispensable non-diverse party to cure a defect in\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\n2001) (stating that, “where it is appropriate to relate back an\namendment to a pleading under Rule 15, jurisdiction is\nassessed as if the amendment had taken place at the time the\ncomplaint was first filed[,]” and thus replacing a non-diverse\n\n\n\n\n 35\n\fplaintiff with a diverse plaintiff cured any jurisdiction\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\ncomplaint could be cured by a later complaint that pled an\nassignment occurring after the original complaint was filed).\n\n Nonetheless, “[a]mendments that go beyond the mere\ncorrection or factual modification of the original pleading and\nsignificantly alter the claim or defense alleged in that\npleading are treated more cautiously by the courts in applying\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\nSecond Circuit, for instance, only sometimes allows\njurisdictional defects to be cured “when the underlying facts,\nif properly pled, would have supported jurisdiction at the time\nthe action commenced.” Correspondent Servs. Corp. v. First\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\ncure the original complaint since they were defects “not [in\nthe] allegations of existing underlying jurisdictional facts but\nrather [in] the prerequisite jurisdictional facts themselves”).\nWilmington argues such hesitance is appropriate here because\nallowing relation back to cure the jurisdictional problem with\nT Mobile’s initial complaint “would allow two wrongs under\nSection 332 [(filing early and filing late)] to make a right.”\n(Answering Br. at 2.)\n\n We again disagree with the City. It is quite true that\nT Mobile has made procedural matters more difficult than\nthey should be in this case. But denying relation-back to cure\nthe defect in this instance would not comport with Rule 15’s\naim to encourage resolution of disputes on the merits\nwhenever possible. The ripeness requirement exists so that\n\n\n\n\n 36\n\fcourts avoid issuing essentially advisory opinions. See\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\nCourts and the Federal System 224 (5th ed. 2003) (noting that\nthe ripeness doctrine allows courts to avoid a “dispute … too\n‘ill-defined’ to be appropriate for judicial resolution until\nfurther developments … more sharply framed the issues for\ndecision.”). That concern ceased to exist here once the\nsupplemental pleading was in place. At that point, the dispute\nhad matured and become capable of judicial review,\ndemonstrating that, “actions taken after the filing of the initial\ncomplaint can be used to establish subject matter\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\nF.3d 1329, 1337 (Fed. Cir. 2008).\n\n If a supplemental complaint cannot cure an unripe\ncomplaint, an endless feedback loop would be created\nwhereby the ripeness problem could never be overcome, even\nthough, as here, the dispute later became obviously ripe. Our\nsister circuits have recognized that problem and concluded\nthat a supplemental complaint is the solution. 22 In Wilson v.\nWestinghouse Electric Corp., the Eighth Circuit determined\nthat prohibiting an amended (or supplemental) complaint\nfrom alleging facts that occurred after the date the initial\n\n 22\n In our Circuit, a thoughtful district court decision\nhad long ago reached that conclusion. It held that an\nuntimely supplement adding facts occurring after the initial\nfiling that showed exhaustion of administrative remedies\ncould relate back to the initial premature complaint and allow\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\n521, 526-27 (E.D. Pa. 1976).\n\n\n\n\n 37\n\fcomplaint was filed would turn a premature complaint into an\n“irretrievable mistake that bars jurisdiction” and would be\n“precisely the kind of procedural mousetrap that the Federal\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\nCir. 1988). The court held that, “[e]ven when the District\nCourt lacks jurisdiction over a claim at the time of its original\nfiling, a supplemental complaint may cure the defect by\nalleging the subsequent fact which eliminates the\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\n75). While Wilson addressed a circumstance in which the\nsupplemental complaint was timely filed, the proposition still\napplies in a case like ours because, if a party was limited to\nrefiling within an applicable time limit, there would be little\nneed to make provision for supplementation of a complaint,\nas a new complaint could be filed. 23\n\n 23\n We note that sparing the cost of refiling and\nproviding convenience to the Court would remain legitimate\nreasons for allowing supplemental complaints. But the\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\n1504 (“The purpose of subdivision (d) is to promote as\ncomplete an adjudication of the dispute between the parties as\nis possible. … A supplemental pleading may be employed\nfor a variety of purposes.”). Wilmington contends that\nWilson is inapposite since it involved a timely supplemental\ncomplaint. Thus, concern about a perpetual loop outcome\nwas not proper because the plaintiff could have simply refiled\nhis complaint. But we agree that “a plaintiff need not\ncommence a new action when after-occurring events\ndemonstrate that it has a right to relief even if the original\ncomplaint was insufficient. A plaintiff may also be allowed\nto supplement the complaint even if jurisdiction … would not\nhave been proper if the claim had been asserted in an\n\n\n\n\n 38\n\f The Ninth Circuit, in Security Insurance Co. of New\nHaven v. United States ex rel. Haydis, also relied on that logic\nto find that relation back could cure an unripe complaint filed\nbefore a statutory filing window opened. 338 F.2d 444, 448-\n49 (9th Cir. 1964). In a fact scenario with striking similarities\nto the present appeal, the plaintiff had filed its claim before a\nstatutory waiting period was over and then did not file an\namended complaint until after the statute of limitations period\nhad run. Id. at 445-46. The appeals court held that the\ndistrict court was “not required to apply the doctrine of\nrelation back so literally as to carry it to a time [before it was\nripe] so as to prevent the maintenance of the action in the first\nplace.” Id. at 449.\n\n The Supreme Court has favorably cited Security\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\na precondition of filing a complaint by first filing an\napplication with a particular agency. 426 U.S. at 72, 75. The\nCourt noted that a supplemental complaint, alleging that the\napplication had since been filed, would have cured the\njurisdictional defect. Id. at 75. In saying so, the Court relied\n\n\n\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\n2018) (citation omitted). If supplemental complaints could\nnot cure ripeness, “then all supplemental pleadings of this\nnature would be defeated for lack of jurisdiction – [the]\n‘procedural mousetrap’ would render all supplemental\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\nomitted).\n\n\n\n\n 39\n\fon Security Insurance. Id. at 75 n.8 (citing Security\nInsurance, 338 F.2d at 447-49). 24\n\n Yet Wilmington asserts that ripeness can never be\ncured by a later complaint. It advances four cases for that\nproposition, but none are helpful. First, the City cites\nDelaware Riverkeeper Network v. Secretary Pennsylvania\nDepartment of Environmental Protection, (Riverkeeper I),\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\n“even though the underlying claim became ripe for review\nduring the pendency of the case, the ripening of the claim did\nnot cure deficient pleadings.” (App. at 8.) In that case,\nhowever, no attempt to file a later complaint alleging ripeness\nwas made. Riverkeeper I, 833 F.3d at 369-70.\n\n Likewise, in another two of the four cases that\nWilmington cites, there was no effort made to amend or\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\naction at the time of filing of petition may only be reviewed\nupon the filing of another petition); W. Union Tel. Co., 773\nF.2d at 377-78 (concluding that the court lacked jurisdiction\nover challenges filed before the action became final).\nTherefore, neither case determined whether relation back of a\nlater-filed complaint could cure a ripeness problem in the\ninitial complaint.\n\n 24\n Wilmington contends that Mathews is inapposite\nsince the statute of limitations was waived. That argument\nhas no traction since, if it were a jurisdictional bar, it could\nnot be waived.\n\n\n\n\n 40\n\f The City fares no better relying on Council Tree\nCommunications v. FCC, in which we stated that “[a] petition\nto review a non-final agency order is incurably premature.”\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\nwas the complaint ripe, and the petitioner still had a petition\nfor reconsideration pending before the relevant agency on the\ndate the case was decided. Id. at 287. Furthermore, Council\nTree explicitly acknowledged that a supplemental complaint\ncan cure an unripe complaint when there is jurisdiction over\nthat supplemental pleading. See id. at 291 (“[W]e note that\n‘nothing prevented [the petitioners] from supplementing their\npremature petition with a later protective petition.’” (second\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\n\n Wilmington also makes three policy arguments in\nsupport of its position that an untimely supplemental\ncomplaint should not be able to cure an unripe complaint.\nFirst, it contends that allowing suits to be filed before an\naction is ripe would “extend[] federal court jurisdiction over\nlocal government actions before those actions are final[.]”\n(Answering Br. at 9.) Second, such filings would waste\njudicial resources and, in this case, cost taxpayers money, by\nforcing courts to deal with a higher volume of unripe\ncomplaints. Third, the purpose of § 332 is to preserve local\nzoning authority, which would be undermined by allowing\nplaintiffs to file suit early and thereby places undue pressure\non zoning commissions.\n\n Those contentions, however, are unpersuasive. First, a\ncourt would remain without jurisdiction if the claim had not\nripened by the time of the supplemental complaint. Second, it\n\n\n\n\n 41\n\fseems that Wilmington overstates the impact that a decision\nallowing an unripe complaint to be cured would have, since\nour holding today makes it clear that an action is not final\nuntil a written decision has been issued. Clarifying when a\ndetermination is ripe for review should end any incentive for\naggrieved parties to file early to ensure they have not filed too\nlate.\n\n Perhaps more importantly, however, courts can police\nany potential abuse on a case-by-case basis using Rule 15(d)\nand the Rule 15(c) test for relation back. It is understood that\n“relation back of a supplemental pleading should not result in\nproviding unfair procedural advantages to a plaintiff[,] so …\nrelation back may not be for all purposes.” Wright et al.,\nsupra, § 1508. But here no unfair advantage has resulted, and\ndefendants in general will be adequately protected by a\ndistrict court’s Rule 15(d) analysis, which will determine if a\nsupplemental complaint should be allowed at all. For\ninstance, if a locality’s action is not yet a final action at the\ntime a Rule 15(d) motion is filed, the motion can easily be\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\n530 (9th Cir. 1986) (supplemental pleading denied when it\nstill failed to cure defective original pleading).\n\n When all is said and done here, we conclude that, to\neffectuate the liberal purpose of Rule 15 and to avoid the\nendless feedback loop that the City’s legal argument would\ncreate, Rule 15 allows an untimely supplemental complaint to\nrelate back and cure an unripe initial complaint.\n\n\n\n\n 42\n\fIII. CONCLUSION\n\n For the foregoing reasons, we will reverse the District\nCourt’s grant of the City’s motion for summary judgment,\nvacate the District Court’s denial of T Mobile’s motion for\nsummary judgment, and remand to the District Court for\nfurther proceedings consistent with this opinion.25\n\n\n\n\n 25\n We will vacate the District Court’s denial of\nT Mobile’s motion for summary judgment because it was\nsolely based on a finding that T Mobile’s suit was not timely\nbrought.\n\n\n\n\n 43\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: T MOBILE NORTHEAST LLC, Appellant v. CITY OF WILMINGTON, DELAWARE ; City of Wilmington Zoning Board of Adjustment\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-10\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 18-1831\\n _____________\\n\\n T MOBILE NORTHEAST LLC,\\n Appellant\\n\\n v.\\n\\n CITY OF WILMINGTON, DELAWARE;\\nCITY OF WILMINGTON ZONING BOARD OF ADJUSTMENT\\n _____________\\n\\n On Appeal from the United States District Court\\n for the District of Delaware\\n (D.C. No. 1-16-cv-01108)\\n District Judge: Hon. Eduardo C. Robreno\\n _______________\\n\\n Argued\\n September 12, 2018\\n\\nBefore: JORDAN, NYGAARD, and VANASKIE, * Circuit Judge\\n (Filed: January 10, 2019)\\n\\n\\n *\\n The Honorable Thomas I. Vanaskie retired from the\\nCourt on January 1, 2019 after the argument and conference\\nin this case, but before the filing of the opinion. This opinion\\nis filed by a quorum of the panel pursuant to 28 U.S.C.\\n§ 46(d) and Third Circuit I.O.P. Chapter 12.\\n\\f _______________\\n\\nThomas S. Thompson [ARGUED]\\nDavis Wright Tremaine\\n1919 Pennsylvania Avenue, NW\\nSte. 800\\nWashington, DC 20006\\n\\nCounsel for Appellant\\n\\nJoseph Van Eaton [ARGUED]\\nBest Best & Krieger\\n2000 Pennsylvania Avenue\\nSte. 5300\\nWashington, DC 20006\\n\\nCounsel for Appellees\\n _______________\\n\\n OPINION OF THE COURT\\n _______________\\n\\n\\nJORDAN, Circuit Judge.\\n\\n No one likes bad cell phone reception or slow\\nstreaming data on their smartphone, but that does not mean\\nanyone wants a cellular antenna in their neighborhood, which\\nis why there are zoning battles like the one central to this\\ncase.\\n\\n T Mobile Northeast LLC (“T Mobile”), a wireless\\ntelecommunications service provider, applied to the Zoning\\nBoard of Adjustment (“ZBA”) of the City of Wilmington,\\nDelaware for permission to erect an antenna in the City. The\\n\\n\\n\\n\\n 2\\n\\fZBA said no. So, relying on a provision of federal law that\\nallows a disappointed wireless service provider like T Mobile\\nto seek review in a district court “within 30 days after” a\\nzoning authority’s “final action,” 47 U.S.C.\\n§ 332(c)(7)(B)(v), T Mobile filed suit. After the case had\\nproceeded for over a year, however, the District Court\\nconcluded that it lacked jurisdiction. The Court reasoned that\\nbecause T Mobile filed its complaint before the ZBA released\\na written decision confirming an earlier oral rejection of the\\nzoning application, the claim was not ripe. And, since\\nT Mobile did not supplement its complaint to include the\\nZBA’s written decision within 30 days of its issuance, the\\nCourt also concluded that relation back could not remedy the\\nripeness defect. The District Court thus granted the City’s\\nmotion for summary judgment.\\n\\n T Mobile now appeals. It argues that its complaint\\nwas not premature or, in the alternative, that its supplemental\\npleading cured any ripeness problem. We agree that the grant\\nof summary judgment was improper and, for the reasons that\\nfollow, will remand the case for further proceedings\\nconsistent with this opinion.\\n\\nI. BACKGROUND\\n\\n A. Statutory Framework\\n\\n This dispute is governed by the Telecommunications\\nAct of 1996 (“TCA”), which amended the Federal\\nCommunications Act of 1934 and includes provisions on\\nmobile phone services. Pub. L. No. 104-104, §§ 1, 704, 110\\nStat. 56, 56, 151 (1996); 47 U.S.C. § 332. Passed to\\n“encourage the rapid deployment of new telecommunications\\n\\n\\n\\n\\n 3\\n\\ftechnologies,” Preamble, 110 Stat. at 56, the TCA provides\\nfor expedited review in federal court of a denial of permission\\nto build a cell phone antenna, id. § 704, 110 Stat. at 151-52.\\nSuch review is a “benefit Congress expressly intended to\\nconfer on wireless providers[.]” Nextel W. Corp. v. Unity\\nTwp., 282 F.3d 257, 264 (3d Cir. 2002). At the same time,\\nthe TCA also serves to preserve local zoning authority. 47\\nU.S.C. § 332(c)(7).\\n\\n At issue here are three key sections of the statute.\\nFirst, the TCA mandates that “[a] State or local government\\nor instrumentality thereof shall act on any request for\\nauthorization to place, construct, or modify personal wireless\\nservice facilities within a reasonable period of time after the\\nrequest is duly filed[.]” Id. § 332(c)(7)(B)(ii). The Federal\\nCommunications Commission (“FCC”) has interpreted\\n“reasonable period of time” in that statutory provision to\\nmean that zoning authorities have a “shot clock” 1 and must\\nact within 90 days of an application to attach an antenna to an\\nexisting structure or 150 days of an application where a new\\nsupport structure is to be built. Petition for Declaratory\\n\\n 1\\n “Shot clock” is a term borrowed from basketball. In\\nthat game, it signifies a time limit to make a shot attempt,\\nbeginning once a team has possession of the basketball. See,\\ne.g., Nat’s Basketball Ass’n, NBA Rulebook Rule No. 7: Shot\\nClock (2018-2019), http://official.nba.com/rule-no-7-24-\\nsecond-clock/. If the team has not made a shot attempt, i.e.,\\nacted, within the prescribed time limit, it forfeits possession\\nof the ball. Id. Here, the permitting authority has exclusive\\njurisdiction over an application until it fails to act within a\\n“reasonable period of time.” 47 U.S.C. §§ 332(c)(7)(A),\\n332(c)(7)(B)(ii).\\n\\n\\n\\n\\n 4\\n\\fRuling to Clarify Provisions of Section 332(c)(7)(B), 24 FCC\\nRcd. 13994, 14008, 14012 (2009). Second, in what we will\\ncall the “review provision” of the statute, the TCA grants\\n“[a]ny person adversely affected by any final action or failure\\nto act by a State or local government or any instrumentality\\nthereof” a right to have that locality’s decision reviewed by\\n“commenc[ing] an action” “within 30 days” in district court.\\n47 U.S.C. § 332(c)(7)(B)(v). Third, in the statute’s “denial\\nprovision,” the TCA states that “[a]ny decision by a State or\\nlocal government or instrumentality thereof to deny a request\\nto place, construct, or modify personal wireless service\\nfacilities shall be in writing and supported by substantial\\nevidence contained in a written record.” Id.\\n§ 332(c)(7)(B)(iii). Notably, the terms “act,” “final action,”\\nand “decision … to deny” are not defined in the TCA.\\nFurthermore, the statute does not make clear whether “final\\naction” should be read to encompass all decisions to deny,\\nincluding oral ones, nor does it address whether there is a\\ndifference between an “act” for purposes of the shot clock\\nand a “final action” for purposes of judicial review.\\n\\n B. Factual Background\\n\\n T Mobile is a telecommunications service provider. It\\nsays that it needs to erect a cellular antenna to fill “a\\nsignificant gap” in coverage for its customers in Wilmington,\\nDelaware, (Opening Br. at 3) presumably where there has\\nbeen an increase in phone calls and data usage. T Mobile\\nwants to put its antenna on top of a senior living high-rise in\\nthe City, but, because a special exception to local zoning laws\\nis needed, it first had to go to the ZBA. It filed an initial\\napplication and then, on August 25, 2016, a final amended\\napplication, seeking the exception.\\n\\n\\n\\n\\n 5\\n\\f The ZBA held a hearing on October 26, 2016, to\\nconsider T Mobile’s request, some two months after the final\\namended application was submitted. During the hearing,\\nT Mobile presented evidence of the need for the antenna and\\ndiscussed proposals to address aesthetic concerns. The ZBA\\nalso received objections from members of the local\\ncommunity, some of whom were outspoken in worrying\\nabout the effects of radio frequency emissions. At the end of\\nthe hearing, the ZBA denied T Mobile’s application in a\\nunanimous oral decision.\\n\\n The Board gave several reasons for the denial. One\\nboard member said the ZBA should not encourage the use of\\na senior living community rooftop as the base for an antenna\\nbecause of the potential adverse effect on the properties in the\\nneighborhood. Another board member said there was not\\nenough proof of a need for additional coverage to support the\\napplication. The Chairman said there was not enough\\nevidence that T Mobile needed the antenna and that it did not\\nappear to satisfy the zoning code in terms of placement and\\nheight restrictions.\\n\\n The ZBA’s oral decision to deny the application was\\nnot put in writing on October 26 or anytime soon thereafter.\\nAccording to T Mobile, that fits a “pattern and practice of\\n[the ZBA] not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) Only\\nafter T Mobile had filed its initial complaint in the District\\nCourt, and after the City filed its answer, did the ZBA issue\\nits written decision and explanation of its reasoning for\\ndenying the application.\\n\\n\\n\\n\\n 6\\n\\f T Mobile asserts that the denial of its application\\nviolates the TCA. Under the statute, such a denial is invalid\\nif it has the “effect of prohibiting the provision of personal\\nwireless services[,]” 47 U.S.C. § 332(c)(7)(B)(i)(II), or is “on\\nthe basis of the environmental effects of radio frequency\\nemissions[,]” id. at § 332(c)(7)(B)(iv). T Mobile claims that\\nWilmington’s denial was improper on both of those grounds. 2\\nBut those assertions go to the merits and are not actually\\nbefore us on this appeal. At issue now is whether T Mobile’s\\nclaim can be heard at all.\\n\\n C. Procedural History\\n\\n Evidently with its eye on the 30-day deadline in the\\nTCA’s review provision, T Mobile filed a lawsuit in the\\nUnited States District Court for the District of Delaware\\nwithin 30 days of the ZBA’s oral decision, challenging that\\ndenial. 3 In addition to its claims on the merits, T Mobile’s\\ninitial complaint alleged that the City violated procedures\\nmandated in the TCA, specifically those in the denial\\nprovision, by failing to provide a written decision\\n\\n 2\\n T Mobile also raised a Delaware state law claim.\\nThat claim is not at issue here and does not impact\\nT Mobile’s claims under federal law.\\n 3\\n For reasons discussed herein, the 30-day filing\\ndeadline was not triggered by the oral decision. See infra pp.\\n12-20. If it were, however, T Mobile’s complaint would have\\nbeen timely. The oral decision was delivered at the\\nOctober 26, 2016 hearing. Suit was filed on November 28,\\n2016, but because the thirtieth day from October 26 fell on a\\nweekend, the November 28 filing was within the 30-day\\nwindow. Fed. R. Civ. P. 6(a)(1).\\n\\n\\n\\n\\n 7\\n\\fcontemporaneous with its oral decision and by not supporting\\nthe denial with substantial evidence.\\n\\n The parties entered into a stipulation asking the\\nDistrict Court for an expedited case schedule, as provided for\\nin the review provision of the TCA. 47 U.S.C.\\n§ 332(c)(7)(B)(v). That request was granted. Wilmington\\nthen answered the complaint, asserting a number of\\naffirmative defenses, including that the complaint was not\\nripe because the ZBA had not yet issued a final written\\ndecision. Nevertheless, the City did not, at that time, file a\\nmotion to dismiss for failure to state a claim or for lack of\\njurisdiction. Two days after the City filed its answer, the\\nZBA issued a written decision on T Mobile’s application.\\nThe parties pressed forward with the suit and prepared a\\ndiscovery plan, which specifically mentioned the written\\ndecision. T Mobile filed a motion for summary judgment,\\nwhich the City met with a cross-motion for summary\\njudgment. The City’s motion was styled in the alternative as\\na motion to dismiss the complaint as unripe because it was\\nfiled prematurely, i.e., before the written decision had been\\nissued.\\n\\n Not until December 21, 2017, nearly a year after the\\nZBA issued its written denial, did T Mobile file a motion\\nseeking leave to amend or supplement the initial complaint to\\nnote the issuance of that written decision. 4 The District Court\\n\\n 4\\n When “[a] claim or defense set out in a pleading [is]\\naffected by events that occur after the pleading is filed ….\\nRule 15(d) allows a court,” to permit a supplemental\\npleading. 3 James Wm. Moore et al., Moore’s Federal\\nPractice ¶ 15.30 (3d ed. 2018). Supplemental pleadings\\n\\n\\n\\n\\n 8\\n\\fgranted the motion to supplement. Wilmington then\\nresponded by moving to dismiss the supplemental complaint\\nas untimely because it failed to cure the defect.\\n\\n Ultimately, the District Court granted Wilmington’s\\ncross-motion for summary judgment for want of jurisdiction,\\nwithout ruling on the City’s motion to dismiss. The Court\\nfirst concluded that the initial complaint was irreparably\\nunripe because both the TCA and Delaware law require the\\nZBA to issue a written decision before the agency’s action\\ncould be considered final, and T Mobile had thus filed its\\ninitial complaint too soon. Second, the Court said that the\\nsupplemental complaint could not fix the ripeness problem\\nbecause it was filed past the 30-day window for seeking\\nreview of the ZBA’s final action. Because the Court reached\\n\\n\\n\\nunder Rule 15(d) differ from amended pleadings made under\\nRule 15(a). First, amended pleadings “relate to matters that\\noccurred prior to the filing of the original pleading and\\nentirely replace the earlier pleading; [supplemental pleadings]\\ndeal with events subsequent to the pleading to be altered and\\nrepresent additions to or continuations of the earlier\\npleadings.” 6A Charles Alan Wright et al., Federal Practice\\n& Procedure § 1504 (3d ed. 2018). Second “certain\\namendments may be made as a matter of course within stated\\ntime periods, whereas all supplemental pleadings require\\nleave of court under Rule 15(d).” Id. “Parties and courts\\noccasionally confuse supplemental pleadings with amended\\npleadings and mislabeling is common.” Id. Here, T Mobile’s\\ncomplaint was filed as an amended complaint but it is\\nproperly categorized as a supplemental complaint, and we\\nwill refer to it as such herein.\\n\\n\\n\\n\\n 9\\n\\fthat determination, it found it unnecessary to conclude\\nwhether T Mobile’s supplemental complaint was entitled to\\nthe benefit of the relation-back doctrine under Rule 15(c).\\n\\n This appeal followed.\\nII. DISCUSSION 5\\n\\n T Mobile challenges the District Court’s grant of\\nsummary judgment in favor of Wilmington, contending that\\nthere is jurisdiction to hear its case. It advances two\\nalternative grounds for reversal: that its complaint was ripe\\nbecause the ZBA’s oral decision qualifies as a “final action”\\nunder the review provision of the TCA, and, in the\\nalternative, that the supplemental complaint relates back to\\nand cures any ripeness problem with its initial complaint.\\nThose arguments in turn raise three questions for determining\\nwhether the District Court’s jurisdictional ruling was proper.\\nFirst, whether the oral decision of the ZBA was a final action.\\nSecond, whether the timing requirement in the TCA’s review\\nprovision is jurisdictional. And third, whether an untimely\\n\\n 5\\n The District Court had jurisdiction to consider its\\njurisdiction under 28 U.S.C. §§ 1331 and 1367(a), but\\ndetermined the complaint contained incurable jurisdictional\\ndefects and declined to reach the merits. We have jurisdiction\\npursuant to 28 U.S.C. § 1291. We review all the issues\\npresented in this case de novo, as they involve only legal\\nissues, i.e., interpretation of a federal statute and of a Federal\\nRule of Civil Procedure. Giles v. Campbell, 698 F.3d 153,\\n155 (3d Cir. 2012); Viera v. Life Ins. Co. of N. Am., 642 F.3d\\n407, 413 (3d Cir. 2011); DIRECTV Inc. v. Seijas, 508 F.3d\\n123, 125 (3d Cir. 2007).\\n\\n\\n\\n\\n 10\\n\\fsupplemental complaint can relate back and cure an unripe\\ninitial complaint. Although we disagree with T Mobile that\\nan oral decision of the ZBA qualifies as a “final action,” we\\nagree that jurisdiction was proper in the District Court\\nbecause the timing requirement in the TCA’s review\\nprovision is non-jurisdictional, and T Mobile’s supplemental\\ncomplaint therefore relates back and cures the ripeness\\nproblem with the initial complaint. The District Court should\\nthus have reached the merits of the dispute.\\n\\n A. The Oral Decision Was Not a Final Action of\\n the ZBA.\\n\\n The ripeness of T Mobile’s initial complaint depends\\nupon whether the ZBA’s oral decision was a “final action”\\nwithin the meaning of the TCA. Consideration of that issue\\nuncovers another: whether the TCA requires a locality to\\nrender its decision in writing for that decision to qualify as a\\nfinal action. The District Court held that, under both federal\\nand Delaware law, only a written decision can serve as a final\\naction of the ZBA. Because traditional hallmarks of agency\\naction and the statutory text and structure of the TCA favor\\nthat approach, we agree that only a written decision can serve\\nas a locality’s final action when denying an application.\\n\\n In Delaware Riverkeeper Network v. Secretary\\nPennsylvania Department of Environmental Protection,\\n(Riverkeeper III), we determined that, when reviewing\\nfinality under the Natural Gas Act, “[a]lthough the\\ndecisionmaking process we are reviewing is defined by [state]\\nlaw, we nevertheless apply a federal finality standard to\\ndetermine whether Congress has made the results of that\\nprocess reviewable[.]” 903 F.3d 65, 72 (3d Cir. 2018). The\\n\\n\\n\\n\\n 11\\n\\fsame reasoning holds true here, since, for the TCA just as for\\nthe Natural Gas Act, “the finality requirement itself, along\\nwith the presumption that Congress intended us to apply it,\\nare creatures of federal, not state, law.” Id. at 71.\\n\\n Under federal law, not all agency determinations are\\nfinal actions. Bacon v. Sullivan, 969 F.2d 1517, 1519 (3d Cir.\\n1992). Final agency actions bear certain “traditional\\nhallmarks” that demonstrate “[t]here is nothing left for the\\nagency to do[,]” Del. Riverkeeper Network v. Sec’y of Pa.\\nDep’t of Envtl. Prot., (Riverkeeper II), 870 F.3d 171, 178 (3d\\nCir. 2017). We noted those hallmarks on an earlier occasion\\nwhen we said that, “[f]inal agency action must mark the\\nconsummation of the agency’s decisionmaking process, must\\nnot be of a merely tentative or interlocutory nature, and must\\nbe one by which rights or obligations have been determined,\\nor from which legal consequences will flow.” Riverkeeper\\nIII, 903 F.3d at 72, 75 (citation and internal quotation marks\\nomitted).\\n\\n To decide what the TCA requires for finality, we\\nbegin, of course, with the text. See, e.g., Ross v. Blake, 136 S.\\nCt. 1850, 1856 (2016) (“Statutory interpretation … begins\\nwith the text[.]”) Here, the statutory text makes it clear that,\\nif a denial is not in writing, there is something left for the\\nagency to do. The denial provision of the TCA states that\\n“[a]ny decision … to deny … shall be in writing and\\nsupported by substantial evidence contained in a written\\nrecord.” 47 U.S.C. § 332(c)(7)(B)(iii). We see no reason\\nwhy the same should not be true for actions besides denial, 6\\n\\n 6\\n For instance, it is not apparent why community\\nmembers aggrieved by a decision to grant some permit to a\\n\\n\\n\\n\\n 12\\n\\fbut we need not decide that today. It is enough to say that, in\\nthose zoning decisions governed by the TCA, a locality’s oral\\ndeclaration of a denial is “of a merely tentative or\\ninterlocutory nature.” Riverkeeper III, 903 F.3d at 72\\n(citation omitted) (speaking in reference to the Natural Gas\\nAct); cf. Athens Cellular, Inc. v. Oconee Cty., 886 F.3d 1094,\\n1104-05, 1107 (11th Cir. 2018) (noting that a zoning board\\ncould have approved the minutes, revised them, or rejected\\nthem, and thus until the board approved the minutes its\\ndecision was not final).\\n\\n Moreover, an oral decision is not an action from which\\nlegal consequences flow. Federal law governs finality, but\\nDelaware’s procedures still matter, and the Delaware\\nSuperior Court has concluded that a written document must\\nbe filed for a ZBA action to be final. McDonald’s Corp. v.\\nZoning Bd. of Adjustment for the City of Wilmington, No.\\nCIV. A. 01A-05-011CG, 2002 WL 88944, at *1 (Del. Super.\\nCt. Jan. 10, 2002). The court reasoned that Section 328 of\\nTitle 22 of the Delaware Code, the section that governs\\nappeals from ZBA proceedings, requires a written document\\nto be filed because the statute “provides that [s]uch petition\\nshall be presented to the Court within 30 days after the filing\\nof the decision in the office of the board.” Id. (internal\\nquotation marks omitted). That reasoning is persuasive and\\n\\n\\n\\n\\nwireless provider, assuming those members have standing to\\nsue, would not be equally entitled to a zoning authority’s\\nwritten decision before the time limit in the TCA’s review\\nprovision is triggered.\\n\\n\\n\\n\\n 13\\n\\fshows that, under Delaware law, the ZBA’s oral decision is\\nwithout legal consequences. 7\\n\\n There are distinct policy advantages to forestalling\\njudicial scrutiny until a written denial is issued. Requiring a\\nwritten decision focuses review on a particular, documented\\nstatement of reasons. See USCOC of Greater Mo. v. City of\\nFerguson, 583 F.3d 1035, 1042 (8th Cir. 2009) (“Because the\\nwritten decision is the central object of our scrutiny under the\\nTCA, the process of judicial review is best served by delaying\\nthe ripening of a TCA claim until the local authority has\\nissued its written decision.”). It also prevents ambiguity with\\nrespect to when a claim can be brought. As the District Court\\nhere stated, to hold otherwise “would promote a pernicious\\nambiguity as to when that short period of time begins to run.”\\n(App. at 7.) And it promotes uniformity of federal procedures\\nby clarifying when, across all jurisdictions, an action becomes\\nfinal.\\n\\n 7\\n T Mobile cites to a different opinion, Schmalhofer v.\\nBoard of Adjustment of Newark, to advance a contrary\\nposition. No. C.A. 99A-05-010-WTQ, 2000 WL 703510\\n(Del. Super. Ct. May 9, 2000). Schmalhofer states in a\\nfootnote that “a written decision is not required or expressly\\ncontemplated by this section.” Id. at *3 n.3. But T Mobile is\\nstretching the Schmalhofer court’s language too far. In that\\ncase, the City of Newark had issued a verbatim transcript of\\nthe hearing, so there was a writing. Id. at *3; see infra note\\n11. There is no indication of any written decision in this case,\\nprior to December 22, 2016, when the City issued the written\\ndenial bearing the date of December 21, 2016.\\n\\n\\n\\n\\n 14\\n\\f The Supreme Court’s decision in T-Mobile South, LLC\\nv. City of Roswell, Georgia, also adds support to the\\nconclusion that only a written denial can constitute final\\naction, triggering a party’s right to review. 135 S. Ct. 808\\n(2015). In that case, the Court held that the “substantial\\nevidence” supporting a locality’s decision to deny must be\\nreleased contemporaneously with the written decision to\\ndeny. 8 Id. at 811-12. In doing so, the Court tied together a\\nlocal zoning authority’s final action, which triggers judicial\\nreview, and its decision to deny, which must be in writing.\\nIndeed, the Supreme Court said in no uncertain terms that,\\n“[t]he relevant ‘final action’ [in that case, was] the issuance of\\nthe written notice of denial[.]” Id. at 817 n.4. The Court\\nlinked the locality’s decision to deny to the 30-day time limit\\nto file a complaint after a final action has been taken. Id. at\\n817 (“Only once the denial is issued would the 30-day\\ncommencement-of-suit clock begin.”); id. at 813 (“[N]ow 29\\ndays after the City denied petitioner’s application—petitioner\\nfiled suit in Federal District Court.”).\\n\\n The Court went on to discuss timing, saying, “the\\nlocality must provide or make available its written reasons at\\nessentially the same time as it communicates its denial[,]”\\n“[b]ecause an entity may not be able to make a considered\\n\\n 8\\n The Court was interpreting the denial provision,\\nwhich, as we noted earlier, states that, “[a]ny decision by a\\nState or local government or instrumentality thereof to deny a\\nrequest to place, construct, or modify personal wireless\\nservice facilities shall be in writing and supported by\\nsubstantial evidence contained in a written record.” 47\\nU.S.C. § 332(c)(7)(B)(iii), City of Roswell, 135 S. Ct. at 811.\\n\\n\\n\\n\\n 15\\n\\fdecision whether to seek judicial review without knowing the\\nreasons for the denial of its application, and because a court\\ncannot review the denial without knowing the locality’s\\nreasons[.]” Id. at 816. The majority opinion was critical of\\nthe dissent for attempting to “fashion a world in which a\\nlocality can wait until a lawsuit is commenced and a court\\norders it to state its reasons[,] … [leaving the challenging\\nentity to] risk being sandbagged by the written reasons that\\nthe locality subsequently provides in litigation after the\\nchallenging entity has shown its cards.” Id. at 816 n.3. That\\ncritique is premised on the written decision being the final\\naction that starts the 30-day time limit for commencing suit. 9\\n\\n The Supreme Court anticipated that localities might\\nneed to delay issuing a written denial if they are not ready to\\nrelease their substantial reasons. See id. at 817 (noting that\\n\\n 9\\n T Mobile asserts that Wilmington has a “pattern and\\npractice of not issuing a written decision of land use denials\\nunless or until the City is sued.” (Opening Br. at 7.) But if\\nonly a written denial is a final action, the shot clock requires\\nthe City to issue that written decision within a given time\\nperiod. 24 FCC Rcd. 13994, 14012 (2009). T Mobile also\\nasserts that when a locality has a pattern and practice of not\\nreleasing written decisions, that practice delays the overall\\nprocess, since a cellular service provider would be required to\\ninitiate two causes of action: one to compel a written decision\\nand another to challenge that written decision. That,\\nhowever, is precisely what Congress envisioned by providing\\nseparate remedies for a failure to “act” within a reasonable\\ntime period and for an improper denial. 47 U.S.C.\\n§ 332(c)(7)(B)(iii).\\n\\n\\n\\n\\n 16\\n\\f“[i]f a locality is not in a position to provide its reasons\\npromptly, the locality can delay the issuance of its denial\\nwithin this 90– or 150–day window, and instead release it\\nalong with its reasons once those reasons are ready to be\\nprovided.”). That further counsels against treating an oral\\ndetermination as a final action since, if an oral determination\\nis deemed a final action, localities will be unable to take\\nadvantage of the permissible delay afforded by the shot clock\\nfor publishing their reasoning.\\n\\n Two of our sister courts of appeals agree that only a\\nwritten decision can constitute final action. The Eighth\\nCircuit in USCOC of Greater Missouri v. City of Ferguson\\nstated that “[t]he plain language of the TCA indicates that\\n‘final action’ does not occur until issuance of a written\\ndecision.” 583 F.3d at 1041. The Eleventh Circuit in\\nPreferred Sites LLC v. Troup County likewise held a\\ncomplaint to be timely when it was filed within 30 days of a\\nwritten decision, even though it was filed more than 30 days\\nafter an oral decision. 10 296 F.3d 1210, 1217-18 (11th Cir.\\n\\n 10\\n T Mobile attempts to distinguish Preferred Sites by\\nstating that, unlike here, the case did “not address a city that\\ndoes not issue a written decision close in time to when it\\nmakes the decision to deny.” (Opening Br. at 37.) But that\\nargument is irrelevant to whether the statutory text requires a\\nwriting for an agency decision to be final. T Mobile also cites\\nto Preferred Sites to argue that it should not matter if there is\\na writing requirement since the oral denial could be seen as\\nakin to a court announcing a decision. It explains that “when\\nan appeal is filed after the court announces a decision, but\\nbefore the entry of the judgment, it is treated as being filed on\\nthe date of entry.” (Opening Br. at 28-29 (citing Preferred\\n\\n\\n\\n\\n 17\\n\\f2002) (concluding that, “[b]ased on the plain language of the\\nstatute,” that “a ‘final action’ occurs when the state or local\\nauthority issues its written decision. The statute expressly\\nmandates a … decision … committed to writing. Until the\\nstate or local authority issues its written notification, its task\\nunder the statute is not complete.”). No circuit has held\\notherwise.\\n\\n Persuasive authority thus indicates that any action, and\\ncertainly a denial, must be in writing to be final. But, there is\\nanother possible interpretation of the statutory text. The\\nwords “shall be in writing” could be read not as a condition of\\nfinality, but instead as a simple directive to state and local\\ngovernments to place their final action in writing. “The TCA\\nprovides no express answer to … when a local government’s\\npermitting decision becomes a ‘final action,’ which starts the\\nthirty-day clock.” Athens Cellular, 886 F.3d at 1102-03. The\\nstatute only states that denials must be in writing. 47 U.S.C.\\n§ 332(c)(7)(b)(iii). Decisions to grant are not limited in the\\nsame way. Id. And, Congress used the words “decision to\\ndeny” in one statutory subsection and “final action” in\\nanother, which could evince an intent to give those terms\\ndifferent meanings. As the Supreme Court has “recognized\\n… Congress’s use of certain language in one part of the\\nstatute and different language in another can indicate that\\ndifferent meanings were intended.” Sebelius v. Auburn Reg’l\\nMed. Ctr., 568 U.S. 145, 156 (2013) (citation and quotation\\n\\n\\n\\nSites, 296 F.3d at 1217 n.7).) That analogy did appear in\\nPreferred Sites, but it was only contained in a footnote. No\\nother court has followed that line of reasoning, and we\\ndecline to follow it here.\\n\\n\\n\\n\\n 18\\n\\fmarks omitted). Thus, it could be argued, if Congress wanted\\nto mandate a writing for zoning denials to constitute final\\naction, it could have been more explicit, providing, for\\ninstance, that a “decision must be in writing to qualify as a\\nfinal action.”\\n\\n But, of course, one can almost always fault legislative\\ndrafting, like other kinds of writing, after the fact. That\\nsomething might have been said even more clearly does not\\nmean it is not clear enough. So, “[r]ather than expecting (let\\nalone demanding) perfection in drafting,” we can “construe[]\\nstatutes to have a particular meaning even as we\\nacknowledge[] that Congress could have expressed itself\\nmore clearly.” Torres v. Lynch, 136 S. Ct. 1619, 1633\\n(2016).\\n\\n The text and structure of the statute, Delaware\\nprocedures, Supreme Court reasoning, our sister circuits’\\ndecisions, and policy arguments all support the conclusion\\nthat a writing is in fact a requirement for a denial to be final. 11\\nIn light of that conclusion, the ZBA’s oral determination on\\n\\n 11\\n What constitutes a “writing” has some flexibility,\\nthough. See, e.g., Omnipoint Holdings, Inc. v. City of\\nSouthfield, 355 F.3d 601, 605-07 (6th Cir. 2004) (approving\\nminutes by written resolution was a final action that bound\\nthe parties). In City of Roswell, for example, the Supreme\\nCourt indicated that minutes of an oral meeting could be\\nsufficient. 135 S. Ct. at 816. Here, however, there is no\\nevidence that the ZBA’s oral determination was noted in the\\nminutes of the October 26th meeting and issued by the City as\\nits formal decision.\\n\\n\\n\\n\\n 19\\n\\fOctober 26, 2016, was not a final action ripe for judicial\\nreview. Therefore, as that oral determination was not reduced\\nto writing until December 22, 2016, preceding the filing of\\nT Mobile’s initial complaint, that complaint’s cause of action\\nwas not ripe.\\n\\n\\n\\n\\n 20\\n\\f B. No Separate Time Limit Exists Following an\\n Oral Determination.\\n\\n As an alternative to its argument that the ZBA’s oral\\ndecision was a final action, T Mobile asks us to consider\\nwhether a “local government must issue the ‘writing’ close in\\ntime to the ‘decision … to deny’ to establish a ‘final action’\\nthat will be subject to expedited review.” 12 (Opening Br. at\\n41.) Essentially, T Mobile is asserting that the “shot clock”\\ngoverning the time to act, which allows a wireless carrier to\\nsue for a locality’s failure to act, is insufficient, and that a\\nnew requirement, albeit not in the statute, should be imposed\\non localities. Under T Mobile’s proposed rule, an oral\\ndecision would have to be reduced to writing within a\\nspecified time period. That argument assumes that an oral\\ndetermination can serve to satisfy the requirement to “act” on\\na request within the limits of the shot clock, and that, without\\na separate judicially created time limit, there would be no\\ndeadline for the locality to release its written decision to deny,\\ndespite City of Rowell’s contemporaneous writing\\nrequirement. Because we conclude that a denial must be in\\nwriting to be a final action, the issuance of that writing is the\\ngovernment “act” ruled by the shot clock. 13 Aside from the\\n\\n 12\\n Wilmington argues that T Mobile has waived that\\nissue, but we need not address that argument because we\\nconclude that no such requirement exists.\\n 13\\n Again, the Supreme Court held in City of Roswell\\nthat a locality’s decision to deny must be accompanied by\\nsubstantial reasons. 135 S. Ct. at 811-12. Otherwise, if a\\nlocality were able to withhold its reasoning for its decision,\\nthose aggrieved by the locality’s actions would “be left to\\n\\n\\n\\n\\n 21\\n\\ftime limits associated with the “shot clock,” there is no other\\ndeadline governing the issuance of a written decision\\nfollowing an oral determination. 47 U.S.C. § 332(c)(7)(b).\\nAny time limit we fabricated would be inappropriate.\\n\\n T Mobile argues that, without a requirement for\\nlocalities to issue a written decision within a set amount of\\ntime following an oral determination, wireless carriers are left\\n“to wait until the FCC ‘shot clock’ expires – which could be\\n90 or 150 days depending on the type of installation involved\\n– and then [to] file an action alleging that the City has failed\\nto act in a reasonable time[.]” (Opening Br. at 45.) It also\\ncontends that a “failure to act” lawsuit is insufficient because\\nthe remedy for a successful suit is simply an order telling the\\nCity to issue a written decision. In T Mobile’s view, forcing\\nwireless providers to sue both to compel a written decision\\nonce the shot clock is violated and again to contest the written\\ndecision serves only to “create yet further delay.” (Opening\\nBr. at 46.)\\n\\n\\n\\n\\nguess at what the locality’s written reasons will be, write a\\ncomplaint that contains those hypotheses, and risk being\\nsandbagged by the written reasons that the locality\\nsubsequently provides in litigation after the challenging entity\\nhas shown its cards.” Id. at 816 n.3. If an applicant cannot\\nfile suit, however, because the locality’s “final action” has not\\nyet occurred, those concerns vanish. The ZBA’s decision\\nhere, when reduced to writing, was both its decision to deny\\nand its final action.\\n\\n\\n\\n\\n 22\\n\\f Those concerns are overstated and, in any case,\\nirrelevant. The shot clock begins to run once a wireless\\nprovider files its application, so it is already ticking before\\nany oral decision is made. If the locality fails to meet that\\ndeadline by not issuing a written decision before the shot\\nclock expires, the wireless provider can bring a claim for a\\n“failure to act.” 14 24 FCC Rcd. 13994, 14012 (2009). T\\nMobile asserts that requiring a separate failure-to-act suit, in\\naddition to a suit on the merits, undercuts the statutory\\npurpose of expedited judicial review, particularly in cases\\nwhere the locality has a “pattern and practice of not issuing a\\nwritten decision of land use denials unless or until [it] is\\nsued.” (Opening Br. at 7.) But the statute’s own remedies\\ncannot possibly undercut its purpose. A separate failure-to-\\nact claim is the very remedy Congress chose for shot clock\\nviolations. 24 FCC Rcd. 14013 at ¶ 4 (2009). Whether or not\\nT Mobile likes that policy choice, it is the one Congress\\nmade, and we are not free to change it.\\n\\n C. The Timing Requirement Is Not\\n Jurisdictional.\\n\\n Because we hold that a writing is required for a denial\\nto constitute a final action, T Mobile’s initial complaint was\\nnot ripe for review when filed. And, T Mobile’s\\nsupplemental complaint was filed more than 30 days after the\\nZBA issued its written decision and was therefore untimely\\nunder the TCA’s review provision. 47 U.S.C.\\n§ 332(c)(7)(B)(v). Thus, the District Court only had\\njurisdiction if T Mobile’s supplemental complaint cured the\\n\\n 14\\n It is not clear which time limit would have applied in\\nthis case and whether it would have been violated.\\n\\n\\n\\n\\n 23\\n\\fripeness flaw in its initial complaint by relating back to the\\noriginal filing date. If the 30-day time limit in the TCA’s\\nreview provision is nonjurisdictional, we can safely say that\\nrelation back is possible and allows a supplemental complaint\\nto cure a defective premature filing. 15 At the outset, then, we\\nmust determine whether that 30-day time limit is\\njurisdictional, being mindful both of the Supreme Court’s\\ncounsel to exercise caution before holding timing\\nrequirements to be jurisdictional and of its guidance regarding\\nwhat constitutes a jurisdictional limit. 16 Sebelius, 568 U.S. at\\n149, 153-54. Caution is indeed warranted because statutes of\\nlimitations and other filing deadlines “ordinarily are not\\njurisdictional.” Id. at 154; see also United States v. Kwai Fun\\nWong, 135 S. Ct. 1625, 1632 (2015) (“[M]ost time bars are\\nnonjurisdictional.”).\\n\\n\\n 15\\n We do not reach the issue of whether an unripe\\ncomplaint can be cured by a supplemental or amended\\npleading over which the Court lacked jurisdiction.\\n 16\\n The City claims that our decision in Nextel Partners\\nInc. v. Kingston Township, 286 F.3d 687 (3d Cir. 2002) is\\neffectively determinative. Not so. In Kingston Township,\\nthen-Judge Alito noted that the District Court had held the\\ntiming requirement in the TCA’s review provision was\\njurisdictional. Id. at 695. But we did not address whether\\nthat determination was correct, nor did we rely on it. Instead,\\nwe concluded that there could be no “failure to act” towards\\nan application that was not submitted. Id. at 692. Since our\\ndecision in that case, the Supreme Court has clarified the\\nprocess for determining if a time limit is jurisdictional.\\nSebelius, 568 U.S. at 149.\\n\\n\\n\\n\\n 24\\n\\f “[T]o ward off profligate use of the term ‘jurisdiction,’\\n[the Supreme Court has] adopted a readily administrable\\nbright line for determining whether to classify a statutory\\nlimitation as jurisdictional.” Sebelius, 568 U.S. at 153 (citing\\nArbaugh v. Y & H Corp., 546 U.S. 500, 516 (2006))\\n(quotation marks omitted). We are to ask “whether Congress\\nhas clearly state[d] that the rule is jurisdictional; absent such a\\nclear statement, we … should treat the restriction as\\nnonjurisdictional in character.” Id. (alteration in original)\\n(citation and quotation marks omitted); see also Musacchio v.\\nUnited States, 136 S. Ct. 709, 716 (2016) (Thus, “[w]e treat a\\ntime bar as jurisdictional only if Congress has ‘clearly stated’\\nthat it is.”). In deciding whether Congress has made such a\\nclear statement, “we evaluate the ‘text, context, and relevant\\nhistorical treatment.’” United States v. Kalb, 891 F.3d 455,\\n460 (2018) (quoting Reed Elsevier, 559 U.S. 154, 166\\n(2010)).\\n\\n Referencing that last test, Wilmington asserts that\\n“[s]ection 332’s statutory grant of jurisdiction to district\\ncourts, the text of the statute, the placement of the filing\\nwindow in that same section, and the well-established\\ntreatment of the filing window as jurisdictional, [all\\ndemonstrate] that the filing window is jurisdictional.”\\n(Answering Br. at 15.) We disagree. The differences\\nbetween the review provision’s timing requirement and the\\ntiming requirement we held to be jurisdictional in Kalb, and\\nthe similarities between the review provision’s timing\\nrequirements and those at issue in Sebelius and Musacchio,\\nwhich the Supreme Court held to be nonjurisdictional,\\nactually support treating the timing requirement in the TCA’s\\nreview provision as nonjurisdictional.\\n\\n\\n\\n\\n 25\\n\\f First, although Wilmington says that the text of the\\nstatute indicates Congress’s desire to make the 30-day timing\\nrequirement jurisdictional, the text does not use the term\\n“jurisdictional” or any variation of it to describe the timing\\nrequirement. 47 U.S.C. § 332(c)(7)(B)(v). To the contrary,\\nthe statute uses permissive rather than mandatory language.\\nUnlike the timing requirement we held to be jurisdictional in\\nKalb, which mandated that an action would be barred if not\\nfiled in time, the TCA’s review provision states that an action\\n“may” be filed within 30-days. Compare Kalb, 891 F.3d at\\n460 with 47 U.S.C. § 332(c)(7)(B)(v). The language is much\\ncloser to that which the Supreme Court decided was\\nnonjurisdictional in Sebelius. The statute at issue in that case,\\nlike the review provision here, uses a permissive phrase –\\n“may obtain a hearing” – before it states the timing\\nrequirement. 17 Compare Sebelius, 568 U.S. at 154, with 47\\nU.S.C. § 332(c)(7)(B)(v) (“may … commence an action”).\\nSimilar to the timing requirement the Supreme Court held to\\nbe nonjurisdictional in Musacchio, the review provision does\\nnot confer jurisdiction, instead it allows an action to be\\n\\n 17\\n T Mobile also points to Henderson v. Shinseki,\\nwhich held a timing requirement to be nonjurisdictional even\\nthough it used the mandatory “shall” before stating the timing\\nrequirement. 562 U.S. 428, 441-42 (2011). But the decision\\nin Shinseki, where the pertinent timing requirement could\\nhave barred a veteran’s appeal, was partly based on “the\\ncanon that provisions for benefits to members of the Armed\\nServices are to be construed in the beneficiaries’ favor,” and\\nso it is of less utility in deciding this dispute. Id. at 441\\n(quotation marks and citations omitted).\\n\\n\\n\\n\\n 26\\n\\fcommenced “in any court of competent jurisdiction.” See\\nMusacchio, 136 S. Ct. at 717 (“[The provision] does not\\nexpressly refer to subject-matter jurisdiction or speak in\\njurisdictional terms.”). The text of the statute therefore favors\\na holding that the timing requirement is nonjurisdictional.\\n\\n Wilmington next contends that the context of the\\ntiming requirement favors the view that the requirement is\\njurisdictional, because the Supreme Court has stated that it is\\n“inextricably linked to … the language that creates the right\\nof action[.]” (Answering Br. at 13-14 (citing City of Rancho\\nPalos Verdes v. Abrams, 544 U.S. 113, 125 (2005)).) Thus,\\nsays the City, the “filing window created by [the review\\nprovision] is jurisdictional [because] it is integral to the\\nexpress purpose of the section, to this Court’s jurisdiction,\\nand to the parties’ rights and obligations[.]” (Answering Br.\\nat 8.)\\n\\n True enough, the review provision’s timing\\nrequirement does appear in the same subsection as the\\nstatutory text granting jurisdiction. 47 U.S.C.\\n§ 332(c)(7)(B)(v). And, as we stated in Kalb, the Supreme\\nCourt’s decisions in Bowles v. Russell, 551 U.S. 205, 210\\n(2007), and Reed Elsevier, Inc. v. Muchnick, 559 U.S. at 166,\\nboth found the source of the timing requirement to be\\nimportant in determining whether that requirement was\\njurisdictional. 891 F.3d at 462. In Kalb, moreover, we made\\nthe same point the City now does, stating that a timing\\nrequirement was jurisdictional because “the thirty-day appeal\\nperiod here is embedded in the same statutory section that\\ngrants jurisdiction to the court of appeals.” Id.\\n\\n\\n\\n\\n 27\\n\\f But the location of the timing requirement within the\\nstatutory structure, without more, does not clearly reveal\\nCongressional intent. As noted by the Supreme Court in\\nSebelius, a timing requirement should not be classified as\\njurisdictional solely based on its placement in a jurisdictional\\nprovision. Sebelius, 568 U.S. at 155 (“A requirement we\\nwould otherwise classify as nonjurisdictional … does not\\nbecome jurisdictional simply because it is placed in a section\\nof a statute that also contains jurisdictional provisions.”\\n(citing Gonzalez v. Thaler, 565 U.S. 134, 146-47 (2012))). In\\nMusacchio too, the Supreme Court held that a timing\\nrequirement was nonjurisdictional despite its presence in the\\njurisdiction-granting section of the statute at issue. 136 S. Ct.\\nat 717. The Court emphasized that the statute did not directly\\nspeak of the timing requirement as jurisdictional, despite its\\nmandatory language. Id. That reasoning applies with at least\\nequal force here, so the context of the review provision’s\\ntiming requirement does not make the requirement\\njurisdictional.\\n\\n Finally, Wilmington asserts that the timing\\nrequirement is jurisdictional because of the historical\\ntreatment of similar provisions. The City asserts that the\\nphrase “within 30 days after” creates a “window,” during\\nwhich a complaint must be filed, and not a “deadline.”\\n(Answering Br. at 11-12 (citing W. Union Tel. Co. v. FCC,\\n773 F.2d 375, 377 (D.C. Cir. 1985)) (noting that “within 60\\ndays after” creates a 60-day filing window while “no later\\nthan 60 days after” creates a filing deadline).) But that\\nargument misses the point because it goes to whether the rule\\nbars suit between certain dates or only after a certain date, not\\nto whether the timing requirement is jurisdictional. See, e.g.,\\nUnion Tel. Co., 773 F.2d at 377-78 (discussing whether the\\n\\n\\n\\n\\n 28\\n\\ffiling window is a jurisdictional bar for suits filed before the\\nwindow opens). And just because a complaint may be unripe\\nbefore a particular date does not mean that a deadline by\\nwhich suit must be filed is jurisdictional. As we stated in\\nKalb, the Supreme Court’s decisions in Bowles and Reed\\nElsevier both looked to “the Court’s prior treatment of\\n[similar timing requirements.]” Kalb, 891 F.3d at 460. In\\nSebelius, the timing requirement, as here, used the phrase\\n“within” and thus, under Wilmington’s logic, it would have\\nbeen a jurisdictional limit. Sebelius, 568 U.S. at 154. But the\\nSupreme Court held otherwise, id., and that is of high\\nimportance.\\n\\n Because the text and context of this statute, and\\nhistorical treatment of timing requirements in similar statutes,\\ndo not reveal a clear intent from Congress to make the review\\nprovision’s timing requirement jurisdictional, we conclude\\nthat it is not. 18\\n\\n D. Rule 15 Allows a Supplemental Complaint\\n Filed After a Claims Processing Deadline To\\n Relate Back and Cure an Unripe Initial\\n Complaint.\\n\\n We next consider whether an untimely supplemental\\ncomplaint can, by relating back, cure an initial complaint that\\nwas unripe. We believe it can, and because T Mobile’s\\n\\n 18\\n That conclusion is further supported by the\\nthoughtful concurrence in Athens Cellular, concluding after\\nSebelius that the timing requirement “imposed by Congress in\\nthe TCA … is not a jurisdictional bar.” Athens Cellular, 886\\nF.3d at 1113 (Kaplan, J. concurring).\\n\\n\\n\\n\\n 29\\n\\fmotion to supplement its complaint was properly granted, that\\nsupplemental complaint relates back and is ripe. The District\\nCourt therefore had jurisdiction and should not have granted\\nWilmington’s motion for summary judgment.\\n\\n At the outset, we note that the parties do not dispute,\\nand we agree, that the District Court was within its discretion\\nto grant T Mobile’s motion to supplement its complaint.\\nPursuant to Federal Rule of Civil Procedure 15(d), “[o]n\\nmotion and reasonable notice, the [district] court may, on just\\nterms, permit a [moving] party to serve a supplemental\\npleading setting out any … event that happened after the date\\nof the pleading to be supplemented.” Fed. R. Civ. P. 15(d);\\nsee also 3 James Wm. Moore et al., Moore’s Federal Practice\\n¶ 15.30 (3d ed. 2018) (“Supplemental pleadings … are\\nlimited to subsequent events related to the claim or defense\\npresented in the original pleading.”). Here, the District Court\\nrightly granted T Mobile’s motion to supplement. That\\ndecision was just, since Wilmington had long since had notice\\nof the event – the filing of the written denial – that occurred\\nafter the initial pleading. After all, the City issued that denial,\\nand the denial was featured in the parties’ discovery plan.\\nThe issuance of it was also plainly related to T Mobile’s\\ninitial complaint.\\n\\n That the initial complaint was premature is not a bar\\nsince, under Rule 15(d), “[t]he court may permit\\nsupplementation even though the original pleading is\\ndefective in stating a claim for relief or defense.” Fed. R.\\nCiv. P. 15(d). As the Advisory Committee Notes make clear,\\n“Rule 15(d) is intended to give the [district] court broad\\ndiscretion in allowing a supplemental pleading.” Fed. R. Civ.\\nP. 15(d) advisory committee’s note to 1963 amendment. It is\\n\\n\\n\\n\\n 30\\n\\ffurthermore “within the discretion of the court to allow a\\nsupplemental pleading to be filed at any stage of the case[.]”\\nMoore et al., supra, ¶ 15.30. The District Court here was thus\\nwell within its discretion in granting T Mobile’s motion to\\nsupplement the complaint.\\n\\n Rule 15 does not indicate whether or under what\\ncircumstances a supplemental pleading can relate back to the\\ndate of the original pleading to avoid the effect of a time\\nlimit. 6A Charles Alan Wright et al., Federal Practice &\\nProcedure § 1508 (3d ed. 2018). Subsection (c) of the Rule,\\nwhich provides for the relation back of amended pleadings,\\ndoes not specifically refer to supplemental pleadings. Fed. R.\\nCiv. P. 15(c). Nor does Rule 15(d) make any mention of\\nrelation back. Fed. R. Civ. P. 15(d). But case law and\\nsecondary sources have long instructed that once a\\nsupplemental complaint is granted, it is treated like an\\namended complaint for purposes of relation back. 19 Thus,\\neven though Rule 15(d) is in a separate statutory provision\\nfrom Rule 15(c), a supplemental complaint can relate back.\\nWright et al., supra, § 1508; see also F.D.I.C. v. Knostman,\\n966 F.2d 1133, 1138 (7th Cir. 1992) (“The distinction\\nbetween an amended pleading and a supplemental pleading is\\n\\n 19\\n Courts have generally held that a supplemental\\ncomplaint is eligible for relation back, but rely on different\\nrationales to do so. See Wright et al., supra, § 1508 (“[S]ome\\ncourts have held that for purposes of applying the relation-\\nback doctrine a supplemental pleading may be treated as an\\namended pleading under Rule 15(c); other courts have\\napplied the relation-back principle directly to supplemental\\npleadings even though Rule 15(d) does not mention it.”)\\n(internal citations omitted).\\n\\n\\n\\n\\n 31\\n\\foften disregarded for purposes of relation back under Rule\\n15(c).”); Russell v. New Amsterdam Cas. Co., 303 F.2d 674,\\n680-81 (8th Cir. 1962) (finding supplemental pleading related\\nback despite plaintiff suing in the wrong capacity and not\\nachieving appropriate status for diversity jurisdiction until\\nafter the limitations period had expired). That stands to\\nreason, since, if a “defendant had notice of the subject matter\\nof the dispute and was not prejudiced in preparing a defense\\n…[,] the policy against stale claims becomes subsidiary to the\\npolicy expressed throughout the rules in favor of allowing a\\nparty to set forth all the grievances against another party in\\none action and resolving them on their merits.” Wright et al.,\\nsupra, § 1508.\\n\\n So a pleading filed according to Rule 15(d) can relate\\nback, assuming it meets “the basic test for relation back\\nprescribed by Rule 15(c).” Id.; see also Moore et al., supra,\\n¶ 15.30 (“A supplemental pleading may relate back to the\\ndate of the original complaint if the requirements under Rule\\n15(c) for relation back are satisfied”); Davis v. Piper Aircraft\\nCorp., 615 F.2d 606, 609 n.3 (4th Cir. 1980) (supplemental\\npleading relates back if Rule 15(c)’s test is met). In fact, as\\nthe District Court observed, if a supplemental complaint\\nmeets the requirements for relation back then “[r]elation back\\nis mandatory,” and not subject to additional equitable\\nconsiderations. 20 (App. at 6 (citing Arthur v. Maersk, Inc.,\\n434 F.3d 196, 202-03 (3d Cir. 2006)).)\\n\\n 20\\n We note, however, that “[a] party opposing the\\nintroduction of a supplemental pleading might wish to raise\\nthe statute-of-limitations defense when the additional\\npleading (1) alleges new matter that brings the earlier\\npleading up to date; (2) cures a defect in the original pleading;\\n\\n\\n\\n\\n 32\\n\\f Looking then to Rule 15(c), a complaint “relates back\\nto the date of the original pleading when … [it] asserts a\\nclaim or defense that arose out of the conduct, transaction, or\\noccurrence set out -- or attempted to be set out -- in the\\noriginal pleading[.]” Fed. R. Civ. P. 15(c)(1)(B). The\\nDistrict Court here concluded that there was no need to\\ndetermine whether T Mobile’s supplemental complaint\\nrelated back, because, even if it did, “it fail[ed] to cure the\\ndeficiencies of the initial complaint[.]” (App. at 8.) But\\ngiven our view that the supplemental complaint could indeed\\ncure the ripeness problem with the initial complaint, we must\\ncontend with the relation-back question.\\n\\n To determine if relation back is proper, the only issue\\nis whether there is a “common core of operative facts in the\\ntwo pleadings.” Bensel v. Allied Pilots Ass’n, 387 F.3d 298,\\n310 (3d Cir. 2004.) Here, that test is met. Both complaints\\nrely on the same core facts. The written denial was a\\ncertification and restatement of the earlier oral denial.\\n\\n Thus, the only question remaining is whether a\\ncomplaint that relates back can cure an untimely initial\\ncomplaint, and the answer is yes. The clear preference\\nembodied in Rule 15 is for merits-based decision making. Cf.\\nMoore et al., supra, ¶ 15.30 (“The same principles that\\nsupport the liberal amendment of pleadings also apply to\\nsupplemental pleadings.”). As the Supreme Court has stated,\\nthe purpose of Rule 15 is “to balance the interests of the\\n\\n\\nor (3) states a new claim that arose after the filing of the\\ncomplaint.” Wright et al., supra, § 1508.\\n\\n\\n\\n\\n 33\\n\\fdefendant protected by the statute of limitations with the\\npreference expressed in the Federal Rules of Civil Procedure\\nin general, and Rule 15 in particular, for resolving disputes on\\ntheir merits.” Krupski v. Costa Crociere S.p.A., 560 U.S. 538,\\n550 (2010). The requirements of Rule 15 itself protect\\ndefendants from an unfair relation back. 21 Under that Rule,\\ncourts “look[s] to whether the opposing party has had fair\\nnotice of the general fact situation and legal theory upon\\nwhich the amending party proceeds.” Bensel, 387 F.3d at\\n310. In this instance, Wilmington had sufficient notice since\\nthe supplemented complaint simply alleged the issuance of\\nthe ZBA’s written denial. And, of course, Wilmington had\\nnotice of everything in the supplemental complaint. It not\\nonly knew of the written denial and the reasons given, it\\ngenerated them.\\n\\n Relation back has been allowed to address\\njurisdictional problems. We said in Berkshire Fashions, Inc.\\nv. M.V. Hakusan II that relation back may be used to cure\\ndefects in jurisdictional allegations. 954 F.2d 874, 878 (3rd\\nCir. 1992). In that case, the District Court had dismissed the\\nplaintiff’s claim based on admiralty jurisdiction and denied\\nthe plaintiff’s motion to amend its complaint to allege\\ndiversity jurisdiction. Id. at 877. We concluded that both\\ndecisions were in error, holding that an amended complaint\\nrelates back and can cure insufficient pleading of subject\\nmatter jurisdiction. Id. at 878. Recently, our Circuit allowed\\n\\n 21\\n This is not a pass for endless delay in\\nsupplementing a complaint. Indeed, we have endeavored to\\nemphasize that whether to allow supplemental pleading\\ndepends on equitable considerations of fairness and notice\\nthat district courts must take into account.\\n\\n\\n\\n\\n 34\\n\\fa plaintiff to cure a diversity defect when the case had been\\nlitigated for years. See GBForefront, L.P., v. Forefront\\nMgmt. Grp., LLC, 888 F.3d 29, 32 (3d Cir. 2018)\\n(“instruct[ing] the [d]istrict [c]ourt to give leave to further\\namend the complaint … to cure defective jurisdictional\\nallegations”).\\n\\n Other circuits have held the same. See Woods v. Ind.\\nUniv.-Purdue Univ. at Indianapolis, 996 F.2d 880, 884 (7th\\nCir. 1993) (“Consistent with its history and purpose, Rule\\n15(c) has uniformly been applied to relate back [filings] that\\ncure defective statements of jurisdiction ….”); Boyce v.\\nAnderson, 405 F.2d 605, 607 (9th Cir. 1968) (allowing\\namendment alleging that no previous appeal had been taken\\nto the United States Court of Customs and Patent Appeals to\\ncure jurisdictional defect in complaint after statute of\\nlimitations had expired). That conclusion is also consistent\\nwith 28 U.S.C. § 1653, which allows “[d]efective allegations\\nof jurisdiction [to] be amended, upon terms, in the trial or\\nappellate courts.” Id.\\n\\n Courts have similarly permitted cure of actual defects\\nin the court’s jurisdiction, going beyond just jurisdictional\\nallegations. For instance, although not in a case involving a\\nlater complaint, the Supreme Court has said that a court can\\ndrop a dispensable non-diverse party to cure a defect in\\ndiversity jurisdiction. Newman-Green, Inc. v. Alfonzo-\\nLarrain, 490 U.S. 826, 837-38 (1989); see also E.R. Squibb &\\nSons, Inc. v. Lloyd’s & Cos., 241 F.3d 154, 163 (2d Cir.\\n2001) (stating that, “where it is appropriate to relate back an\\namendment to a pleading under Rule 15, jurisdiction is\\nassessed as if the amendment had taken place at the time the\\ncomplaint was first filed[,]” and thus replacing a non-diverse\\n\\n\\n\\n\\n 35\\n\\fplaintiff with a diverse plaintiff cured any jurisdiction\\nproblem); Rowe v. United States Fid. & Guar. Co., 421 F.2d\\n937, 939, 944 (4th Cir. 1970) (concluding that a defective\\ncomplaint could be cured by a later complaint that pled an\\nassignment occurring after the original complaint was filed).\\n\\n Nonetheless, “[a]mendments that go beyond the mere\\ncorrection or factual modification of the original pleading and\\nsignificantly alter the claim or defense alleged in that\\npleading are treated more cautiously by the courts in applying\\nthe relation-back doctrine.” Wright et al., supra, § 1497. The\\nSecond Circuit, for instance, only sometimes allows\\njurisdictional defects to be cured “when the underlying facts,\\nif properly pled, would have supported jurisdiction at the time\\nthe action commenced.” Correspondent Servs. Corp. v. First\\nEquities Corp. of Fla., 338 F.3d 119, 125 (2d Cir. 2003); see\\nalso, e.g., Barton v. Ellis, No. 75-1188, 1977 WL 15469, at\\n*1 (D.S.C. Apr. 26, 1977) (denying using relation back to\\ncure the original complaint since they were defects “not [in\\nthe] allegations of existing underlying jurisdictional facts but\\nrather [in] the prerequisite jurisdictional facts themselves”).\\nWilmington argues such hesitance is appropriate here because\\nallowing relation back to cure the jurisdictional problem with\\nT Mobile’s initial complaint “would allow two wrongs under\\nSection 332 [(filing early and filing late)] to make a right.”\\n(Answering Br. at 2.)\\n\\n We again disagree with the City. It is quite true that\\nT Mobile has made procedural matters more difficult than\\nthey should be in this case. But denying relation-back to cure\\nthe defect in this instance would not comport with Rule 15’s\\naim to encourage resolution of disputes on the merits\\nwhenever possible. The ripeness requirement exists so that\\n\\n\\n\\n\\n 36\\n\\fcourts avoid issuing essentially advisory opinions. See\\nRichard H. Fallon, Jr. et al., Hart and Wechsler’s the Federal\\nCourts and the Federal System 224 (5th ed. 2003) (noting that\\nthe ripeness doctrine allows courts to avoid a “dispute … too\\n‘ill-defined’ to be appropriate for judicial resolution until\\nfurther developments … more sharply framed the issues for\\ndecision.”). That concern ceased to exist here once the\\nsupplemental pleading was in place. At that point, the dispute\\nhad matured and become capable of judicial review,\\ndemonstrating that, “actions taken after the filing of the initial\\ncomplaint can be used to establish subject matter\\njurisdiction.” Prasco, LLC v. Medicis Pharm. Corp., 537\\nF.3d 1329, 1337 (Fed. Cir. 2008).\\n\\n If a supplemental complaint cannot cure an unripe\\ncomplaint, an endless feedback loop would be created\\nwhereby the ripeness problem could never be overcome, even\\nthough, as here, the dispute later became obviously ripe. Our\\nsister circuits have recognized that problem and concluded\\nthat a supplemental complaint is the solution. 22 In Wilson v.\\nWestinghouse Electric Corp., the Eighth Circuit determined\\nthat prohibiting an amended (or supplemental) complaint\\nfrom alleging facts that occurred after the date the initial\\n\\n 22\\n In our Circuit, a thoughtful district court decision\\nhad long ago reached that conclusion. It held that an\\nuntimely supplement adding facts occurring after the initial\\nfiling that showed exhaustion of administrative remedies\\ncould relate back to the initial premature complaint and allow\\nmaintenance of the lawsuit. Bates v. W. Elec., 420 F. Supp.\\n521, 526-27 (E.D. Pa. 1976).\\n\\n\\n\\n\\n 37\\n\\fcomplaint was filed would turn a premature complaint into an\\n“irretrievable mistake that bars jurisdiction” and would be\\n“precisely the kind of procedural mousetrap that the Federal\\nRules were designed to dismantle.” 838 F.2d 286, 289 (8th\\nCir. 1988). The court held that, “[e]ven when the District\\nCourt lacks jurisdiction over a claim at the time of its original\\nfiling, a supplemental complaint may cure the defect by\\nalleging the subsequent fact which eliminates the\\njurisdictional bar.” Id. at 290 (citing Mathews, 426 U.S. at\\n75). While Wilson addressed a circumstance in which the\\nsupplemental complaint was timely filed, the proposition still\\napplies in a case like ours because, if a party was limited to\\nrefiling within an applicable time limit, there would be little\\nneed to make provision for supplementation of a complaint,\\nas a new complaint could be filed. 23\\n\\n 23\\n We note that sparing the cost of refiling and\\nproviding convenience to the Court would remain legitimate\\nreasons for allowing supplemental complaints. But the\\npurpose of Rule 15(d) is broader. See Wright et al., supra, §\\n1504 (“The purpose of subdivision (d) is to promote as\\ncomplete an adjudication of the dispute between the parties as\\nis possible. … A supplemental pleading may be employed\\nfor a variety of purposes.”). Wilmington contends that\\nWilson is inapposite since it involved a timely supplemental\\ncomplaint. Thus, concern about a perpetual loop outcome\\nwas not proper because the plaintiff could have simply refiled\\nhis complaint. But we agree that “a plaintiff need not\\ncommence a new action when after-occurring events\\ndemonstrate that it has a right to relief even if the original\\ncomplaint was insufficient. A plaintiff may also be allowed\\nto supplement the complaint even if jurisdiction … would not\\nhave been proper if the claim had been asserted in an\\n\\n\\n\\n\\n 38\\n\\f The Ninth Circuit, in Security Insurance Co. of New\\nHaven v. United States ex rel. Haydis, also relied on that logic\\nto find that relation back could cure an unripe complaint filed\\nbefore a statutory filing window opened. 338 F.2d 444, 448-\\n49 (9th Cir. 1964). In a fact scenario with striking similarities\\nto the present appeal, the plaintiff had filed its claim before a\\nstatutory waiting period was over and then did not file an\\namended complaint until after the statute of limitations period\\nhad run. Id. at 445-46. The appeals court held that the\\ndistrict court was “not required to apply the doctrine of\\nrelation back so literally as to carry it to a time [before it was\\nripe] so as to prevent the maintenance of the action in the first\\nplace.” Id. at 449.\\n\\n The Supreme Court has favorably cited Security\\nInsurance’s ruling. In Mathews, the plaintiff had not satisfied\\na precondition of filing a complaint by first filing an\\napplication with a particular agency. 426 U.S. at 72, 75. The\\nCourt noted that a supplemental complaint, alleging that the\\napplication had since been filed, would have cured the\\njurisdictional defect. Id. at 75. In saying so, the Court relied\\n\\n\\n\\nindependent action.” Moore et al., supra, ¶ 15.30 (3d ed.\\n2018) (citation omitted). If supplemental complaints could\\nnot cure ripeness, “then all supplemental pleadings of this\\nnature would be defeated for lack of jurisdiction – [the]\\n‘procedural mousetrap’ would render all supplemental\\npleadings void.” George v. IRS, No. C05-00955 MJJ, 2006\\nWL 3499230, at *3 (N.D. Cal. Dec. 4, 2006) (citation\\nomitted).\\n\\n\\n\\n\\n 39\\n\\fon Security Insurance. Id. at 75 n.8 (citing Security\\nInsurance, 338 F.2d at 447-49). 24\\n\\n Yet Wilmington asserts that ripeness can never be\\ncured by a later complaint. It advances four cases for that\\nproposition, but none are helpful. First, the City cites\\nDelaware Riverkeeper Network v. Secretary Pennsylvania\\nDepartment of Environmental Protection, (Riverkeeper I),\\n833 F.3d 360 (3d Cir. 2016), in which we concluded that,\\n“even though the underlying claim became ripe for review\\nduring the pendency of the case, the ripening of the claim did\\nnot cure deficient pleadings.” (App. at 8.) In that case,\\nhowever, no attempt to file a later complaint alleging ripeness\\nwas made. Riverkeeper I, 833 F.3d at 369-70.\\n\\n Likewise, in another two of the four cases that\\nWilmington cites, there was no effort made to amend or\\nsupplement the complaint. See TeleSTAR, Inc. v. FCC, 888\\nF.2d 132, 134 (D.C. Cir. 1989) (concluding non-final agency\\naction at the time of filing of petition may only be reviewed\\nupon the filing of another petition); W. Union Tel. Co., 773\\nF.2d at 377-78 (concluding that the court lacked jurisdiction\\nover challenges filed before the action became final).\\nTherefore, neither case determined whether relation back of a\\nlater-filed complaint could cure a ripeness problem in the\\ninitial complaint.\\n\\n 24\\n Wilmington contends that Mathews is inapposite\\nsince the statute of limitations was waived. That argument\\nhas no traction since, if it were a jurisdictional bar, it could\\nnot be waived.\\n\\n\\n\\n\\n 40\\n\\f The City fares no better relying on Council Tree\\nCommunications v. FCC, in which we stated that “[a] petition\\nto review a non-final agency order is incurably premature.”\\n503 F.3d 284, 291 (3d Cir. 2007). At no point in that case\\nwas the complaint ripe, and the petitioner still had a petition\\nfor reconsideration pending before the relevant agency on the\\ndate the case was decided. Id. at 287. Furthermore, Council\\nTree explicitly acknowledged that a supplemental complaint\\ncan cure an unripe complaint when there is jurisdiction over\\nthat supplemental pleading. See id. at 291 (“[W]e note that\\n‘nothing prevented [the petitioners] from supplementing their\\npremature petition with a later protective petition.’” (second\\nalteration in original) (quoting Horsehead Res. Dev. Co. v.\\nE.P.A., 130 F.3d 1090, 1095 (D.C. Cir. 1997))).\\n\\n Wilmington also makes three policy arguments in\\nsupport of its position that an untimely supplemental\\ncomplaint should not be able to cure an unripe complaint.\\nFirst, it contends that allowing suits to be filed before an\\naction is ripe would “extend[] federal court jurisdiction over\\nlocal government actions before those actions are final[.]”\\n(Answering Br. at 9.) Second, such filings would waste\\njudicial resources and, in this case, cost taxpayers money, by\\nforcing courts to deal with a higher volume of unripe\\ncomplaints. Third, the purpose of § 332 is to preserve local\\nzoning authority, which would be undermined by allowing\\nplaintiffs to file suit early and thereby places undue pressure\\non zoning commissions.\\n\\n Those contentions, however, are unpersuasive. First, a\\ncourt would remain without jurisdiction if the claim had not\\nripened by the time of the supplemental complaint. Second, it\\n\\n\\n\\n\\n 41\\n\\fseems that Wilmington overstates the impact that a decision\\nallowing an unripe complaint to be cured would have, since\\nour holding today makes it clear that an action is not final\\nuntil a written decision has been issued. Clarifying when a\\ndetermination is ripe for review should end any incentive for\\naggrieved parties to file early to ensure they have not filed too\\nlate.\\n\\n Perhaps more importantly, however, courts can police\\nany potential abuse on a case-by-case basis using Rule 15(d)\\nand the Rule 15(c) test for relation back. It is understood that\\n“relation back of a supplemental pleading should not result in\\nproviding unfair procedural advantages to a plaintiff[,] so …\\nrelation back may not be for all purposes.” Wright et al.,\\nsupra, § 1508. But here no unfair advantage has resulted, and\\ndefendants in general will be adequately protected by a\\ndistrict court’s Rule 15(d) analysis, which will determine if a\\nsupplemental complaint should be allowed at all. For\\ninstance, if a locality’s action is not yet a final action at the\\ntime a Rule 15(d) motion is filed, the motion can easily be\\ndenied. See Beezley v. Fremont Indem. Co., 804 F.2d 530,\\n530 (9th Cir. 1986) (supplemental pleading denied when it\\nstill failed to cure defective original pleading).\\n\\n When all is said and done here, we conclude that, to\\neffectuate the liberal purpose of Rule 15 and to avoid the\\nendless feedback loop that the City’s legal argument would\\ncreate, Rule 15 allows an untimely supplemental complaint to\\nrelate back and cure an unripe initial complaint.\\n\\n\\n\\n\\n 42\\n\\fIII. CONCLUSION\\n\\n For the foregoing reasons, we will reverse the District\\nCourt’s grant of the City’s motion for summary judgment,\\nvacate the District Court’s denial of T Mobile’s motion for\\nsummary judgment, and remand to the District Court for\\nfurther proceedings consistent with this opinion.25\\n\\n\\n\\n\\n 25\\n We will vacate the District Court’s denial of\\nT Mobile’s motion for summary judgment because it was\\nsolely based on a finding that T Mobile’s suit was not timely\\nbrought.\\n\\n\\n\\n\\n 43\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":62,"cells":{"id":{"kind":"number","value":4582001,"string":"4,582,001"},"name":{"kind":"string","value":"UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427"},"name_abbreviation":{"kind":"string","value":"United States v. Herbert Vederman"},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"16-4397; 16-4410; 16-4411; 16-4427; 17-1346"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith, Greenaway, Krause\", \"parties\": \"\", \"opinions\": [{\"author\": \"SMITH, Chief Judge\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n Nos. 16-4397, 16-4410, 16-4411,\\n 16-4427, 17-1346\\n _____________\\n\\n UNITED STATES OF AMERICA\\n Appellant in 17-1346\\n\\n v.\\n\\n CHAKA FATTAH, SR.,\\n Appellant in 16-4397\\n\\n KAREN NICHOLAS,\\n Appellant in 16-4410\\n\\n ROBERT BRAND,\\n Appellant in 16-4411\\n\\n HERBERT VEDERMAN,\\n Appellant in 16-4427\\n _____________\\n\\nOn Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n District Court Nos. 2-15-cr-00346-001,\\n\\f 2-15-cr-00346-002, 2-15-cr-00346-003,\\n 2-15-cr-00346-004\\n District Judge: The Honorable Harvey Bartle III\\n\\n Argued January 18, 2018\\n\\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\\n KRAUSE, Circuit Judges\\n\\n (Filed: January 16, 2019)\\n\\nAndrea G. Foulkes\\nEric L. Gibson\\nPaul L. Gray\\nRobert A. Zauzmer\\nOffice of United States Attorney\\n615 Chestnut Street\\nSuite 1250\\nPhiladelphia, PA 19106\\n\\nJonathan Ian Kravis [ARGUED]\\nUnited States Department of Justice\\nCriminal Division, Public Integrity Section\\n1400 New York Avenue, N.W.\\nWashington, DC 20005\\n Counsel for the United States\\n\\nMark M. Lee\\nBruce P. Merenstein [ARGUED]\\nSamuel W. Silver\\n 2\\n\\fSchnader Harrison Segal & Lewis\\n1600 Market Street\\nSuite 3600\\nPhiladelphia, PA 19103\\n Counsel for Appellant Fattah\\n\\nAnn C. Flannery [ARGUED]\\nSuite 2700\\n1835 Market Street\\nPhiladelphia, PA 19103\\n\\nLisa A. Mathewson\\nSuite 810\\n123 South Broad Street\\nPhiladelphia, PA 19109\\n Counsel for Appellant Nicholas\\n\\nAlan Silber\\nPashman Stein Walder Hayden\\n21 Main Street\\nSuite 200\\nHackensack, NJ 07601\\n Counsel for National Association of Criminal\\n Defense Lawyers, Amicus Appellant Nicholas\\n\\nMira E. Baylson\\nBarry Gross [ARGUED]\\nMeredith C. Slawe\\nDrinker Biddle & Reath\\nOne Logan Square\\n 3\\n\\fSuite 2000\\nPhiladelphia, PA 19103\\n Counsel for Appellant Brand\\n\\nHenry W. Asbill\\nBuckley Sandler\\n1250 24th Street, N.W.\\nSuite 700\\nWashington, DC 20037\\n\\nGlen D. Nager [ARGUED]\\nJacob M. Roth\\nJulia W. M. F. Sheketoff\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n Counsel for Appellant Vederman\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nSMITH, Chief Judge.\\n\\n\\n\\n\\n 4\\n\\f Table of Contents\\nI. Introduction ................................................................... 8\\nII. Background .................................................................. 9\\n A. The Fattah for Mayor Scheme ................................. 9\\n 1. The Lord Loan and Its Repayment ..................... 10\\n 2. The College Tuition Component of the FFM\\n Scheme ................................................................ 27\\n 3. The NOAA Grant and the Phantom Conference 28\\n B. The Blue Guardians Scheme.................................. 31\\n C. The Fattah–Vederman Bribery Scheme................. 33\\n D. The Indictment and Trial ....................................... 39\\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\\n A. Investigation of Alleged Juror Misconduct ........... 58\\n B. Dismissal of Juror 12 ............................................. 64\\nIV. The District Court’s Instructions Under McDonnell 70\\n A. The McDonnell Framework................................... 71\\n B. The Kirk Meeting ................................................... 76\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship.......................................................... 79\\n D. The Zionts Hiring .................................................. 82\\n E. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23.................................................................... 89\\n F. Blue Guardians ....................................................... 91\\n\\n 5\\n\\fV. Sufficiency of the Evidence for the RICO Conspiracy\\nConviction ...................................................................... 95\\nVI. Variance from the Indictment and Sufficiency of the\\nEvidence for Count 2.................................................... 110\\nVII. The District Court’s Instruction to the Jury on the\\nMeaning of Intent ......................................................... 120\\nVIII. Sending the Indictment to the Jury ...................... 126\\nIX. The District Court’s Evidentiary Rulings .............. 129\\n A. The District Court’s Application of Rule 404(b) 129\\n B. Evidentiary Rulings Regarding Nicholas’s\\n Defense ..................................................................... 134\\n 1. The EAA Board Minutes .................................. 134\\n 2. Jones’ Memory Regarding Other Contracts ..... 136\\n 3. Exclusion of NOAA Evidence.......................... 137\\n C. The Cooperating Witness’s Mental Health\\n Records ..................................................................... 138\\n 1. The District Court’s Denial of Access to the\\n Mental Health Records ..................................... 140\\n 2. The District Court’s Grant of the Motion in\\n Limine ............................................................... 142\\nX. The Government’s Cross-Appeal ............................ 147\\n A. CUMA is a Mortgage Lending Business............. 148\\n B. Sufficiency of the Evidence ................................. 155\\nXI. Prejudicial Spillover ............................................... 158\\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\\n 6\\n\\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\\nXII. Conclusion ............................................................ 164\\n\\n\\n\\n\\n 7\\n\\f I. Introduction\\n Chaka Fattah, Sr., a powerful and prominent fixture\\nin Philadelphia politics, financially overextended himself\\nin both his personal life and his professional career during\\nan ultimately unsuccessful run for mayor. Fattah received\\na substantial illicit loan to his mayoral campaign and used\\nhis political influence and personal connections to engage\\nfriends, employees, and others in an elaborate series of\\nschemes aimed at preserving his political status by hiding\\nthe source of the illicit loan and its repayment. In so doing,\\nFattah and his allies engaged in shady and, at times, illegal\\nbehavior, including the misuse of federal grant money and\\nfederal appropriations, the siphoning of money from\\nnonprofit organizations to pay campaign debts, and the\\nmisappropriation of campaign funds to pay personal\\nobligations.\\n Based upon their actions, Fattah and four of his\\nassociates—Herbert Vederman, Robert Brand, Bonnie\\nBowser, and Karen Nicholas—were charged with\\nnumerous criminal acts in a twenty-nine count indictment.\\nAfter a jury trial, each was convicted on multiple counts.\\nAll but Bowser appealed. As we explain below, the\\nDistrict Court’s judgment will be affirmed in part and\\nreversed in part.\\n\\n\\n\\n\\n 8\\n\\f II. Background1\\n During the 1980s and ’90s, Fattah served in both\\nhouses of the Pennsylvania General Assembly, first as a\\nmember of the House of Representatives and later as a\\nSenator. In 1995, Fattah was elected to the United States\\nHouse of Representatives for Pennsylvania’s Second\\nCongressional District. In 2006, Fattah launched an\\nunsuccessful run for Mayor of Philadelphia, setting in\\nmotion the events that would lead to his criminal\\nconviction and resignation from Congress ten years later.\\n\\n A. The Fattah for Mayor Scheme\\n Fattah declared his candidacy for mayor in\\nNovember of 2006. Thomas Lindenfeld, a political\\nconsultant on Fattah’s exploratory committee, believed\\nthat “[a]t the beginning of the campaign, [Fattah] was a\\nconsiderable . . . candidate and somebody who had a very\\nlikely chance of success.” JA1618. But Fattah’s campaign\\nsoon began to experience difficulties, particularly with\\nfundraising. Philadelphia had adopted its first-ever\\ncampaign contribution limits, which limited contributions\\nto $2,500 from individuals and $10,000 from political\\naction committees and certain types of business\\norganizations. Fattah’s fundraising difficulties led him to\\n\\n\\n\\n1\\n The facts are drawn from the trial record unless otherwise\\nnoted.\\n 9\\n\\fseek a substantial loan, far in excess of the new\\ncontribution limits.\\n\\n 1. The Lord Loan and Its Repayment\\n While serving in Congress, Fattah became\\nacquainted with Albert Lord, II. The two first met around\\n1998, when Lord was a member of the Board of Directors\\nof Sallie Mae.\\n As the May 15, 2007 primary date for the\\nPhiladelphia mayoral race approached, Fattah met Lord to\\nask for assistance, telling Lord that the Fattah for Mayor\\n(FFM) campaign was running low on funds. Fattah asked\\nLord to meet with Thomas Lindenfeld, a political\\nconsultant in Washington, D.C., and part-owner of LSG\\nStrategies, Inc. (Strategies), a company that was working\\nwith the FFM campaign and that specialized in direct voter\\ncontact initiatives. Lindenfeld had been part of the\\nexploratory group that initially considered Fattah’s\\nviability as a candidate for mayor. Lindenfeld had known\\nFattah since 1999, when Fattah endorsed Philadelphia\\nMayor John Street. Through Fattah, Lindenfeld had also\\ngotten to know several of Fattah’s associates, including\\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\\nHerbert Vederman, a businessman and former state\\nofficial, was the finance director for the FFM campaign.\\nRobert Brand owned Solutions for Progress (Solutions), a\\n“Philadelphia-based public policy technology company,\\nwhose mission [was] to deliver technology that directly\\nassists low and middle income families [in obtaining]\\n 10\\n\\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\\nStaff and campaign treasurer, and served in his district\\noffice in Philadelphia.\\n Lord’s assistant contacted Lindenfeld to arrange a\\nmeeting, and Lindenfeld informed Fattah that he would be\\nmeeting with Lord. Lindenfeld, along with his partner,\\nMichael Matthews, met with Lord and discussed Fattah’s\\nneed for funds to mount an intensive media campaign.\\nAfter that meeting, Lindenfeld reported to Fattah that Lord\\nwanted to help, but that they had not discussed a specific\\ndollar amount. Approximately a week later, Fattah\\ninstructed Lindenfeld to meet with Lord a second time.\\nLord “wanted to know if he could give a substantial\\namount of money, a million dollars” to Fattah’s campaign.\\nJA1630. That prompted Lindenfeld to reply that the\\namount “would be beyond the campaign finance limits.”\\nId.\\n\\n Lord proposed a solution: he offered to instead give\\na million dollars to Strategies in the form of a loan. To that\\nend, Lindenfeld had a promissory note drafted which\\nspecified that Lord was lending Strategies $1 million, and\\nthat Strategies promised to repay the $1 million at 9.25%\\ninterest, with repayment to commence January 31, 2008.\\nLindenfeld later acknowledged that the promissory note\\nwould make it appear as though Lord’s $1 million was not\\na contribution directly to the Congressman, although he\\nknew that it was actually a loan to the FFM campaign.\\nIndeed, Lindenfeld confirmed with Fattah that neither\\n\\n 11\\n\\fLindenfeld nor Strategies would be responsible for\\nrepayment. With that understanding, Lindenfeld executed\\nboth the note and a security agreement purporting to\\nencumber Strategies’ accounts receivable and all its assets.\\n\\n On May 1, shortly before the primary election, Lord\\nwired $1 million to Lindenfeld. Lindenfeld held the money\\nin Strategies’ operating account until Fattah told him how\\nit was to be spent. Some of the money was eventually used\\nfor print materials mailed directly to voters. And, at\\nFattah’s direction, Lindenfeld wired a substantial sum to\\nSydney Lei and Associates (SLA), a company owned by\\nGregory Naylor which specialized in “get out the vote”\\nefforts.\\n Naylor had known Fattah for more than 30 years.2\\nDuring the campaign, Naylor worked as the field director\\nand was in charge of getting out the vote on election day.\\n\\n2\\n Naylor first worked with Fattah when he was in the state\\nlegislature. When Fattah was elected to Congress, Naylor\\nworked in his Philadelphia office. Naylor met Nicholas\\nwhen she joined Fattah’s staff at some point in the 1990s.\\nAfter concluding her employment with Fattah’s office,\\nNicholas worked with the Educational Advancement\\nAlliance (EAA), an education nonprofit entity founded by\\nFattah. This entity helped to recruit underrepresented\\nstudents for scholarship and college opportunities. Around\\n2009, Naylor left Fattah’s office to work exclusively with\\nSLA. Naylor also knew Brand.\\n 12\\n\\fOn the final day of the campaign, Naylor worked with\\nVederman, who allowed Naylor to use his credit card to\\nrent vans that would transport Fattah voters to the polls.\\n As the primary date neared, Fattah and Naylor knew\\nthe campaign was running out of money. The campaign\\nwas unable to finance “media buys,” and Naylor needed\\nmoney for field operations to cover Philadelphia’s more\\nthan one thousand polling places. In early May,\\nLindenfeld called Naylor to say that Lindenfeld “would be\\nsending some money [Naylor’s] way.” JA3057. Within\\ndays, SLA received a six-figure sum for Naylor to use in\\nthe campaign and on election day. Naylor used the money\\nto pay some outstanding bills, including salaries for FFM\\nemployees, and allocated $200,000 to field operations for\\nelection day.\\n\\n Fattah lost the mayoral primary on May 15, 2007.\\nAfterward, Lindenfeld spoke with Fattah, Naylor and\\nBowser about accounting for the FFM campaign money\\nfrom Lord that had been spent. They decided that the\\namounts should not appear in the FFM campaign finance\\nreports, and Fattah instructed Naylor to have his firm,\\nSLA, create an invoice. Naylor did so, creating an invoice\\ndated June 1, 2007 from SLA to FFM, seeking payment of\\n$193,580.19. Naylor later acknowledged that the FFM\\ncampaign did not actually owe money to SLA, and that the\\nfalse invoice was created to “hide the transaction that took\\nplace earlier” and “make it look like [SLA] was owed\\nmoney.” JA3075–76. Although FFM did not owe SLA\\n\\n 13\\n\\fanything for the election day expenses, the FFM campaign\\nfinance reports from 2009 through 2013 listed a $20,000\\nin-kind contribution from SLA for each year, thereby\\nlowering FFM’s alleged outstanding debt to SLA.\\n\\n Of the total $1 million Lord loan, $400,000 had not\\nbeen spent. Lindenfeld returned that sum to Lord on June\\n3, 2007. He included a cover letter which stated: “As it\\nturns out the business opportunities we had contemplated\\ndo not seem to be as fruitful as previously expected.”\\nJA1254. Lindenfeld later admitted that there were no such\\n“business opportunities” and that the letter was simply an\\neffort to conceal the loan.\\n In late 2007, faced with financial pressures, Lord\\nasked his son, Albert Lord, III, to collect the outstanding\\n$600,000 balance on the loan to Strategies. Lord III\\ncontacted Lindenfeld about repayment and expressed a\\nwillingness to forgive the interest owed if the principal\\nwas paid. Lindenfeld immediately called Fattah and\\ninformed him that repayment could not be put off any\\nlonger. Fattah told Lindenfeld more than once that “[h]e\\nwould take care of it,” JA1652, but Fattah did not act.\\nNeeding someone who might have Fattah’s ear,\\nLindenfeld reached out to Naylor and Bowser. Naylor\\ntalked to Fattah on several occasions and told him that\\nLindenfeld was under considerable pressure to repay the\\nloan. Fattah told Naylor more than once that he was\\n“working on it.” JA3082–83.\\n\\n\\n 14\\n\\f During his political career, Fattah had focused on\\neducation, especially for the underprivileged. Indeed,\\nFattah founded two nonprofit organizations: College\\nOpportunity Resources for Education (CORE), and the\\nEducational Advancement Alliance (EAA).\\n\\n EAA held the annual Fattah Conference on Higher\\nEducation (the “annual conference”) to acquaint high\\nschool students with higher education options. JA3079.\\nSallie Mae regularly sponsored the conference. According\\nto Raymond Jones, EAA’s chairman of the board from\\n2004 through 2007, EAA offered a variety of programs to\\nprovide “marginalized students with educational\\nopportunities so they could continue and go to college.”\\nJA1360. EAA was funded with federal grant money which\\ncould only be spent for the purposes described in the\\nparticular grant. Karen Nicholas served as EAA’s\\nexecutive director, handling the organization’s day-to-day\\nadministrative responsibilities. Nicholas had previously\\nbeen a staffer for Fattah when he was a member of\\nPennsylvania’s House of Representatives.\\n CORE was an organization that awarded\\nscholarships to graduating high school students in\\nPhiladelphia who had gained admission to a state\\nuniversity or the Community College of Philadelphia.\\nCORE received funding from a variety of sources,\\nincluding Sallie Mae. Because CORE also received\\nfederal funds, and because EAA had experience working\\nwith federal grants, EAA received and handled the federal\\n\\n 15\\n\\ffunds awarded to CORE. In short, EAA functioned as a\\nfiduciary for CORE. When money became a problem for\\nthe FFM campaign, Fattah’s involvement with EAA and\\nCORE soon became less about helping underprivileged\\nstudents, and more about providing an avenue for\\ndisguising efforts to repay the illicit campaign funds from\\nLord.\\n\\n On January 7, 2008, Robert Brand contacted Fattah\\nby telephone. Shortly thereafter, Lindenfeld received an\\nunexpected call from Brand proposing an arrangement for\\nBrand’s company, Solutions, to work with Strategies.\\nSolutions had developed a software tool called “The\\nBenefit Bank,” which was designed to “assist low and\\nmoderate income families to have enhanced access to\\nbenefits and taxes.” JA1993. During the telephone call,\\nBrand referred to The Benefit Bank and suggested a\\ncontract under which Strategies would be paid $600,000\\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\\nBrand followed up on his call to Lindenfeld with an email\\nabout “develop[ing] a working relationship where you\\ncould help us to grow The Benefit Bank and our process\\nof civic engagement. While I know this is not your core\\nbusiness I would like to try to convince you to take us on\\nas a client.” JA6427. Lindenfeld responded that he was\\ninterested. To Lindenfeld, “this was the way that\\nCongressman Fattah was going to repay the debt to Al\\nLord.” JA1654. When Lindenfeld called Fattah and told\\nhim of the contact from Brand, Fattah simply replied that\\nLindenfeld “should just proceed.” JA1666–67.\\n 16\\n\\f A few days later, Brand emailed Nicholas at EAA a\\nproposal from Solutions concerning The Benefit Bank,\\nwhich sought EAA’s support in developing an education\\nedition of The Benefit Bank and a $900,000 upfront\\npayment.\\n\\n As the January 31 date for repayment of the balance\\nof the $1 million Lord loan approached, a flurry of activity\\ntook place. On January 24, both Raymond Jones, chair of\\nthe EAA Board, and Nicholas signed a check from EAA\\nmade out to Solutions in the amount of $500,000.\\nAlthough no contract existed between EAA and Solutions,\\nthe memo line of the check indicated that it was for a\\ncontract, and Nicholas entered it into EAA’s ledger.3\\n\\n That same day, Ivy Butts, an employee of\\nStrategies, emailed Lindenfeld the instructions Brand\\nwould need to wire the $600,000 balance on the Lord loan.\\n\\n3\\n Raymond Jones, who was EAA’s Chairman of the Board\\nfrom 2004 through 2007, recalled at trial that the Board\\nhad a limit on the amount that Nicholas could spend\\nwithout board approval. JA1358, 1369. Nicholas was\\nauthorized to sign contracts on behalf of EAA for no more\\nthan $100,000. JA1369–71. Jones did not recall the\\ncontract between EAA and Solutions, nor did the EAA\\nboard minutes for December 2007, February 2008, or May\\n2008 refer to the EAA–Solutions contract or to the\\nsubstantial upfront payment of half a million dollars upon\\nexecution of the agreement. JA6358–63; 6567.\\n 17\\n\\fWithin minutes, Lindenfeld forwarded that email to Brand\\nat Solutions. Brand then made two telephone calls to\\nFattah. By late afternoon, Brand emailed Nicholas,\\ninforming her that he had “met with all the people I need\\nto meet with and have a pretty clear schedule of what\\nworks best for us. I am also seeing what line of credit we\\nhave to stretch out the payments until you get your line of\\ncredit in place.” JA6558. Brand asked if they could talk\\nand “finalize this effort.” JA6558. On January 25 and 26,\\nthere were a number of calls between Fattah, Brand, and\\nNicholas.\\n\\n On Sunday January 27, at 5:46 pm, Brand\\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\\na revised contract between EAA and Solutions for the\\nengagement of services. Brand indicated he would send\\nsomeone to pick up the check at about 1:00 pm the\\nfollowing day. The revised contract called for the same\\n$900,000 payment from EAA to Solutions, yet specified\\nthat $500,000 was to be paid on signing, with $100,000\\ndue three weeks later, and another $100,000 to be paid six\\nweeks out. No due date for the $200,000 balance was\\nspecified. The terms of the contract called for EAA to\\nassist Solutions with further developing The Benefit Bank.\\nIn addition, under the contract, EAA would receive certain\\n\\n\\n\\n\\n 18\\n\\ffunds from the Commonwealth of Pennsylvania for a\\nprogram relating to FAFSA applications. 4\\n\\n The same evening, Brand sent Lindenfeld a contract\\nentitled “Cooperative Development Agreement to Provide\\nServices to Solutions for Progress, Inc. for Growth of The\\nBenefit Bank.” JA6569. The agreement proposed a\\nworking partnership in which Strategies would work with\\nSolutions to identify and secure a Benefit Bank affiliate in\\nthe District of Columbia and two other states, and to\\nfacilitate introductions to key officials in other states\\nwhere The Benefit Bank might expand. The terms of the\\nagreement provided that Solutions would pay $600,000 to\\nStrategies by January 31, 2008, which would “enable\\n[Strategies’] team to assess opportunities and develop\\ndetailed work plans for each area.” JA6572. Brand copied\\nSolutions’ Chief Financial Officer, Michael Golden.\\nLindenfeld responded to Brand’s email within a minute,\\nasking if Brand had received the wiring instructions.\\nBrand immediately confirmed that he had.\\n\\n Concerned that Solutions did not have $600,000 to\\npay Strategies, Golden talked to Brand, who informed him\\nthat Solutions would be receiving a check for $500,000\\nfrom EAA. Early the next morning, Nicholas responded to\\nBrand’s email from the night before. She advised Brand\\nthat he could pick up the check, “but as I stated I am not\\n\\n4\\n FAFSA is an acronym for Free Application for Federal\\nStudent Aid.\\n 19\\n\\fin a position to sign a contract committing funds that I am\\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\\nsame day, a $540,000 transfer was made from the\\nconference account, which EAA handled, into EAA’s\\nchecking account. The conference account was maintained\\nto handle expenses for Fattah’s annual higher education\\nconference. Prior to this transfer, EAA had only\\n$23,170.95 in its account. EAA then tendered a $500,000\\ncheck to Solutions, which promptly deposited the check\\nbefore the close of that day’s business. EAA never\\nreplenished the $540,000 withdrawal from the conference\\naccount.\\n Brand received the executed contract between\\nSolutions and Strategies on January 28. Even though the\\ncontract called for Strategies to perform services in\\nexchange for the $600,000 payment, Lindenfeld neither\\nexpected to do any work for the $600,000, nor did he in\\nfact do any work.\\n\\n In sum, by January 28, Solutions had received\\n$500,000 from EAA, but it still had to come up with\\n$100,000 to provide Strategies with the entire amount\\nneeded to repay the Lord loan. Golden obtained the needed\\nfunds the following day by drawing $150,000 on a line of\\ncredit held by Brand’s wife. Brand and Fattah spoke four\\nmore times on the telephone on January 29. Trial evidence\\nlater showed that, during the month of January 2008,\\nneither the FFM campaign bank account nor Fattah’s\\n\\n\\n 20\\n\\fpersonal account had a sufficient balance to fund a\\n$600,000 payment.\\n On the morning of January 30, frustrated by the\\ndelay, Lindenfeld sent Brand an email with a subject line\\n“You are killing me.” JA6430. Lindenfeld stated that he\\nhad “made a commitment based on yours to me. Please\\ndon’t drag this out. I have a lot on the line.” Id. Brand\\nresponded late in the afternoon, stating: “just met with\\nMichael. He does the transfer at 8 AM tomorrow. It should\\nbe in your account ($600K) early tomorrow morning.” Id.\\nLindenfeld replied: “The earlier the better.” Id. The\\nfollowing morning, Golden wired $600,000 from\\nSolutions’ Pennsylvania bank account into Strategies’\\nWashington D.C. bank account. JA2745, 2874. Strategies\\nin turn, wired the same amount from its Washington D.C.\\nbank account to Lord’s bank account in Virginia. JA2874,\\n6549. Around noon, Brand telephoned Lindenfeld.\\n\\n In the days following the exhaustive efforts to meet\\nthe January 31 loan repayment deadline, four more\\ntelephone calls took place between Brand and Fattah.5\\nNaylor learned at some point that the loan had been paid\\noff. When Naylor asked Fattah about details of the\\nrepayment, Fattah simply replied “[t]hat it went through\\nEAA to Solutions and it was done.” JA3088.\\n\\n5\\n By contrast, between October to December 2007, Brand\\nand Fattah spoke by telephone only “once or twice [a]\\nmonth.” JA2734.\\n 21\\n\\f Meanwhile, at some point in January, EAA received\\nnotice that the Department of Justice Office of the\\nInspector General (DOJ) intended to audit its books.6 DOJ\\nauditors told EAA to provide, at the “entrance\\nconference,” documentation containing budgetary and\\naccounting information. EAA failed to produce any\\naccounting information.\\n Although Lindenfeld was no longer making\\ndemands of Brand, Brand was still owed the remaining\\n$100,000 that Solutions had paid to satisfy the Lord loan.\\nOn March 23, 2008, Brand sent Nicholas an email\\noutlining his efforts to contact her over the previous two\\nweeks about documentation on the CORE work, how to\\nproceed with the paperwork for the Commonwealth of\\nPennsylvania, and “how we can get our proposed contract\\nsigned and the outstanding payments made.” JA2749.\\nNicholas responded that evening, writing:\\n\\n I can appreciate your urgency however I do\\n have EAA work that I continue to do,\\n including the [usual] facilitation of programs,\\n our financial audit, the start-up of two new\\n programs[,] and of course the DOJ audit. I am\\n still trying to obtain a line of credit without a\\n completed 2007 audit and things are getting a\\n\\n\\n\\n6\\n One of the terms and conditions of a federal grant is that\\nthe recipient “be readily prepared for an audit.” JA2314.\\n 22\\n\\f little uncomfortable now as I try to keep us\\n afloat.\\nJA6576. Nicholas told Brand that the DOJ auditors were\\nmaking demands and would soon be on site. She noted that\\n“[t]hey are still very uncomfortable with your contract\\namongst other things and depending on their findings\\nsome of the funding received may have to be returned.” Id.\\nNicholas said that she had submitted the paperwork to the\\nstate, and she told Brand that “in the future . . . as a result\\nof the DOJ audit I will not be in a position to do another\\ncontract such as this.” Id.\\n Shortly after Nicholas’s reply to Brand, Nicholas\\nforwarded the Brand–Nicholas email chain to Fattah. The\\nbody of the email stated, in its entirety: “I really don’t\\nappreciate the tone of Bob’s email. I can appreciate that he\\nhas some things going on however I am doing my best to\\nassist him. Some other things are a priority. He needs to\\nback off.” GSA2. Later that night, Bowser sent Fattah an\\nemail with a subject line that read “Karen N” and a\\ntelephone number. JA2752.\\n\\n As the audit continued, the auditors found other\\ndeficiencies. During April of 2008, DOJ issued a notice of\\nirregularity to EAA, which resulted in the audit being\\nreferred to DOJ’s Investigations Division for a more\\ncomprehensive review.\\n\\n On April 24, 2008, Brand emailed Nicholas asking\\nfor a time to update her on The Benefit Bank. In early May,\\n 23\\n\\fBrand sent another email to Nicholas attaching a revised\\nEAA–Solutions contract proposal, which decreased the\\ninitial upfront cost from $900,000 to $700,000.\\n Although Solutions and EAA had still not signed a\\ncontract, EAA paid Solutions another $100,000 in May.\\nThat money was obtained via a loan to EAA from CORE.\\nThomas Butler, who had worked for Fattah both when\\nFattah was in Congress and when he was in the General\\nAssembly, was CORE’s executive director. Butler had\\nbeen contacted in mid-May by Jackie Barnett, a member\\nof CORE’s Board who had also worked with\\nCongressman Fattah. Barnett informed Butler that\\nNicholas had requested a loan from CORE to EAA, and\\nthat Fattah, as Chairman of CORE’s Board, had approved\\nit. Butler and Barnett withdrew funds from two CORE\\nbank accounts and obtained a cashier’s check, dated May\\n19, in the amount of $225,000 and made payable to EAA.\\nThe withdrawals were from accounts used for Sallie Mae\\nfunds and other scholarship money.\\n After EAA received the $225,000 check, EAA\\ntendered a $100,000 check to Solutions. The check bore\\nthe notation “Commonwealth of Pennsylvania.” EAA\\nrepaid CORE the following month. Because EAA lacked\\nsufficient funds of its own to cover this payment, EAA\\ndrew on grant money that it had received from NASA.\\n\\n Brand and Lindenfeld continued to communicate\\nconcerning The Benefit Bank. In July of 2008, a meeting\\nwas held at Solutions with Brand, Lindenfeld, Golden, and\\n 24\\n\\fother Solutions employees to discuss “an enormous\\namount of work” that Brand wanted Strategies to do.\\nJA1670. Lindenfeld said in response “we’d be glad to do\\nthat, but . . . we would have to be paid.” Id. At that point,\\nsomeone in the meeting stated that Strategies “had already\\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\\nwas for Congressman Fattah, . . . that’s not for us. So if\\nyou want us to do work, we have to get paid for it\\nseparately.” Id. Brand became upset with Lindenfeld over\\nhis comment about being paid because his colleagues at\\nSolutions were not aware of the reason for the $600,000\\npayment.\\n Meanwhile, EAA was attempting to meet the\\ndemands of the DOJ auditors, who were focused on the\\nrelationship between EAA and CORE. DOJ served a\\nsubpoena upon Solutions to produce “[a]ny and all\\ndocuments including, but not limited to, contract\\ndocuments, invoices, correspondence, timesheets,\\ndeliverables and proof of payment related to any services\\nprovided to or payments received” from CORE or EAA.\\nJA2350.\\n\\n Special Agent Dieffenbach, from the DOJ,\\ninterviewed Nicholas on July 14, 2008. During that\\ninterview, Nicholas discussed the relationship between\\nEAA and CORE, how invoices were paid, and how\\nconsultants were handled. Nicholas also answered\\nquestions about EAA’s relationship with Solutions,\\nincluding the payment of invoices. She did not inform\\n\\n 25\\n\\fAgent Dieffenbach of the $500,000 payment in January or\\nthe subsequent $100,000 payment in May. Nor did the\\ninterview address the EAA–Solutions contract that\\npurportedly required those payments, because the contract\\nhad yet to be produced.\\n\\n Solutions failed to comply with the subpoena,\\nprompting an email from Agent Dieffenbach on August 26\\nasking for an update concerning Solutions’ reply to the\\nDOJ subpoena. Solutions then produced an undated\\nversion of the EAA–Solutions contract that required the\\n$600,000 upfront payment. Neither Brand nor Nicholas\\nprovided the auditors with the January and May checks\\nfrom EAA to Solutions.\\n Efforts to conceal the repayment of the Lord loan\\nand to promote the political and financial interests of\\nFattah continued. The FFM campaign reports indicated in-\\nkind contributions of debt forgiveness by SLA even\\nthough there had been no actual debt. In September of\\n2009, with EAA’s ledgers still under scrutiny, Nicholas\\naltered the description of the entry for the $100,000 check\\nto Solutions from “professional fees consulting” to\\n“CORE Philly.” JA2546. Other FFM campaign debt was\\nreduced further after Vederman negotiated with creditors.\\n\\n EAA never fully recovered from its payment of the\\n$600,000 balance on the Lord loan and the audits that took\\nplace in 2008. It began laying off employees in 2011, and\\nby June of 2012, only four employees remained. JA3659.\\nEAA ceased operations at some point in 2012. JA1530.\\n 26\\n\\f 2. The College Tuition Component of the FFM\\n Scheme\\n Although the FFM campaign was close to insolvent,\\nit nevertheless made tuition payments for Fattah’s son,\\nChaka Fattah Jr., also known as Chip. Chip attended\\nDrexel University, but had yet to complete his coursework\\nbecause he had failed to pay an outstanding tuition\\nbalance. As the FFM campaign got underway in 2007,\\nFattah wanted Chip to re-enroll in classes at Drexel and\\nget a degree. Fattah asked Naylor to help financially, and\\nhe did so by writing checks from SLA to Drexel toward\\nChip’s outstanding tuition. By October of 2007, Chip was\\npermitted to re-enroll in classes.\\n Although Naylor never directly addressed the issue\\nwith Fattah, he agreed to assist with Chip’s outstanding\\ntuition with the expectation that SLA would be repaid. The\\nfirst check to Drexel in the amount of $5,000 was sent in\\nAugust of 2007, with $400 payments in the months that\\nfollowed until August of 2008. At some point, Chip\\ninformed Naylor that the payee was no longer Drexel, but\\nSallie Mae. Naylor then began sending monthly checks\\nfrom SLA to Sallie Mae. Those payments, in the amount\\nof $525.52, began in March of 2009 and continued until\\nApril of 2011, after which Fattah told Naylor he no longer\\nneeded to make them. SLA’s payments to Drexel and\\nSallie Mae totaled $23,063.52.\\n\\n Naylor’s expectation of repayment was eventually\\nrealized. Beginning in January of 2008 and continuing\\n 27\\n\\funtil November 2010, Bowser sporadically sent SLA\\nreimbursement checks from the FFM campaign with a\\nnotation that payment was for “election day operation\\nexpenses.” JA3136. The FFM funds had been transferred\\nfrom the Fattah for Congress campaign. These\\nreimbursement checks totaled $25,400. In an effort to\\nconceal the source of the payments to Drexel and Sallie\\nMae, and to make it appear that the younger Fattah had\\nperformed services for SLA, Naylor created false tax\\nforms for Chip. Chip, however, had never performed\\nservices for SLA.\\n\\n 3. The NOAA Grant and the Phantom Conference\\n In mid-December 2011, when EAA was\\nexperiencing serious financial difficulties, Nicholas\\nsubmitted an email request to the educational partnership\\nprogram of the National Oceanic & Atmospheric\\nAdministration (NOAA) for a grant “designed to provide\\ntraining opportunities and funding to students at minority\\nserving institutions” interested in science, technology,\\nengineering, and math fields related to NOAA’s mission.\\nJA3354–55. The request sought $409,000 to fund EAA’s\\nannual conference scheduled for February 17–19, 2012.\\nJacqueline Rousseau, a supervisory program manager at\\nNOAA, participated in a conference call with Nicholas\\nshortly thereafter and advised Nicholas that the agency\\ncould not afford the $409,000 request but would consider\\na smaller grant. Rousseau advised Nicholas that EAA\\n\\n\\n 28\\n\\fwould need to submit an application if it wished to be\\nconsidered for a grant.\\n Before submitting a grant application, Nicholas\\nemailed Rousseau about sponsoring the conference. On\\nJanuary 11, 2012, Rousseau informed Nicholas that the\\n“NOAA Office of Education, Scholarship Programs has\\nagreed to participate and provide sponsorship funds of\\n$50K to support the referenced conference.” JA6453.\\nRousseau also informed Nicholas that Chantell Haskins,\\nwho also worked with the student scholarship program,\\nwould be the point of contact for NOAA.\\n In February 2012, EAA held its annual conference\\nat the Sheraton Hotel in downtown Philadelphia. The\\nconference had been held at the same location each year\\nsince 2008.\\n\\n Nicholas contacted Haskins at some point in early\\n2012, inquiring about the $50,000 grant. On May 8, 2012,\\nHaskins sent Nicholas an e-mail which included\\ninformation about submitting proposals to fund a\\nconference for students. EAA then submitted a grant\\napplication, which Haskins reviewed. She advised\\nNicholas on June 28, 2012 that the grant could not be used\\nto provide meals, and that the date of the conference would\\nhave to be pushed back, with the new date included in a\\nmodified application. When Nicholas asked if expenses\\nfrom a previous conference could be paid from the new\\ngrant, Haskins informed her that this was not allowed.\\n\\n 29\\n\\f In early July 2012, Nicholas sent a modified grant\\nproposal to Haskins. It eliminated the budget item for food\\nand changed the date of the 2012 conference to October\\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\\nwhere EAA’s annual conference had taken place earlier in\\nthe year. NOAA approved a $50,000 grant for the October\\n2012 conference—a conference that would never be held.\\n\\n Unaware that no October 2012 conference had\\ntaken place, NOAA allowed Nicholas access to the\\n$50,000 grant in March of 2013. She then transferred the\\nentire amount from NOAA to EAA’s bank account a few\\ndays later. Naylor had performed services for EAA for\\nwhich he was still owed $116,590. JA3119. In discussions\\nwith Naylor, Nicholas had informed him that the\\nlikelihood of EAA’s being able to pay him was “[n]ot very\\ngood.” JA3120. Yet several days after EAA had received\\nthe $50,000 from NOAA, Nicholas sent Naylor a check\\nfor $20,000. JA3120, 4283.\\n\\n On April 3, 2013, Nicholas submitted a final report\\nto NOAA concerning EAA’s use of the grant. Notably,\\npage 4 of the report stated the conference had been held in\\nFebruary 2012, while page 17 stated that the conference\\nhad been held from October 19 to 21, 2012. NOAA issued\\na notice asking for clarification and for a list of students\\nwho had been supported at the conference. Nicholas failed\\nto file either a clarifying report regarding the date of the\\nconference or a timely report regarding the disbursement\\nof the grant. Finally, in November of 2013, Nicholas\\n\\n 30\\n\\fsubmitted the final Federal Financial Report in which she\\ncertified, falsely, that the $50,000 had been used for a\\nproject during the period from August 1, 2012 to\\nDecember 30, 2012.\\n\\n B. The Blue Guardians Scheme\\n In addition to functioning as the conduit for Lord’s\\n$1 million loan to Fattah’s campaign, Lindenfeld’s\\ncompany, Strategies, also performed services for the\\ncampaign. The work resulted in indebtedness from FFM\\nto Strategies of approximately $95,000. Fattah made\\nseveral small payments, but failed to pay the full amount\\ndue. Although Lindenfeld spoke to Fattah, Naylor and\\nBowser about the debt, no payments were forthcoming.\\nDuring a meeting in Fattah’s D.C. office, Fattah told\\nLindenfeld “that [repayment] really wasn’t going to be\\npossible because the campaign had been over for a long\\ntime” and the funds were not available. JA1693. Fattah\\nthen asked Lindenfeld if he could write off the debt on his\\nFFM campaign finance reports. Id. Lindenfeld told Fattah\\nthat as long as he was paid, it was not his business how\\nFattah disclosed it on the campaign finance reports.\\nJA1694.\\n In lieu of repayment, Fattah suggested that\\nStrategies could claim to be interested in setting up an\\nentity to address environmental issues and ocean pollution\\nalong the coastline and in the Caribbean. Fattah explained\\nthat creating such an entity would make it possible to\\nobtain an appropriation from the government. Hearing\\n 31\\n\\fthis, Lindenfeld knew he was not going to be paid by the\\nFFM campaign, and was amenable to receiving money\\nfrom an appropriation instead. At a later meeting,\\nLindenfeld told Fattah that the name of the entity would\\nbe “Blue Guardians.” Lindenfeld consulted with an\\nattorney about creating Blue Guardians as an entity to\\nreceive the federal grant. He emailed Fattah, asking\\nquestions about how to complete an application to the\\nHouse Appropriations Committee. Fattah provided\\nsuggestions, and an application was eventually completed.\\nIt indicated that Blue Guardians would be “in operation for\\na minimum of ten years,” and, in accordance with Fattah’s\\nguidance, requested $15 million in federal funds. JA1711–\\n13.\\n Lindenfeld submitted the application to Fattah’s\\noffice in April of 2009. Afterward, a Fattah staffer\\ncontacted Lindenfeld to suggest that he change his\\nWashington, D.C., address to Philadelphia because that\\nwas the location of Fattah’s district. Fattah later suggested\\nto Lindenfeld that Brand might allow the use of his\\nPhiladelphia office address, a plan to which Brand agreed.\\n\\n In February 2010, Lindenfeld submitted a second\\napplication to the Appropriations Committee. In March,\\nFattah submitted a project request using his congressional\\nletterhead and seeking $3,000,000 for the “Blue\\nGuardians, Coastal Environmental Education Outreach\\nProgram.” JA6432. Within a month, Blue Guardians had\\nboth articles of incorporation and a bank account. Around\\n\\n 32\\n\\fthat time, a news reporter contacted Lindenfeld to discuss\\nthe new Blue Guardians entity. The inquiry made\\nLindenfeld uncomfortable, and he ultimately decided to\\nabandon the Blue Guardians project. He continued to seek\\npayment from Fattah, to no avail.\\n\\n Nonetheless, having obtained Lindenfeld’s\\nacquiescence to writing off the campaign’s debt to\\nStrategies, Fattah started falsifying FFM’s campaign\\nreports. Beginning in 2009 and extending through 2013,\\nthe FFM campaign reports executed by Fattah and Bowser\\nstated that Strategies made in-kind contributions of\\n$20,000, until the debt appeared to have been paid in full.\\n\\n C. The Fattah–Vederman Bribery Scheme\\n Vederman and Fattah were personal friends.\\nVederman was a successful businessman who had also\\nserved in prominent roles in the administrations of Ed\\nRendell when he was Mayor of Philadelphia and Governor\\nof Pennsylvania. In November of 2008, Vederman was a\\nsenior consultant in the government and public affairs\\npractice group of a Philadelphia law firm. His assistance\\nto the FFM campaign included paying for rented vans used\\nin the get-out-the-vote effort.\\n\\n After Fattah’s electoral defeat, the campaign still\\nowed more than $84,000 to a different law firm for\\nservices performed for the campaign. Vederman\\napproached that firm in the summer of 2008 asking if it\\nwould forgive FFM’s debt. Negotiations resulted in a\\n 33\\n\\fcommitment from FFM to pay the firm $30,000 by the end\\nof 2008 in exchange for forgiveness of $20,000, all of\\nwhich would appear on the FFM campaign finance report.\\nVederman’s efforts also led to payment by Fattah of an\\nadditional $10,000 in 2009 to the law firm, in exchange\\nfor additional forgiveness of $20,000 of debt. It was not\\nlong after Vederman’s successful efforts to lower Fattah’s\\ncampaign debt, that Fattah wrote a letter to U.S. Senator\\nRobert P. Casey recommending Vederman for an\\nambassadorship.\\n\\n At some point in 2010, Vederman again intervened\\non behalf of the FFM campaign. FFM remained in debt to\\nan advertising and public relations firm owned by Robert\\nDilella. By late 2011, Vederman and Dilella had worked\\nout a settlement to resolve the outstanding debt. Pursuant\\nto that settlement, Dilella received partial payment from\\nthe FFM campaign: $25,000 in satisfaction of a $55,000\\ndebt. Dilella testified at trial that he would not have agreed\\nto retire a portion of the debt had he known the FFM\\ncampaign was paying college tuition for Fattah’s son.\\n Vederman helped Fattah financially in other ways.\\nBefore the 2006 FFM campaign, Fattah and his wife,\\nRenee Chenault-Fattah, sponsored a young woman named\\nSimone Muller to live with them as an au pair exchange\\nvisitor. Muller was from South Africa, and her J-1 visa\\nallowed her to serve as a nanny and to study in the United\\nStates. Muller later applied for and received a second visa,\\nan F-1 student visa that indicated she had been accepted as\\n\\n 34\\n\\fan international student at the Community College of\\nPhiladelphia. The application indicated that Muller would\\nagain be residing with the Fattahs. Notwithstanding this\\nliving arrangement, Fattah identified Vederman as the\\nperson who would be paying for Muller’s trip to the\\nUnited States.\\n By the beginning of 2010, Muller wished to transfer\\nto Philadelphia University. This required her to submit\\nverification that funds were available to pay for her study.\\nAlthough the Fattahs were Muller’s sponsors, Fattah\\nexplained to the University’s Dean of Enrollment Services\\nthat he was submitting a letter of secondary support from\\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\\nJanuary 2010 letter of support, the University would not\\nhave admitted Muller. In addition to this pledge of support,\\nVederman paid $3,000 of Muller’s tuition. Shortly\\nthereafter, Fattah resumed his efforts to secure an\\nambassadorship for Vederman.\\n\\n In February of 2010, Fattah staffer Maisha Leek\\ncontacted Katherine Kochman, a scheduler for White\\nHouse Chief of Staff Rahm Emanuel. Leek requested a\\ntelephone conference with Emanuel, Rendell, and Fattah\\nto discuss Vederman’s “serving his country in an\\ninternational capacity.” JA2893. In a follow-up email on\\nMarch 26, Leek sent documents to Kristin Sheehy, a\\nsecretary to White House Deputy Chief of Staff James\\nMessina. The documents included Fattah’s 2008 letter to\\nSenator Casey and Vederman’s biography. After\\n\\n 35\\n\\fparticipating in a telephone conference about Vederman\\nwith Fattah and Rendell, Messina sent Vederman’s\\nbiography to the White House personnel office for\\nconsideration.\\n\\n As the April 2010 tax deadline approached, Fattah\\nstill owed the City of Philadelphia earned income tax in\\nthe amount of $2,381. Just days before the filing deadline,\\nVederman gave a check to Chip Fattah for $3,500. The\\nyounger Fattah quickly deposited $2,310 into his father’s\\nbank account. Fattah paid his tax bill on April 15. Without\\nChip’s deposit into his father’s bank account, the older\\nFattah would not have had sufficient funds to pay his tax\\nbill.\\n On October 30, 2010, Vederman gave Chip another\\ncheck, this one for $2,800. That same day, Fattah hand-\\ndelivered a letter to President Obama recommending\\nVederman for an ambassadorship. A few weeks later,\\nFattah’s staffer, Leek, sent the letter that Fattah had given\\nto President Obama to Messina’s office. That letter\\npointed out that both Rendell and Fattah had sent letters\\non behalf of Vederman, and that he was an\\n“unquestionably exceptional candidate for an\\nambassadorship.” JA6291–92.\\n\\n Fattah’s efforts to secure Vederman an\\nambassadorship were unsuccessful. Fattah then shifted\\ngears and sought to secure Vederman a position on a\\nfederal trade committee. Fattah approached Ron Kirk, who\\nserved as U.S. Trade Representative, and asked him to\\n 36\\n\\fspeak with a constituent. In May of 2011, Leek followed\\nup on that discussion by emailing Kirk and asking him to\\nmeet with Vederman. Kirk met with Vederman on June 5,\\n2011 and explained to him the role of the trade advisory\\ncommittees. Although the two men “had a very nice\\nconversation,” JA 3566, it soon became “pretty apparent\\nto [Kirk and his staff] that [serving on a trade advisory\\ncommittee was] not what Mr. Vederman was interested\\nin.” JA3567. As Kirk put it, “it was obvious that\\n[Vederman] was looking for something perhaps more\\nrobust in his mind or . . . higher profile than one of our\\nadvisory committees.” Id. Given Vederman’s lukewarm\\ninterest, no appointment to an advisory committee was\\nforthcoming.\\n In late December 2011, the Fattahs applied for a\\nmortgage so they could purchase a second home in the\\nPoconos. Shortly after applying for the mortgage, Fattah\\nemailed Vederman, offering to sell him his wife’s 1989\\nPorsche for $18,000. Vederman accepted the offer. The\\nnext day, Vederman wired $18,000 to Fattah’s Wright\\nPatman Federal Credit Union account.\\n\\n The Credit Union Mortgage Association (CUMA)\\nacted as the loan processing organization for the home\\nmortgage. Because CUMA is required to verify the source\\nof any large deposits, CUMA’s mortgage loan processor,\\nVictoria Souza, contacted Fattah on January 17, 2012, to\\nconfirm the source of the $18,000. Fattah informed Souza\\nthat the $18,000 represented the proceeds of the Porsche\\n\\n 37\\n\\fsale. Souza requested documentation, including a signed\\nbill of sale and title.\\n That same day, Bowser emailed Vederman a blank\\nbill of sale for the Porsche. After Vederman signed the bill\\nof sale, Fattah forwarded it to Souza. The bill of sale was\\ndated January 16, 2012, which was the day before Souza\\nhad requested the documentation. It bore the signatures of\\nRenee Chenault-Fattah and Herbert Vederman, with\\nBonnie Bowser as a witness.\\n\\n Fattah also provided Souza with a copy of the\\nPorsche’s title. It was dated the same day it was sent to\\nSouza, and bore signatures of Chenault-Fattah as the seller\\nand Vederman as buyer, along with a notary’s stamp.\\nNeither Vederman nor Chenault-Fattah actually appeared\\nbefore the notary.\\n\\n Vederman never took possession of the Porsche.\\nRenee Chenault-Fattah continued to have the Porsche\\nserviced and insured long after the purported sale had\\ntaken place. Moreover, the Porsche remained registered in\\nChenault-Fattah’s name, and was never registered to\\nHerbert Vederman. When FBI agents searched the\\nFattahs’ home in 2014, the Porsche was discovered in the\\nFattahs’ garage.\\n\\n On January 24, 2012, the Fattahs wired $25,000 to\\nthe attorney handling the escrow account for the purchase\\nof the vacation home. Without the $18,000 transfer from\\n\\n 38\\n\\fVederman, the Fattahs would not have had sufficient funds\\nin their bank accounts to close on the home.\\n Around the same time that the Fattahs were\\npurchasing the house in the Poconos, Fattah’s Philadelphia\\noffice hired Vederman’s longtime girlfriend, Alexandra\\nZionts. Zionts had long worked for a federal magistrate\\njudge in Florida. Near the end of 2011, the magistrate\\njudge retired, leaving Zionts ten months shy of obtaining\\nthe necessary service required to receive retirement\\nbenefits. If Zionts could find another job in the federal\\ngovernment, her benefits and pension would not be\\nadversely affected. Vederman assisted Zionts in her job\\nsearch, which included calling Fattah. Fattah hired her, a\\nmove that put his congressional office overbudget. Zionts\\nworked in Fattah’s office for only about two months,\\nleaving to work for a congressman from Florida.\\n\\n Tia Watson, who performed constituent services for\\nFattah and worked on the same floor as Zionts in Fattah’s\\ndistrict office, testified she had no idea what work Zionts\\nperformed. Although Zionts contacted Temple University\\nabout archiving Fattah’s papers from his career in both the\\nstate and federal government, an employee from Temple\\nUniversity observed that Zionts’ work contributed nothing\\nof value to the papers project.\\n\\n D. The Indictment and Trial\\n Fattah’s schemes eventually unraveled. On July 29,\\n2015, a federal grand jury in the Eastern District of\\n 39\\n\\fPennsylvania returned a twenty-nine count indictment\\nalleging that Fattah and his associates had engaged in a\\nvariety of criminal acts. Fattah, Vederman, Nicholas,\\nBrand, and Bowser were charged with unlawfully\\nconspiring to violate the Racketeer Influenced and Corrupt\\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\\naddition to the RICO charge, the indictment alleged that\\nFattah and certain co-defendants had unlawfully conspired\\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\\nSeveral defendants were also charged with making false\\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\\n§§ 1341, 1343, and 1344.\\n\\n The RICO charge alleged that the defendants and\\nother co-conspirators constituted an enterprise aimed at\\nsupporting and promoting Fattah’s political and financial\\ninterests. The efforts to conceal the $1 million Lord loan\\nand its repayment are at the heart of the RICO conspiracy\\nand the Fattah for Mayor scheme. The indictment further\\nalleged that the RICO enterprise involved: (1) the scheme\\nto satisfy an outstanding campaign debt by creating the\\nfake “Blue Guardians” nonprofit; and (2) the bribery\\nscheme to obtain payments and things of value from\\nVederman in exchange for Fattah’s efforts to secure\\nVederman an appointment as a United States Ambassador.\\n 40\\n\\f A jury trial, before the Honorable Harvey Bartle III\\nof the Eastern District of Pennsylvania, began on May 16,\\n2016, and lasted about a month. 7 Judge Bartle charged the\\njury on Wednesday, June 15, 2016, and deliberations\\nbegan late that afternoon. The following day, after\\ndeliberating for only four hours, the jury sent a note to the\\njudge. Written by the foreperson, the note read:\\n Juror Number 12 refuses to vote by the letter\\n of the law. He will not, after proof, still\\n change his vote. His answer will not change.\\n He has the 11 of us a total wreck knowing that\\n we are not getting anywhere in the hour of\\n deliberation yesterday and the three hours\\n today. We have zero verdicts at this time all\\n due to Juror Number 12. He will not listen or\\n reason with anybody. He is killing every\\n other juror’s experience. We showed him all\\n the proof. He doesn’t care. Juror Number 12\\n has an agenda or ax to grind w/govt.\\nJA5916.\\n\\n Shortly after receiving the foreperson’s note, the\\nCourt received a second communication—a note signed\\n\\n\\n\\n 7\\n The District Court dismissed one charge prior to\\ntrial: an individual money laundering count against\\nNicholas.\\n 41\\n\\fby nine jurors, including the foreperson. The second note\\nread:\\n We feel that [Juror 12] is argumentative,\\n incapable of making decision. He constantly\\n scream [sic] at all of us.\\nId.\\n Judge Bartle met with counsel in his chambers and\\nadvised them of his intention to voir dire both the\\nforeperson and Juror 12 in an effort to determine whether\\nthe juror was deliberating as required by his oath. The\\nJudge also indicated that he would “stay away from the\\nmerits of the case,” and that whether he would voir dire\\nmore jurors “remain[ed] to be seen.” JA5917.\\n Counsel for the defendants objected to the Court’s\\nproposed inquiry. As a group, they indicated that while the\\nnote could be read as suggesting “a flat refusal to\\ndeliberate,” they were of the opinion that it sounded “more\\nin the manner of a disagreement over the evidence.”\\nJA5918. Nicholas’s counsel specifically argued that\\nquestioning the jurors so quickly after the start of\\ndeliberations would send a message that differences of\\nopinion among a block of jurors could be resolved by\\ncomplaining to the Court. Defense counsel acknowledged\\nthat the case law gave Judge Bartle wide discretion on how\\nto proceed, but suggested that a “less intrusive” course of\\naction was preferred. JA5918–19. They collectively urged\\n\\n 42\\n\\fthe Court to do nothing more than remind the jurors of\\ntheir duty to deliberate.\\n The Government agreed with Judge Bartle’s\\nproposed voir dire. In the prosecution’s view, the Court\\nhad already given proper instructions to the jury on their\\nduty to deliberate. The Government further argued that if\\nJuror 12 had exhibited bias, as suggested in the notes, he\\nwould have lied during the voir dire process and his\\nrefusal to deliberate would be “further evidence of that and\\nhis unsuitability as a juror.” JA5921.\\n\\n With all counsel present, and over defense counsel’s\\nobjections, Judge Bartle ultimately questioned five jurors\\nin chambers. He questioned Juror 2 (the foreperson), Juror\\n12 (the subject of the complaints), Juror 3, Juror 6, and\\nJuror 1.\\n\\n Judge Bartle began each voir dire by informing the\\njuror that he would ask a series of questions, but would not\\ninquire into the merits of the case or how any juror was\\nvoting. Each juror was placed under oath, and Judge Bartle\\nasked, among other questions, whether screaming was\\noccurring; whether the jurors were discussing the\\nevidence; whether Juror 12 was placing his hands on other\\njurors; and whether Juror 12 was unwilling to follow his\\ninstructions.\\n The foreperson acknowledged that he had written\\nthe initial note during lunch earlier that day. He stated that\\nJuror 12 was not willing to follow the law, but instead\\n 43\\n\\f“want[ed] to add his own piece of the law . . . which has\\nnothing to do with it.” JA5927–28. The foreperson further\\ntestified that Juror 12 “was standing up screaming” and\\nthat “[i]t was everybody pretty much against [Juror 12].”\\nJA5929. He testified that Juror 12 “has his own agenda,”\\nand that Juror 12 put his hand on another juror. JA5930.\\nThe foreperson also stated that the jury had discussed only\\na single count since the day before, and that they were still\\ndiscussing it. When the District Court responded that the\\njurors should understand that they could take as much time\\nas they needed, the foreperson responded: “I understand\\nthat. . . . [W]e all understand it. But we feel that he’s just—\\nhe’s got another agenda.” JA5934.\\n Judge Bartle advised counsel that he considered this\\n“a very serious situation” and that he would proceed to\\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\\nobjection to questioning Juror 12, which the Court\\noverruled. Brand’s counsel argued that because the Court\\nhad decided to voir dire Juror 12, it should also voir dire\\nan additional juror. The Court agreed to do so.\\n When the Court questioned Juror 12, he admitted to\\nhaving “yelled back” at others, but only when they raised\\ntheir voices to him. JA5939. Juror 12 contended that he, in\\nfact, was “the only one” deliberating. Id. When an initial\\nvote was taken the previous afternoon, his vote “was\\ndifferent than everybody else’s.” Id. Juror 12 explained to\\nthe other jurors why his vote was different, bringing up\\nspecific evidence. In response, the other jurors said “that\\n\\n 44\\n\\fdoesn’t mean anything” and “pointed to the indictment.”\\nJA5940. Juror 12 told the other jurors that the indictment\\nis not evidence. Id. In response, the others “threatened to\\nhave [him] thrown off.” Id.\\n\\n Juror 12 testified that a similar sequence of events\\nhad taken place that morning. After a brief period of\\ndeliberations, another vote was taken, and with the same\\nresult as the previous afternoon. A discussion ensued, and\\nthe other jurors again “point[ed] to the indictment.” Id.\\nJuror 12 told them to “read the charge,” “[t]he indictment\\nis not evidence.” Id. They read the charge, and Juror 12\\nagain attempted to explain his view, but the other jurors\\npaid little attention. Accordingly, Juror 12 told the others\\nthat if they did not want him there, he “[didn’t] want to be\\n[there]”—he would be “[o]kay with it” if they wanted him\\ntaken off the jury. JA5941.\\n Upon hearing this testimony, Judge Bartle again\\nasked about the tone of deliberations. Juror 12 repeated\\nthat he raised his voice only in response to others who did\\nso—he did “not want to yell at anybody.” JA5942. Judge\\nBartle then asked whether he had touched other jurors.\\nJuror 12 replied that he had not hurt anyone. When asked\\nif he had put his hand on anybody’s shoulder, Juror 12\\nanswered: “I couldn’t remember to be honest with you.”\\nJA5946.\\n\\n Following Juror 12’s voir dire, the Court summoned\\nJuror 3 to chambers. Juror 3 testified that, after discussion\\nof a particular count, there was one juror at odds with the\\n 45\\n\\fothers. According to Juror 3, “the rest of the jurors\\npounced on the gentleman with the . . . dissenting\\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\\ndefensive and just a little bit [] impatient” and that “the\\nother jurors were very impatient with him.” Id. Juror 3 did\\nnot recall witnessing Juror 12 putting his hand on any\\nother jurors.\\n\\n The Government requested that the Court voir dire\\nanother juror. Defense counsel objected, claiming that the\\nquestioning “threaten[ed] . . . the entire deliberative\\nprocess.” JA5949–50. Judge Bartle reminded counsel that\\nhe had the authority to question each juror, and called for\\nvoir dire of Juror 6.\\n Juror 6 testified that the jury had been discussing the\\ncase and reviewing the evidence, but that Juror 12 “wants\\nto be seen” and was “being obstinate.” JA5951–52.\\nAccording to Juror 6, Juror 12 “may not agree” with the\\nconclusion of other jurors but “doesn’t give valid reasons\\nas to why he may disagree with the charge.” JA5952. Juror\\n6 also revealed that Juror 12 was the first to raise his voice,\\nand that he may have touched her and another juror. When\\nasked to clarify what she meant by Juror 12 disagreeing\\nwith “the charge,” Juror 6 testified that Juror 12 was\\n“reading maybe too deeply into it and putting his own\\nemotions into it instead of just looking at what it says [and]\\nwhat the facts are.” JA5952, 5955. According to Juror 6,\\nJuror 12 “just continues to read past that into his own mind\\nof what he feels it should be.” JA5955. Juror 6 testified\\n\\n 46\\n\\fthat Juror 12’s “justification for some of his responses [did\\nnot] seem to relate to what the matter [was] before\\n[them].” JA5957.\\n Judge Bartle chose to hear from yet another juror.\\nJuror 1 was called and informed the Court and counsel that\\nthe jury “really [hadn’t] been able to even start the\\ndeliberation process” in light of the disruptive behavior of\\n“one particular individual.” JA5958–59. The particular\\nindividual, according to Juror 1, was “very opinionated”\\nand “[came] into the process with his view already\\nestablished, refusing to even listen to any of the evidence\\n. . . [being] very forceful . . . standing up, yelling, pointing\\nhis finger.” JA5959. When asked if this individual was\\nwilling to follow the Court’s instructions, Juror 1 testified\\nthat he “pours [sic] over the documents very well” but that\\nhe was adding other factors to answer the question on the\\nverdict form, such as “what did this person feel.” JA5961.\\nWhen Judge Bartle advised that intent was an appropriate\\nconsideration, Juror 1 agreed but said that Juror 12 was\\n“trying to investigate . . . going way beyond the scope” of\\nthe evidence before them. JA5961–62. Juror 12, he said,\\n“has an opinion and that opinion is established.” JA5962.\\nHe stated that Juror 12 was “not willing to listen to any\\nsort of reason or any sort of what everyone else is saying”\\nbut instead, was “trying to force everyone else to get to his\\npoint of view.” Id. “[I]f he feels like he’s not getting there,\\nhe gets louder and louder and points and puts his hand on\\nyour shoulder . . . .” Id.\\n\\n 47\\n\\f After questioning the five jurors (Jurors 1, 2, 3, 6,\\nand 12), Judge Bartle heard argument from counsel. The\\nattorney for the Government pointed out that the Court\\nwould have to make a credibility determination because\\nJuror 12 stated that he did not recall touching anyone. In\\nthe Government’s view, Juror 12 was disrupting the\\nprocess and should be removed. Defense counsel\\ndisagreed. They argued that Juror 12 was conscientious\\nand was engaging with the evidence. They pointed out that\\ndespite the testimony that Juror 12 was reading too deeply\\ninto the instructions or introducing new factors for the jury\\nto consider, Juror 6 had testified that the jurors “talked it\\nthrough” and resolved the concern. JA5965. Defense\\ncounsel argued that the jury was discussing intent, an issue\\nthat was at the heart of the case. Defense counsel perceived\\nno breakdown in deliberations and argued that dismissal\\nwould be premature. They suggested, instead, that the\\nCourt provide a supplemental instruction.\\n\\n Judge Bartle decided to adjourn for the afternoon.\\nBut before he left the courtroom, defense counsel brought\\ntwo matters to his attention. First, in light of testimony\\nduring the voir dire, they asked that the jury be\\nreinstructed that the verdict form and indictment were not\\nevidence. Second, they apprised the Judge of the standard\\nfor juror dismissal set forth in United States v. Kemp, 500\\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\\nKemp, a request to discharge a juror must be denied if there\\nis a possibility that the request stems from the juror’s view\\nof the evidence. Judge Bartle expressed hesitation on\\n 48\\n\\freinstructing the jury, but agreed that Kemp would control\\nhis determination as to whether dismissal was appropriate.\\n With the following morning came a new revelation.\\nWith counsel in chambers, the Judge informed them that\\n“additional significant evidence” had come to light since\\nthe previous day’s recess. JA5980. He placed his\\ncourtroom deputy under oath, and she proceeded to testify\\nto an exchange that had occurred the previous day as she\\nwas escorting Juror 12 back to the jury room after he had\\nbeen voir dired. According to the deputy, Juror 12 stopped\\nher in the hallway, placed his hand on her shoulder, and\\nlooked her “straight in the eye.” JA5981. He then said:\\n“I’m going to hang this jury.” Id. The deputy then related\\nthat before any further conversation could take place\\nbetween Juror 12 and the deputy, Judge Bartle summoned\\nJuror 12 back to his chambers. Later that day, however,\\nJuror 12 and the courtroom deputy had another exchange.\\nShe testified that after all five jurors had been questioned,\\nJuror 12 emerged from the jury room and told her “I really\\nneed to talk to you.” JA5982. She informed Judge Bartle\\nand counsel that Juror 12 “said more about how they’re\\ntreating him and what he’s saying to them.” Id. He flatly\\nstated that “it’s going to be 11 to 1 no matter what.” Id.\\n\\n There were no follow-up questions for the deputy.\\nInstead, defense counsel suggested that what Juror 12 may\\nhave meant was that he was willing to hang the jury\\nbecause of a lack of evidence. They requested that Juror\\n12 be asked about his comments to the deputy.\\n\\n 49\\n\\f After once again summoning Juror 12 to his\\nchambers, the Judge advised him that “[s]ome questions\\nhave arisen” about what he may have done after being voir\\ndired the previous day. JA5985. Juror 12 acknowledged\\nhaving conversations with the courtroom deputy. When\\nasked “what happened” and “[w]hat occurred,” Juror 12\\nresponded: “Basically, I said that there was a lot of name\\ncalling going on.” JA5985. He said comments had been\\nmade by other jurors about his service in the military. He\\nspecifically referred to other jurors’ suggesting that he had\\npossibly “hit [his] head . . . hard a few times” while\\nserving in a parachute regiment. JA5986. He testified he\\nhad conveyed these comments to the deputy and that he\\nfound them offensive. When asked if he said anything else\\nto the deputy, Juror 12 responded: “I may have. I really\\ncan’t recall.” JA5987. And when Judge Bartle followed up\\nby asking if he could recall anything else that he said to\\nthe deputy, Juror 12 simply replied: “No. To me, that was\\nthe most important thing.” Id. Juror 12 was then excused\\nfrom chambers.\\n Defense counsel next requested that the juror be\\nasked directly whether he told the courtroom deputy that\\nhe was going to “hang this jury.” JA5988. Juror 12 was\\nrecalled to chambers, and the following back and forth\\ntook place:\\n\\n The Court: You may be seated. And, of\\n course, [Juror 12], you know you’re under\\n oath here from yesterday?\\n\\n 50\\n\\f Juror 12: Yes, sir.\\n The Court: . . . Did you say to [the courtroom\\n deputy] that you’re going to hang this jury?\\n Juror 12: I said I would.\\n The Court: You did?\\n Juror 12: I did. I said—I told her—I said, we\\n don’t agree; I’m not just going to say guilty\\n because everybody wants me to, and if that\\n hangs this jury, so be it.\\n ....\\n Juror 12: I did say that, sir.\\n The Court: You didn’t remember that before?\\n Juror 12: I’m more concerned about people\\n spitting on my military record.\\n The Court: Did you say that you’d hang the\\n jury no matter what?\\n Juror 12: If they do—if we cannot come to—\\n The Court: No. The question is what you said\\n to her. Did you say to her you would hang the\\n jury no matter what?\\n Juror 12: I can’t really remember that. I did\\n say that if we didn’t—a person—no matter\\n what, I can’t recall that exactly.\\n The Court: All right. Thank you very much.\\n You can wait just out there in the anteroom.\\nJA5989–90.\\n\\n Defense counsel continued to oppose Juror 12’s\\ndismissal. They argued that the juror’s concern was about\\n\\n 51\\n\\fthe evidence, and that his comments to the courtroom\\ndeputy reflected a conviction that “he’s not going to agree\\njust because others want him to agree.” JA5991. They also\\nargued that nothing should be made of Juror 12’s failure\\nto mention the comments when initially questioned by the\\nCourt, and that a supplemental instruction was all that was\\nwarranted given the early stage of the deliberations.\\n\\n The Government strongly disagreed. The Assistant\\nUnited States Attorney argued that Juror 12 “should\\nabsolutely be removed” because “his demeanor ha[d]\\ndemonstrated a hostility . . . both to the other jurors and to\\nthe court.” JA5993. The Government also suggested that\\nJuror 12’s comments that he would hang the jury meant\\nthat he was not participating in the deliberations and was\\nignoring the evidence and the law.\\n\\n Ruling from the bench, Judge Bartle announced:\\n I find [the deputy clerk] to be credible. I find\\n [Juror 12], not to be credible. I find that [Juror\\n 12] did tell [the deputy clerk] that he was\\n going to hang this jury no matter what.\\n There have been only approximately\\n four hours of deliberation. There’s no way in\\n the world he could have reviewed and\\n considered all of the evidence in the case and\\n my instructions on the law.\\n I instructed the jury to deliberate,\\n meaning to discuss the evidence; obviously,\\n to hold onto your honestly held beliefs, but at\\n 52\\n\\f least you have to be willing to discuss the\\n evidence and participate in the discussion\\n with other jurors.\\n Juror number 12 has delayed,\\n disrupted, impeded, and obstructed the\\n deliberative process and had the intent to do\\n so. I base that having observed him, based on\\n his words and his demeanor before me.\\n He wants only to have his own voice\\n heard. He has preconceived notions about the\\n case. He has violated his oath as a juror.\\n And I do not believe that any further\\n instructions or admonitions would do any\\n good. I think he’s intent on, as he said,\\n hanging this jury no matter what the law is,\\n no matter what the evidence is.\\n Therefore, he will be excused, and I\\n will replace him with the next alternate . . . .\\n\\nJA5994–95.\\n In response, defense counsel moved for a mistrial,\\nwhich the judge promptly denied. He then informed the\\nreconstituted jury that deliberations would need to start\\nover, and reinstructed them on certain points of law,\\nincluding that the verdict slip does not constitute evidence.\\n\\n Judge Bartle elaborated upon his decision to remove\\nJuror 12 in two post-trial memorandum opinions. In the\\nfirst, ruling on a media request for the sealed transcripts,\\nhe explained:\\n 53\\n\\f Here, there is no doubt that Juror 12\\n intentionally refused to deliberate when he\\n declared so early in the process that he would\\n hang the jury no matter what. This finding\\n was predicated on the admission of Juror 12\\n as reported by the court’s deputy clerk. The\\n facts became clear to the court after hearing\\n the credible testimony of the deputy clerk and\\n the less credible testimony of Juror 12. The\\n demeanor of Juror 12 before the court\\n confirmed the court’s findings.\\n\\nGSA23–24. The second opinion addressed motions for\\nbail pending appeal from Nicholas and Brand. GSA25.\\nThere, Judge Bartle explained:\\n\\n The law is well-settled that the court has\\n discretion to act as it did under these\\n circumstances. See United States v. Kemp,\\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\\n after taking testimony, specifically found that\\n the juror, following only a few hours of\\n deliberation, stated to the court’s courtroom\\n deputy clerk that he would hang this jury no\\n matter what. He could not possibly have\\n reviewed all of the law and evidence of this\\n five-week trial at the time he made his\\n remark. The court examined the deputy clerk\\n and the juror under oath in the presence of\\n counsel for all parties. The undersigned\\n\\n 54\\n\\f found the deputy clerk to be credible and the\\n juror not to be credible. Based on the juror’s\\n demeanor, it was clear he would not change\\n his attitude and that his intent had been and\\n would continue to be to refuse to deliberate\\n in good faith concerning the law and the\\n evidence.\\n\\nGSA32.\\n After deliberating for approximately 15 hours, the\\njury returned with its verdicts on June 21, 2016, finding\\nthe defendants guilty on most counts. Fattah, Vederman,\\nand Brand were convicted on all counts. The jury acquitted\\nBowser on sixteen counts, but found her guilty of the\\nbribery conspiracy and the associated charges of bank\\nfraud, making false statements to a financial institution,\\nfalsifying records, and money laundering (Counts 16, 19,\\n20, 21 and 22). The jury also acquitted Nicholas of wire\\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\\n The following week, on June 27, the Supreme Court\\nissued its opinion in McDonnell v. United States, 136 S.\\nCt. 2355 (2016). McDonnell provided new limitations on\\nthe definition of “official acts” as used in the honest\\nservices fraud and bribery statutes under which Fattah and\\nVederman had been convicted. Id. at 2369–72. Fattah and\\nVederman both moved to set aside their convictions. The\\nDistrict Court “acknowledge[d] that under McDonnell our\\ninstructions to the jury on the meaning of official act\\nturned out to be incomplete and thus erroneous.” JA103.\\n 55\\n\\fBut the Court held that “the incomplete and thus erroneous\\njury instruction on the meaning of official acts did not\\ninfluence the verdict on the bribery counts” and upheld the\\nverdict on Counts 16–18 and 22–23. JA107, 121.\\n\\n Fattah, Vederman, and Bowser had more success\\nwith their other post-verdict motions. The District Court,\\nin a thoughtful opinion, granted relief under Federal Rule\\nof Criminal Procedure 29, acquitting Vederman of the\\nRICO conspiracy (Count 1) and Fattah, Vederman, and\\nBowser of bank fraud, making false statements to a\\nfinancial institution, and falsifying records (Counts 19, 20,\\nand 21). JA37–139.\\n This appeal followed. 8 The defendants raise a\\nvariety of challenges to their convictions. All defendants\\nbut Bowser challenge the District Court’s decision to\\ndismiss Juror 12. Fattah and Vederman argue that the\\nDistrict Court erred in upholding the jury’s verdict on the\\nbribery and honest services fraud counts in light of the\\nSupreme Court’s decision in McDonnell. Fattah, Brand\\nand Nicholas challenge the sufficiency of the evidence\\nunderlying the RICO conviction. Several of the defendants\\ncontend the District Court erred in its instruction on intent\\nand by sending the indictment out to the jury. There are\\n\\n\\n\\n8\\n Fattah, Brand, Vederman, and Nicholas each filed a\\ntimely notice of appeal, but Bowser did not challenge her\\nconvictions.\\n 56\\n\\falso several evidentiary challenges.9 The Government\\ncross-appeals from the District Court’s judgment\\nacquitting Fattah and Vederman on Counts 19 and 20,\\narguing that the District Court erred in interpreting the\\ndefinition of a “mortgage lending business” under 18\\nU.S.C. § 27. We address these arguments in turn.\\n\\n We hold that the District Court erred in upholding\\nthe jury verdict in light of McDonnell, and we will\\ntherefore reverse and remand for retrial on Counts 16, 17,\\n18, 22, and 23. We also hold that the District Court erred\\n\\n9\\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\\nHerbert Vederman, Robert Brand, and Karen Nicholas to\\nthe extent their arguments on appeal apply to Mr. Fattah.”\\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\\n28(i) provides that a defendant, “[i]n a case involving\\nmore than one appellant . . . may adopt by reference a part\\nof another’s brief.” Here, Fattah’s decision to join fails to\\nspecify which of the many issues of his codefendants he\\nbelieves worthy of our consideration. Rather, it appears\\nthat he presumes we will scour the record and make that\\ndetermination for him. This type of blanket request fails to\\nsatisfy Rule 28(a)(5)’s directive requiring that the\\n“appellant’s brief must contain . . . a statement of the\\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\\nconclude that expecting the appellate court to identify the\\nissues to be adopted simply results in the abandonment and\\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\\n1 F.3d 176, 182 (3d Cir. 1993).\\n 57\\n\\fin acquitting Fattah and Vederman on Counts 19 and 20.\\nBecause the jury’s verdict was supported by the evidence,\\nwe will reinstate the convictions as to those counts. In all\\nother respects, we will affirm the judgment of the District\\nCourt.\\n\\n III. Juror Misconduct and Dismissal of Juror 12 10\\n Defendant Fattah challenges the District Court’s\\ndecision to conduct an in camera inquiry into alleged juror\\nmisconduct and the ultimate dismissal of Juror 12. 11 We\\nreject both challenges. The record reveals credible\\nallegations of juror misconduct and a sufficient basis to\\nsupport the finding that Juror 12 violated his oath.\\n\\n A. Investigation of Alleged Juror Misconduct\\n We first consider whether the District Court erred in\\nits handling of the two notes from jurors. A trial court’s\\nresponse to allegations of juror misconduct is reviewed\\nunder an abuse of discretion standard. United States v.\\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\\nconclude that the District Court did not abuse its discretion\\n\\n\\n10\\n The District Court had jurisdiction under 18 U.S.C.\\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\\n18 U.S.C. § 3742(a).\\n11\\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\\nreversible error concerning the dismissal of Juror 12.\\n 58\\n\\fin addressing the issues raised in the jurors’ notes to the\\nCourt.\\n Trial courts are afforded discretion in responding to\\nallegations of juror misconduct. This is so because “the\\ntrial court is in a superior position to observe the ‘mood at\\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\\n690 (quoting United States v. Chiantese, 582 F.2d 974,\\n980 (5th Cir. 1978)). But this discretion is not unlimited.\\nOnce the jury retires to deliberate, the confidentiality of its\\ndeliberations must be closely guarded. An accused is\\nconstitutionally entitled to be tried before a jury of his\\npeers. As ordinary citizens, jurors are “expected to speak,\\ndebate, argue, and make decisions the way ordinary people\\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\\nagainst intrusion into a defendant’s right to be judged only\\nby fellow citizens, “the door to the jury room [is] locked.”\\nId. at 875.\\n In Boone, this Court considered the threshold for\\nintervention by a trial judge who is presented with\\nallegations of juror misconduct during the course of\\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\\nbeyond question that the secrecy of deliberations is critical\\nto the success of the jury system.” Id. at 329. But that\\nsecrecy abuts a competing interest—the jury’s proper\\nexecution of its duties. That is, “a juror who refuses to\\ndeliberate or who commits jury nullification violates the\\nsworn jury oath and prevents the jury from fulfilling its\\n\\n 59\\n\\fconstitutional role.” Id. Recognizing these competing\\ninterests, we declined in Boone to adopt a sweeping\\nlimitation on a trial court’s ability to investigate\\nallegations of misconduct during jury deliberations. See id.\\nConsistent with the standard applied at other stages of\\ncriminal proceedings, Boone teaches that “where\\nsubstantial evidence of jury misconduct—including\\ncredible allegations of jury nullification or of a refusal to\\ndeliberate—arises during deliberations, a district court\\nmay, within its sound discretion, investigate the\\nallegations through juror questioning or other appropriate\\nmeans.” Id.\\n Fattah argues that the District Court had no basis to\\nquestion any of the jurors. Fattah Br. 20. We disagree. In\\nBoone, notes from the jury presented substantial credible\\nevidence of misconduct. 458 F.3d at 330. Here, the initial\\nnote from the foreperson alleged that Juror 12 “refuse[d]\\nto vote by the letter of the law,” would “not listen or reason\\nwith anybody,” and that he had “an agenda or ax to grind”\\nwith the Government. JA5916. The note contained\\nallegations of both a refusal to deliberate and a suggestion\\nof nullification. A refusal to deliberate is a violation of a\\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\\nsettled that jurors have a duty to deliberate.”)). Moreover,\\nnullification—a juror’s refusal to follow the law—is a\\nviolation of the juror’s sworn oath to render a verdict\\naccording to the law and evidence. See United States v.\\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\\n 60\\n\\fboth “benevolent” and “shameful” examples of juror\\nnullification, but “categorically reject[ing] the idea that, in\\na society committed to the rule of law, jury nullification is\\ndesirable or that courts may permit it to occur when it is\\nwithin their authority to prevent”). The second jury note,\\nsigned by nine jurors, supported the claim of misconduct\\nby asserting that Juror 12 was “incapable of making\\ndecision[s]” and was “constantly scream[ing]” at the other\\njurors. JA5916–17. We conclude that the District Court\\ndid not abuse its discretion in deciding to initially question\\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\\n\\n Fattah also challenges the scope of the District\\nCourt’s questioning. He argues that the rights to an\\nimpartial jury and to a unanimous verdict “would be\\nrendered toothless if trial courts had free rein to question\\njurors during deliberations.” Fattah Br. 36. Indeed, we\\nacknowledged the legitimacy of such a concern in Boone.\\nDespite adopting a modest “credible allegations” standard\\nfor investigating misconduct, we “ke[pt] in mind the\\nimportance of maintaining deliberative secrecy.” Boone,\\n458 F.3d at 329. Fattah asserts that the trial court’s\\nquestions to the five jurors were “intrusive and pointed”\\nand “nothing like the questioning . . . approved in Boone.”\\nFattah Br. 38. But Fattah does not elaborate on how, in his\\nview, the questions posed by Judge Bartle specifically\\nintruded into deliberative secrecy.\\n\\n To be sure, Judge Bartle’s questioning of each juror\\nwas more extemporaneous than the juror questioning in\\n\\n 61\\n\\fBoone. There, the district court asked a single juror four\\n“concise and carefully-worded” questions. 458 F.3d at\\n330. Judge Bartle’s voir dire of each of the five jurors took\\non a more conversational tone. We take no issue with that\\napproach. The substance of the judge’s questions was\\nlimited and mirrored that of questions we deemed\\nappropriate in Kemp. There, the court conducted three\\nrounds of questioning. In the first round, each juror was\\nasked:\\n (1) “Are you personally experiencing any\\n problems with how the deliberations are\\n proceeding without telling us anything about\\n the votes as to guilt or innocence? If yes,\\n describe the problem.” (2) “Are all the jurors\\n discussing the evidence or lack of evidence?”\\n (3) “Are all the jurors following the court’s\\n instructions on the law?”\\n\\nKemp, 500 F.3d at 273. In the second and third rounds,\\neach juror was asked:\\n (1) “Is there any juror or jurors who are\\n refusing to deliberate?” (2) “Is there any juror\\n who is refusing to discuss the evidence or\\n lack of evidence?” (3) “Is there any juror who\\n is refusing to follow the Court’s\\n instructions?”\\nId. at 274. Here, Judge Bartle began his voir dire of each\\njuror by stating that he did not wish for the juror to discuss\\n 62\\n\\fthe merits of the case or to reveal the content of the\\ndeliberations that had taken place. He asked the jurors\\nwhether screaming was occurring, whether the jurors were\\ndiscussing the evidence, whether Juror 12 was placing his\\nhands on other jurors, and whether Juror 12 was unwilling\\nto follow his instructions.\\n Fattah points to no specific question posed or topic\\ndiscussed that was inappropriate, and we see little to no\\nsubstantive difference between the questions here and\\nthose asked by the trial judge in Kemp. As in Kemp, “the\\nDistrict Court took care to limit its questions to appropriate\\nmatters that did not touch on the merits of the jury’s\\ndeliberation, and expressly informed each juror on\\nmultiple occasions that he or she should not reveal the\\nsubstance of the deliberations.” Id. at 302 (citing United\\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\\n Fattah also argues that once the remarks of Juror 2\\nand Juror 12 revealed no further evidence of misconduct,\\nthe court had no basis to question other jurors. Fattah\\nReply 19. Yet, our cases make clear that a trial court may,\\nin its discretion, examine each juror. Kemp, 500 F.3d at\\n302 (“We have recognized that there are times in which\\nindividual questioning is the optimal way in which to root\\nout misconduct.”). Indeed, “the District Court must utilize\\nprocedures that will ‘provide a reasonable assurance for\\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\\n\\n\\n\\n 63\\n\\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\\n(3d Cir. 1981)). 12\\n\\n Judge Bartle, a very able and experienced district\\njudge, was in the best position to determine what type of\\ninquiry was warranted under the circumstances. We\\nconclude that his questioning of the five jurors was not an\\nabuse of discretion. See id. at 302.\\n\\n B. Dismissal of Juror 12\\n Fattah, joined by Vederman, Brand, and Nicholas,\\nstrongly contends that the District Court committed\\nreversible error by dismissing Juror 12. “We review the\\ndismissal of a juror for cause for abuse of discretion.”\\n\\n12\\n Our cases do not suggest that a trial judge confronted\\nwith allegations that a jury’s deliberations are being\\nobstructed by one of its members should always resort to\\ninterviewing jurors. Reinstructing the jury on its duty to\\ndeliberate will often be the better course at the first sign of\\ntrouble. Mere disagreement among jurors—even spirited\\ndisagreement—is no ground for intervention.\\nFurthermore, intrusive or leading questions about the\\ndeliberative process may work against the twin goals of\\nprotecting that process and ensuring that jurors remain\\nfaithful to their oaths. We share the Eleventh Circuit’s\\npreference of “err[ing] on the side of too little inquiry as\\nopposed to too much.” United States v. Oscar, 877 F.3d\\n1270, 1287 (11th Cir. 2017) (quoting United States v.\\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\\n 64\\n\\fKemp, 500 F.3d at 303. That deferential standard compels\\nus to affirm.\\n Rule 23(b) of the Federal Rules of Criminal\\nProcedure permits a trial court to excuse a deliberating\\njuror for good cause. See id. (citing Fed. R. Crim. P.\\n23(b)). Good cause exists where a juror refuses to apply\\nthe law, refuses to follow the court’s instructions, refuses\\nto deliberate with his or her fellow jurors, or demonstrates\\nbias. See Kemp, 500 F.3d at 305–06; United States v.\\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\\nF.3d at 617. Good cause does not exist when there is\\nreasonable but sustained disagreement about how a juror\\nviews the evidence. The courts of appeals are emphatic\\nthat trial courts “may not dismiss a juror during\\ndeliberations if the request for discharge stems from\\ndoubts the juror harbors about the sufficiency of the\\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\\nThomas, 116 F.3d at 622.\\n\\n To reinforce a defendant’s right to a unanimous\\njury, we have adopted a high standard for juror dismissal.\\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\\ndischarge a juror for bias, failure to deliberate, failure to\\nfollow the district court’s instructions, or jury nullification\\nwhen there is no reasonable possibility that the allegations\\nof misconduct stem from the juror’s view of the evidence.”\\n\\n 65\\n\\fId. at 304 (emphasis added). This “no reasonable\\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\\ncorresponds with the burden for establishing guilt in a\\ncriminal trial.” Id.\\n\\n We first applied this standard in Kemp, but have not\\nhad occasion to do so since. There, the evidence\\nsupporting the district court’s removal decision was\\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\\nand consistently reported that a juror was improperly\\nbiased, and did so only after three rounds of questioning\\nand careful and correct instructions from the district court\\nas to the distinction between appropriate skepticism and\\nimpermissible bias. Id. at 304–05; see id. at 275–76\\n(district court’s instruction). The testimony also showed\\nthat the juror in question refused to deliberate or to discuss\\nthe evidence with her fellow jurors. Id. at 305.\\n Whether the evidence of misconduct in this case is\\nas strong as that in Kemp is beside the point. After only\\nfour hours of deliberations, Juror 12 stated unequivocally\\nto the courtroom deputy that he was “going to hang” the\\njury, and that it would be “11 to 1 no matter what.”\\nJA5981–82 (emphasis added). These statements, coupled\\nwith the District Court’s finding that Juror 12 lacked\\ncredibility, provided a sufficient basis for Juror 12’s\\ndismissal.\\n\\n As grounds for excusing Juror 12, the District Court\\nfound that he refused to deliberate in good faith, “delayed,\\ndisrupted, impeded, and obstructed the deliberative\\n 66\\n\\fprocess and had the intent to do so,” JA5995, and that he\\nwas “intent on . . . hanging this jury no matter what the law\\nis, no matter what the evidence is.” Id. The District Court\\ndetermined from this that Juror 12 had violated his oath as\\na juror and that no further instructions or admonitions\\ncould rehabilitate the juror. Id. The District Court based\\nthese findings on personal observation, including Juror\\n12’s words and demeanor, and making the specific finding\\nthat Juror 12 was not credible. That finding is amply\\nsupported by the record.\\n\\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\\nCir. 2001), the Ninth Circuit recognized that “the\\ndemeanor of the pertinent juror is important to juror\\nmisconduct determinations” because the “juror’s\\nmotivations and intentions are at issue.” That court\\nemphasized, as we do, that a district judge is best situated\\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\\nhe could not recall putting his hand on another juror’s\\nshoulder, while his fellow jurors’ testimony was consistent\\non this point. Juror 12 also failed, at first, to recall his\\ntroubling statements to the courtroom deputy despite\\nhaving made those statements only the previous afternoon.\\nWhen questioned a second time and asked directly about\\nthe statements, he admitted to saying that he would hang\\nthe jury but claimed he could not “really remember”\\nsaying “no matter what” the day before. JA5989–90. Juror\\n12’s spotty recollection of the previous day’s events\\nfurther supports the District Court’s finding that he was\\nnot credible.\\n 67\\n\\f Fattah argues that the credibility determination was\\nnot, by itself, a sufficient reason to dismiss the juror\\nbecause the record demonstrates more than a reasonable\\npossibility that the complaints about his conduct stemmed\\nfrom Juror 12’s own view of the Government’s case.\\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\\nthe District Court abused its discretion by dismissing Juror\\n12 “on the basis of, in effect, six words the juror\\npurportedly said to the court’s deputy after he was verbally\\nattacked by other jurors.” Fattah Br. 24. According to\\nFattah, the questioning of the other jurors “confirmed that\\nthere were no legitimate grounds for removing juror 12.”\\nId. at 26. We conclude otherwise.\\n “A district court’s finding on the question whether\\na juror has impermissibly refused to participate in the\\ndeliberation process is a finding of fact to which\\nappropriate deference is due.” Baker, 262 F.3d at 130.\\nWhile district courts must apply a high standard for juror\\ndismissal, their underlying findings are afforded\\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\\nif the decision to dismiss a juror was “without factual\\nsupport, or for a legally irrelevant reason.” Abbell, 271\\nF.3d at 1302 (citation omitted).\\n Here, the District Court had a legitimate reason for\\nremoving Juror 12. Refusal to deliberate constitutes good\\ncause for dismissal. Although the judge did not expressly\\narticulate the Kemp standard when he announced that he\\n\\n 68\\n\\fwould dismiss Juror 12, he did acknowledge the “no\\nreasonable possibility” standard in his discussion with\\ncounsel. The unmistakable import of the District Court’s\\nstatement from the bench is that there was no reasonable\\npossibility that Juror 12’s intransigence was based on his\\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\\n Fattah contends that there is no record support for\\nthe finding that Juror 12 said “he was going to hang this\\njury no matter what.” Fattah Br. 29. To be sure, the\\ncourtroom deputy’s testimony is not that Juror 12 used the\\nwords “hang this jury” and “no matter what” in the same\\nsentence. She testified that Juror 12 first stated “I am going\\nto hang this jury,” then later stated “it is going to be 11 to\\n1 no matter what.” JA5981–82. This is a distinction\\nwithout a difference. Likewise, Fattah challenges the\\nDistrict Court’s finding that Juror 12 was determined to\\nhang the jury “no matter what the law is” and “no matter\\nwhat the evidence is.” Fattah Br. 29. Although there is no\\nevidence that Juror 12 uttered the phrases “no matter what\\nthe law is” or “no matter what the evidence is,” the District\\nCourt was describing the import of Juror 12’s statements.\\nThis was not error.\\n Fattah expresses the concern that “[i]f jurors are\\nasked the right questions or interrogated long enough, it\\nwould not be difficult for a trial court to elicit testimony\\nfrom [a] majority [of] jurors that can be held up as\\nevidence of a dissenting juror’s bias or refusal to\\ndeliberate.” Fattah Br. 22. He also worries that a group of\\n\\n 69\\n\\fjurors might have an incentive to rid themselves of a juror\\nwho holds a different view. Id. These are valid concerns—\\nbut no basis existed for such concerns in this case. Juror\\n12’s own words provided most of the support for his\\neventual dismissal. Furthermore, his statements were\\nmade early in the deliberations, in a complex case, before\\nany juror could reasonably be expected to have reached\\nfinal verdicts on the twenty-nine counts before the jury.\\n\\n The able District Judge did not err in finding that\\nJuror 12 refused to deliberate and therefore violated his\\noath.\\n\\n IV. The District Court’s Instructions Under\\n McDonnell\\n On appeal, Fattah and Vederman renew their\\nchallenge to the jury instructions given on Counts 3, 16,\\n17, 18, 22, and 23, concerning the meaning of the term\\n“official act” as used in the bribery statute (pursuant to\\nwhich both were convicted) and the honest services fraud\\nstatute (pursuant to which Fattah alone was convicted).\\n\\n In light of the Supreme Court’s opinion in\\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\\nreleased the week after the jury verdict, the District Court\\nconceded that its instructions were incomplete and\\nerroneous, at least as to Counts 16–18. Nevertheless, the\\nDistrict Court held that the erroneous jury instructions had\\nnot influenced the verdict on the bribery counts, and\\ndeclined to set aside Fattah and Vederman’s convictions.\\n 70\\n\\fAs to Counts 16–18 and 22–23, we disagree, and will\\nreverse the District Court’s judgment. The District Court’s\\njudgment with respect to Count 3, which did not involve\\nVederman, will be affirmed. JA78–79.\\n\\n A. The McDonnell Framework\\n In McDonnell, the Supreme Court interpreted the\\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\\nS. Ct. at 2368. The statute defines an “official act” as “any\\ndecision or action on any question, matter, cause, suit,\\nproceeding or controversy, which may at any time be\\npending, or which may by law be brought before any\\npublic official, in such official’s official capacity, or in\\nsuch official’s place of trust or profit.” 18 U.S.C.\\n§ 201(a)(3). The McDonnell Court distilled this definition\\ninto two requirements:\\n First, the Government must identify a\\n “question, matter, cause, suit, proceeding or\\n controversy” that “may at any time be\\n pending” or “may by law be brought” before\\n a public official. Second, the Government\\n must prove that the public official made a\\n decision or took an action “on” that question,\\n matter, cause, suit, proceeding, or\\n controversy, or agreed to do so.\\n\\n136 S. Ct. at 2368. Applying this two-step test to Governor\\nRobert McDonnell’s convictions, the Supreme Court\\nconcluded that “the jury was not correctly instructed on\\n 71\\n\\fthe meaning of ‘official act,’ ” and as a result, “may have\\nconvicted Governor McDonnell for conduct that is not\\nunlawful.” Id. at 2375. Given that uncertainty, the Court\\n“[could not] conclude that the errors in the jury\\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\\nThe Supreme Court, therefore, vacated Governor\\nMcDonnell’s convictions. Id.\\n\\n McDonnell lays out a clear path for the Government\\nto follow in proving that an accused has performed an\\n“official act.” First, the Government must “identify a\\n‘question, matter, cause, suit, proceeding or controversy’\\nthat ‘may at any time be pending’ or ‘may by law be\\nbrought’ before a public official.” 136 S. Ct. at 2368\\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\\ninto two sub-components. In Step 1(A), the Government\\nmust “identify a ‘question, matter, cause, suit, proceeding\\nor controversy.’ ” Id. Step 1(B) then clarifies that the\\nidentified “question, matter, cause, suit, proceeding or\\ncontroversy” be one that “ ‘may at any time be pending’ or\\n‘may by law be brought’ before a public official.” Id.\\n\\n Under Step 1(A), a “question, matter, cause, suit,\\nproceeding or controversy” must be “a formal exercise of\\ngovernmental power that is similar in nature to a lawsuit\\nbefore a court, a determination before an agency, or a\\nhearing before a committee.” Id. at 2372. Importantly, “a\\ntypical meeting, telephone call, or event arranged by a\\n\\n\\n 72\\n\\fpublic official” does not qualify as such a formal exercise\\nof governmental power. Id. at 2368.\\n Step 1(B) then requires us to ask whether the\\nqualifying “question, matter, cause, suit, proceeding or\\ncontroversy” was one that “ ‘may at any time be pending’\\nor ‘may by law be brought’ before a public official.” Id.\\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\\nby law be brought’ suggest something that is relatively\\ncircumscribed—the kind of thing that can be put on an\\nagenda, tracked for progress, and then checked off as\\ncomplete.” Id. at 2369; accord United States v. Repak, 852\\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\\nCt. at 2369). By contrast, matters described at a high level\\nof generality—for example, “[e]conomic development,”\\n“justice,” and “national security”—are not sufficiently\\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\\n\\n In McDonnell, the Court concluded that at least\\nthree questions or matters identified by the Fourth Circuit\\nwere sufficiently focused:\\n (1) whether researchers at any of Virginia’s\\n state universities would initiate a study of [a\\n drug]; (2) whether the state-created Tobacco\\n Indemnification and Community\\n Revitalization Commission would allocate\\n grant money for the study of [a chemical\\n compound]; and (3) whether the health\\n insurance plan for state employees in\\n\\n 73\\n\\f Virginia would include [a specific drug] as a\\n covered drug.\\nId. at 2370 (internal quotations omitted) (quoting United\\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\\n2015)). We provided guidance in the form of a fourth\\nexample in Repak, when we held that a redevelopment\\nauthority’s awarding of contracts was “a concrete\\ndetermination made by the [redevelopment authority’s]\\nBoard of Directors.” 852 F.3d at 253.\\n\\n Step 2 requires the Government to prove that the\\npublic official made a “decision” or took “an action” on\\nthe identified “question, matter, cause, suit, proceeding or\\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\\nMcDonnell Court explained:\\n Setting up a meeting, hosting an event, or\\n calling an official (or agreeing to do so)\\n merely to talk about a research study or to\\n gather additional information . . . does not\\n qualify as a decision or action on the pending\\n question of whether to initiate the study.\\n Simply expressing support for the research\\n study at a meeting, event, or call—or sending\\n a subordinate to such a meeting, event, or\\n call—similarly does not qualify as a decision\\n or action on the study, as long as the public\\n official does not intend to exert pressure on\\n another official or provide advice, knowing\\n\\n 74\\n\\f or intending such advice to form the basis for\\n an “official act.”\\nId. at 2371. The Court further clarified:\\n\\n If an official sets up a meeting, hosts an\\n event, or makes a phone call on a question or\\n matter that is or could be pending before\\n another official, that could serve as evidence\\n of an agreement to take an official act. A jury\\n could conclude, for example, that the official\\n was attempting to pressure or advise another\\n official on a pending matter. And if the\\n official agreed to exert that pressure or give\\n that advice in exchange for a thing of value,\\n that would be illegal.\\nId.\\n Here, Fattah was charged with engaging in three\\ncategories of official acts, which we analyze in accordance\\nwith the McDonnell framework. In Counts 16–18 and 22–\\n23, Fattah is alleged to have set up a meeting between\\nVederman and the U.S. Trade Representative, attempted\\nto secure Vederman an ambassadorship, and hired\\nVederman’s girlfriend, all in return for a course of conduct\\nwherein Vederman provided things of value to Fattah.\\n\\n In this case, as in McDonnell, the jury instructions\\nwere erroneous. We conclude that the first category of the\\ncharged acts—setting up a meeting between Vederman\\n 75\\n\\fand the U.S. Trade Representative—is not unlawful, and\\nthat the second category—attempting to secure Vederman\\nan ambassadorship—requires reconsideration by a\\nproperly instructed jury. The third charged act—hiring\\nVederman’s girlfriend—is clearly an official act. But\\nbecause we cannot isolate the jury’s consideration of the\\nhiring from the first two categories of charged acts, we\\nmust reverse and remand the judgment of the District\\nCourt.\\n\\n B. The Kirk Meeting\\n We turn first to Fattah’s scheduling of a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk. Under McDonnell, “setting up a meeting . . .\\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\\nS. Ct. at 2368. Fattah’s setting up the meeting between\\nVederman and Kirk was therefore not an official act, a\\nconcession implicit in the Government’s opening brief.\\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\\none of the “two categories” of allegedly “official acts”).\\nBut the jury was not properly instructed on this point.\\nWithout the benefit of the principles laid down in\\nMcDonnell, the jury was free to conclude that arranging\\nthe Kirk meeting was an official act—and it may have\\ndone so. The District Court’s erroneous jury instructions,\\ntherefore, cannot survive harmless error review.\\n\\n In a footnote in its brief to this Court, the\\nGovernment argues that evidence about the Kirk meeting\\nwas offered only “because it established the strength of\\n 76\\n\\fVederman’s desire to be an ambassador” and not because\\nthe Government was attempting to establish the meeting\\nas an independent official act. Id. at79–80 n.6. But the\\nrecord undercuts the Government’s post hoc justification.\\n\\n The indictment, provided to the jury in redacted\\nform for use in its deliberations, lists Fattah’s setting up\\nthe Kirk meeting as an official act under the heading\\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\\nUnder this heading are three distinct subheadings:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) “Hiring\\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\\nJA494–95. The second subheading, “The Pursuit of\\nAnother Executive Branch Position,” describes the\\narrangement of the Kirk meeting. Quite clearly, then, this\\nthree-part structure demonstrates that setting up the Kirk\\nmeeting was one of three distinct categories of official acts\\nalleged by the Government.\\n\\n Although there is some support for the\\nGovernment’s argument that evidence of the Kirk meeting\\nwas presented at trial only to establish the extent of\\nVederman’s interest in becoming an ambassador, JA827,\\n852–53 (mentioning the Kirk meeting in close proximity\\nto references to Fattah’s attempts to secure Vederman an\\nambassadorship), it is undermined by language in the\\nredacted indictment itself, and by the way in which the\\nGovernment presented its case at trial as a “pattern” of\\nconnected acts.\\n\\n 77\\n\\f The redacted indictment, for example, refers to the\\nKirk meeting as “The Pursuit of Another Executive\\nBranch Position.” JA495 (emphasis added). The use of the\\nword “Another” strongly suggests that evidence about the\\nKirk meeting was not merely evidence of Fattah’s attempt\\nto secure Vederman an ambassadorship, but was also\\nevidence of a separate and distinct attempt to secure\\nVederman a position on a federal trade-related\\ncommission. The redacted indictment also notes that “[i]n\\nor around May 2011, with little progress made on securing\\nan ambassadorship for VEDERMAN, FATTAH turned\\ntowards obtaining for VEDERMAN an appointment in the\\nExecutive Branch to a federal trade commission.” Id.\\n(emphasis added). The words “turned towards,” taken\\nliterally, clearly convey that arranging the Kirk meeting\\nwas presented as distinct from Fattah’s efforts to secure\\nVederman an ambassadorship.\\n\\n The District Court denied Fattah and Vederman a\\nnew trial on Counts 17 and 18, referring to evidence of the\\nKirk meeting as “de minimis” and noting that “Kirk’s\\ntestimony during this lengthy trial lasted a mere sixteen\\nminutes.” JA97 n.14. In the District Court’s view,\\nevidence of the Kirk meeting “played no role in the\\noutcome” of the case. Id. Considering the record in light\\nof McDonnell, we are not so sure.\\n\\n Although it is possible that evidence of the Kirk\\nmeeting played a minor role at trial when compared to the\\nother acts on which the Government presented evidence,\\n\\n 78\\n\\fthe redacted indictment suggests that the Kirk meeting was\\na significant part of the Government’s case. The\\nindictment dedicates five paragraphs to describing the\\nKirk meeting, but just three paragraphs to describing the\\nhiring of Vederman’s girlfriend—a hiring that, as we\\nexplain below, is clearly an official act. JA495–96. While\\nneither the number of minutes used at trial nor the number\\nof paragraphs contained in an indictment is a dispositive\\nunit of measurement for determining the significance of\\nevidence, we conclude that the District Court’s erroneous\\njury instructions pertaining to the Kirk meeting were not\\nharmless.\\n We conclude, in accordance with McDonnell, that\\nFattah’s arranging a meeting between Vederman and the\\nU.S. Trade Representative was not itself an official act.\\nBecause the jury may have convicted Fattah for conduct\\nthat is not unlawful, we cannot conclude that the error in\\nthe jury instruction was harmless beyond a reasonable\\ndoubt, and we must vacate and remand the convictions of\\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\\n\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship\\n The nature of Fattah’s efforts to secure Vederman\\nan ambassadorship is less clear, and presents a closer\\nquestion than the Kirk meeting. We ultimately conclude\\nthat the question warrants remand so that it may be\\nanswered by a properly instructed jury. On remand, the\\njury must decide whether Fattah’s conduct constituted a\\n 79\\n\\f“decision” or “action” under Step 2 of the McDonnell\\nanalysis.\\n At the outset, it is clear to us that, under Steps 1(A)\\nand 1(B), a formal appointment of Vederman as an\\nambassador would qualify as a “matter” that “may at any\\ntime be pending” before a public official. The formal\\nappointment of a particular person (Vederman), to a\\nspecific position (an ambassadorship), constitutes a matter\\nthat is sufficiently focused and concrete. The formal\\nappointment of an ambassador is a matter that is “pending”\\nbefore the President—the constitutional actor charged\\nwith nominating ambassadors—as well Senators, who are\\ncharged with confirming the President’s ambassadorial\\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\\nand by and with the Advice and Consent of the Senate,\\nshall appoint Ambassadors . . . .”). It is beyond cavil that\\nthe formal appointment of an ambassador satisfies both\\nsub-components of McDonnell’s Step 1.\\n Turning to Step 2, we consider whether Fattah’s\\nefforts to secure Vederman an ambassadorship qualify as\\nmaking a “decision” or taking “an action” on the identified\\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\\nAlthough those efforts—three emails, two letters, and one\\nphone call—do not themselves qualify as a “question,\\nmatter, cause, suit, proceeding, or controversy” under\\nMcDonnell’s Step 1, they may nonetheless qualify as the\\nmaking of a “decision” or taking “an action” on the\\nidentified matter of appointment. Id.\\n\\n 80\\n\\f McDonnell’s Step 2 requires us to determine\\nwhether Fattah’s efforts qualify as permissible attempts to\\n“express[] support,” or impermissible attempts “to\\npressure or advise another official on a pending matter.”\\nId. at 2371. At trial, the jury was not instructed that they\\nhad to place Fattah’s efforts on one side or the other of this\\ndivide. The jury might even have thought they were\\npermitted to find Fattah’s efforts—three emails, two\\nletters, and one phone call—to themselves be official acts,\\nrather than a “decision” or “action” on the properly\\nidentified matter of appointment. Such a determination\\nwould have been contrary to the dictates of McDonnell.\\n Faced with such uncertainty, we cannot assume the\\njury verdict was proper. Although the jury might not have\\nconcluded that Fattah’s efforts were themselves official\\nacts, and although the jury might not have concluded that\\nthose efforts crossed the line into impermissible attempts\\n“to pressure or advise,” we are unable to conclude that the\\njury necessarily did so. Nor can we, on the cold record\\nbefore us, determine whether Fattah’s efforts to secure\\nVederman an ambassadorship crossed the line.\\nDetermining, for example, just how forceful a strongly\\nworded letter of recommendation must be before it\\nbecomes impermissible “pressure or advice” is a fact-\\nintensive inquiry that falls within the domain of a properly\\ninstructed jury. Should the Government elect to retry these\\ncounts after remand, the finder of fact will need to decide\\nwhether Fattah’s efforts constituted permissible attempts\\nto “express[] support,” or impermissible attempts “to\\n 81\\n\\fpressure or advise another official on a pending matter.”\\nId.\\n\\n D. The Zionts Hiring\\n The third group of acts charged in the Fattah–\\nVederman scheme involves Fattah’s decision to hire\\nVederman’s girlfriend, Alexandra Zionts, as a\\ncongressional staffer. We conclude that the hiring was an\\nofficial act. A brief analysis of McDonnell’s two steps\\nsuffices to show why this is so.\\n Here, under McDonnell’s Step 1(A), the relevant\\n“matter” is the decision to hire Zionts. Step 1(B) of the\\nanalysis is satisfied because the hiring decision was\\n“pending” before Fattah himself. And that hiring was\\n“focused and concrete,” “within the specific duties of an\\nofficial’s position—the function conferred by the\\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\\nStep 2 requires that the “Government . . . prove that the\\npublic official made a decision or took an action ‘on’ [the\\nidentified] question, matter, cause, suit, proceeding, or\\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\\ndecision to hire Zionts clearly satisfies that requirement.\\nWe therefore conclude that the hiring of Zionts was an\\nofficial act under McDonnell.\\n\\n Vederman concedes that the Zionts hiring was an\\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\\nhis part, maintains that “hiring someone for a routine, part-\\ntime, short-term position falls well outside [the] definition\\n 82\\n\\f[of ‘official act’] and is nothing like a lawsuit, agency\\ndetermination, or committee hearing, even if each shares\\nthe happenstance that federal funds will be used.” Fattah\\nReply Br. 25.\\n\\n Fattah’s argument lacks traction. Official acts need\\nnot be momentous decisions—or even notable ones.\\nJudges, for example, make “routine” evidentiary rulings\\nevery day, and yet it is beyond question that those rulings\\nare official acts. In the realm of official acts, it is of no\\nmoment that Zionts provided only “part-time, short term”\\nlabor. When a public official hires an employee to work in\\nhis government office, he has engaged in an official act.\\n * * *\\n If we could conclude that the Zionts hiring was the\\nonly category of actions that the jury relied on when it\\nfound that Fattah performed an official act under Counts\\n16–18 and 22–23, remand would not be necessary. But, as\\nwe have explained, we cannot rule out that the jury\\nerroneously convicted Fattah and Vederman based on\\nother actions that were not official acts under\\nMcDonnell.13\\n\\n\\n13\\n More specifically, the incomplete, and therefore\\nerroneous, instructions could have led the jury to commit\\nat least one of three mistakes. First, the jury could have\\nimproperly convicted Vederman and Fattah based on the\\nKirk meeting alone, or misunderstood the Kirk meeting to\\n 83\\n\\f The Government argues that because the Zionts\\nhiring was an official act, the effect of the erroneous jury\\ninstructions could be no more than harmless. The jury’s\\nverdict, the Government contends, permits us to deduce\\nthat the jury necessarily concluded the Zionts hiring was\\nan official act, and that this conclusion alone supported\\nFattah’s and Vederman’s convictions as to Counts 16–18\\nand 22–23—regardless of whether the jury erroneously\\nfound any unofficial acts to be official acts. We disagree.\\n Fattah and Vederman objected to the definition of\\n“official act” at trial. We thus apply the harmless error\\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\\nGovernment argues that because the jury convicted Fattah\\nand Vederman of illegally laundering the proceeds of a\\n“scheme to commit bribery” under Count 23, the jury\\nfound that the scheme must have encompassed only the\\nZionts hiring. JA531.That would mean that the jury did not\\nconclude that the “scheme to commit bribery” included\\n\\nbe a necessary component of an impermissible “pattern”\\nof official acts. Second, the jury might have concluded that\\nFattah’s efforts to secure Vederman an ambassadorship\\nwere themselves official acts. Third, the jury might have\\nconcluded that Fattah’s efforts to secure Vederman an\\nambassadorship were merely attempts to “express[]\\nsupport,” rather than to “exert pressure . . . or provide\\nadvice,” but nonetheless erroneously concluded that those\\nexpressions of support were official acts. McDonnell, 136\\nS. Ct. at 2371.\\n 84\\n\\fany acts that McDonnell now makes clear were unofficial.\\nYet the redacted indictment, jury instructions, and the fact\\nthat the Government presented its case under a “pattern”\\ntheory at trial compel us to reject the Government’s\\nargument.\\n\\n The very first sentence under Count 23 of the\\nredacted indictment incorporates all three categories of\\n“Overt Acts” contained within paragraphs “58 through 95\\nof Count One.” 14 All three of these categories fall under a\\ngeneral heading within the redacted indictment titled “The\\nBribery and Fraud Scheme [redacted].” JA494. The jury\\nhad before it instructions for Count 23 which referred to\\n“the alleged bribery scheme involving an $18,000\\npayment,” JA448 (emphasis added), and the redacted\\nindictment which referred to “a scheme to commit\\nbribery,” JA531 (emphasis added). The parallel language\\ncould well lead a rational jury to conclude that the relevant\\n“scheme” included all three categories of acts listed under\\nthe general heading: “The Bribery and Fraud Scheme\\n[redacted].” JA494 (emphasis added).\\n\\n\\n\\n14\\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\\nthree categories of allegedly official acts discussed above:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) the\\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\\nStaff.” JA494–95.\\n 85\\n\\f Like the redacted indictment and jury instructions,\\nthe Government’s trial arguments referred to patterns and\\na course of conduct, and stressed that the jury need not\\nconnect specific payments to particular official acts. In its\\nclosing argument to the jury, the Government stated that\\nthe alleged “scheme took place over a period of several\\nyears. Over and over again you’re going to see the same\\npattern.” JA5383 (emphasis added). Then, in its rebuttal\\nargument, the Government went out of its way to\\nexplicitly distinguish its “pattern” theory from an\\nalternative theory that would have directly connected\\nindividual payments to individual acts. As the prosecutor\\nargued to the jury:\\n Ms. Recker appears to argue that each thing\\n of value must coincide with some specific\\n official act, but that is not the law and that is\\n not what Judge Bartle is going to instruct you.\\n Instead what he will tell you is that the\\n government is not required to prove that\\n Vederman intended to influence Fattah to\\n perform a set number of official acts in return\\n for things of value so long as the evidence\\n shows a course of conduct of giving things of\\n value, things of value to Fattah in exchange\\n for a pattern of official acts favorable to\\n Vederman. In other words a stream of\\n benefits. These for those, not this for that.\\n\\n\\n\\n 86\\n\\fJA5715–16 (emphases added). In closing to the jury, the\\nGovernment made several other references to this\\n“pattern” theory, 15 and the District Court referred to this\\n“pattern” theory in its instructions to the jury. As Judge\\nBartle instructed:\\n\\n [I]t is not necessary for the government to\\n prove that a defendant intended to induce a\\n public official to perform a number of official\\n acts in return for things of value.\\n So as long as the evidence shows a\\n course of conduct of giving things of value to\\n a public official in exchange for a pattern of\\n official acts favorable to the giver.\\n\\nJA5833–34 (emphasis added). On appeal, the Government\\nchanges course, asking us to assume that the jury ignored\\nthese repeated references to a “pattern of official acts” and\\n\\n15\\n See, e.g., JA5389 (“And the exchange of an official act\\nfor a thing of value is called a bribe. There’s the pattern.\\nFattah needs money, Vederman gets an official act.”); JA\\n5393 (“That’s why you see the pattern over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5400 (“The same pattern we saw over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5409 (“[Y]ou know that these were bribes because of\\nthe pattern you saw over and over and over again. Fattah\\nneeds money, Vederman gets an official act, that makes\\nthese things a bribe.”).\\n 87\\n\\finstead considered the Zionts hiring and Vederman’s\\n$18,000 payment to Fattah as an isolated quid pro quo.\\nThis is an invitation to speculate, and we decline to do so.16\\nThe jury began its deliberations accompanied by a copy of\\nthe redacted indictment which alleged a pattern of official\\nacts, consisting of any combination of three categories of\\nacts: pursuing an ambassadorship, arranging the Kirk\\nmeeting, and hiring Zionts. In light of the erroneous\\ninstructions, and because only one category clearly\\n\\n16\\n Providing some support to the Government’s ultimately\\nunconvincing argument that the jury considered the Zionts\\nhiring and $18,000 payment in isolation, we note that the\\nredacted indictment does mention those two events side-\\nby-side in paragraph 78 of the indictment’s Part V. JA497\\n(“On January 13, 2012, VEDERMAN wired $18,000 to\\nFATTAH, and six days later, on January 19, 2012,\\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\\nwelcoming her as a new employee to FATTAH’s\\nCongressional Staff.”). But although paragraph 78\\nmentions the $18,000 wire transfer and the Zionts hiring\\nin the same breath, paragraph 78 does not instruct the jury\\nto connect these two events apart from the rest of the\\nevidence presented at trial. In light of the other instructions\\nand arguments indicating that the jury should not consider\\nthe Zionts hiring in isolation, but instead should consider\\nthe hiring as one part of a three-part scheme, paragraph 78\\nis not sufficient to avoid a reversal and remand on the\\nconvictions of Fattah and Vederman as to Counts 16–18\\nand 22–23.\\n 88\\n\\fqualifies as an “official act,” the jury’s deliberations were\\nfraught with the potential for McDonnell error. We will\\nvacate the convictions of Fattah and Vederman as to\\nCounts 16, 17, 18, 22, and 23, and remand to the District\\nCourt.\\n\\nE. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23\\n Vederman argues that there is insufficient evidence\\nto support a conviction, even if a jury were properly\\ninstructed under McDonnell. Specifically, Vederman\\nargues that there is insufficient evidence to convict him\\nand Fattah, after remand, on Counts 16–18 and 22–23\\nbecause “[a]t least seven of the eight alleged ‘official acts’\\nwere, as a matter of law, not official at all.” Vederman Br.\\n35. As to the single act that Vederman implicitly concedes\\nto be an official act—the Zionts hiring—Vederman argues\\nthat “[t]he only thing that even arguably associates” the\\nZionts hiring with Vederman was its timing in relation to\\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\\nAccording to Vederman, “the undisputed chronology\\nprecludes any inference that Vederman conferred this\\nbenefit on his friend as an illegal bribe.” Id. (emphasis\\nomitted). Vederman is wrong. Sufficient evidence was\\nproduced at trial to have allowed a properly-instructed jury\\nto convict Fattah and Vederman of Counts 16–18 and 22–\\n23.\\n To begin with, even if the Zionts hiring had been the\\nsole official act to survive this Court’s interpretation of\\n 89\\n\\fMcDonnell, there would still be sufficient evidence to\\nconvict Fattah and Vederman. Zionts did not receive\\nwritten notice of her official hiring until six days after the\\nsham Porsche purchase. Moreover, the jury would not be\\nrestricted to considering the chronology of the sham\\npurchase alone. It would be free to consider Vederman’s\\nentire course of conduct. Under the general heading\\n“VEDERMAN’S Payments and Things of Value to\\nFATTAH,” the redacted indictment not only refers to the\\n$18,000 wire transaction from Vederman to Fattah as part\\nof the sham Porsche purchase, but also to Vederman’s\\n$3,000 payment for the college tuition of Simone Muller,\\nFattah’s live-in au pair, as well as thousands of dollars in\\npayments made by Vederman for Chip Fattah’s college\\ntuition. JA496–97.\\n And the Zionts hiring is not the only act to survive\\nour application of McDonnell. As we explained, a jury\\ncould find that Fattah’s efforts to secure Vederman an\\nambassadorship—three emails, two letters, and a phone\\ncall—were an impermissible attempt to “pressure or\\nadvise” President Obama, Senator Casey, or both men.17\\n\\n17\\n Although Fattah’s efforts to secure Vederman an\\nambassadorship present a jury question that is not for us to\\nanswer on appeal, we note that not one of these efforts\\nalone could qualify as an official act itself. See McDonnell,\\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\\nanother official, or organizing an event (or agreeing to do\\nso)—without more—does not fit that definition of ‘official\\n 90\\n\\fThis means that a properly instructed jury on remand,\\npresented with evidence of Fattah’s efforts to secure an\\nambassadorship for Vederman and evidence of the Zionts\\nhiring, could find more than a single official act.\\n\\n F. Blue Guardians\\n In addition to the charges arising from his dealings\\nwith Vederman, Fattah was charged in Count 3 with\\n\\n\\nact.’ ”). The relevant question for a jury to consider on\\nremand, then, is whether these actions constituted “a\\n‘decision or action’ on a different question or matter”—to\\nwit, the formal appointment of an ambassador. Id. at 2369\\n(emphasis omitted).\\n Even though the emails, letters, and phone call are\\nnot, individually, official acts, it will be for a jury to decide\\nif Fattah’s efforts to secure an ambassadorship for\\nVederman crossed the line from permissible “support” to\\nimpermissible “pressure or advice.” While we express\\ndoubt that some of Fattah’s efforts concerning the\\nambassadorship are, when considered in isolation, enough\\nto cross that line, a properly instructed jury considering all\\nof the facts in context might nonetheless conclude that\\nother efforts—such as a hand-delivered letter to the\\nPresident of the United States—indeed crossed that line.\\nFurther, a jury might find that in the aggregate, three\\nemails, two letters, and a phone call crossed the line and\\ntherefore constituted a “decision or action” on the\\nidentified matter of appointment.\\n 91\\n\\fparticipating in a scheme with Lindenfeld to funnel money\\nto a fraudulent nonprofit organization. In connection with\\nthis scheme, Fattah was convicted of conspiring to commit\\nhonest services fraud.\\n\\n Fattah owed Lindenfeld nearly $100,000 for work\\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\\nrepayment, Fattah suggested that Lindenfeld create an\\nentity, later named Blue Guardians, to which Fattah would\\ndirect $15,000,000 in public funds by using his position as\\na member of the House Committee on Appropriations.\\nNothing in McDonnell requires us to upset Fattah’s\\nconviction on Count 3.\\n Step 1(A) of our McDonnell analysis requires the\\nGovernment to “identify a ‘question, matter, cause, suit,\\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\\n“matter” is the appropriation of millions of dollars in\\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\\nawarding of redevelopment funds to be an official act). In\\nparticular, it was Fattah’s promise to perform this official\\nact that was unlawful. As McDonnell makes clear:\\n\\n [A] public official is not required to actually\\n make a decision or take an action on a\\n “question, matter, cause, suit, proceeding or\\n controversy”; it is enough that the official\\n agree to do so. The agreement need not be\\n explicit, and the public official need not\\n specify the means that he will use to perform\\n his end of the bargain.\\n 92\\n\\f136 S. Ct. at 2370–71 (internal citations omitted). That\\nFattah took steps to actually carry out his promise (e.g., by\\ndrafting and sending a formal appropriations request on\\nofficial congressional letterhead) is evidence of his illegal\\npromise. See id. at 2371.\\n\\n Step 1(B) requires the Government to establish that\\nthe “ ‘question, matter, cause, suit, proceeding or\\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\\nlaw be brought’ before a public official.” McDonnell, 136\\nS. Ct. at 2368. Appropriating public funds was not only a\\nmatter that was pending before Fattah as a member of the\\nAppropriations Committee, it was also a matter that was\\npending before the Chairman and Ranking Member of an\\nAppropriations Subcommittee to whom Fattah ultimately\\nsent a formal written request. See id. at 2369 (“[T]he\\nmatter may be pending either before the public official\\nwho is performing the official act, or before another public\\nofficial.”). Appropriating millions of dollars in response to\\nthe Blue Guardians request is “focused and concrete,” and\\n“the kind of thing that can be put on an agenda, tracked for\\nprogress, and then checked off as complete.” Id.\\n\\n Given Fattah’s membership on the Appropriations\\nCommittee, this was “something within the specific duties\\nof an official’s position—the function conferred by the\\nauthority of his office.” Id. Even if we were to assume,\\nagainst all reason, that an appropriation is not “something\\nwithin the specific duties” of either Fattah or the Chairman\\nor Ranking Member of an Appropriations Subcommittee,\\n\\n 93\\n\\fFattah’s formal request for an appropriation was\\nsomething that Fattah had the authority to do. Like the\\nExecutive Director in Repak, who lacked authority himself\\nto award redevelopment funds but could request such\\nfunds from the Board, Fattah used his position as a\\nCongressman to formally request appropriations for the\\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\\nto, and indeed did, make recommendations to the\\n[redevelopment authority.\\n Step 2 of McDonnell requires the Government to\\n“prove that the public official made a decision or took an\\naction ‘on’ that question, matter, cause, suit, proceeding,\\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\\n(emphasis added). Here, Fattah agreed to request an\\nappropriation for a bogus purpose. Unlike Fattah’s letters,\\nemails, and phone call seeking an ambassadorship for\\nVederman, there is no potential for the jury to have made\\na mistake when it found Fattah’s Blue Guardians promise\\nunlawful.\\n Fattah argues that the Government presented “[n]o\\nevidence . . . that would have allowed [the jury] to\\nconclude that [he] made a decision or took an action, or\\ncould have done so, on the question whether Blue\\nGuardians would receive a $15 million federal grant.”\\nFattah Br. 46. This argument misses the point. It was\\nFattah’s agreement to engage in the official act of formally\\nrequesting the appropriation that was illegal. See\\nMcDonnell, 136 S. Ct. at 2371.\\n\\n 94\\n\\f Lindenfeld’s trial testimony provided sufficient\\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\\nFattah’s letter provided additional evidence from which\\nthe jury could have concluded that Fattah illegally agreed\\nto perform an official act. 18 In short, the agreement itself\\nwas illegal, and the Government provided sufficient\\nevidence for the jury to conclude that the illegal agreement\\ntook place.\\n\\n The Government’s evidence in support of the Blue\\nGuardians scheme meets the requirements of McDonnell,\\nand the Count 3 verdict will stand.\\n\\n V. Sufficiency of the Evidence for the RICO\\n Conspiracy Conviction\\n The jury found Fattah, Vederman, Brand, and\\nNicholas guilty of the RICO conspiracy charged in Count\\n1 of the indictment, but acquitted Bowser. Vederman filed\\na post-verdict motion, and the District Court overturned\\nhis RICO conspiracy conviction.\\n\\n\\n\\n18\\n Despite Fattah’s protestation to the contrary, there is\\nevidence that Fattah took steps to carry out his official act.\\nJA6432–33 (Letter from Congressman Fattah to House\\nAppropriations Subcommittee members “request[ing]\\nfunding and support for the following projects and\\nprograms of critical importance,” including $3,000,000\\nfor “Blue Guardians”).\\n 95\\n\\f On appeal, Fattah, Brand, and Nicholas challenge\\nthe sufficiency of the evidence supporting their RICO\\nconspiracy convictions. We “review[] the sufficiency of\\nthe evidence in the light most favorable to the government\\nand must credit all available inferences in favor of the\\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\\n(3d Cir. 1998). If a rational juror could have found the\\nelements of the crime beyond a reasonable doubt, we must\\nsustain the verdict. United States v. Cartwright, 359 F.3d\\n281, 286 (3d Cir. 2004), abrogated on other grounds by\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\\nCir. 2013) (en banc).\\n The indictment charged a RICO conspiracy in\\nviolation of 18 U.S.C. § 1962(d), which makes it\\n“unlawful for any person to conspire to violate” § 1962(c).\\nSection 1962(c) provides:\\n It shall be unlawful for any person . . .\\n associated with any enterprise engaged in, or\\n the activities of which affect, interstate . . .\\n commerce, to conduct or participate, directly\\n or indirectly, in the conduct of such\\n enterprise’s affairs through a pattern of\\n racketeering activity . . . .\\n\\n18 U.S.C. § 1962(c).\\n\\n In Salinas v. United States, 522 U.S. 52 (1997), the\\ndefendant was convicted of a § 1962(d) RICO conspiracy,\\nbut a jury acquitted him of the substantive RICO offense\\n 96\\n\\funder § 1962(c). Id. at 55. The Supreme Court rejected\\nSalinas’s contention that his conviction had to be set aside\\nbecause he had neither committed nor agreed to commit\\nthe two predicate acts required for the § 1962(c) offense.\\nId. at 66. The Court declared that liability for a RICO\\nconspiracy under § 1962(d), “unlike the general\\nconspiracy provision applicable to federal crimes,” does\\nnot require proof of an overt act. Id. at 63. A conspiracy\\nmay be found, the Court explained, “even if a conspirator\\ndoes not agree to commit or facilitate each and every part\\nof the substantive offense. The partners in the criminal\\nplan must agree to pursue the same criminal objective and\\nmay divide up the work, yet each is responsible for the acts\\nof each other.” Id. at 63–64 (citations omitted). This means\\nthat, if a plan “calls for some conspirators to perpetrate the\\ncrime and others to provide support, the supporters are as\\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\\nparticipating in a conspiracy may result in criminal\\nliability for the acts of one’s co-conspirators. Smith v.\\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\\n Accordingly, liability for a RICO conspiracy may\\nbe found where the conspirator intended to “further an\\nendeavor which, if completed, would satisfy all of the\\nelements of a substantive criminal offense, but it suffices\\nthat he adopt the goal of furthering or facilitating the\\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\\nsubstantive criminal offense here was conducting a\\n§ 1962(c) enterprise, the government had to prove:\\n\\n 97\\n\\f (1) that two or more persons agreed to\\n conduct or to participate, directly or\\n indirectly, in the conduct of an enterprise’s\\n affairs through a pattern of racketeering\\n activity; (2) that the defendant was a party to\\n or member of that agreement; and (3) that the\\n defendant joined the agreement or conspiracy\\n knowing of its objective to conduct or\\n participate, directly or indirectly, in the\\n conduct of an enterprise’s affairs through a\\n pattern of racketeering activity.\\n\\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\\n2014).\\n In United States v. Turkette, 452 U.S. 576 (1981),\\nthe Supreme Court instructed that an enterprise is a “group\\nof persons associated together for a common purpose of\\nengaging in a course of conduct.” Id. at 583. The\\ngovernment can prove an enterprise “by evidence of an\\nongoing organization, formal or informal, and by evidence\\nthat the various associates function as a continuing unit.”\\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\\nSupreme Court established that an “association-in-fact\\nenterprise must have at least three structural features: a\\npurpose, relationships among those associated with the\\nenterprise, and longevity sufficient to permit these\\nassociates to pursue the enterprise’s purpose.” Id. at 946.\\nThe structure necessary for a § 1962(c) enterprise is not\\ncomplex. Boyle explained that an enterprise\\n\\n 98\\n\\f need not have a hierarchical structure or a\\n “chain of command”; decisions may be made\\n on an ad hoc basis and by any number of\\n methods—by majority vote, consensus, a\\n show of strength, etc. Members of the group\\n need not have fixed roles; different members\\n may perform different roles at different\\n times. The group need not have a name,\\n regular meetings, dues, [or] established rules\\n and regulations . . . .While the group must\\n function as a continuing unit and remain in\\n existence long enough to pursue a course of\\n conduct, nothing in RICO exempts an\\n enterprise whose associates engage in spurts\\n of activity punctuated by periods of\\n quiescence.\\n\\nId. at 948.\\n\\n Another element of a substantive § 1962(c) RICO\\nenterprise is that the enterprise must conduct its affairs\\nthrough a pattern of racketeering activity. Section 1961\\ndefines racketeering activity to include various criminal\\noffenses, including wire fraud, 18 U.S.C. § 1344, and\\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\\n§ 1961(1). A pattern of such activity “requires at least two\\nacts of racketeering activity.” Id. § 1961(5). The\\nracketeering predicates may establish a pattern if they\\n“related and . . . amounted to, or threatened the likelihood\\n\\n\\n 99\\n\\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\\nCo., 492 U.S. 229, 237 (1989).\\n Here, the District Court denied the post-trial\\nsufficiency arguments raised by Fattah, Brand, and\\nNicholas. It reasoned:\\n For a RICO conspiracy to exist, the\\n conspirators must agree to participate in an\\n enterprise with a unity of purpose as well as\\n relationships among those involved. The\\n evidence demonstrates that an agreement\\n among Fattah, Brand, Nicholas, Lindenfeld,\\n and Naylor existed for the overall purpose of\\n maintaining and enhancing Fattah as a\\n political figure and of preventing his standing\\n from being weakened by the failure to be able\\n to pay or write down his campaign debts.\\n These five persons agreed to work together as\\n a continuing unit, albeit with different roles.\\n The Government established that\\n Fattah, Brand, and Nicholas conspired along\\n with Naylor and Lindenfeld to conceal and\\n repay the 2007 illegal $1,000,000 loan to the\\n Fattah for Mayor campaign.\\n\\nJA128–29. The District Court further determined that\\n [w]hile each member may not have been\\n involved in every aspect of the enterprise, its\\n activities were sufficiently structured and\\n 100\\n\\f coordinated to achieve the purpose of\\n maintaining and enhancing Fattah’s political\\n standing and of preventing him from being\\n weakened politically because of his\\n campaign debts.\\n A RICO conspiracy also requires an\\n agreement to participate in an enterprise with\\n longevity sufficient to pursue its purpose.\\n This was established. In May 2007 the illegal\\n loan was obtained and continued through its\\n repayment in January 2008 and into at least\\n 2014 when the last campaign report reducing\\n a fake campaign debt to Naylor’s consulting\\n firm was filed by Fattah.\\nJA131.\\n\\n The defendants argue that the evidence is\\ninsufficient to show either an enterprise for purposes of\\n§ 1962(c) or an agreement as required for a § 1962(d)\\nconspiracy. We disagree, and conclude that the District\\nCourt’s analysis is on the mark.\\n\\n We begin by considering whether there was an\\nagreement. The evidence showed that Fattah knew each\\nmember involved in the scheme to conceal the unlawful\\ncampaign loan. When Lindenfeld learned of the $1 million\\nloan, he informed Fattah that it exceeded campaign\\nfinance limits. In short, the transaction was unlawful, and\\nthe two knew it. The transaction nonetheless went\\nforward, disguised as a loan, with Lindenfeld executing\\n 101\\n\\fthe promissory note as Strategies’ officer and obligating\\nStrategies to repay Lord $1 million. The concealment\\nefforts continued as Lindenfeld funneled a substantial\\nportion of the loan proceeds to Naylor for get-out-the-vote\\nefforts. After the losing campaign, Lindenfeld spoke with\\nFattah and Naylor about accounting for the funds that had\\nbeen spent. They decided not to include the amounts in the\\nFFM campaign reports. Fattah instructed Naylor to\\nprepare a fictitious invoice, and Naylor complied. The\\nFFM campaign reports filed from 2008 to 2014 disclosed\\nnothing about the unlawful $1 million loan. Instead, they\\nfalsely showed that Naylor’s consulting firm made yearly\\nin-kind contributions of $20,000 in debt forgiveness, when\\nin reality there was no debt to forgive.\\n As Lindenfeld fretted over repaying the $600,000\\nbalance of the Lord loan, Naylor assured him that Fattah\\nhad promised to take care of the repayment. And the\\nevidence supports an inference that Fattah recruited both\\nNicholas and Brand in doing so. As EAA’s director,\\nNicholas could fund the repayment. Brand, through his\\ncompany, Solutions, acted as the middleman: he received\\nthe payment from EAA pursuant to a fictitious contract,\\nand then forwarded the balance due to Strategies pursuant\\nto yet another fictitious contract. Nicholas and Brand\\ncontinued in the spring and summer of 2008 to hide the\\nfictitious agreement and the $600,000 payment to\\nLindenfeld to satisfy the Lord loan.\\n\\n\\n\\n 102\\n\\f In short, this evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\\nparticipate in Fattah’s plan to conceal the unlawful\\ncampaign loan to maintain his political stature. Nicholas\\nand Brand claim that they had no knowledge of the false\\ncampaign reporting aspect of the plan. But as Salinas\\ninstructs, conspirators need not “agree to commit or\\nfacilitate each and every part of the” conspiracy. 522 U.S.\\nat 63. Rather, they “must agree to pursue the same criminal\\nobjective and may divide up the work, yet each [be]\\nresponsible for the acts of each other.” Id. at 63–64. Thus,\\na conspirator may agree to “facilitate only some of the acts\\nleading to the substantive offense” yet still be criminally\\nliable. Id. at 65.\\n The evidence showed that a substantial amount of\\nmoney was needed to repay Lord, and that the source of\\nthe repayment was EAA, a non-profit organization whose\\nfunds could be spent only for purposes consistent with the\\nterms of the grants it received. It also showed that Nicholas\\nwas presented with a sham contract to legitimize the\\nEAA–Solutions transaction. We conclude that the\\nevidence is sufficient to support an inference that Nicholas\\nknew at the start that the plan was unlawful. Yet she still\\nagreed to provide the requisite funds and to play a role in\\nconcealing the illegal campaign loan so that Fattah could\\nmaintain his political stature.\\n\\n As to Brand, even if he did not know that false\\ncampaign reports were being filed, the evidence is\\n\\n 103\\n\\fsufficient to show he played a key role in the enterprise.\\nFrom the outset, Brand worked to disguise the repayment\\nof the Lord loan as the consideration in a sham contract\\nbetween EAA and Solutions. He then arranged for the\\ntransfer of funds to Strategies in satisfaction of a\\ncontractual term in another purported business agreement\\nbetween Solutions and Strategies. The evidence reveals\\nthat Brand was the point man in the effort to meet the\\nJanuary 31, 2008 deadline to repay the Lord loan, and it\\namply shows that Brand also agreed to participate in the\\nplan to hide the illegal campaign loan and its repayment to\\nbenefit Fattah politically.\\n Fattah, Brand, and Nicholas attack their RICO\\nconspiracy convictions on another front. They argue that\\nthose verdicts should be set aside because the evidence\\nfails to show that the various schemes alleged in the\\nindictment as part of the RICO conspiracy are connected.\\nThe RICO count, they assert, charges a hub-and-spoke\\nconspiracy that is unconnected by a rim. In their view,\\nFattah is the hub, and the spokes consist of a series of\\nindependent schemes: the Vederman bribery scheme, the\\npayment of the outstanding tuition debt of Fattah’s son\\nChip, the Blue Guardians plan, and the repayment of the\\nillegal Lord loan to maintain Fattah’s political stature.\\nThey argue that, without a unifying rim, their actions\\ncannot constitute an enterprise. Again, we disagree.\\n\\n In In re Insurance Brokerage Antitrust Litigation,\\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\\n\\n 104\\n\\fone of plaintiffs’ RICO claims, that the alleged hub-and-\\nspoke enterprise—comprised of broker hubs and insurer\\nspokes—could not withstand a motion to dismiss because\\nit did not have a unifying rim. Id. at 374. We explained\\nthat the allegations did “not plausibly imply concerted\\naction—as opposed to merely parallel conduct—by the\\ninsurers, and therefore cannot provide a ‘rim’ enclosing\\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\\nenterprises.” Id. Thus, the allegations did not “adequately\\nplead an association-in-fact enterprise” because the hub-\\nand-spoke conspiracy failed to “function as a unit.” Id.\\n\\n That is not the case here. The evidence showed that\\nFattah, Brand, and Nicholas agreed to conceal the illegal\\nLord loan. Each acted for the common purpose of\\nfurthering Fattah’s political interests. In short, they\\nengaged in concerted activity and functioned as a unit. The\\njury convicted Fattah, Brand, and Nicholas of the RICO\\nconspiracy based on the racketeering activity of wire fraud\\nand obstruction of justice to conceal the unlawful\\ntransaction. Because the evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\\nFattah’s political status by acting to maintain the secrecy\\nof the unlawful Lord loan, the alleged lack of a unifying\\n“rim” is not fatal to this RICO enterprise. What matters in\\nanalyzing the structure of this enterprise is that it\\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\\nrequirement” was met. Id.\\n\\n 105\\n\\f We turn next to the contention that the evidence\\nfails to establish other components of an enterprise. We\\nconclude that much of the evidence supporting the\\nexistence of an agreement also shows that there was an\\nassociation-in-fact enterprise.\\n\\n Boyle made clear that an association-in-fact\\nenterprise must have “a purpose, relationships among\\nthose associated with the enterprise, and longevity\\nsufficient to permit these associates to pursue the\\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\\nhave repeatedly observed, was to maintain and preserve\\nFattah’s political stature by concealing the illegal loan and\\nits repayment. Though informal, there were relationships\\namong those associated with the enterprise. Fattah was at\\nthe center of this association and he directed its activity.\\nHe knew each of the association’s members, and the\\nmembers knew each other (except, perhaps, for Nicholas,\\nwho may not have known Lindenfeld).19\\n\\n\\n19\\n Nicholas’s lack of familiarity with Lindenfeld does not\\nundermine her membership in this association-in-fact\\nenterprise. We have previously explained that “[i]t is well-\\nestablished that one conspirator need not know the\\nidentities of all his co-conspirators, nor be aware of all the\\ndetails of the conspiracy in order to be found to have\\nagreed to participate in it.” United States v. Riccobene, 709\\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\\nby Griffin v. United States, 502 U.S. 46 (1991).\\n 106\\n\\f The Government also adduced sufficient proof of\\nthe longevity component required for an enterprise. The\\nscheme began in mid-2007, when Lord made the\\ncampaign loan, directing the proceeds of the loan to\\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\\nall knew they needed to conceal this illegal transaction.\\nThey began by fabricating an explanation for the source of\\nthe funds they spent on election day. SLA created a fake\\ninvoice for the campaign, showing a fictitious debt that\\nNaylor could later forgive by fictitious in-kind\\ncontributions existing only on Fattah’s campaign finance\\nreports.\\n The effort to disguise the Lord loan was not limited\\nto filing false campaign reports. Nicholas and Brand, who\\njoined the conspiracy a few months later than the other\\nmembers, understood that they too had to make the\\nfraudulent $600,000 payment by EAA to Solutions appear\\nlegitimate. Nicholas and Brand tried to disguise the sham\\ncontract as an ordinary transaction (even though it called\\nfor a six-figure upfront payment simply to support\\nSolutions’ various projects), and they succeeded in\\nkeeping it out of the DOJ auditors’ view until August\\n2008. The ruse continued as Solutions funneled the\\n$600,000 payment to Strategies under the guise of another\\nsham contract (which also required an upfront six-figure\\npayment). The scheme then continued as Fattah submitted\\nfalse FFM campaign reports from 2008 through 2014.\\n\\n\\n\\n 107\\n\\f Finally, we consider whether the enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity, as required for a § 1962(c) enterprise. Wire fraud\\nand obstruction of justice may constitute “racketeering\\nactivity” under § 1961(1). As the Supreme Court\\ninstructed in H.J. Inc., the “multiple predicates within a\\nsingle scheme” must be related and “amount[] to, or\\nthreaten[] the likelihood of, continued criminal activity.”\\n492 U.S. at 237. Here, the amount of the illegal loan to be\\nconcealed was substantial. The enterprise needed to write\\noff the fictitious debt to Naylor’s consulting firm, and it\\nwas urgent that both the EAA–Solutions contract and the\\nSolutions–Strategies contract be legitimized. We conclude\\nthe evidence was sufficient to establish that this enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity and that the predicate acts of wire fraud and\\nobstruction of justice were related. The racketeering\\nactivity furthered the goals of maintaining the secrecy of\\nthis $1 million illicit campaign loan and of preserving\\nFattah’s political stature.\\n Nicholas contends that the evidence fails to\\nestablish a pattern of racketeering activity because the\\nactions to which she agreed did not “extend[] over a\\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\\nat 242. That case indeed instructs that the continuity\\nrequirement of a pattern is a “temporal concept,” and that\\n“[p]redicate acts extending over a few weeks or months”\\ndo not satisfy the continuity concept. Id. But the Supreme\\nCourt explained that continuity may also be established by\\n 108\\n\\fshowing that there is a “threat of continued racketeering\\nactivity.” Id. Here, the course of fraudulent conduct\\nundertaken to secure and to conceal the $1 million Lord\\nloan consisted of the creation of sham debts, fictitious\\ncontracts, and false accounting entries over the course of\\nabout a year. But because Fattah needed to appear able to\\nretire his campaign debt, the enterprise needed to continue\\nfiling false campaign reports for several years, allowing\\nthe annual $20,000 in-kind debt forgiveness contributions\\nto appear to satisfy Naylor’s fake $193,000 invoice. That\\nevidence was sufficient to establish the requisite threat of\\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\\n43.\\n We conclude that the Government met its burden in\\nproving that Fattah, Brand, and Nicholas 20 engaged in a\\nRICO conspiracy in violation of § 1962(d).\\n\\n\\n20\\n Nicholas also asserts, in passing, that that her conviction\\nunder § 1962(d) should be set aside because that statutory\\nprovision is unconstitutionally vague as applied to her.\\nAccording to Nicholas, a person of ordinary intelligence\\nwould not know that her actions constituted an agreement\\nto participate in a RICO enterprise. See United States v.\\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\\ncontrary, a person of ordinary intelligence, who had been\\nemployed by a prominent politician and then became the\\nCEO of a nonprofit organization which that politician had\\nfounded (and, to some extent, continued to direct), would\\n 109\\n\\f VI. Variance from the Indictment and Sufficiency of\\n the Evidence for Count 2\\n Brand and Nicholas challenge their convictions for\\nconspiracy to commit wire fraud by arguing that the\\nGovernment’s evidence at trial impermissibly varied from\\nthe indictment. Nicholas also challenges the sufficiency of\\nthe evidence to support her conviction for conspiracy to\\ncommit wire fraud. We address these contentions\\ntogether. 21\\n\\n Count 2 of the indictment alleged a single\\nconspiracy. JA277–79. Brand and Nicholas assert that the\\nGovernment’s evidence at trial did not support the\\nexistence of a single conspiracy but instead showed two\\nindependent conspiracies, only one of which involved the\\ntwo of them. According to Brand and Nicholas, the only\\nconspiracy with which they were involved ended more\\nthan five years before the Government charged them. That\\nwould mean that all their conduct falls outside the five-\\nyear limitations period for wire fraud conspiracy under 18\\nU.S.C. § 3282.\\n\\n\\nrealize that agreeing to participate with others in hiding an\\nunlawful campaign loan of $1 million could constitute an\\nunlawful RICO conspiracy.\\n21\\n In her briefing, Nicholas discusses variance in far less\\ndetail than Brand, so we refer primarily to Brand’s\\narguments. See Nicholas Br. 54–56. Her variance\\narguments fail for the same reasons that Brand’s fail.\\n 110\\n\\f “A conviction must be vacated when (1) there is a\\nvariance between the indictment and the proof presented\\nat trial and (2) the variance prejudices a substantial right\\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\\nno variance, and will affirm the District Court.\\n A variance exists “if the indictment charges a single\\nconspiracy while the evidence presented at trial proves\\nonly the existence of multiple conspiracies.” Id. “We must\\ndetermine ‘whether there was sufficient evidence from\\nwhich the jury could have concluded that the government\\nproved the single conspiracy alleged in the indictment.’ ”\\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\\nthe light most favorable to the Government, we consider\\nthree factors: (1) “whether there was a common goal\\namong the conspirators”; (2) “whether the agreement\\ncontemplated bringing to pass a continuous result that will\\nnot continue without the continuous cooperation of the\\nconspirators”; and (3) “the extent to which the participants\\noverlap in the various dealings.” Id. (quoting Kelly, 892\\nF.2d at 259).\\n\\n Brand argues that the Government failed to\\nestablish a common goal among the conspirators. To\\ndetermine whether the conspirators shared a common\\ngoal, “we look to the underlying purpose of the alleged\\ncriminal activity” in a fairly broad sense. United States v.\\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\\nRigas, we described the common goal of the defendants as\\n\\n 111\\n\\f“enriching [themselves] through the plunder of [their\\ncorporate employer],” id., and we have similarly\\narticulated the common goal in fairly general terms\\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\\n93 (3d Cir. 2007) (“There was certainly evidence of a\\ncommon goal among these co-conspirators: to make\\nmoney by depositing stolen and altered corporate checks\\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\\ncommon goal of all the participants was simply to make\\nmoney selling ‘speed.’ ”). Importantly, a common goal\\nmay exist even when “conspirators individually or in\\ngroups perform different tasks in pursuing the common\\ngoal,” and a single conspiracy may “attract[] different\\nmembers at different times” or “involve[] different sub-\\ngroups committing acts in furtherance of the overall plan.”\\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\\n\\n Here, the indictment described the purpose of the\\nunified conspiracy in Count 2 at length:\\n\\n It was a purpose of the conspiracy to obtain\\n an illegal campaign loan and to fraudulently\\n repay that loan with hundreds of thousands of\\n dollars of misappropriated charitable funds\\n from Sallie Mae and federal grant funds from\\n NASA which were intended for educational\\n purposes.\\n\\n . . . . It was further a purpose of the\\n conspiracy to present FATTAH to the public\\n as a perennially viable candidate for public\\n 112\\n\\f office who honored his obligations to his\\n creditors and was able to retire his publicly\\n reported campaign debts.\\n . . . . It was further a purpose of the\\n conspiracy to promote FATTAH’s political\\n and financial goals through deception by\\n concealing and protecting the conspirators’\\n activities from detection and prosecution by\\n law enforcement officials and the federal\\n judiciary, as well as from exposure by the\\n news media, through means that included\\n obstruction of justice and the falsification of\\n documents, including Campaign Finance\\n Reports, false invoices, contracts, and other\\n documents and records.\\n\\nJA277–78, ¶¶ 3–5.\\n Brand characterizes the evidence at trial as\\nestablishing two distinct conspiracies. The first he labels\\nthe “diversion of funds scheme,” covering the\\nmisappropriation of funds by Nicholas, Brand,\\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\\n34. Brand calls the second conspiracy the “CFR scheme,”\\nin which Fattah and Naylor filed the false campaign\\nfinance reports showing Naylor gradually forgiving a non-\\nexistent debt. Id.\\n Brand argues that the only goal of the CFR scheme\\nwas to cover up how the funds from the illegal campaign\\n 113\\n\\floan were spent, a goal he distinguishes from that of the\\ndiversion of funds scheme, which he characterizes as a\\nplan to cover up the repayment of the loan with stolen\\nfunds. He also argues that the evidence does not establish\\nhe was involved in, or even aware of, the false campaign\\nfinance reports filed by Fattah. In Brand’s view, that\\nnecessarily means the evidence showed two separate\\nconspiracies.\\n\\n In considering these arguments, we begin by noting\\nthat one conspiracy can involve multiple subsidiary\\nschemes. Rigas, 605 F.3d at 214. It is true that the false\\ncampaign finance reports, in the narrowest sense, had the\\nspecific purpose of covering up how the illegal loan funds\\nwere used during the election. But the false campaign\\nfinance reports were also filed in furtherance of a broader\\ngoal shared by the conspirators involved in repayment of\\nthe Lord loan. They sought to promote Fattah’s political\\nand financial goals by preserving his image as a viable\\ncandidate and making him appear able to repay or\\notherwise service his campaign debts without resorting to\\nillegal means in doing so. The two subsidiary schemes\\nworked in concert in furtherance of this overarching goal,\\nand both were directed at covering up how the loan was\\ntruly repaid. The “diversion of funds scheme” hid the\\nillegal (but real) loan repayment through the use of fake\\ncontracts; the “CFR scheme” showed the seemingly legal\\n(but fake) loan forgiveness installments through the\\ncreation of fake invoices and campaign finance reports.\\nThe existence of two concealment schemes acting in\\n 114\\n\\fconcert does not undermine the unity of the conspiracy of\\nwhich they were both a part. We have no difficulty\\nconcluding that the false campaign finance reports and the\\nconcealed use of stolen funds to repay the Lord loan\\noperated together in furtherance of a common goal.\\n\\n As for Brand’s argument that he was unaware of the\\nfalse campaign finance reports and therefore could not be\\na part of any conspiracy involving them, it is well-settled\\nthat “each member of the charged conspiracy is liable for\\nthe substantive crimes his coconspirators commit in\\nfurtherance of the conspiracy even if he neither\\nparticipates in his co-conspirators’ crimes nor has any\\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\\nU.S. 640 (1946)). The exceptions to that rule allow a\\ndefendant to escape liability for a co-conspirator’s crime\\nif: (1) “the substantive offense committed by one of the\\nconspirators was not in fact done in furtherance of the\\nconspiracy,” (2) “the substantive offense committed by\\none of the conspirators ‘did not fall within the scope of the\\nunlawful project,’ ” or (3) “the substantive offense\\ncommitted by one of the conspirators ‘could not be\\nreasonably foreseen as a necessary or natural consequence\\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\\nU.S. at 647–48). There was, as we have concluded, a unity\\nof purpose between the co-conspirators to further Fattah’s\\npolitical and financial goals by secretly obtaining and\\nrepaying an illegal campaign loan with stolen funds. The\\nfiling of false campaign reports does not fit within any of\\n 115\\n\\fthe recognized exceptions to co-conspirator liability, as it\\nwas in furtherance of the conspiracy’s shared goal, within\\nthe scope of the agreement to conceal the loan, and\\nforeseeable to Brand and Nicholas.\\n\\n Neither Brand nor Nicholas briefed the other two\\nfactors we consider when determining whether the\\nevidence impermissibly varied from the evidence,\\n“whether the agreement contemplated bringing to pass a\\ncontinuous result that will not continue without the\\ncontinuous cooperation of the conspirators,” and “the\\nextent to which the participants overlap in the various\\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\\nat 258). The unified goal of promoting Fattah’s political\\ncareer and maintaining secrecy surrounding the illegal\\nloan and the misappropriated funds used to repay it\\nrequired the continuous cooperation of the conspirators.\\nIndeed, the efforts of several of them overlapped in every\\naspect of the scheme. And Lindenfeld and Fattah were, at\\na minimum, involved in some way in nearly every aspect\\nof the origination of the loan, the false campaign finance\\nreports, and the use of misappropriated funds to repay the\\nloan. For his part, Naylor was involved in the use of the\\nfunds, the false campaign finance reports, and to a lesser\\nextent, the repayment of the loan.\\n Brand (as part of his variance argument) and\\nNicholas (as part of her sufficiency argument) argue that\\nthe Government did not prove they agreed to conceal their\\nactions, and thus the false campaign reports would not be\\n\\n 116\\n\\fsufficient to extend the duration of the conspiracy so that\\nit fell within the statute of limitations. Acts of\\nconcealment, such as the false campaign reports, are not\\nautomatically “in furtherance” of a conspiracy. We must\\ndetermine whether there was “an express original\\nagreement among the conspirators to continue to act in\\nconcert in order to cover up, for their own self-protection,\\ntraces of the crime after its commission,” as opposed to “a\\nconspiracy to conceal . . . being implied from elements\\nwhich will be present in virtually every conspiracy case,\\nthat is, secrecy plus overt acts of concealment.”\\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\\nthe indictment “specifically alleges a continuing\\nconspiracy” to conceal the crime after the completion of\\nthe wire fraud, and such a conspiracy can be proven, the\\nstatute of limitations does not begin to run until the last\\novert act of concealment. United States v. Moses, 148 F.3d\\n277, 282 (3d Cir. 1998).\\n\\n Here, the evidence shows that the conspirators\\nexpressly agreed to conceal the loan and its repayment. As\\nan initial matter, Brand’s only role in the conspiracy was\\nto cover up the use of stolen funds by (1) serving as an\\nintermediary between Nicholas and Lindenfeld; and\\n(2) agreeing to create false documentation (the contracts)\\nwith both EAA and Strategies for the sole purpose of\\ndisguising the payments and covering up the wire fraud\\nconspiracy. Nicholas could simply have paid Lindenfeld\\nherself (or paid Lord) if she and Brand had not agreed to\\nconceal the crime from the start. Additionally, and as\\n 117\\n\\fBrand acknowledges, the false campaign finance reports\\nbegan before the loan was repaid, proving that\\nconcealment of the crime was contemplated and begun as\\na direct purpose of the conspiracy before Brand and\\nNicholas became involved in the repayment. Nicholas too\\nagreed to conceal the repayment, as she implicitly\\nacknowledged in her emails with Brand and Fattah. GSA2.\\nFinally, when Lindenfeld briefly strayed from the\\nconspiracy’s commitment to secrecy by mentioning the\\nrepayment in front of others who did not know of the\\nscheme, Brand became “angry,” “took [Lindenfeld] out in\\nthe hallway,” and chastised him, saying that “[Lindenfeld]\\ncouldn’t say that sort of []thing” in front of other people.\\nJA1670–71. We conclude that the evidence is consistent\\nwith the allegations in the indictment, which charge a\\nsingle conspiracy consisting of an original agreement to\\nconceal the illegal loan and its subsequent illegal\\nrepayment to further Fattah’s political career.\\n\\n Nicholas makes several arguments in passing. She\\nsuggests that the District Court upheld the conviction after\\ntrial “on a theory not submitted to the jury.” Nicholas Br.\\n51. This argument is, essentially, that the indictment and\\nthe District Court’s post-trial ruling described the\\nconspiracy one way, but that the jury charge described the\\nconspiracy differently. Nicholas argues that the jury was\\npresented with the theory that the sole purpose of the false\\ncampaign reports under Count 2 was to “conceal[] the\\nalleged scheme to defraud,” JA5849, rather than to support\\n\\n 118\\n\\fFattah’s political career, as the District Court described the\\npurpose after trial, see JA74.\\n Nicholas ignores that part of the jury charge which\\ninstructed that Count 2 required a finding “[t]hat two or\\nmore persons agreed to commit wire fraud as charged in\\nthe indictment.” JA5845 (emphasis added). The jury had\\naccess to the indictment, and as Nicholas points out,\\nNicholas Br. 45–46, the indictment outlines the offense in\\nthe same way the District Court later described it in its\\npost-trial ruling. The District Court consistently described\\nthe count, and we see no reversible error.\\n Nicholas also argues that the conspiracy charged in\\nCount 2 has an objective—“to ‘present Fattah’ as\\n‘perennially viable’ ”—and that such an objective is not\\nillegal. Nicholas Br. 53. But, of course, the jury was not\\ninstructed that it was illegal to be a Fattah supporter, or\\neven to work on his campaign. The jury was charged\\nspecifically on the crime of wire fraud.\\n\\n We conclude that there was no impermissible\\nvariance between the indictment and the Government’s\\nevidence at trial, and that there was sufficient evidence to\\nsupport the convictions. We will affirm the convictions of\\nBrand and Nicholas for conspiracy to commit wire fraud\\nunder Count 2.\\n\\n\\n\\n\\n 119\\n\\f VII. The District Court’s Instruction to the Jury on\\n the Meaning of Intent\\n Nicholas contends that the District Court\\nimproperly instructed the jury by using the disjunctive\\nrather than the conjunctive at one point in its definition of\\nintent. When providing its final charge to the jury, the\\nDistrict Court explained:\\n Certain of the offenses charged in the\\n indictment require that the government prove\\n that the charged defendant acted intentionally\\n or with intent. This means that the\\n government must prove either that (1), it was\\n the defendant’s conscious desire or purpose\\n to act in a certain way or to cause a certain\\n result; or (2), the defendant knew that he or\\n she was acting in that way or it would be\\n practically certain to cause that result.\\n\\nJA5787 (emphasis added). According to Nicholas, an\\naccurate definition of intent required that the final “or” be\\nan “and.” Nicholas argues that this was an error so\\ngrievous as to “effectively eliminate[] the intent element\\nfrom each offense of conviction.” 22 Nicholas Br. 26.\\n\\n\\n22\\n The Comment to Third Circuit Model Criminal Jury\\nInstruction 5.03 makes clear that the definition of intent\\nencapsulates both “specific intent” (acting “purposely” or\\nwith “conscious object”) and “general intent” (acting\\n 120\\n\\f Our review of whether a jury instruction stated the\\nproper legal standard is plenary. United States v. Petersen,\\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\\nfailed to object to this portion of the jury charge.\\nAccordingly, our review must be for plain error. See\\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\\n2014) (en banc).\\n\\n To prevail on plain error review, Nicholas must\\nestablish that there was an error, that it was plain (i.e., clear\\nunder current law), and that it affected her substantial\\nrights (i.e., whether there is a reasonable likelihood that\\nthe jury applied the challenged instruction in an\\nimpermissible manner). United States v. Olano, 507 U.S.\\n\\n“knowingly” or “with awareness”). Although Nicholas\\ndescribes the alleged error as “essentially eliminating” the\\nelement of intent, we think Nicholas’s argument is better\\nunderstood as a claim that the instruction given could have\\npermitted a jury to conclude that she acted with only\\ngeneral intent (that she was aware of what she was doing),\\nwhen her crimes require specific intent (that she had an\\nillegal purpose). As her brief states, “[p]lainly she\\n‘knowingly’ wrote checks from EAA to [Solutions] and\\nmade record entries about them; the question was whether\\nshe intended to defraud EAA and NASA, or to obstruct\\njustice, by doing so.” Nicholas Br. 24. We cannot agree\\nwith her characterization that the instruction resulted in the\\n“effective omission” of the intent element from the jury\\ninstructions.\\n 121\\n\\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\\n231, 239–40 (3d Cir. 2005). If these requirements are met,\\nwe may then exercise our discretion to address the error,\\nbut only if we conclude that the error seriously affected the\\nfairness, integrity, or public reputation of the judicial\\nproceeding. United States v. Andrews, 681 F.3d 509, 517\\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\\n461, 467 (1997)). A failure to instruct the jury on a\\nnecessary element of an offense ordinarily constitutes\\nplain error, unless the instructions as a whole otherwise\\nmake clear to the jury all the necessary elements of the\\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\\nCir. 2017).\\n Nicholas acknowledges, as she must, that the\\ninstruction given was a verbatim recitation of Instruction\\n5.03 of the Third Circuit’s Model Criminal Jury\\nInstructions. She nonetheless contends that our Model\\nInstruction is erroneous. Even if we were to accept\\nNicholas’s contention that the instruction is incorrect, a\\nproposition we consider as highly doubtful, see Petersen,\\n622 F.3d at 208 (“We have a hard time concluding that the\\nuse of our own model jury instruction can constitute error\\n. . . .”), we conclude that, considering the instructions as a\\nwhole, the District Court clearly and specifically\\ninstructed the jury on the intent element as it applied to\\neach of Nicholas’s charged crimes.\\n\\n The disputed intent instruction was given at the\\nbeginning of the final charge, explaining the general\\n\\n 122\\n\\fmeaning of the intent applicable to “[c]ertain of the\\noffenses charged.”23 JA5787. The District Court went on\\nto instruct the jury in specific detail on the elements of\\neach of the crimes of which Nicholas was accused,\\n\\n\\n\\n\\n23\\n The introductory definition did not end with the\\nlanguage Nicholas cites. The District Court elaborated that\\nacting in good faith is a complete defense to the charges:\\n\\n The offenses charged in the indictment\\n require proof that the charged defendants\\n acted with criminal intent. If you find that a\\n defendant acted in good faith that would be a\\n complete defense to such a charge, because\\n good faith on the part of the defendant would\\n be inconsistent with his or her acting\\n knowingly, willfully, corruptly, or with intent\\n to defraud or intent to impede, obstruct, or\\n wrongfully influence.\\n\\nJA5788–89 (emphasis added). This instruction\\nundermines Nicholas’s claim that the jury could have\\nreasonably concluded that she “ ‘knowingly’ wrote\\nchecks” but did not “intend[] to defraud . . . or to obstruct\\njustice[] by doing so,” Nicholas Br. 24, as this instruction\\nleaves little room for doubt that good faith is at odds with\\n“criminal intent.”\\n\\n 123\\n\\fexplaining also the intent element of each. 24 See JA5791\\n(describing the third element of the RICO conspiracy\\ncharge as: “the particular defendant and at least one other\\nalleged conspirator shared a unity of purpose and the intent\\nto achieve the objective of conducting or participating in\\nthe conduct of an enterprise’s affairs through a pattern of\\nracketeering activity”); JA5823 (regarding wire fraud,\\ninstructing that the government must prove “[t]hat the\\ndefendant under consideration acted with the intent to\\ndefraud”); JA5838–39 (regarding obstruction of justice,\\ninstructing that the defendant must have acted “with the\\nintent to impair the record, document, or object’s integrity\\nor availability for use in an official proceeding,” and must\\nhave acted corruptly “with the purpose of wrongfully\\nimpeding the due administration of justice”); JA5860\\n(explaining that falsification of records requires that “the\\ndefendant under consideration acted with the intent to\\nimpede, obstruct or influence the investigation or proper\\nadministration of a matter”). These instructions are\\nconsistent with both our Model Jury Instructions and our\\ncase law concerning the elements of these crimes. See\\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\\nof justice); United States v. Sussman, 709 F.3d 155, 168\\n(3d Cir. 2013) (obstruction of justice); United States v.\\n\\n24\\n Nicholas did not object to the knowledge and intent\\ninstructions when the District Court discussed each of the\\nindividual charges, and does not identify a disagreement\\nwith any specific instruction on any particular charge.\\n 124\\n\\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\\n193, 216 (3d Cir. 1992) (wire fraud).\\n The District Court also provided a separate\\ndefinition of the knowledge element of each charge,\\nillustrating the difference between knowledge and intent.\\nSee JA5793 (explaining that the evidence must show that\\na RICO defendant “knowingly agreed to facilitate or\\nfurther a course of conduct, which if completed would\\ninclude a pattern of racketeering activity”); JA5823 (wire\\nfraud means that the defendant “knowingly devised a\\nscheme to defraud a victim . . . by materially false or\\nfraudulent pretenses”); JA5860 (falsification of records\\nhas as an element “[t]hat the defendant under\\nconsideration knowingly concealed, covered up, falsified\\nor made false entries in a document or record”). These\\ninstructions made clear that knowledge and intent are\\nseparate considerations, undermining Nicholas’s\\ncontention that the jury was led to believe that “knowledge\\nis sufficient to prove intent.” Nicholas Br. 24.\\n The District Court provided each member of the\\njury with more than 100 pages of instructions before\\ndeliberations began. Viewing those instructions as a\\nwhole, we are satisfied that the jury was apprised of the\\ncorrect meaning of intent as an element of the crimes with\\nwhich Nicholas was charged, as well as the distinction\\nbetween knowledge and intent. We perceive no error,\\n\\n\\n 125\\n\\fmuch less error that is plain, in the District Court’s\\ninstructions to the jury. 25\\n\\n VIII. Sending the Indictment to the Jury\\n At trial, Vederman, Nicholas, and Brand objected to\\nthe District Court’s decision to give the jury a redacted\\ncopy of the indictment to use during its deliberations. Only\\nNicholas and Brand raise this issue on appeal. In\\nNicholas’s view, sending the indictment to the jury\\nunfairly prejudiced her because it contained unsupported\\nallegations that she had obstructed federal agencies and\\nreferred to a nonexistent certification requirement for\\nSallie Mae funds. Brand argues that he was prejudiced by\\nthe indictment’s references to “schemes” and “fake”\\ncontracts, and because it mentioned Brand’s spouse and\\nthat she was a former member of Fattah’s congressional\\nstaff. Nicholas and Brand together assert that the\\nindictment included legal theories on which the jury was\\nnot instructed. They contend that the indictment’s\\nnarrative of the Government’s case set out a roadmap that\\nomitted any averments relating to the defense theory and\\nallowed the Government to yet again present its case. To\\nbuttress that argument, Nicholas and Brand cite the\\ntestimony of Juror 12, who described the jury’s initial\\n\\n\\n\\n25\\n Accordingly, we need not consider the merits of\\nNicholas’s argument that Model Criminal Jury Instruction\\n5.03 is erroneous.\\n 126\\n\\fdeliberations and alleged that the jurors viewed the\\nindictment as evidence.\\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\\n1971), we held that the decision to allow “jurors to have a\\ncopy of the indictment with them during their\\ndeliberations . . . is a matter within the discretion of the\\nDistrict Judge, subject to a limiting instruction that the\\nindictment does not constitute evidence, but is an\\naccusation only.” Subsequently, in United States v.\\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\\nacknowledged that the District Court has the power to\\nredact the indictment if doing so would be appropriate to\\navoid prejudice to the defendant. See also United States v.\\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\\ncourt may redact an indictment before submitting it to the\\njury).\\n\\n While both Nicholas and Brand objected in general\\nterms to the District Court’s decision to provide the\\nindictment to the jury, they have not directed us to any\\nspecific request to redact the information they now claim\\nis prejudicial. And the District Court provided a limiting\\ninstruction on four occasions during its charge, repeatedly\\nemphasizing that the indictment was not evidence.\\nJA5765, 5767, 5782, 5880. The Court instructed the jury\\non its duty to base its verdict “solely upon the evidence in\\nthe case.” JA5764. Just before the jury retired to\\ndeliberate, the Court reiterated that the purpose of the\\n\\n\\n 127\\n\\findictment is to set forth the charges, and that it is “merely\\nan accusation.” JA5909.\\n “[J]uries are presumed to follow their instructions\\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\\nour view, Juror 12’s assertion that the indictment was\\nbeing considered evidence does not, standing alone,\\nestablish that his fellow jurors actually did so. We reject\\nthe notion that the jury, after hearing weeks of testimony\\nand having viewed substantial documentary evidence,\\nwent on to ignore the Court’s limiting instruction\\nconcerning the indictment. 26 Accordingly, we conclude\\n\\n\\n26\\n We acknowledge that our case law provides minimal\\nguidance to district courts concerning the practice of\\nsending an indictment to the jury for their use during\\ndeliberations. We are also aware that some courts have\\ndisapproved the practice of sending the indictment out\\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\\nemphasize that this practice is committed to the sound\\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\\nour view, such an exercise of a judge’s discretion should\\nbe informed by considering the nature of the case, the\\nnumber of defendants, the length of the indictment, the\\nextent of the factual recitation supporting the criminal\\ncharges, and most importantly, whether the indictment\\n(especially if lengthy and fact-laden) will be useful to the\\njury, in light of the judge’s own carefully tailored jury\\n 128\\n\\fthat the District Court did not abuse its discretion in\\nsending the indictment out to the jury.\\n\\n IX. The District Court’s Evidentiary Rulings\\n Vederman, Nicholas, and Brand each challenge\\nevidentiary rulings by the District Court. We conclude that\\nnone of these contentions warrants setting aside their\\nconvictions.\\n\\n A. The District Court’s Application of Rule 404(b)\\n Vederman argues that the District Court misapplied\\nFederal Rule of Evidence 404(b) when it excluded\\nevidence of Vederman’s prior gift-giving. 27 This Court\\nreviews a district court’s application of Rule 404(b) for\\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\\n\\ninstruction, as supplemented by a verdict slip. See Esso,\\n684 F.3d at 352 n.5.\\n27\\n Although Rule 404(b) determinations are usually in\\nresponse to attempts to introduce “bad” acts evidence,\\nVederman’s attempt to introduce “good” acts of gift-\\ngiving is properly analyzed under the same rule. Ansell v.\\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\\n2003) (“The evidence admitted in this case differs from\\ngarden variety Rule 404(b) matter because it is evidence,\\nnot of a prior bad act in a criminal case, but of a subsequent\\ngood act in a civil case. Nonetheless, this evidence is\\nencompassed by the plain text of Rule 404(b) which\\naddresses ‘other . . . acts,’ not just prior bad acts.”).\\n 129\\n\\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\\n“[a]n abuse of discretion . . . when [the] district court’s\\ndecision rests upon a clearly erroneous finding of fact, an\\nerrant conclusion of law or an improper application of law\\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\\n\\n Federal Rule of Evidence 404(b) provides in part:\\n (b) Crimes, Wrongs, or Other Acts.\\n\\n (1) Prohibited Uses. Evidence of a\\n crime, wrong, or other act is not\\n admissible to prove a person’s\\n character in order to show that on a\\n particular occasion the person\\n acted in accordance with the\\n character.\\n\\n (2) Permitted Uses; Notice in a\\n Criminal Case. This evidence may\\n be admissible for another purpose,\\n such as proving motive,\\n opportunity, intent, preparation,\\n plan, knowledge, identity, absence\\n of mistake, or lack of accident.\\nFed. R. Evid. 404(b)(1)–(2).\\n\\n 130\\n\\f At trial, Vederman sought to present a witness from\\nAmerican University who would have testified that\\n“Vederman agreed, on more than fifty instances, to\\nfinancially assist students [at American] who needed help\\nwith tuition, book money, or travel funds to visit their\\nfamilies.” Vederman Br. 42 (emphasis omitted).\\nAccording to Vederman, the testimony was relevant to\\nrefuting the Government’s argument that he agreed to\\nguarantee the tuition expenses of Fattah’s au pair as a way\\nof bribing the congressman. In excluding this evidence\\nunder Rule 404(b), the District Court stated at sidebar:\\n\\n I sustain the government’s objection to\\n calling a representative of American\\n University to testify on behalf of Herbert\\n Vederman.\\n\\n In my view the testimony runs afoul of\\n Rule 404(b)(1) of the Federal Rules of\\n Evidence. I find it to be propensity evidence.\\n He or she would be testifying about Mr.\\n Vederman’s financial generosity with respect\\n to students of American University.\\n The issue here is payment of partial\\n tuition of a student at the Philadelphia\\n University. I see no connection between the\\n generosity at American University and the\\n situation with Philadelphia University.\\n\\n\\n 131\\n\\fJA4459–60. Vederman argues that because the proposed\\nevidence related to Vederman’s intent, and not solely his\\npropensity to perform good acts, we should conclude that\\nthe District Court abused its discretion. We see no error in\\nthe District Court’s ruling.\\n\\n Vederman challenges as arbitrary the District\\nCourt’s “assertion that support for American University\\nstudents is too remote from support for Philadelphia\\nUniversity students” such that it constitutes inadmissible\\nevidence. Vederman Reply Br. 23. This distinction was far\\nfrom arbitrary. Vederman may well have financially\\nsupported American University students because of\\nconnections he had to that school or to the D.C.\\ncommunity at large—connections Vederman did not have\\nto Philadelphia University. And the excluded testimony\\nappears to have described support for students Vederman\\ndid not previously know. By supporting Fattah’s au pair,\\nVederman was helping an employee of a man whom he\\nknew quite well. JA889 (“[Fattah and Vederman] spent a\\nlot of time together traveling back and forth to\\nWashington, in the case of a death in the family attending\\ncertain ceremonies that were important, and above all\\nspending time with each other and their families\\ntogether.”). Vederman’s decision to help Fattah’s au pair,\\nwho wished to attend Philadelphia University, seems more\\nlike a departure from, rather than a continuation of, his\\npattern of support for American University students.\\n\\n\\n\\n 132\\n\\f As the party seeking admission of evidence under\\nRule 404(b), Vederman bore “the burden of demonstrating\\nits applicability” and “identifying a proper purpose.”\\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\\n2014). By failing to explain sufficiently why the factual\\ndistinctions discussed above were not material, Vederman\\nfailed to meet his burden. In particular, although\\nVederman argues that he offered evidence of his prior gift-\\ngiving to prove intent—“a proper non-propensity\\npurpose”—he failed to show why the proposed testimony\\nwas “relevant to that identified purpose.” Id. at 277. 28 As\\nwe noted in Ansell v. Green Acres Contracting, an\\nemployment discrimination case on which Vederman\\nheavily relies, “[t]here is. . . no bright line rule for\\ndetermining when evidence is too remote to be relevant.”\\n347 F.3d at 525. As such, a district court’s determination\\nunder Rule 404(b) “will not be disturbed on appeal unless\\nit amounts to an abuse of discretion.” Id. The District\\n\\n\\n\\n28\\n Under Rule 404(b), “prior act evidence is inadmissible\\nunless the evidence is (1) offered for a proper non-\\npropensity purpose that is at issue in the case; (2) relevant\\nto that identified purpose; (3) sufficiently probative under\\nRule 403 such that its probative value is not outweighed\\nby any inherent danger of unfair prejudice; and\\n(4) accompanied by a limiting instruction, if requested.”\\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\\n2014).\\n 133\\n\\fCourt did not abuse its discretion in excluding evidence of\\nVederman’s support for students at American University.\\n\\nB. Evidentiary Rulings Regarding Nicholas’s Defense\\n Nicholas argues that the District Court rendered\\nthree erroneous evidentiary rulings that prejudiced her\\ndefense. We do not find any of her arguments convincing.\\n\\n 1. The EAA Board Minutes\\n In support of its theory that Nicholas defrauded\\nEAA, the Government introduced minutes from EAA’s\\nBoard. Minutes from 2005 revealed that the Board limited\\nNicholas’s signing authority to $100,000. Minutes from\\nDecember 2007, February 2008, and May 2008 failed to\\nreference either the EAA–Solutions contract or the checks,\\ndrawn from EAA’s account for $500,000 and $100,000,\\nthat were purportedly paid pursuant to the contract.\\nNicholas contends that the Board minutes were\\nerroneously admitted because they constituted improper\\nhearsay which failed to satisfy either the exception for\\nbusiness records under Federal Rule of Evidence 803(6)\\nor the absence of records exception under Federal Rule of\\nEvidence 803(7). “We review the District Court’s\\nevidentiary ruling[s] for abuse of discretion, but also\\n‘exercise plenary review . . . to the extent [the rulings] are\\nbased on a legal interpretation of the Federal Rules of\\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\\n(second alteration in original).\\n\\n 134\\n\\f Applying those standards here,29 we conclude there\\nwas sufficient basis to admit exhibit EAA-48 under\\nFederal Rule of Evidence 803(6) as a business record.\\nAlthough allowing the prosecution to inquire over\\nNicholas’s earlier objection based on Federal Rule of\\nEvidence 803(7) to the absence of any mention of the\\n$500,000 check in the 2008 Board Minutes was error, it\\nwas not reversible error. Other evidence in the record\\noverwhelmingly showed that Nicholas made the $500,000\\nand $100,000 payments to Solutions with the requisite\\nfraudulent intent. That evidence included the 2005 policy\\nlimiting Nicholas’s authority to approve expenditures to\\n$100,000, the accountant’s testimony about the\\ndisbursement policy requiring the completion of a check\\nrequest form for the issuance of a check, and Jones’\\ntestimony that he never saw a request for the $500,000\\ncheck. That evidence, coupled with Nicholas’s tendering\\nof the upfront half-million dollar payment before the terms\\nof the purported agreement had been finalized or executed,\\nher failure to mention the $600,000 in payments to\\nSolutions during her interview with FBI Agent\\n\\n29\\n We note that the argument section of Nicholas’s brief on\\nthis issue specifically cited to the page in the record where\\nexhibit EAA-48 was admitted without objection by any\\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\\n82). Nonetheless, there was an earlier objection to the\\nadmission of exhibit EAA-48 that was preserved and that\\nwas referenced in a string citation elsewhere in Nicholas’s\\nbrief.\\n 135\\n\\fDieffenbach, and her alteration of EAA’s general ledger\\nto conceal the $100,000 payment, makes it “highly\\nprobable” that the jury would have reached the same\\nresult. See United States v. Friedman, 658 F.3d 342, 352\\n(3d Cir. 2011).\\n\\n Nicholas also asserts that the Board minutes were\\nunfairly prejudicial. We disagree. Any possible prejudice\\nwas minimized by the fact that the Board minutes make no\\nreference to either the EAA–Solutions contract or to any\\nfinancial matters whatsoever. Indeed, given these lacunae\\nin the Government’s proof, a reasonable factfinder might\\nwell have concluded that the Board’s intention to limit\\nNicholas’s signing authority had not been implemented\\nand that Nicholas had not concealed the contract from the\\nBoard.\\n\\n 2. Jones’ Memory Regarding Other Contracts\\n Nicholas next asserts that the District Court erred\\nduring her cross-examination of Board Chairman Jones by\\nsustaining the prosecution’s objection to her inquiry into\\nwhether he remembered other contracts in excess of\\n$100,000 being brought to the Board. See JA1386–87. The\\nbasis of the prosecution’s objection seemed to be that\\nNicholas’s line of inquiry was beyond the scope of the\\ndirect testimony. JA1387 (“I showed checks concerning\\nwhat’s going on, not other programs.”); see Fed. R. Evid.\\n611(b). The District Court sustained the objection,\\ndeclaring that “it has absolutely nothing to do with this\\ncase.” JA1387. Nicholas contends that if Jones did not\\n 136\\n\\frecall whether other large contracts had been presented to\\nthe Board, his inability to recall the EAA–Solutions\\ncontract would have been “unremarkable rather than\\nevidence of fraud or concealment.” Nicholas Br. 61.\\n\\n We acknowledge that whether Jones remembered\\nother large contracts requiring Board approval had some\\nrelevance under Rule 401. Yet any error by the District\\nCourt in prohibiting Nicholas’s counsel from pursuing this\\nline of inquiry is harmless. Jones admitted that he did not\\nknow if the Board ever implemented the policy requiring\\nits approval of contracts exceeding $100,000. He also\\nconceded that the EAA Board focused less on the financial\\nside of EAA than on its programs. JA1383–85. Nicholas\\ncould not have been prejudiced by the District Court’s\\nruling.\\n\\n 3. Exclusion of NOAA Evidence\\n Nicholas defended against the criminal charges\\narising out of the non-existent October 2012 conference\\nby asserting that she acted in “good faith in spending the\\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\\ndifference in the dates in the paperwork was not material,\\nand that NOAA had received the benefits of the\\nsponsorship because its logo was displayed on the signage\\nused at the February conference. Nicholas succeeded in\\npresenting testimony and introducing photographs that\\nshowed NOAA’s logo on the February 2012 annual\\nconference bags, padfolios, and name tags. The Court\\nexcluded a photograph of a NOAA intern at the February\\n 137\\n\\f2012 conference, other photographs of the February\\nconference signage, and some checks that pertained to the\\nFebruary conference. Nicholas claims that her inability to\\nintroduce those exhibits frustrated her ability to present\\nher good faith defense. We are not persuaded.\\n\\n The photographs were excluded as cumulative, the\\nsort of ruling to which we afford trial judges very broad\\ndiscretion. See Fed. R. Evid. 403; United States v.\\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\\nerror to exclude the student intern’s photograph. The\\nconference brochure included photographs from previous\\nconferences, and the witness from NOAA was unable to\\ntestify to the year the student served as an intern. Finally,\\nthe checks tendered for the travel expenses incurred for the\\nFebruary conference were excluded as irrelevant to\\nwhether Nicholas had a good faith belief that NOAA\\nsponsored the October conference.\\n\\nC. The Cooperating Witness’s Mental Health Records\\n During discovery, Brand learned that a cooperating\\nwitness was diagnosed with bipolar II disorder and was\\ntaking medication to treat that condition. Brand\\nsubpoenaed mental health records kept by the witness’s\\ncurrent and former psychiatrists in hopes of using those\\nrecords to attack the witness’s memory, truthfulness, and\\ncredibility. The witness and the Government both filed\\nmotions to quash the subpoena, arguing that the witness’s\\nmental health records were protected by the\\npsychotherapist–patient privilege recognized by the\\n 138\\n\\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\\nThe Government also filed a motion in limine seeking to\\nrestrict the scope of cross-examination to prevent Brand\\nfrom questioning the witness about his mental health.\\n\\n Alongside his motion to quash, the witness\\nvoluntarily produced for the Court his mental health\\nrecords. The Court concluded that the psychotherapist–\\npatient privilege would ordinarily apply to the mental\\nhealth records, but that the privilege was not absolute,\\nespecially when invoked in response to a criminal\\ndefendant’s efforts to obtain through discovery evidence\\nthat is favorable to his case. Following the procedure set\\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\\nDistrict Court conducted an in camera review of the\\nmental health records to determine if they contained\\nmaterial evidence—that is, evidence that would “give[]\\nrise to a reasonable probability that it [would] affect the\\noutcome of the case.” JA149. The District Court found\\n“nothing in the mental health records of the [witness] . . .\\nmaterial for this criminal action,” noting that “[t]he\\nrecords reveal nothing that calls into question [the\\nwitness’s] memory, perception, competence, or veracity.”\\nJA150. Accordingly, the Court entered an order granting\\nthe motions to quash the subpoena.\\n The District Court also granted the Government’s\\nmotion in limine and restricted the scope of cross-\\nexamination, ruling that “no reference may be made to [the\\nwitness’s] bipolar disorder or the medications he takes to\\n\\n 139\\n\\fmanage it.” JA142, 156. The Court reasoned that bipolar\\ndisorder varied in its effects from person to person, and\\nconcluded that Brand had not shown that the effects of the\\ndisorder had any bearing on the witness’s credibility. The\\nDistrict Court ruled that cross-examination would not\\nserve any valid impeachment purpose.\\n Brand claims that the District Court’s order ran\\nafoul of the Due Process Clause of the Fifth Amendment\\nand the Confrontation Clause of the Sixth Amendment.\\nWe review a district court’s rulings to quash a subpoena\\nand to limit the scope of cross-examination for abuse of\\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\\nCir. 1992). Here, the District Court did not abuse that\\ndiscretion.\\n\\n1. The District Court’s Denial of Access to the Mental\\n Health Records\\n In claiming that the District Court’s decision to\\nreview the mental health records in camera before ruling\\non their admissibility violated his rights under both the\\nFifth and Sixth Amendments, Brand specifically argues\\nthat his right to confront the witness was impeded because\\nhe was denied access to records he could have used to\\nimpeach the witness. This very argument was considered\\nand rejected by a plurality of the Supreme Court in Ritchie,\\nwhich noted that “the effect [of the argument] would be to\\ntransform the Confrontation Clause into a constitutionally\\ncompelled rule of pretrial discovery. . . . [T]he right to\\n 140\\n\\fconfrontation is a trial right, designed to prevent improper\\nrestrictions on the types of questions that defense counsel\\nmay ask during cross-examination.” 480 U.S. at 52. We\\nfollow the Ritchie plurality, and conclude that the\\nConfrontation Clause did not require the District Court to\\ngrant Brand access to the witness’s mental health records.\\n Brand next challenges the District Court’s decision\\nto quash the subpoena as a violation of the Fifth\\nAmendment’s Due Process Clause. He concedes that\\nRitchie’s Due Process holding allowed the District Court\\nto review the mental health records in camera without\\ndisclosing them to him. See id. at 59–60 (“A defendant’s\\nright to discover exculpatory evidence does not include the\\nunsupervised authority to search through [the\\nGovernment’s] files. . . . We find that [the defendant’s]\\ninterest . . . in ensuring a fair trial can be protected fully by\\nrequiring that the [privileged] files be submitted only to\\nthe trial court for in camera review.”). Brand instead\\nargues that the District Court abused its discretion by\\nfocusing on “irrelevant facts and spurious symptoms. . . .\\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\\nevidence of cognitive impairment and memory issues.”\\nBrand Br. 30. The record reveals, however, that the\\nDistrict Court reviewed the mental health records and\\ndetermined that they “reveal[ed] nothing that calls into\\nquestion [the witness’s] memory, perception, competence,\\nor veracity.” JA150. This hardly amounts to a refusal to\\nconsider evidence of cognitive impairment or memory\\nissues.\\n 141\\n\\f Brand also challenges the legal standard applied by\\nthe District Court, arguing that the court “focused solely\\non whether disclosure would ‘change the outcome’ of\\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\\nconsidering “whether the ultimate verdict is one ‘worthy\\nof confidence.’ ” Id. (quoting United States v. Robinson,\\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\\nmisleadingly quotes from the District Court’s opinion. The\\nDistrict Court considered, in accordance with Ritchie,\\n“whether there is a reasonable probability that disclosure\\nwould change the outcome” of Brand’s trial, JA148\\n(emphasis added), not whether disclosure would\\nnecessarily change the outcome. As articulated in Ritchie,\\na “ ‘reasonable probability’ is a probability sufficient to\\nundermine confidence in the outcome.” 480 U.S. at 57\\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\\n(Blackmun, J.)). The District Court applied the correct\\nstandard.\\n\\n2. The District Court’s Grant of the Motion in Limine\\n In granting the Government’s motion in limine, the\\nDistrict Court ruled that Brand could not “reference . . .\\n[the witness’s] bipolar disorder or the medications he takes\\nto manage it.” JA156. Yet that ruling placed no restriction\\non Brand’s ability to cross-examine the witness with\\nrespect to “his memory, competence, or truthfulness.” Id.\\nBrand argues, nevertheless, that his Sixth Amendment\\nright “to be confronted with the witnesses against him”\\nwas violated. U.S. Const. amend. VI.\\n\\n 142\\n\\f The Confrontation Clause protects a defendant’s\\nright to cross-examine a witness with respect to any\\ntestimonial statements made by that witness. United States\\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\\nthe scope of cross-examination is not unlimited, and “[a]\\ndistrict court retains ‘wide latitude insofar as the\\nConfrontation Clause is concerned to impose reasonable\\nlimits on such cross-examination based on concerns about\\n. . . harassment, prejudice, confusion of the issues, the\\nwitness’ safety, or interrogation that is repetitive or only\\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\\nCir. 2005)). We review limitations on cross-examination\\nfor abuse of discretion, and reverse “only when the\\nrestriction ‘is so severe as to constitute a denial of the\\ndefendant’s right to confront witnesses against him and . . .\\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\\nin original) (quoting United States v. Conley, 92 F.3d 157,\\n169 (3d Cir. 1996)).\\n In United States v. Chandler, 326 F.3d 210, 219 (3d\\nCir. 2003), we analyzed whether a district court’s decision\\nto limit cross-examination with respect to a witness’s\\nmotivation for testifying violated the Confrontation\\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\\n747 F.3d at 211–12. Consistent with Delaware v. Van\\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\\nexposure of a witness’ motivation in testifying is a proper\\n 143\\n\\fand important function of the constitutionally protected\\nright of cross-examination.” Chandler, 326 F.3d at 219–\\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\\nnoted that the Confrontation Clause does not prevent a trial\\njudge from imposing reasonable limits on cross-\\nexamination. Id. In reviewing a district judge’s imposition\\nof such limitations, we apply a two-part analysis. As we\\nhave since described, “we inquire into: ‘(1) whether the\\nlimitation significantly limited the defendant’s right to\\ninquire into a witness’s motivation for testifying; and\\n(2) whether the constraints imposed fell within the\\nreasonable limits that a district court has the authority to\\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\\nMussare, 405 F.3d at 169).\\n The same analytical framework is appropriate when\\ndetermining whether a restriction on the cross-\\nexamination of a witness with respect to his memory and\\nperception violates the Confrontation Clause. See Davis v.\\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\\n578, 582 (3d Cir. 1976). Memory and perception, like\\nmotivation for testifying, are central issues affecting the\\ncredibility of any witness, and unreasonable limitations on\\nthe right to cross-examine on those subjects cannot be\\ncountenanced. We therefore ask, paraphrasing Chandler:\\n(1) whether the District Court’s decision to put the\\nwitness’s diagnosis and medications off limits\\nsignificantly impaired Brand’s right to inquire into the\\nwitness’s memory and perception; and (2) whether the\\n 144\\n\\fruling fell within the reasonable limits that the District\\nCourt has the authority to impose.\\n We conclude that the District Court did not err. As\\nan initial matter, the District Court permitted Brand to\\ncross-examine the witness about his memory and\\nperception, and limited cross-examination only with\\nrespect to the witness’s bipolar disorder and the\\nmedications he was taking to treat that condition. Brand\\nwas free to question the witness about his memory and\\nperception, and indeed did so. The restriction on asking\\nthe witness about his bipolar disorder was not a significant\\nlimitation of Brand’s right to inquire into the witness’s\\nmemory or perception. Moreover, as the District Court\\npointed out, Brand failed to show how inquiry into the\\nwitness’s bipolar disorder would be useful for\\nimpeachment purposes. See JA154.\\n\\n Given that failure, the District Court’s limits on\\ncross-examination were reasonable. The Court concluded,\\nafter reviewing the evidence submitted by Brand and the\\nwitness’s mental health records, that any mention of the\\nwitness’s bipolar disorder would “only be designed to\\nconfuse the jury or to stigmatize him unfairly because of a\\n‘mental problem’ without any countervailing probative\\nvalue.” JA155. The District Court did not abuse its\\ndiscretion in limiting Brand’s cross-examination on a topic\\nthat would be far more prejudicial than probative. See\\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\\n\\n\\n 145\\n\\fwell within its discretion to restrict irrelevant and\\nconfusing testimony.”).\\n All of this is not to suggest that a witness’s mental\\nhealth is always off limits. The appropriate course in any\\ngiven case must be determined from the facts and\\ncircumstances surrounding that case and the witness’s\\nparticular condition. See United States v. George, 532 F.3d\\n933, 937 (D.C. Cir. 2008) (“The days are long past when\\nany mental illness was presumed to undermine a witness’s\\ncompetence to testify. . . . [M]ental illness [is] potentially\\nrelevant in a broad[] range of circumstances . . . . [But]\\nsome indication is needed that a particular witness’s\\nmedical history throws some doubt on the witness’s\\ncompetence or credibility.”). Here, Brand failed to show,\\nthrough mental health records or otherwise, any\\nparticularized reason to doubt the credibility of the witness\\nfor medical reasons.\\n\\n Brand states that the witness provided “the only\\nevidence offered” on the intent element of his conspiracy\\nconviction and that he should therefore be entitled to\\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\\nmatter the importance of a witness to any party, a district\\ncourt may always place reasonable limits on cross-\\nexamination to avoid “harassment, prejudice, confusion of\\nthe issues, the witness’ safety, or interrogation that is\\nrepetitive or only marginally relevant.” John-Baptiste, 747\\nF.3d at 211 (citation omitted).\\n\\n\\n 146\\n\\f We conclude that the District Court did not abuse\\nits discretion in restricting the scope of Brand’s cross-\\nexamination of the cooperating witness.\\n\\n X. The Government’s Cross-Appeal\\n The jury convicted Fattah, Vederman, and Bowser\\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\\nfalse statements to a financial institution, 18 U.S.C.\\n§ 1014 31 (Count 20). In response to post-trial motions, the\\nDistrict Court granted a judgment of acquittal on both\\ncounts under Fed. R. Crim. P. 29, concluding that the\\n\\n30\\n “Whoever knowingly executes, or attempts to execute,\\na scheme or artifice . . . to defraud a financial institution\\n. . . shall be fined not more than $1,000,000 or imprisoned\\nnot more than 30 years, or both.” The definition of\\n“financial institution” for purposes of § 1344 is set forth at\\n18 U.S.C. § 20, and includes “a credit union with accounts\\ninsured by the National Credit Union Share Insurance\\nFund” and “a mortgage lending business (as defined in\\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\\n31\\n “Whoever knowingly makes any false statement or\\nreport, or willfully overvalues any land, property or\\nsecurity, for the purpose of influencing in any way the\\naction of . . . a Federal credit union . . . any institution the\\naccounts of which are insured by . . . the National Credit\\nUnion Administration Board . . . or a mortgage lending\\nbusiness . . . shall be fined not more than $1,000,000 or\\nimprisoned not more than 30 years, or both.”\\n 147\\n\\fevidence was insufficient to establish that the Credit\\nUnion Mortgage Association (CUMA), the entity to whom\\nFattah, Vederman, and Bowser made the false statements,\\nis a “financial institution,” or, more specifically, a\\n“mortgage lending business” as defined in 18 U.S.C. § 27.\\nThe Government claims that, viewing the evidence in the\\nlight most favorable to it, the District Court erred and that\\nCUMA is, indeed, a “mortgage lending business.” We\\nagree. Because the evidence is sufficient to support the\\njury’s verdict, we will remand so Fattah and Vederman\\nmay be resentenced on these charges.32\\n\\n A. CUMA is a Mortgage Lending Business\\n In reviewing the District Court’s post-verdict\\njudgment of acquittal under Rule 29 of the Federal Rules\\nof Civil Procedure, we consider whether the evidence,\\nwhen viewed in a light most favorable to the government,\\nsupports the jury’s verdict. United States v. Dixon, 658\\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\\nsame as that applied by the District Court, and we must\\nuphold the jury’s verdict unless no reasonable juror could\\naccept the evidence as sufficient to support the defendant’s\\nguilt beyond a reasonable doubt. United States v.\\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\\n\\n32\\n Because the Government did not file an appeal as to\\nBowser, the cross-appeal is limited to Fattah and\\nVederman. The judgment of acquittal as to Bowser is\\ntherefore unaffected by our ruling today.\\n 148\\n\\f Initially, the grand jury’s indictment alleged that\\nCUMA is a financial institution because it is federally\\ninsured. JA302–03. At trial, however, the jury was\\ninstructed that CUMA could qualify as a financial\\ninstitution either because it is federally insured or because\\nit is a “mortgage lending business.” See JA111, 401–02. A\\n“mortgage lending business” is “an organization which\\nfinances or refinances any debt secured by an interest in\\nreal estate, including private mortgage companies and any\\nsubsidiaries of such organizations, and whose activities\\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\\n\\n At trial, CUMA’s president and CEO, Eddie Scott\\nToler, testified that CUMA is not federally insured.\\nJA4235. The Government therefore attempted to prove\\nthat CUMA is a “mortgage lending business” by\\npresenting evidence that CUMA funds mortgages and then\\nsells them in a secondary market.\\n\\n Toler also testified that CUMA is a “credit union\\nservice organization”—a for-profit company owned by 48\\ncredit unions, which serves small credit unions that do not\\nhave the infrastructure or in-house expertise to handle\\nmortgage loans themselves. JA4235. According to Toler,\\n“[CUMA] exclusively provide[s] First Trust Residential\\nMortgage loaning [sic] services, all the way from the\\norigination of the mortgage loan through processing,\\nunderwriting, closing and access to the secondary market\\nwhere—and we’re selling the mortgage loan on the\\nsecondary market.” JA4236–37. In jurisdictions in which\\n\\n 149\\n\\fCUMA is licensed, 33 CUMA holds the mortgage for a\\nlimited period, generally from two to thirty days, and then\\nsells the mortgage either to a partner credit union or on the\\nsecondary market. JA4240.\\n\\n The District Court concluded that CUMA is not a\\n“mortgage lending business” because “[t]he record is\\ndevoid of any evidence that CUMA finances or refinances\\nany debt.” JA113. Concluding that CUMA “simply is a\\nloan processor for various credit unions which do the\\nfinancing or refinancing,” id., the District Court ruled that\\nCUMA’s “activity does not constitute the financing or\\nrefinancing of any debt. CUMA is not the mortgagee. It is\\nmerely selling the debt instrument to a third party.” JA114.\\n We cannot agree with the District Court’s view of\\nthe evidence. Toler testified that in “Maryland, D.C., and\\nVirginia . . . all of the loans are closed in the name of\\nCUMA.” JA4238–39. As Toler described it, CUMA\\nborrows on a line of credit to fund the loan, and when the\\nloan is sold, CUMA pays off its line of credit. JA4239–40.\\nSo contrary to the District Court’s assessment, the\\nevidence, viewed in a light most favorable to the\\nGovernment, shows that CUMA is indeed the\\nmortgagee—at least during the time from closing until the\\nloan is sold to a partner credit union or on the secondary\\nmarket. The fact that CUMA funds the closing and then\\n\\n33\\n CUMA is licensed in Maryland, Washington, D.C., and\\nVirginia. JA4238.\\n 150\\n\\fholds the mortgage, even for a brief time, is sufficient to\\nsupport a conclusion that CUMA is “an organization\\nwhich finances or refinances any debt secured by an\\ninterest in real estate.” 18 U.S.C. § 27.\\n\\n Fattah and Vederman attempt to refute the argument\\nthat CUMA engages in financing mortgages by focusing\\non Toler’s testimony that CUMA “doesn’t actually have\\nany money to fund these mortgage loans.” JA4239; see\\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\\ntestified that CUMA employs a credit line to borrow the\\nfunds necessary to close on mortgages. See JA4239. That\\nCUMA incurs debt to finance mortgages hardly\\nundermines a conclusion that CUMA finances mortgages.\\nIndeed, it is the very nature of modern banking that\\nfinancial institutions do not hold cash reserves equal to the\\nfull amount of their liabilities. See, e.g., Timothy C.\\nHarker, Bailment Ailment: An Analysis of the Legal Status\\nof Ordinary Demand Deposits in the Shadow of the\\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\\nde facto standard for all modern banks.”).\\n\\n Vederman also argues that, even if CUMA acts as a\\nmortgage lending business in some transactions, it was not\\nacting as a mortgage lending business in this transaction.\\nVederman points to Toler’s testimony that, in a state in\\nwhich CUMA is not licensed, the mortgage is closed in the\\nname of a credit union. In such cases, the credit union, and\\nnot CUMA, owns the mortgage for the short period before\\n\\n 151\\n\\fthe loan is sold on the secondary market. JA4241. CUMA\\nis not licensed in the Commonwealth of Pennsylvania. See\\nid. Thus, according to Vederman, CUMA was acting in its\\ncapacity as a mortgage servicing company for Fattah’s\\nvacation home purchase and did not—and could not—\\nfinance Fattah’s mortgage. That would mean that CUMA\\ncould not have been a victim of a crime against a financial\\ninstitution in this instance: “When an entity is not\\nfunctioning as a mortgage lender, the ‘pertinent federal\\ninterest’ behind the statutes is not implicated.” Vederman\\nReply Br. 38 (citation omitted).\\n\\n The Government responds that neither of the\\nstatutes of conviction requires that the fraud or false\\nstatement occur in connection with the same transaction\\nthat places the entity within the definition of “financial\\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\\nGovernment.\\n\\n Both § 1344 and § 1014 protect entities that fall\\nwithin the definition of “financial institution” and are\\notherwise quite broad in their application. See Loughrin v.\\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\\n§ 1344 as not requiring specific intent to defraud a bank);\\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\\n(“[Section 1014’s] reach is not limited to false statements\\nmade with regard to loans, but extends to any application,\\ncommitment or other specified transaction.”). Neither\\nstatute is expressly limited in the manner that Vederman\\nsuggests. Williams v. United States, 458 U.S. 279, 284\\n\\n 152\\n\\f(1982) (“To obtain a conviction under § 1014, the\\nGovernment must establish two propositions: it must\\ndemonstrate (1) that the defendant made a ‘false statement\\nor report,’ . . . and (2) that he did so ‘for the purpose of\\ninfluencing in any way the action of [a described financial\\ninstitution] upon any application, advance, . . .\\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\\nstatute is to protect the ‘financial integrity of [banking]\\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\\nother grounds by Loughrin, 134 S. Ct. at 2389.\\n In support of his position, Vederman relies on\\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\\nwhich the Fifth Circuit concluded that § 1014 (false\\nstatements to a financial institution) is not intended to\\ncapture fraud unrelated to an entity’s lending activities,\\nand therefore held that it “applies only to actions involving\\nlending transactions.” Id. at 580. The Fifth Circuit stated:\\n [W]e are not persuaded that the statute\\n imposes liability whenever a defendant’s\\n false statement was intended to interfere with\\n any activity of a financial institution; such a\\n broad interpretation of section 1014\\n presumably would encompass fraud or false\\n representations having nothing to do with\\n financial transactions, such as fraud in an\\n employment contract or, for example, in a\\n\\n 153\\n\\f contract to provide goods or services for\\n custodial care, premises repair, or renovation.\\nId.\\n\\n Yet a majority of circuits, including our own, have\\ndeclined to follow Devoll’s suggestion that § 1014 is\\nrestricted to lending transactions. As the Ninth Circuit has\\nheld, “we join at least six of our sister circuits—the First,\\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\\n18 U.S.C. § 1014 is not limited to lending transactions,\\nand reject the minority rule to the contrary.” Boren, 278\\nF.3d at 915. And even if we were to adopt Devoll’s narrow\\nconstruction of § 1014 to lending transactions, that would\\nnot resolve the more specific question of whether the\\ndefrauded entity must be defined as a “mortgage lending\\nbusiness” by virtue of the specific transaction in which the\\nfalse statements arose.\\n Recently, the Eighth Circuit addressed precisely\\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\\nCir. 2017), that Court considered the defendant’s appeal\\nfrom the district court’s denial of a Rule 29 motion on\\ngrounds that GMAC, the entity defrauded, was not a\\n“financial institution.” The Court upheld the district\\ncourt’s determination that the evidence was sufficient to\\nestablish that GMAC is in the mortgage lending business\\nbecause there was testimony that “it had made hundreds or\\nthousands of loans secured by mortgages in 2010 and 2011\\nin states all across the country,” which established that its\\nactivities affect interstate commerce. Id. at 953. It was not\\n 154\\n\\fdeterminative that GMAC did not own the specific loan at\\nissue in the case: “we discern no requirement in the\\ndefinition of ‘mortgage lending business’ that the business\\nown the particular loan in question; it need only finance or\\nrefinance any debt secured by an interest in real estate, or,\\nin other words, be in the interstate mortgage lending\\nbusiness in general.” Id.\\n\\n In our view, the Eighth Circuit’s analysis is correct.\\nWe therefore adopt that Court’s reasoning in Springer and\\nconclude that it is of no moment that CUMA did not\\nfinance the mortgage at issue in Fattah’s case. CUMA is a\\n“mortgage lending business,” and that alone suffices to\\nsupport the convictions under §§ 1014 and 1344.\\n\\n B. Sufficiency of the Evidence\\n Finally, Vederman argues that, even if CUMA is a\\nfinancial institution, the judgment of acquittal should\\nstand because the Government did not put forth any\\nevidence that he made a false representation to CUMA.34\\nSpecifically, Vederman argues that the title to the Porsche\\nwas actually changed to his name, making it a “true sale”\\nas a matter of law, without regard to whether Fattah’s wife\\n\\n34\\n Although Vederman presented this argument in his Rule\\n29 motion, the District Court did not need to reach it in the\\ncontext of Counts 19 and 20 because the Court granted the\\nmotion on the ground that CUMA is not a financial\\ninstitution. The District Court rejected the argument as to\\nCounts 16, 17, and 18. See JA100–02.\\n 155\\n\\fcontinued to retain possession. See United States v.\\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\\nanother context that “the government must be able to show\\nthat [the defendant] made a statement to government\\nagents that was untrue, and the government cannot satisfy\\nthat burden by showing that the defendant intended to\\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\\nCons. Stat. § 102 (defining “owner” as “[a] person, other\\nthan a lienholder, having the property right in or title to a\\nvehicle”).\\n\\n The Government responds that, regardless of\\nwhether it is legally possible for one person to hold a title\\nwhile a different person possesses the vehicle, the jury was\\npermitted to consider all the circumstances in deciding\\nwhether the Porsche sale was a sham. We agree.\\n\\n First, as the District Court observed, it was unclear\\nas to whether the title had been properly executed under\\nPennsylvania law. For instance, Fattah’s wife never\\nappeared before a notary. 35 JA101. In addition, title 75,\\nsection 1111(a) of the Pennsylvania Consolidated Statutes\\nrequires that, “[i]n the event of the sale or transfer of the\\nownership of a vehicle within this Commonwealth, the\\nowner shall . . . deliver the certificate to the transferee at\\n\\n35\\n Vederman argues that it is of no significance that the\\nparties did not appear before a notary as the statute\\nrequires, but he offers cases only from states other than\\nPennsylvania to support this proposition.\\n 156\\n\\fthe time of the delivery of the vehicle.” And, the transferee\\nmust, within twenty days of the assignment of the vehicle,\\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\\nNeither of these requirements was fulfilled. Finally,\\nVederman never registered the Porsche in his name with\\nthe Department of Motor Vehicles. See id.; JA4254.\\n Second, and more importantly, even if the title had\\nbeen properly transferred to Vederman, the title provisions\\nof the Pennsylvania Motor Vehicle Code “were [not]\\ndesigned to establish conclusively the ownership of an\\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\\na certificate of title is not to conclusively establish\\nownership in a motor vehicle, but rather to establish the\\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\\nprovides evidence of ownership; it is not dispositive of the\\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\\n(Pa. Super. Ct. 1967).\\n Vederman’s argument that the title in his name\\nconstitutes conclusive evidence of ownership rests upon\\nan erroneous conclusion that the jury was prohibited from\\nconsidering all the circumstances of the transfer. As the\\nDistrict Court observed, though, Pennsylvania’s\\nCommonwealth Court has held that “[w]hether a\\ntransferor has transferred ownership of a motor vehicle to\\na transferee is a factual determination to be made by the\\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\\n\\n 157\\n\\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\\nof title was appropriately treated as one piece of evidence\\nfor the jury to consider in assessing the validity of the\\nvehicle transfer. Considered in the light most favorable to\\nthe Government, the totality of the evidence is sufficient\\nto support the jury’s conclusion that the Porsche sale was\\na sham.\\n\\n XI. Prejudicial Spillover\\n Finally, Fattah, Vederman, Nicholas, and Brand\\neach contend that their convictions on various counts\\nresulted from prejudicial spillover. We are not persuaded.\\n We exercise plenary review over a district court’s\\ndenial of a claim of prejudicial spillover, United States v.\\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\\ntwo-step test when reviewing such a claim. United States\\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\\nmust consider “whether the jury heard evidence that would\\nhave been inadmissible at a trial limited to the remaining\\nvalid count[s].” Id. (quoting United States v. Cross, 308\\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\\nthat we “ask whether that evidence (the ‘spillover\\nevidence’) was prejudicial.” Id. We consider four factors:\\n“whether (1) the charges are intertwined with each other;\\n(2) the evidence for the remaining counts is sufficiently\\ndistinct to support the verdict on these counts; (3) the\\nelimination of the invalid count [will] significantly\\nchange[] the strategy of the trial; and (4) the prosecution\\nused language of the sort to arouse a jury.” Id. (quoting\\n 158\\n\\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\\n2003)); see also United States v. Pelullo (Pellulo II), 14\\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\\nconsidered in a light “somewhat favorable to the\\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\\nF.3d at 122); see also Gov’t Br. 198 (same).\\n\\n A. Fattah’s Claim of Prejudicial Spillover\\n Fattah argues that he suffered prejudicial spillover\\non the remaining counts of conviction in light of (1)\\nevidence pertinent to the alleged Vederman bribery\\nschemes that is now arguably inadmissible under\\nMcDonnell; and (2) “the government’s flawed RICO\\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\\nis undercut substantially because of our determination that\\nMcDonnell requires a new trial for Counts 16, 17, 22, and\\n23 and our decision to affirm the RICO conspiracy\\nconviction. The only possible spillover left to consider is\\nthe evidence pertaining to Fattah’s arranging a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk, which in light of McDonnell is now arguably\\ninadmissible.36\\n\\n The evidence of the Kirk meeting admitted during\\nthis five-week trial was limited. Although this evidence\\n\\n36\\n Nothing in this opinion is intended to foreclose the\\npossibility that evidence of the Kirk meeting may be\\nadmissible on retrial for some purpose other than as proof\\nof an official act.\\n 159\\n\\fwas part of the Government’s proof as to both the RICO\\nand the bribery related charges, there is more than\\nsufficient—and distinct —evidence to support Fattah’s\\nconviction on all the other counts. In our view, eliminating\\nany evidence of the Kirk meeting would not have altered\\nthe strategy of the trial, nor should it significantly change\\nthe strategy for any new trial that may be held. Because\\nFattah has not pointed us to any argument by the\\nprosecution relating to this meeting that could have\\ninflamed the jury, we conclude that Fattah’s prejudicial\\nspillover claim fails. Like the District Court, we presume\\nthat the jury followed the Court’s instructions to consider\\nand weigh separately the evidence on each count as to each\\ndefendant and not to be swayed by evidence pertaining to\\nother defendants. 37\\n\\n B. Vederman’s Assertion of Prejudicial Spillover\\n Because the District Court acquitted Vederman of\\nthe RICO charge, Vederman argues that he was “severely\\nprejudiced by the presentation to the jury of a legally\\nflawed racketeering conspiracy charge,” and as a\\nconsequence his bribery and money laundering\\n\\n37\\n We likewise reject Brand’s prejudicial spillover\\narguments. See Brand Br. 6 (“Brand adopts the significant\\nissue advanced by his co-appellant pursuant to Fed. R.\\nApp. P. 28(i) that improper jury instructions and the\\nresulting spillover of related improperly admitted\\nevidence and argument unfairly prejudiced Brand.”).\\n 160\\n\\fconvictions should be overturned. Vederman Br. 46. In\\nresponse to the Government’s appeal of the District\\nCourt’s Rule 29 acquittal on Counts 19–20 involving\\nCUMA, Vederman asserts that these two counts also were\\naffected by spillover evidence because the Government’s\\ntheory tied the bribery charges to the actions taken to\\ndefraud CUMA. In that we are vacating Vederman’s\\nconvictions of Counts 16–18 and 22–23 based on\\nMcDonnell and remanding for further proceedings, we\\nneed address only Vederman’s argument of prejudicial\\nspillover as it relates to the charges involving CUMA in\\nCounts 19–20, charges that we will reinstate.\\n The District Court’s acquittal of Vederman on the\\nRICO count establishes that step one of the Wright\\nspillover test has been met. “[T]he jury heard evidence that\\nwould have been inadmissible at a trial limited” to the\\nbribery and CUMA-related counts. Wright, 665 F.3d at\\n575 (quoting Cross, 308 F.3d at 317).\\n\\n Wright’s second step requires “ask[ing] whether\\nthat evidence (the ‘spillover evidence’) was prejudicial.”\\nId. Vederman submits that the RICO, bribery, and CUMA-\\nrelated charges were intertwined “in that the acts relating\\nto the alleged bribery scheme were also charged as\\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\\n\\n To be sure, the RICO, bribery, and CUMA Counts\\nare related to one another. But in this instance, mere\\nrelatedness is not enough to demonstrate the foundation\\nnecessary for spillover. This is so because the bribery\\n 161\\n\\fcharges were a predicate to the RICO charge. In other\\nwords, the jury had to determine if Vederman was guilty\\nof bribery, and the jury then used that “predicate” to\\nconsider whether he was also guilty of the RICO\\nconspiracy. Thus, the necessarily tiered structure of the\\nquestions presented to the jury refute Vederman’s\\nargument that the counts were intertwined.\\n\\n That the bribery charges were predicates for the\\nRICO conspiracy further demonstrates that the “evidence\\nfor the different counts was sufficiently distinct to support\\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\\n898. Regardless of the evidence pertaining solely to the\\nRICO conviction, the evidence supporting both the bribery\\ncharges and the charges involving CUMA in Counts 19–\\n20 would have remained the same.\\n\\n The next factor we address is “whether the\\nelimination of the count on which the defendant was\\ninvalidly convicted would have significantly changed the\\n[defendant’s] strategy of the trial.” Id. As Vederman\\nargues, “the RICO charge interfered with Vederman’s\\ncentral defense to the bribery charge—that his gestures\\ntoward Fattah ‘were motivated purely by friendship.’ ”\\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\\nwords, the “RICO count made it dangerous to unduly\\nemphasize [Vederman’s] close friendship” with Fattah. Id.\\nFrom Vederman’s perspective, “a bribery-only trial would\\nhave reduced this danger and allowed a freer presentation\\nof the defense.” Id.\\n\\n 162\\n\\f It is quite likely that Vederman’s claim of friendship\\nwould have been less risky as a litigation strategy if he had\\nnot been facing a RICO charge. But Vederman\\nnevertheless chose to take that risk and fully presented his\\nfriendship argument to the jury. Moreover, while\\nVederman’s reliance on friendship might have helped him\\ndefend against the bribery charges, that friendship would\\nnot have altered the evidence pertaining to Counts 19–20\\ninvolving CUMA. Whether done for friendship or some\\nother reason, submitting fraudulent information to a\\nfinancial institution is unlawful.\\n\\n Finally, we “examine the charges, the language that\\nthe government used, and the evidence introduced during\\nthe trial to see whether they are ‘of the sort to arouse a\\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\\nthat Fattah was presented as “a backslapping, corrupt party\\nboss,” with “predictable spillover to his friend and\\nassociate, Vederman.” Vederman Br. 50 (quoting United\\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\\nthis description was of Fattah, not Vederman. Vederman\\ncites other examples of prejudicial, pejorative language in\\nthe Government’s closing arguments. At one point, the\\nGovernment referred to “conspirators engaged in what can\\nonly be described as a white collar crime spree from\\nPhiladelphia all the way to Washington, D.C.” and\\npromised “to untangle the webs of lies and deception that\\nthese conspirators spun.” Vederman Br. 51 (quoting\\nJA5295, 5297). Whatever rhetorical flair these words\\n 163\\n\\fcontained, they did not obscure the evidence which\\nindependently supported the convictions for bank fraud at\\nCount 19 and for making false statements to CUMA at\\nCount 20. Accordingly, because we presume that the jury\\nfollowed the District Court’s instruction to consider and to\\nweigh separately the evidence on each count and as to each\\ndefendant, and because the evidence supporting the\\nCUMA-related charges in Counts 19–20 is sufficiently\\ndistinct from the RICO conspiracy, we conclude that\\nVederman’s spillover argument is unavailing.38\\n\\n XII. Conclusion\\n We will vacate the convictions of Chaka Fattah, Sr.\\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\\n\\n38\\n Nicholas adopted “pertinent portions” of the prejudicial\\nspillover arguments advanced by Vederman and Fattah.\\nNicholas Br. 65. Her spillover claim has no more merit\\nthan theirs. Nicholas’s involvement in the RICO\\nconspiracy was distinct from the bribery charges, which\\ndid not unfairly influence the other counts. As to\\nNicholas’s assertion that the NOAA charges did not\\nbelong in the indictment and should have been tried\\nseparately, we fail to see how this relates to a claim of\\nprejudicial spillover. To the extent it challenges the\\nDistrict Court’s denial of Nicholas’s motion for a\\nseverance, Nicholas has failed to provide legal support for\\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\\n 164\\n\\fFattah and Vederman may be retried on these counts\\nbefore a properly instructed jury. We will also reverse the\\nDistrict Court’s judgment of acquittal on Counts 19 and\\n20. The convictions of Chaka Fattah, Sr. and Herbert\\nVederman will be reinstated, and the case will be\\nremanded for sentencing on those counts. In all other\\nrespects, the judgments of the District Court will be\\naffirmed.\\n\\n\\n\\n\\n 165\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359254/\", \"author_raw\": \"SMITH, Chief Judge\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"GREENAWAY"},"judge3":{"kind":"string","value":"KRAUSE"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582001/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n Nos. 16-4397, 16-4410, 16-4411,\n 16-4427, 17-1346\n _____________\n\n UNITED STATES OF AMERICA\n Appellant in 17-1346\n\n v.\n\n CHAKA FATTAH, SR.,\n Appellant in 16-4397\n\n KAREN NICHOLAS,\n Appellant in 16-4410\n\n ROBERT BRAND,\n Appellant in 16-4411\n\n HERBERT VEDERMAN,\n Appellant in 16-4427\n _____________\n\nOn Appeal from the United States District Court\n for the Eastern District of Pennsylvania\n District Court Nos. 2-15-cr-00346-001,\n\f 2-15-cr-00346-002, 2-15-cr-00346-003,\n 2-15-cr-00346-004\n District Judge: The Honorable Harvey Bartle III\n\n Argued January 18, 2018\n\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\n KRAUSE, Circuit Judges\n\n (Filed: January 16, 2019)\n\nAndrea G. Foulkes\nEric L. Gibson\nPaul L. Gray\nRobert A. Zauzmer\nOffice of United States Attorney\n615 Chestnut Street\nSuite 1250\nPhiladelphia, PA 19106\n\nJonathan Ian Kravis [ARGUED]\nUnited States Department of Justice\nCriminal Division, Public Integrity Section\n1400 New York Avenue, N.W.\nWashington, DC 20005\n Counsel for the United States\n\nMark M. Lee\nBruce P. Merenstein [ARGUED]\nSamuel W. Silver\n 2\n\fSchnader Harrison Segal & Lewis\n1600 Market Street\nSuite 3600\nPhiladelphia, PA 19103\n Counsel for Appellant Fattah\n\nAnn C. Flannery [ARGUED]\nSuite 2700\n1835 Market Street\nPhiladelphia, PA 19103\n\nLisa A. Mathewson\nSuite 810\n123 South Broad Street\nPhiladelphia, PA 19109\n Counsel for Appellant Nicholas\n\nAlan Silber\nPashman Stein Walder Hayden\n21 Main Street\nSuite 200\nHackensack, NJ 07601\n Counsel for National Association of Criminal\n Defense Lawyers, Amicus Appellant Nicholas\n\nMira E. Baylson\nBarry Gross [ARGUED]\nMeredith C. Slawe\nDrinker Biddle & Reath\nOne Logan Square\n 3\n\fSuite 2000\nPhiladelphia, PA 19103\n Counsel for Appellant Brand\n\nHenry W. Asbill\nBuckley Sandler\n1250 24th Street, N.W.\nSuite 700\nWashington, DC 20037\n\nGlen D. Nager [ARGUED]\nJacob M. Roth\nJulia W. M. F. Sheketoff\nJones Day\n51 Louisiana Avenue, N.W.\nWashington, DC 20001\n Counsel for Appellant Vederman\n\n ________________\n\n OPINION\n ________________\n\n\nSMITH, Chief Judge.\n\n\n\n\n 4\n\f Table of Contents\nI. Introduction ................................................................... 8\nII. Background .................................................................. 9\n A. The Fattah for Mayor Scheme ................................. 9\n 1. The Lord Loan and Its Repayment ..................... 10\n 2. The College Tuition Component of the FFM\n Scheme ................................................................ 27\n 3. The NOAA Grant and the Phantom Conference 28\n B. The Blue Guardians Scheme.................................. 31\n C. The Fattah–Vederman Bribery Scheme................. 33\n D. The Indictment and Trial ....................................... 39\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\n A. Investigation of Alleged Juror Misconduct ........... 58\n B. Dismissal of Juror 12 ............................................. 64\nIV. The District Court’s Instructions Under McDonnell 70\n A. The McDonnell Framework................................... 71\n B. The Kirk Meeting ................................................... 76\n C. Fattah’s Efforts to Secure Vederman an\n Ambassadorship.......................................................... 79\n D. The Zionts Hiring .................................................. 82\n E. Vederman’s Sufficiency Challenge to Counts 16–18\n and 22–23.................................................................... 89\n F. Blue Guardians ....................................................... 91\n\n 5\n\fV. Sufficiency of the Evidence for the RICO Conspiracy\nConviction ...................................................................... 95\nVI. Variance from the Indictment and Sufficiency of the\nEvidence for Count 2.................................................... 110\nVII. The District Court’s Instruction to the Jury on the\nMeaning of Intent ......................................................... 120\nVIII. Sending the Indictment to the Jury ...................... 126\nIX. The District Court’s Evidentiary Rulings .............. 129\n A. The District Court’s Application of Rule 404(b) 129\n B. Evidentiary Rulings Regarding Nicholas’s\n Defense ..................................................................... 134\n 1. The EAA Board Minutes .................................. 134\n 2. Jones’ Memory Regarding Other Contracts ..... 136\n 3. Exclusion of NOAA Evidence.......................... 137\n C. The Cooperating Witness’s Mental Health\n Records ..................................................................... 138\n 1. The District Court’s Denial of Access to the\n Mental Health Records ..................................... 140\n 2. The District Court’s Grant of the Motion in\n Limine ............................................................... 142\nX. The Government’s Cross-Appeal ............................ 147\n A. CUMA is a Mortgage Lending Business............. 148\n B. Sufficiency of the Evidence ................................. 155\nXI. Prejudicial Spillover ............................................... 158\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\n 6\n\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\nXII. Conclusion ............................................................ 164\n\n\n\n\n 7\n\f I. Introduction\n Chaka Fattah, Sr., a powerful and prominent fixture\nin Philadelphia politics, financially overextended himself\nin both his personal life and his professional career during\nan ultimately unsuccessful run for mayor. Fattah received\na substantial illicit loan to his mayoral campaign and used\nhis political influence and personal connections to engage\nfriends, employees, and others in an elaborate series of\nschemes aimed at preserving his political status by hiding\nthe source of the illicit loan and its repayment. In so doing,\nFattah and his allies engaged in shady and, at times, illegal\nbehavior, including the misuse of federal grant money and\nfederal appropriations, the siphoning of money from\nnonprofit organizations to pay campaign debts, and the\nmisappropriation of campaign funds to pay personal\nobligations.\n Based upon their actions, Fattah and four of his\nassociates—Herbert Vederman, Robert Brand, Bonnie\nBowser, and Karen Nicholas—were charged with\nnumerous criminal acts in a twenty-nine count indictment.\nAfter a jury trial, each was convicted on multiple counts.\nAll but Bowser appealed. As we explain below, the\nDistrict Court’s judgment will be affirmed in part and\nreversed in part.\n\n\n\n\n 8\n\f II. Background1\n During the 1980s and ’90s, Fattah served in both\nhouses of the Pennsylvania General Assembly, first as a\nmember of the House of Representatives and later as a\nSenator. In 1995, Fattah was elected to the United States\nHouse of Representatives for Pennsylvania’s Second\nCongressional District. In 2006, Fattah launched an\nunsuccessful run for Mayor of Philadelphia, setting in\nmotion the events that would lead to his criminal\nconviction and resignation from Congress ten years later.\n\n A. The Fattah for Mayor Scheme\n Fattah declared his candidacy for mayor in\nNovember of 2006. Thomas Lindenfeld, a political\nconsultant on Fattah’s exploratory committee, believed\nthat “[a]t the beginning of the campaign, [Fattah] was a\nconsiderable . . . candidate and somebody who had a very\nlikely chance of success.” JA1618. But Fattah’s campaign\nsoon began to experience difficulties, particularly with\nfundraising. Philadelphia had adopted its first-ever\ncampaign contribution limits, which limited contributions\nto $2,500 from individuals and $10,000 from political\naction committees and certain types of business\norganizations. Fattah’s fundraising difficulties led him to\n\n\n\n1\n The facts are drawn from the trial record unless otherwise\nnoted.\n 9\n\fseek a substantial loan, far in excess of the new\ncontribution limits.\n\n 1. The Lord Loan and Its Repayment\n While serving in Congress, Fattah became\nacquainted with Albert Lord, II. The two first met around\n1998, when Lord was a member of the Board of Directors\nof Sallie Mae.\n As the May 15, 2007 primary date for the\nPhiladelphia mayoral race approached, Fattah met Lord to\nask for assistance, telling Lord that the Fattah for Mayor\n(FFM) campaign was running low on funds. Fattah asked\nLord to meet with Thomas Lindenfeld, a political\nconsultant in Washington, D.C., and part-owner of LSG\nStrategies, Inc. (Strategies), a company that was working\nwith the FFM campaign and that specialized in direct voter\ncontact initiatives. Lindenfeld had been part of the\nexploratory group that initially considered Fattah’s\nviability as a candidate for mayor. Lindenfeld had known\nFattah since 1999, when Fattah endorsed Philadelphia\nMayor John Street. Through Fattah, Lindenfeld had also\ngotten to know several of Fattah’s associates, including\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\nHerbert Vederman, a businessman and former state\nofficial, was the finance director for the FFM campaign.\nRobert Brand owned Solutions for Progress (Solutions), a\n“Philadelphia-based public policy technology company,\nwhose mission [was] to deliver technology that directly\nassists low and middle income families [in obtaining]\n 10\n\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\nStaff and campaign treasurer, and served in his district\noffice in Philadelphia.\n Lord’s assistant contacted Lindenfeld to arrange a\nmeeting, and Lindenfeld informed Fattah that he would be\nmeeting with Lord. Lindenfeld, along with his partner,\nMichael Matthews, met with Lord and discussed Fattah’s\nneed for funds to mount an intensive media campaign.\nAfter that meeting, Lindenfeld reported to Fattah that Lord\nwanted to help, but that they had not discussed a specific\ndollar amount. Approximately a week later, Fattah\ninstructed Lindenfeld to meet with Lord a second time.\nLord “wanted to know if he could give a substantial\namount of money, a million dollars” to Fattah’s campaign.\nJA1630. That prompted Lindenfeld to reply that the\namount “would be beyond the campaign finance limits.”\nId.\n\n Lord proposed a solution: he offered to instead give\na million dollars to Strategies in the form of a loan. To that\nend, Lindenfeld had a promissory note drafted which\nspecified that Lord was lending Strategies $1 million, and\nthat Strategies promised to repay the $1 million at 9.25%\ninterest, with repayment to commence January 31, 2008.\nLindenfeld later acknowledged that the promissory note\nwould make it appear as though Lord’s $1 million was not\na contribution directly to the Congressman, although he\nknew that it was actually a loan to the FFM campaign.\nIndeed, Lindenfeld confirmed with Fattah that neither\n\n 11\n\fLindenfeld nor Strategies would be responsible for\nrepayment. With that understanding, Lindenfeld executed\nboth the note and a security agreement purporting to\nencumber Strategies’ accounts receivable and all its assets.\n\n On May 1, shortly before the primary election, Lord\nwired $1 million to Lindenfeld. Lindenfeld held the money\nin Strategies’ operating account until Fattah told him how\nit was to be spent. Some of the money was eventually used\nfor print materials mailed directly to voters. And, at\nFattah’s direction, Lindenfeld wired a substantial sum to\nSydney Lei and Associates (SLA), a company owned by\nGregory Naylor which specialized in “get out the vote”\nefforts.\n Naylor had known Fattah for more than 30 years.2\nDuring the campaign, Naylor worked as the field director\nand was in charge of getting out the vote on election day.\n\n2\n Naylor first worked with Fattah when he was in the state\nlegislature. When Fattah was elected to Congress, Naylor\nworked in his Philadelphia office. Naylor met Nicholas\nwhen she joined Fattah’s staff at some point in the 1990s.\nAfter concluding her employment with Fattah’s office,\nNicholas worked with the Educational Advancement\nAlliance (EAA), an education nonprofit entity founded by\nFattah. This entity helped to recruit underrepresented\nstudents for scholarship and college opportunities. Around\n2009, Naylor left Fattah’s office to work exclusively with\nSLA. Naylor also knew Brand.\n 12\n\fOn the final day of the campaign, Naylor worked with\nVederman, who allowed Naylor to use his credit card to\nrent vans that would transport Fattah voters to the polls.\n As the primary date neared, Fattah and Naylor knew\nthe campaign was running out of money. The campaign\nwas unable to finance “media buys,” and Naylor needed\nmoney for field operations to cover Philadelphia’s more\nthan one thousand polling places. In early May,\nLindenfeld called Naylor to say that Lindenfeld “would be\nsending some money [Naylor’s] way.” JA3057. Within\ndays, SLA received a six-figure sum for Naylor to use in\nthe campaign and on election day. Naylor used the money\nto pay some outstanding bills, including salaries for FFM\nemployees, and allocated $200,000 to field operations for\nelection day.\n\n Fattah lost the mayoral primary on May 15, 2007.\nAfterward, Lindenfeld spoke with Fattah, Naylor and\nBowser about accounting for the FFM campaign money\nfrom Lord that had been spent. They decided that the\namounts should not appear in the FFM campaign finance\nreports, and Fattah instructed Naylor to have his firm,\nSLA, create an invoice. Naylor did so, creating an invoice\ndated June 1, 2007 from SLA to FFM, seeking payment of\n$193,580.19. Naylor later acknowledged that the FFM\ncampaign did not actually owe money to SLA, and that the\nfalse invoice was created to “hide the transaction that took\nplace earlier” and “make it look like [SLA] was owed\nmoney.” JA3075–76. Although FFM did not owe SLA\n\n 13\n\fanything for the election day expenses, the FFM campaign\nfinance reports from 2009 through 2013 listed a $20,000\nin-kind contribution from SLA for each year, thereby\nlowering FFM’s alleged outstanding debt to SLA.\n\n Of the total $1 million Lord loan, $400,000 had not\nbeen spent. Lindenfeld returned that sum to Lord on June\n3, 2007. He included a cover letter which stated: “As it\nturns out the business opportunities we had contemplated\ndo not seem to be as fruitful as previously expected.”\nJA1254. Lindenfeld later admitted that there were no such\n“business opportunities” and that the letter was simply an\neffort to conceal the loan.\n In late 2007, faced with financial pressures, Lord\nasked his son, Albert Lord, III, to collect the outstanding\n$600,000 balance on the loan to Strategies. Lord III\ncontacted Lindenfeld about repayment and expressed a\nwillingness to forgive the interest owed if the principal\nwas paid. Lindenfeld immediately called Fattah and\ninformed him that repayment could not be put off any\nlonger. Fattah told Lindenfeld more than once that “[h]e\nwould take care of it,” JA1652, but Fattah did not act.\nNeeding someone who might have Fattah’s ear,\nLindenfeld reached out to Naylor and Bowser. Naylor\ntalked to Fattah on several occasions and told him that\nLindenfeld was under considerable pressure to repay the\nloan. Fattah told Naylor more than once that he was\n“working on it.” JA3082–83.\n\n\n 14\n\f During his political career, Fattah had focused on\neducation, especially for the underprivileged. Indeed,\nFattah founded two nonprofit organizations: College\nOpportunity Resources for Education (CORE), and the\nEducational Advancement Alliance (EAA).\n\n EAA held the annual Fattah Conference on Higher\nEducation (the “annual conference”) to acquaint high\nschool students with higher education options. JA3079.\nSallie Mae regularly sponsored the conference. According\nto Raymond Jones, EAA’s chairman of the board from\n2004 through 2007, EAA offered a variety of programs to\nprovide “marginalized students with educational\nopportunities so they could continue and go to college.”\nJA1360. EAA was funded with federal grant money which\ncould only be spent for the purposes described in the\nparticular grant. Karen Nicholas served as EAA’s\nexecutive director, handling the organization’s day-to-day\nadministrative responsibilities. Nicholas had previously\nbeen a staffer for Fattah when he was a member of\nPennsylvania’s House of Representatives.\n CORE was an organization that awarded\nscholarships to graduating high school students in\nPhiladelphia who had gained admission to a state\nuniversity or the Community College of Philadelphia.\nCORE received funding from a variety of sources,\nincluding Sallie Mae. Because CORE also received\nfederal funds, and because EAA had experience working\nwith federal grants, EAA received and handled the federal\n\n 15\n\ffunds awarded to CORE. In short, EAA functioned as a\nfiduciary for CORE. When money became a problem for\nthe FFM campaign, Fattah’s involvement with EAA and\nCORE soon became less about helping underprivileged\nstudents, and more about providing an avenue for\ndisguising efforts to repay the illicit campaign funds from\nLord.\n\n On January 7, 2008, Robert Brand contacted Fattah\nby telephone. Shortly thereafter, Lindenfeld received an\nunexpected call from Brand proposing an arrangement for\nBrand’s company, Solutions, to work with Strategies.\nSolutions had developed a software tool called “The\nBenefit Bank,” which was designed to “assist low and\nmoderate income families to have enhanced access to\nbenefits and taxes.” JA1993. During the telephone call,\nBrand referred to The Benefit Bank and suggested a\ncontract under which Strategies would be paid $600,000\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\nBrand followed up on his call to Lindenfeld with an email\nabout “develop[ing] a working relationship where you\ncould help us to grow The Benefit Bank and our process\nof civic engagement. While I know this is not your core\nbusiness I would like to try to convince you to take us on\nas a client.” JA6427. Lindenfeld responded that he was\ninterested. To Lindenfeld, “this was the way that\nCongressman Fattah was going to repay the debt to Al\nLord.” JA1654. When Lindenfeld called Fattah and told\nhim of the contact from Brand, Fattah simply replied that\nLindenfeld “should just proceed.” JA1666–67.\n 16\n\f A few days later, Brand emailed Nicholas at EAA a\nproposal from Solutions concerning The Benefit Bank,\nwhich sought EAA’s support in developing an education\nedition of The Benefit Bank and a $900,000 upfront\npayment.\n\n As the January 31 date for repayment of the balance\nof the $1 million Lord loan approached, a flurry of activity\ntook place. On January 24, both Raymond Jones, chair of\nthe EAA Board, and Nicholas signed a check from EAA\nmade out to Solutions in the amount of $500,000.\nAlthough no contract existed between EAA and Solutions,\nthe memo line of the check indicated that it was for a\ncontract, and Nicholas entered it into EAA’s ledger.3\n\n That same day, Ivy Butts, an employee of\nStrategies, emailed Lindenfeld the instructions Brand\nwould need to wire the $600,000 balance on the Lord loan.\n\n3\n Raymond Jones, who was EAA’s Chairman of the Board\nfrom 2004 through 2007, recalled at trial that the Board\nhad a limit on the amount that Nicholas could spend\nwithout board approval. JA1358, 1369. Nicholas was\nauthorized to sign contracts on behalf of EAA for no more\nthan $100,000. JA1369–71. Jones did not recall the\ncontract between EAA and Solutions, nor did the EAA\nboard minutes for December 2007, February 2008, or May\n2008 refer to the EAA–Solutions contract or to the\nsubstantial upfront payment of half a million dollars upon\nexecution of the agreement. JA6358–63; 6567.\n 17\n\fWithin minutes, Lindenfeld forwarded that email to Brand\nat Solutions. Brand then made two telephone calls to\nFattah. By late afternoon, Brand emailed Nicholas,\ninforming her that he had “met with all the people I need\nto meet with and have a pretty clear schedule of what\nworks best for us. I am also seeing what line of credit we\nhave to stretch out the payments until you get your line of\ncredit in place.” JA6558. Brand asked if they could talk\nand “finalize this effort.” JA6558. On January 25 and 26,\nthere were a number of calls between Fattah, Brand, and\nNicholas.\n\n On Sunday January 27, at 5:46 pm, Brand\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\na revised contract between EAA and Solutions for the\nengagement of services. Brand indicated he would send\nsomeone to pick up the check at about 1:00 pm the\nfollowing day. The revised contract called for the same\n$900,000 payment from EAA to Solutions, yet specified\nthat $500,000 was to be paid on signing, with $100,000\ndue three weeks later, and another $100,000 to be paid six\nweeks out. No due date for the $200,000 balance was\nspecified. The terms of the contract called for EAA to\nassist Solutions with further developing The Benefit Bank.\nIn addition, under the contract, EAA would receive certain\n\n\n\n\n 18\n\ffunds from the Commonwealth of Pennsylvania for a\nprogram relating to FAFSA applications. 4\n\n The same evening, Brand sent Lindenfeld a contract\nentitled “Cooperative Development Agreement to Provide\nServices to Solutions for Progress, Inc. for Growth of The\nBenefit Bank.” JA6569. The agreement proposed a\nworking partnership in which Strategies would work with\nSolutions to identify and secure a Benefit Bank affiliate in\nthe District of Columbia and two other states, and to\nfacilitate introductions to key officials in other states\nwhere The Benefit Bank might expand. The terms of the\nagreement provided that Solutions would pay $600,000 to\nStrategies by January 31, 2008, which would “enable\n[Strategies’] team to assess opportunities and develop\ndetailed work plans for each area.” JA6572. Brand copied\nSolutions’ Chief Financial Officer, Michael Golden.\nLindenfeld responded to Brand’s email within a minute,\nasking if Brand had received the wiring instructions.\nBrand immediately confirmed that he had.\n\n Concerned that Solutions did not have $600,000 to\npay Strategies, Golden talked to Brand, who informed him\nthat Solutions would be receiving a check for $500,000\nfrom EAA. Early the next morning, Nicholas responded to\nBrand’s email from the night before. She advised Brand\nthat he could pick up the check, “but as I stated I am not\n\n4\n FAFSA is an acronym for Free Application for Federal\nStudent Aid.\n 19\n\fin a position to sign a contract committing funds that I am\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\nsame day, a $540,000 transfer was made from the\nconference account, which EAA handled, into EAA’s\nchecking account. The conference account was maintained\nto handle expenses for Fattah’s annual higher education\nconference. Prior to this transfer, EAA had only\n$23,170.95 in its account. EAA then tendered a $500,000\ncheck to Solutions, which promptly deposited the check\nbefore the close of that day’s business. EAA never\nreplenished the $540,000 withdrawal from the conference\naccount.\n Brand received the executed contract between\nSolutions and Strategies on January 28. Even though the\ncontract called for Strategies to perform services in\nexchange for the $600,000 payment, Lindenfeld neither\nexpected to do any work for the $600,000, nor did he in\nfact do any work.\n\n In sum, by January 28, Solutions had received\n$500,000 from EAA, but it still had to come up with\n$100,000 to provide Strategies with the entire amount\nneeded to repay the Lord loan. Golden obtained the needed\nfunds the following day by drawing $150,000 on a line of\ncredit held by Brand’s wife. Brand and Fattah spoke four\nmore times on the telephone on January 29. Trial evidence\nlater showed that, during the month of January 2008,\nneither the FFM campaign bank account nor Fattah’s\n\n\n 20\n\fpersonal account had a sufficient balance to fund a\n$600,000 payment.\n On the morning of January 30, frustrated by the\ndelay, Lindenfeld sent Brand an email with a subject line\n“You are killing me.” JA6430. Lindenfeld stated that he\nhad “made a commitment based on yours to me. Please\ndon’t drag this out. I have a lot on the line.” Id. Brand\nresponded late in the afternoon, stating: “just met with\nMichael. He does the transfer at 8 AM tomorrow. It should\nbe in your account ($600K) early tomorrow morning.” Id.\nLindenfeld replied: “The earlier the better.” Id. The\nfollowing morning, Golden wired $600,000 from\nSolutions’ Pennsylvania bank account into Strategies’\nWashington D.C. bank account. JA2745, 2874. Strategies\nin turn, wired the same amount from its Washington D.C.\nbank account to Lord’s bank account in Virginia. JA2874,\n6549. Around noon, Brand telephoned Lindenfeld.\n\n In the days following the exhaustive efforts to meet\nthe January 31 loan repayment deadline, four more\ntelephone calls took place between Brand and Fattah.5\nNaylor learned at some point that the loan had been paid\noff. When Naylor asked Fattah about details of the\nrepayment, Fattah simply replied “[t]hat it went through\nEAA to Solutions and it was done.” JA3088.\n\n5\n By contrast, between October to December 2007, Brand\nand Fattah spoke by telephone only “once or twice [a]\nmonth.” JA2734.\n 21\n\f Meanwhile, at some point in January, EAA received\nnotice that the Department of Justice Office of the\nInspector General (DOJ) intended to audit its books.6 DOJ\nauditors told EAA to provide, at the “entrance\nconference,” documentation containing budgetary and\naccounting information. EAA failed to produce any\naccounting information.\n Although Lindenfeld was no longer making\ndemands of Brand, Brand was still owed the remaining\n$100,000 that Solutions had paid to satisfy the Lord loan.\nOn March 23, 2008, Brand sent Nicholas an email\noutlining his efforts to contact her over the previous two\nweeks about documentation on the CORE work, how to\nproceed with the paperwork for the Commonwealth of\nPennsylvania, and “how we can get our proposed contract\nsigned and the outstanding payments made.” JA2749.\nNicholas responded that evening, writing:\n\n I can appreciate your urgency however I do\n have EAA work that I continue to do,\n including the [usual] facilitation of programs,\n our financial audit, the start-up of two new\n programs[,] and of course the DOJ audit. I am\n still trying to obtain a line of credit without a\n completed 2007 audit and things are getting a\n\n\n\n6\n One of the terms and conditions of a federal grant is that\nthe recipient “be readily prepared for an audit.” JA2314.\n 22\n\f little uncomfortable now as I try to keep us\n afloat.\nJA6576. Nicholas told Brand that the DOJ auditors were\nmaking demands and would soon be on site. She noted that\n“[t]hey are still very uncomfortable with your contract\namongst other things and depending on their findings\nsome of the funding received may have to be returned.” Id.\nNicholas said that she had submitted the paperwork to the\nstate, and she told Brand that “in the future . . . as a result\nof the DOJ audit I will not be in a position to do another\ncontract such as this.” Id.\n Shortly after Nicholas’s reply to Brand, Nicholas\nforwarded the Brand–Nicholas email chain to Fattah. The\nbody of the email stated, in its entirety: “I really don’t\nappreciate the tone of Bob’s email. I can appreciate that he\nhas some things going on however I am doing my best to\nassist him. Some other things are a priority. He needs to\nback off.” GSA2. Later that night, Bowser sent Fattah an\nemail with a subject line that read “Karen N” and a\ntelephone number. JA2752.\n\n As the audit continued, the auditors found other\ndeficiencies. During April of 2008, DOJ issued a notice of\nirregularity to EAA, which resulted in the audit being\nreferred to DOJ’s Investigations Division for a more\ncomprehensive review.\n\n On April 24, 2008, Brand emailed Nicholas asking\nfor a time to update her on The Benefit Bank. In early May,\n 23\n\fBrand sent another email to Nicholas attaching a revised\nEAA–Solutions contract proposal, which decreased the\ninitial upfront cost from $900,000 to $700,000.\n Although Solutions and EAA had still not signed a\ncontract, EAA paid Solutions another $100,000 in May.\nThat money was obtained via a loan to EAA from CORE.\nThomas Butler, who had worked for Fattah both when\nFattah was in Congress and when he was in the General\nAssembly, was CORE’s executive director. Butler had\nbeen contacted in mid-May by Jackie Barnett, a member\nof CORE’s Board who had also worked with\nCongressman Fattah. Barnett informed Butler that\nNicholas had requested a loan from CORE to EAA, and\nthat Fattah, as Chairman of CORE’s Board, had approved\nit. Butler and Barnett withdrew funds from two CORE\nbank accounts and obtained a cashier’s check, dated May\n19, in the amount of $225,000 and made payable to EAA.\nThe withdrawals were from accounts used for Sallie Mae\nfunds and other scholarship money.\n After EAA received the $225,000 check, EAA\ntendered a $100,000 check to Solutions. The check bore\nthe notation “Commonwealth of Pennsylvania.” EAA\nrepaid CORE the following month. Because EAA lacked\nsufficient funds of its own to cover this payment, EAA\ndrew on grant money that it had received from NASA.\n\n Brand and Lindenfeld continued to communicate\nconcerning The Benefit Bank. In July of 2008, a meeting\nwas held at Solutions with Brand, Lindenfeld, Golden, and\n 24\n\fother Solutions employees to discuss “an enormous\namount of work” that Brand wanted Strategies to do.\nJA1670. Lindenfeld said in response “we’d be glad to do\nthat, but . . . we would have to be paid.” Id. At that point,\nsomeone in the meeting stated that Strategies “had already\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\nwas for Congressman Fattah, . . . that’s not for us. So if\nyou want us to do work, we have to get paid for it\nseparately.” Id. Brand became upset with Lindenfeld over\nhis comment about being paid because his colleagues at\nSolutions were not aware of the reason for the $600,000\npayment.\n Meanwhile, EAA was attempting to meet the\ndemands of the DOJ auditors, who were focused on the\nrelationship between EAA and CORE. DOJ served a\nsubpoena upon Solutions to produce “[a]ny and all\ndocuments including, but not limited to, contract\ndocuments, invoices, correspondence, timesheets,\ndeliverables and proof of payment related to any services\nprovided to or payments received” from CORE or EAA.\nJA2350.\n\n Special Agent Dieffenbach, from the DOJ,\ninterviewed Nicholas on July 14, 2008. During that\ninterview, Nicholas discussed the relationship between\nEAA and CORE, how invoices were paid, and how\nconsultants were handled. Nicholas also answered\nquestions about EAA’s relationship with Solutions,\nincluding the payment of invoices. She did not inform\n\n 25\n\fAgent Dieffenbach of the $500,000 payment in January or\nthe subsequent $100,000 payment in May. Nor did the\ninterview address the EAA–Solutions contract that\npurportedly required those payments, because the contract\nhad yet to be produced.\n\n Solutions failed to comply with the subpoena,\nprompting an email from Agent Dieffenbach on August 26\nasking for an update concerning Solutions’ reply to the\nDOJ subpoena. Solutions then produced an undated\nversion of the EAA–Solutions contract that required the\n$600,000 upfront payment. Neither Brand nor Nicholas\nprovided the auditors with the January and May checks\nfrom EAA to Solutions.\n Efforts to conceal the repayment of the Lord loan\nand to promote the political and financial interests of\nFattah continued. The FFM campaign reports indicated in-\nkind contributions of debt forgiveness by SLA even\nthough there had been no actual debt. In September of\n2009, with EAA’s ledgers still under scrutiny, Nicholas\naltered the description of the entry for the $100,000 check\nto Solutions from “professional fees consulting” to\n“CORE Philly.” JA2546. Other FFM campaign debt was\nreduced further after Vederman negotiated with creditors.\n\n EAA never fully recovered from its payment of the\n$600,000 balance on the Lord loan and the audits that took\nplace in 2008. It began laying off employees in 2011, and\nby June of 2012, only four employees remained. JA3659.\nEAA ceased operations at some point in 2012. JA1530.\n 26\n\f 2. The College Tuition Component of the FFM\n Scheme\n Although the FFM campaign was close to insolvent,\nit nevertheless made tuition payments for Fattah’s son,\nChaka Fattah Jr., also known as Chip. Chip attended\nDrexel University, but had yet to complete his coursework\nbecause he had failed to pay an outstanding tuition\nbalance. As the FFM campaign got underway in 2007,\nFattah wanted Chip to re-enroll in classes at Drexel and\nget a degree. Fattah asked Naylor to help financially, and\nhe did so by writing checks from SLA to Drexel toward\nChip’s outstanding tuition. By October of 2007, Chip was\npermitted to re-enroll in classes.\n Although Naylor never directly addressed the issue\nwith Fattah, he agreed to assist with Chip’s outstanding\ntuition with the expectation that SLA would be repaid. The\nfirst check to Drexel in the amount of $5,000 was sent in\nAugust of 2007, with $400 payments in the months that\nfollowed until August of 2008. At some point, Chip\ninformed Naylor that the payee was no longer Drexel, but\nSallie Mae. Naylor then began sending monthly checks\nfrom SLA to Sallie Mae. Those payments, in the amount\nof $525.52, began in March of 2009 and continued until\nApril of 2011, after which Fattah told Naylor he no longer\nneeded to make them. SLA’s payments to Drexel and\nSallie Mae totaled $23,063.52.\n\n Naylor’s expectation of repayment was eventually\nrealized. Beginning in January of 2008 and continuing\n 27\n\funtil November 2010, Bowser sporadically sent SLA\nreimbursement checks from the FFM campaign with a\nnotation that payment was for “election day operation\nexpenses.” JA3136. The FFM funds had been transferred\nfrom the Fattah for Congress campaign. These\nreimbursement checks totaled $25,400. In an effort to\nconceal the source of the payments to Drexel and Sallie\nMae, and to make it appear that the younger Fattah had\nperformed services for SLA, Naylor created false tax\nforms for Chip. Chip, however, had never performed\nservices for SLA.\n\n 3. The NOAA Grant and the Phantom Conference\n In mid-December 2011, when EAA was\nexperiencing serious financial difficulties, Nicholas\nsubmitted an email request to the educational partnership\nprogram of the National Oceanic & Atmospheric\nAdministration (NOAA) for a grant “designed to provide\ntraining opportunities and funding to students at minority\nserving institutions” interested in science, technology,\nengineering, and math fields related to NOAA’s mission.\nJA3354–55. The request sought $409,000 to fund EAA’s\nannual conference scheduled for February 17–19, 2012.\nJacqueline Rousseau, a supervisory program manager at\nNOAA, participated in a conference call with Nicholas\nshortly thereafter and advised Nicholas that the agency\ncould not afford the $409,000 request but would consider\na smaller grant. Rousseau advised Nicholas that EAA\n\n\n 28\n\fwould need to submit an application if it wished to be\nconsidered for a grant.\n Before submitting a grant application, Nicholas\nemailed Rousseau about sponsoring the conference. On\nJanuary 11, 2012, Rousseau informed Nicholas that the\n“NOAA Office of Education, Scholarship Programs has\nagreed to participate and provide sponsorship funds of\n$50K to support the referenced conference.” JA6453.\nRousseau also informed Nicholas that Chantell Haskins,\nwho also worked with the student scholarship program,\nwould be the point of contact for NOAA.\n In February 2012, EAA held its annual conference\nat the Sheraton Hotel in downtown Philadelphia. The\nconference had been held at the same location each year\nsince 2008.\n\n Nicholas contacted Haskins at some point in early\n2012, inquiring about the $50,000 grant. On May 8, 2012,\nHaskins sent Nicholas an e-mail which included\ninformation about submitting proposals to fund a\nconference for students. EAA then submitted a grant\napplication, which Haskins reviewed. She advised\nNicholas on June 28, 2012 that the grant could not be used\nto provide meals, and that the date of the conference would\nhave to be pushed back, with the new date included in a\nmodified application. When Nicholas asked if expenses\nfrom a previous conference could be paid from the new\ngrant, Haskins informed her that this was not allowed.\n\n 29\n\f In early July 2012, Nicholas sent a modified grant\nproposal to Haskins. It eliminated the budget item for food\nand changed the date of the 2012 conference to October\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\nwhere EAA’s annual conference had taken place earlier in\nthe year. NOAA approved a $50,000 grant for the October\n2012 conference—a conference that would never be held.\n\n Unaware that no October 2012 conference had\ntaken place, NOAA allowed Nicholas access to the\n$50,000 grant in March of 2013. She then transferred the\nentire amount from NOAA to EAA’s bank account a few\ndays later. Naylor had performed services for EAA for\nwhich he was still owed $116,590. JA3119. In discussions\nwith Naylor, Nicholas had informed him that the\nlikelihood of EAA’s being able to pay him was “[n]ot very\ngood.” JA3120. Yet several days after EAA had received\nthe $50,000 from NOAA, Nicholas sent Naylor a check\nfor $20,000. JA3120, 4283.\n\n On April 3, 2013, Nicholas submitted a final report\nto NOAA concerning EAA’s use of the grant. Notably,\npage 4 of the report stated the conference had been held in\nFebruary 2012, while page 17 stated that the conference\nhad been held from October 19 to 21, 2012. NOAA issued\na notice asking for clarification and for a list of students\nwho had been supported at the conference. Nicholas failed\nto file either a clarifying report regarding the date of the\nconference or a timely report regarding the disbursement\nof the grant. Finally, in November of 2013, Nicholas\n\n 30\n\fsubmitted the final Federal Financial Report in which she\ncertified, falsely, that the $50,000 had been used for a\nproject during the period from August 1, 2012 to\nDecember 30, 2012.\n\n B. The Blue Guardians Scheme\n In addition to functioning as the conduit for Lord’s\n$1 million loan to Fattah’s campaign, Lindenfeld’s\ncompany, Strategies, also performed services for the\ncampaign. The work resulted in indebtedness from FFM\nto Strategies of approximately $95,000. Fattah made\nseveral small payments, but failed to pay the full amount\ndue. Although Lindenfeld spoke to Fattah, Naylor and\nBowser about the debt, no payments were forthcoming.\nDuring a meeting in Fattah’s D.C. office, Fattah told\nLindenfeld “that [repayment] really wasn’t going to be\npossible because the campaign had been over for a long\ntime” and the funds were not available. JA1693. Fattah\nthen asked Lindenfeld if he could write off the debt on his\nFFM campaign finance reports. Id. Lindenfeld told Fattah\nthat as long as he was paid, it was not his business how\nFattah disclosed it on the campaign finance reports.\nJA1694.\n In lieu of repayment, Fattah suggested that\nStrategies could claim to be interested in setting up an\nentity to address environmental issues and ocean pollution\nalong the coastline and in the Caribbean. Fattah explained\nthat creating such an entity would make it possible to\nobtain an appropriation from the government. Hearing\n 31\n\fthis, Lindenfeld knew he was not going to be paid by the\nFFM campaign, and was amenable to receiving money\nfrom an appropriation instead. At a later meeting,\nLindenfeld told Fattah that the name of the entity would\nbe “Blue Guardians.” Lindenfeld consulted with an\nattorney about creating Blue Guardians as an entity to\nreceive the federal grant. He emailed Fattah, asking\nquestions about how to complete an application to the\nHouse Appropriations Committee. Fattah provided\nsuggestions, and an application was eventually completed.\nIt indicated that Blue Guardians would be “in operation for\na minimum of ten years,” and, in accordance with Fattah’s\nguidance, requested $15 million in federal funds. JA1711–\n13.\n Lindenfeld submitted the application to Fattah’s\noffice in April of 2009. Afterward, a Fattah staffer\ncontacted Lindenfeld to suggest that he change his\nWashington, D.C., address to Philadelphia because that\nwas the location of Fattah’s district. Fattah later suggested\nto Lindenfeld that Brand might allow the use of his\nPhiladelphia office address, a plan to which Brand agreed.\n\n In February 2010, Lindenfeld submitted a second\napplication to the Appropriations Committee. In March,\nFattah submitted a project request using his congressional\nletterhead and seeking $3,000,000 for the “Blue\nGuardians, Coastal Environmental Education Outreach\nProgram.” JA6432. Within a month, Blue Guardians had\nboth articles of incorporation and a bank account. Around\n\n 32\n\fthat time, a news reporter contacted Lindenfeld to discuss\nthe new Blue Guardians entity. The inquiry made\nLindenfeld uncomfortable, and he ultimately decided to\nabandon the Blue Guardians project. He continued to seek\npayment from Fattah, to no avail.\n\n Nonetheless, having obtained Lindenfeld’s\nacquiescence to writing off the campaign’s debt to\nStrategies, Fattah started falsifying FFM’s campaign\nreports. Beginning in 2009 and extending through 2013,\nthe FFM campaign reports executed by Fattah and Bowser\nstated that Strategies made in-kind contributions of\n$20,000, until the debt appeared to have been paid in full.\n\n C. The Fattah–Vederman Bribery Scheme\n Vederman and Fattah were personal friends.\nVederman was a successful businessman who had also\nserved in prominent roles in the administrations of Ed\nRendell when he was Mayor of Philadelphia and Governor\nof Pennsylvania. In November of 2008, Vederman was a\nsenior consultant in the government and public affairs\npractice group of a Philadelphia law firm. His assistance\nto the FFM campaign included paying for rented vans used\nin the get-out-the-vote effort.\n\n After Fattah’s electoral defeat, the campaign still\nowed more than $84,000 to a different law firm for\nservices performed for the campaign. Vederman\napproached that firm in the summer of 2008 asking if it\nwould forgive FFM’s debt. Negotiations resulted in a\n 33\n\fcommitment from FFM to pay the firm $30,000 by the end\nof 2008 in exchange for forgiveness of $20,000, all of\nwhich would appear on the FFM campaign finance report.\nVederman’s efforts also led to payment by Fattah of an\nadditional $10,000 in 2009 to the law firm, in exchange\nfor additional forgiveness of $20,000 of debt. It was not\nlong after Vederman’s successful efforts to lower Fattah’s\ncampaign debt, that Fattah wrote a letter to U.S. Senator\nRobert P. Casey recommending Vederman for an\nambassadorship.\n\n At some point in 2010, Vederman again intervened\non behalf of the FFM campaign. FFM remained in debt to\nan advertising and public relations firm owned by Robert\nDilella. By late 2011, Vederman and Dilella had worked\nout a settlement to resolve the outstanding debt. Pursuant\nto that settlement, Dilella received partial payment from\nthe FFM campaign: $25,000 in satisfaction of a $55,000\ndebt. Dilella testified at trial that he would not have agreed\nto retire a portion of the debt had he known the FFM\ncampaign was paying college tuition for Fattah’s son.\n Vederman helped Fattah financially in other ways.\nBefore the 2006 FFM campaign, Fattah and his wife,\nRenee Chenault-Fattah, sponsored a young woman named\nSimone Muller to live with them as an au pair exchange\nvisitor. Muller was from South Africa, and her J-1 visa\nallowed her to serve as a nanny and to study in the United\nStates. Muller later applied for and received a second visa,\nan F-1 student visa that indicated she had been accepted as\n\n 34\n\fan international student at the Community College of\nPhiladelphia. The application indicated that Muller would\nagain be residing with the Fattahs. Notwithstanding this\nliving arrangement, Fattah identified Vederman as the\nperson who would be paying for Muller’s trip to the\nUnited States.\n By the beginning of 2010, Muller wished to transfer\nto Philadelphia University. This required her to submit\nverification that funds were available to pay for her study.\nAlthough the Fattahs were Muller’s sponsors, Fattah\nexplained to the University’s Dean of Enrollment Services\nthat he was submitting a letter of secondary support from\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\nJanuary 2010 letter of support, the University would not\nhave admitted Muller. In addition to this pledge of support,\nVederman paid $3,000 of Muller’s tuition. Shortly\nthereafter, Fattah resumed his efforts to secure an\nambassadorship for Vederman.\n\n In February of 2010, Fattah staffer Maisha Leek\ncontacted Katherine Kochman, a scheduler for White\nHouse Chief of Staff Rahm Emanuel. Leek requested a\ntelephone conference with Emanuel, Rendell, and Fattah\nto discuss Vederman’s “serving his country in an\ninternational capacity.” JA2893. In a follow-up email on\nMarch 26, Leek sent documents to Kristin Sheehy, a\nsecretary to White House Deputy Chief of Staff James\nMessina. The documents included Fattah’s 2008 letter to\nSenator Casey and Vederman’s biography. After\n\n 35\n\fparticipating in a telephone conference about Vederman\nwith Fattah and Rendell, Messina sent Vederman’s\nbiography to the White House personnel office for\nconsideration.\n\n As the April 2010 tax deadline approached, Fattah\nstill owed the City of Philadelphia earned income tax in\nthe amount of $2,381. Just days before the filing deadline,\nVederman gave a check to Chip Fattah for $3,500. The\nyounger Fattah quickly deposited $2,310 into his father’s\nbank account. Fattah paid his tax bill on April 15. Without\nChip’s deposit into his father’s bank account, the older\nFattah would not have had sufficient funds to pay his tax\nbill.\n On October 30, 2010, Vederman gave Chip another\ncheck, this one for $2,800. That same day, Fattah hand-\ndelivered a letter to President Obama recommending\nVederman for an ambassadorship. A few weeks later,\nFattah’s staffer, Leek, sent the letter that Fattah had given\nto President Obama to Messina’s office. That letter\npointed out that both Rendell and Fattah had sent letters\non behalf of Vederman, and that he was an\n“unquestionably exceptional candidate for an\nambassadorship.” JA6291–92.\n\n Fattah’s efforts to secure Vederman an\nambassadorship were unsuccessful. Fattah then shifted\ngears and sought to secure Vederman a position on a\nfederal trade committee. Fattah approached Ron Kirk, who\nserved as U.S. Trade Representative, and asked him to\n 36\n\fspeak with a constituent. In May of 2011, Leek followed\nup on that discussion by emailing Kirk and asking him to\nmeet with Vederman. Kirk met with Vederman on June 5,\n2011 and explained to him the role of the trade advisory\ncommittees. Although the two men “had a very nice\nconversation,” JA 3566, it soon became “pretty apparent\nto [Kirk and his staff] that [serving on a trade advisory\ncommittee was] not what Mr. Vederman was interested\nin.” JA3567. As Kirk put it, “it was obvious that\n[Vederman] was looking for something perhaps more\nrobust in his mind or . . . higher profile than one of our\nadvisory committees.” Id. Given Vederman’s lukewarm\ninterest, no appointment to an advisory committee was\nforthcoming.\n In late December 2011, the Fattahs applied for a\nmortgage so they could purchase a second home in the\nPoconos. Shortly after applying for the mortgage, Fattah\nemailed Vederman, offering to sell him his wife’s 1989\nPorsche for $18,000. Vederman accepted the offer. The\nnext day, Vederman wired $18,000 to Fattah’s Wright\nPatman Federal Credit Union account.\n\n The Credit Union Mortgage Association (CUMA)\nacted as the loan processing organization for the home\nmortgage. Because CUMA is required to verify the source\nof any large deposits, CUMA’s mortgage loan processor,\nVictoria Souza, contacted Fattah on January 17, 2012, to\nconfirm the source of the $18,000. Fattah informed Souza\nthat the $18,000 represented the proceeds of the Porsche\n\n 37\n\fsale. Souza requested documentation, including a signed\nbill of sale and title.\n That same day, Bowser emailed Vederman a blank\nbill of sale for the Porsche. After Vederman signed the bill\nof sale, Fattah forwarded it to Souza. The bill of sale was\ndated January 16, 2012, which was the day before Souza\nhad requested the documentation. It bore the signatures of\nRenee Chenault-Fattah and Herbert Vederman, with\nBonnie Bowser as a witness.\n\n Fattah also provided Souza with a copy of the\nPorsche’s title. It was dated the same day it was sent to\nSouza, and bore signatures of Chenault-Fattah as the seller\nand Vederman as buyer, along with a notary’s stamp.\nNeither Vederman nor Chenault-Fattah actually appeared\nbefore the notary.\n\n Vederman never took possession of the Porsche.\nRenee Chenault-Fattah continued to have the Porsche\nserviced and insured long after the purported sale had\ntaken place. Moreover, the Porsche remained registered in\nChenault-Fattah’s name, and was never registered to\nHerbert Vederman. When FBI agents searched the\nFattahs’ home in 2014, the Porsche was discovered in the\nFattahs’ garage.\n\n On January 24, 2012, the Fattahs wired $25,000 to\nthe attorney handling the escrow account for the purchase\nof the vacation home. Without the $18,000 transfer from\n\n 38\n\fVederman, the Fattahs would not have had sufficient funds\nin their bank accounts to close on the home.\n Around the same time that the Fattahs were\npurchasing the house in the Poconos, Fattah’s Philadelphia\noffice hired Vederman’s longtime girlfriend, Alexandra\nZionts. Zionts had long worked for a federal magistrate\njudge in Florida. Near the end of 2011, the magistrate\njudge retired, leaving Zionts ten months shy of obtaining\nthe necessary service required to receive retirement\nbenefits. If Zionts could find another job in the federal\ngovernment, her benefits and pension would not be\nadversely affected. Vederman assisted Zionts in her job\nsearch, which included calling Fattah. Fattah hired her, a\nmove that put his congressional office overbudget. Zionts\nworked in Fattah’s office for only about two months,\nleaving to work for a congressman from Florida.\n\n Tia Watson, who performed constituent services for\nFattah and worked on the same floor as Zionts in Fattah’s\ndistrict office, testified she had no idea what work Zionts\nperformed. Although Zionts contacted Temple University\nabout archiving Fattah’s papers from his career in both the\nstate and federal government, an employee from Temple\nUniversity observed that Zionts’ work contributed nothing\nof value to the papers project.\n\n D. The Indictment and Trial\n Fattah’s schemes eventually unraveled. On July 29,\n2015, a federal grand jury in the Eastern District of\n 39\n\fPennsylvania returned a twenty-nine count indictment\nalleging that Fattah and his associates had engaged in a\nvariety of criminal acts. Fattah, Vederman, Nicholas,\nBrand, and Bowser were charged with unlawfully\nconspiring to violate the Racketeer Influenced and Corrupt\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\naddition to the RICO charge, the indictment alleged that\nFattah and certain co-defendants had unlawfully conspired\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\nSeveral defendants were also charged with making false\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\n§§ 1341, 1343, and 1344.\n\n The RICO charge alleged that the defendants and\nother co-conspirators constituted an enterprise aimed at\nsupporting and promoting Fattah’s political and financial\ninterests. The efforts to conceal the $1 million Lord loan\nand its repayment are at the heart of the RICO conspiracy\nand the Fattah for Mayor scheme. The indictment further\nalleged that the RICO enterprise involved: (1) the scheme\nto satisfy an outstanding campaign debt by creating the\nfake “Blue Guardians” nonprofit; and (2) the bribery\nscheme to obtain payments and things of value from\nVederman in exchange for Fattah’s efforts to secure\nVederman an appointment as a United States Ambassador.\n 40\n\f A jury trial, before the Honorable Harvey Bartle III\nof the Eastern District of Pennsylvania, began on May 16,\n2016, and lasted about a month. 7 Judge Bartle charged the\njury on Wednesday, June 15, 2016, and deliberations\nbegan late that afternoon. The following day, after\ndeliberating for only four hours, the jury sent a note to the\njudge. Written by the foreperson, the note read:\n Juror Number 12 refuses to vote by the letter\n of the law. He will not, after proof, still\n change his vote. His answer will not change.\n He has the 11 of us a total wreck knowing that\n we are not getting anywhere in the hour of\n deliberation yesterday and the three hours\n today. We have zero verdicts at this time all\n due to Juror Number 12. He will not listen or\n reason with anybody. He is killing every\n other juror’s experience. We showed him all\n the proof. He doesn’t care. Juror Number 12\n has an agenda or ax to grind w/govt.\nJA5916.\n\n Shortly after receiving the foreperson’s note, the\nCourt received a second communication—a note signed\n\n\n\n 7\n The District Court dismissed one charge prior to\ntrial: an individual money laundering count against\nNicholas.\n 41\n\fby nine jurors, including the foreperson. The second note\nread:\n We feel that [Juror 12] is argumentative,\n incapable of making decision. He constantly\n scream [sic] at all of us.\nId.\n Judge Bartle met with counsel in his chambers and\nadvised them of his intention to voir dire both the\nforeperson and Juror 12 in an effort to determine whether\nthe juror was deliberating as required by his oath. The\nJudge also indicated that he would “stay away from the\nmerits of the case,” and that whether he would voir dire\nmore jurors “remain[ed] to be seen.” JA5917.\n Counsel for the defendants objected to the Court’s\nproposed inquiry. As a group, they indicated that while the\nnote could be read as suggesting “a flat refusal to\ndeliberate,” they were of the opinion that it sounded “more\nin the manner of a disagreement over the evidence.”\nJA5918. Nicholas’s counsel specifically argued that\nquestioning the jurors so quickly after the start of\ndeliberations would send a message that differences of\nopinion among a block of jurors could be resolved by\ncomplaining to the Court. Defense counsel acknowledged\nthat the case law gave Judge Bartle wide discretion on how\nto proceed, but suggested that a “less intrusive” course of\naction was preferred. JA5918–19. They collectively urged\n\n 42\n\fthe Court to do nothing more than remind the jurors of\ntheir duty to deliberate.\n The Government agreed with Judge Bartle’s\nproposed voir dire. In the prosecution’s view, the Court\nhad already given proper instructions to the jury on their\nduty to deliberate. The Government further argued that if\nJuror 12 had exhibited bias, as suggested in the notes, he\nwould have lied during the voir dire process and his\nrefusal to deliberate would be “further evidence of that and\nhis unsuitability as a juror.” JA5921.\n\n With all counsel present, and over defense counsel’s\nobjections, Judge Bartle ultimately questioned five jurors\nin chambers. He questioned Juror 2 (the foreperson), Juror\n12 (the subject of the complaints), Juror 3, Juror 6, and\nJuror 1.\n\n Judge Bartle began each voir dire by informing the\njuror that he would ask a series of questions, but would not\ninquire into the merits of the case or how any juror was\nvoting. Each juror was placed under oath, and Judge Bartle\nasked, among other questions, whether screaming was\noccurring; whether the jurors were discussing the\nevidence; whether Juror 12 was placing his hands on other\njurors; and whether Juror 12 was unwilling to follow his\ninstructions.\n The foreperson acknowledged that he had written\nthe initial note during lunch earlier that day. He stated that\nJuror 12 was not willing to follow the law, but instead\n 43\n\f“want[ed] to add his own piece of the law . . . which has\nnothing to do with it.” JA5927–28. The foreperson further\ntestified that Juror 12 “was standing up screaming” and\nthat “[i]t was everybody pretty much against [Juror 12].”\nJA5929. He testified that Juror 12 “has his own agenda,”\nand that Juror 12 put his hand on another juror. JA5930.\nThe foreperson also stated that the jury had discussed only\na single count since the day before, and that they were still\ndiscussing it. When the District Court responded that the\njurors should understand that they could take as much time\nas they needed, the foreperson responded: “I understand\nthat. . . . [W]e all understand it. But we feel that he’s just—\nhe’s got another agenda.” JA5934.\n Judge Bartle advised counsel that he considered this\n“a very serious situation” and that he would proceed to\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\nobjection to questioning Juror 12, which the Court\noverruled. Brand’s counsel argued that because the Court\nhad decided to voir dire Juror 12, it should also voir dire\nan additional juror. The Court agreed to do so.\n When the Court questioned Juror 12, he admitted to\nhaving “yelled back” at others, but only when they raised\ntheir voices to him. JA5939. Juror 12 contended that he, in\nfact, was “the only one” deliberating. Id. When an initial\nvote was taken the previous afternoon, his vote “was\ndifferent than everybody else’s.” Id. Juror 12 explained to\nthe other jurors why his vote was different, bringing up\nspecific evidence. In response, the other jurors said “that\n\n 44\n\fdoesn’t mean anything” and “pointed to the indictment.”\nJA5940. Juror 12 told the other jurors that the indictment\nis not evidence. Id. In response, the others “threatened to\nhave [him] thrown off.” Id.\n\n Juror 12 testified that a similar sequence of events\nhad taken place that morning. After a brief period of\ndeliberations, another vote was taken, and with the same\nresult as the previous afternoon. A discussion ensued, and\nthe other jurors again “point[ed] to the indictment.” Id.\nJuror 12 told them to “read the charge,” “[t]he indictment\nis not evidence.” Id. They read the charge, and Juror 12\nagain attempted to explain his view, but the other jurors\npaid little attention. Accordingly, Juror 12 told the others\nthat if they did not want him there, he “[didn’t] want to be\n[there]”—he would be “[o]kay with it” if they wanted him\ntaken off the jury. JA5941.\n Upon hearing this testimony, Judge Bartle again\nasked about the tone of deliberations. Juror 12 repeated\nthat he raised his voice only in response to others who did\nso—he did “not want to yell at anybody.” JA5942. Judge\nBartle then asked whether he had touched other jurors.\nJuror 12 replied that he had not hurt anyone. When asked\nif he had put his hand on anybody’s shoulder, Juror 12\nanswered: “I couldn’t remember to be honest with you.”\nJA5946.\n\n Following Juror 12’s voir dire, the Court summoned\nJuror 3 to chambers. Juror 3 testified that, after discussion\nof a particular count, there was one juror at odds with the\n 45\n\fothers. According to Juror 3, “the rest of the jurors\npounced on the gentleman with the . . . dissenting\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\ndefensive and just a little bit [] impatient” and that “the\nother jurors were very impatient with him.” Id. Juror 3 did\nnot recall witnessing Juror 12 putting his hand on any\nother jurors.\n\n The Government requested that the Court voir dire\nanother juror. Defense counsel objected, claiming that the\nquestioning “threaten[ed] . . . the entire deliberative\nprocess.” JA5949–50. Judge Bartle reminded counsel that\nhe had the authority to question each juror, and called for\nvoir dire of Juror 6.\n Juror 6 testified that the jury had been discussing the\ncase and reviewing the evidence, but that Juror 12 “wants\nto be seen” and was “being obstinate.” JA5951–52.\nAccording to Juror 6, Juror 12 “may not agree” with the\nconclusion of other jurors but “doesn’t give valid reasons\nas to why he may disagree with the charge.” JA5952. Juror\n6 also revealed that Juror 12 was the first to raise his voice,\nand that he may have touched her and another juror. When\nasked to clarify what she meant by Juror 12 disagreeing\nwith “the charge,” Juror 6 testified that Juror 12 was\n“reading maybe too deeply into it and putting his own\nemotions into it instead of just looking at what it says [and]\nwhat the facts are.” JA5952, 5955. According to Juror 6,\nJuror 12 “just continues to read past that into his own mind\nof what he feels it should be.” JA5955. Juror 6 testified\n\n 46\n\fthat Juror 12’s “justification for some of his responses [did\nnot] seem to relate to what the matter [was] before\n[them].” JA5957.\n Judge Bartle chose to hear from yet another juror.\nJuror 1 was called and informed the Court and counsel that\nthe jury “really [hadn’t] been able to even start the\ndeliberation process” in light of the disruptive behavior of\n“one particular individual.” JA5958–59. The particular\nindividual, according to Juror 1, was “very opinionated”\nand “[came] into the process with his view already\nestablished, refusing to even listen to any of the evidence\n. . . [being] very forceful . . . standing up, yelling, pointing\nhis finger.” JA5959. When asked if this individual was\nwilling to follow the Court’s instructions, Juror 1 testified\nthat he “pours [sic] over the documents very well” but that\nhe was adding other factors to answer the question on the\nverdict form, such as “what did this person feel.” JA5961.\nWhen Judge Bartle advised that intent was an appropriate\nconsideration, Juror 1 agreed but said that Juror 12 was\n“trying to investigate . . . going way beyond the scope” of\nthe evidence before them. JA5961–62. Juror 12, he said,\n“has an opinion and that opinion is established.” JA5962.\nHe stated that Juror 12 was “not willing to listen to any\nsort of reason or any sort of what everyone else is saying”\nbut instead, was “trying to force everyone else to get to his\npoint of view.” Id. “[I]f he feels like he’s not getting there,\nhe gets louder and louder and points and puts his hand on\nyour shoulder . . . .” Id.\n\n 47\n\f After questioning the five jurors (Jurors 1, 2, 3, 6,\nand 12), Judge Bartle heard argument from counsel. The\nattorney for the Government pointed out that the Court\nwould have to make a credibility determination because\nJuror 12 stated that he did not recall touching anyone. In\nthe Government’s view, Juror 12 was disrupting the\nprocess and should be removed. Defense counsel\ndisagreed. They argued that Juror 12 was conscientious\nand was engaging with the evidence. They pointed out that\ndespite the testimony that Juror 12 was reading too deeply\ninto the instructions or introducing new factors for the jury\nto consider, Juror 6 had testified that the jurors “talked it\nthrough” and resolved the concern. JA5965. Defense\ncounsel argued that the jury was discussing intent, an issue\nthat was at the heart of the case. Defense counsel perceived\nno breakdown in deliberations and argued that dismissal\nwould be premature. They suggested, instead, that the\nCourt provide a supplemental instruction.\n\n Judge Bartle decided to adjourn for the afternoon.\nBut before he left the courtroom, defense counsel brought\ntwo matters to his attention. First, in light of testimony\nduring the voir dire, they asked that the jury be\nreinstructed that the verdict form and indictment were not\nevidence. Second, they apprised the Judge of the standard\nfor juror dismissal set forth in United States v. Kemp, 500\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\nKemp, a request to discharge a juror must be denied if there\nis a possibility that the request stems from the juror’s view\nof the evidence. Judge Bartle expressed hesitation on\n 48\n\freinstructing the jury, but agreed that Kemp would control\nhis determination as to whether dismissal was appropriate.\n With the following morning came a new revelation.\nWith counsel in chambers, the Judge informed them that\n“additional significant evidence” had come to light since\nthe previous day’s recess. JA5980. He placed his\ncourtroom deputy under oath, and she proceeded to testify\nto an exchange that had occurred the previous day as she\nwas escorting Juror 12 back to the jury room after he had\nbeen voir dired. According to the deputy, Juror 12 stopped\nher in the hallway, placed his hand on her shoulder, and\nlooked her “straight in the eye.” JA5981. He then said:\n“I’m going to hang this jury.” Id. The deputy then related\nthat before any further conversation could take place\nbetween Juror 12 and the deputy, Judge Bartle summoned\nJuror 12 back to his chambers. Later that day, however,\nJuror 12 and the courtroom deputy had another exchange.\nShe testified that after all five jurors had been questioned,\nJuror 12 emerged from the jury room and told her “I really\nneed to talk to you.” JA5982. She informed Judge Bartle\nand counsel that Juror 12 “said more about how they’re\ntreating him and what he’s saying to them.” Id. He flatly\nstated that “it’s going to be 11 to 1 no matter what.” Id.\n\n There were no follow-up questions for the deputy.\nInstead, defense counsel suggested that what Juror 12 may\nhave meant was that he was willing to hang the jury\nbecause of a lack of evidence. They requested that Juror\n12 be asked about his comments to the deputy.\n\n 49\n\f After once again summoning Juror 12 to his\nchambers, the Judge advised him that “[s]ome questions\nhave arisen” about what he may have done after being voir\ndired the previous day. JA5985. Juror 12 acknowledged\nhaving conversations with the courtroom deputy. When\nasked “what happened” and “[w]hat occurred,” Juror 12\nresponded: “Basically, I said that there was a lot of name\ncalling going on.” JA5985. He said comments had been\nmade by other jurors about his service in the military. He\nspecifically referred to other jurors’ suggesting that he had\npossibly “hit [his] head . . . hard a few times” while\nserving in a parachute regiment. JA5986. He testified he\nhad conveyed these comments to the deputy and that he\nfound them offensive. When asked if he said anything else\nto the deputy, Juror 12 responded: “I may have. I really\ncan’t recall.” JA5987. And when Judge Bartle followed up\nby asking if he could recall anything else that he said to\nthe deputy, Juror 12 simply replied: “No. To me, that was\nthe most important thing.” Id. Juror 12 was then excused\nfrom chambers.\n Defense counsel next requested that the juror be\nasked directly whether he told the courtroom deputy that\nhe was going to “hang this jury.” JA5988. Juror 12 was\nrecalled to chambers, and the following back and forth\ntook place:\n\n The Court: You may be seated. And, of\n course, [Juror 12], you know you’re under\n oath here from yesterday?\n\n 50\n\f Juror 12: Yes, sir.\n The Court: . . . Did you say to [the courtroom\n deputy] that you’re going to hang this jury?\n Juror 12: I said I would.\n The Court: You did?\n Juror 12: I did. I said—I told her—I said, we\n don’t agree; I’m not just going to say guilty\n because everybody wants me to, and if that\n hangs this jury, so be it.\n ....\n Juror 12: I did say that, sir.\n The Court: You didn’t remember that before?\n Juror 12: I’m more concerned about people\n spitting on my military record.\n The Court: Did you say that you’d hang the\n jury no matter what?\n Juror 12: If they do—if we cannot come to—\n The Court: No. The question is what you said\n to her. Did you say to her you would hang the\n jury no matter what?\n Juror 12: I can’t really remember that. I did\n say that if we didn’t—a person—no matter\n what, I can’t recall that exactly.\n The Court: All right. Thank you very much.\n You can wait just out there in the anteroom.\nJA5989–90.\n\n Defense counsel continued to oppose Juror 12’s\ndismissal. They argued that the juror’s concern was about\n\n 51\n\fthe evidence, and that his comments to the courtroom\ndeputy reflected a conviction that “he’s not going to agree\njust because others want him to agree.” JA5991. They also\nargued that nothing should be made of Juror 12’s failure\nto mention the comments when initially questioned by the\nCourt, and that a supplemental instruction was all that was\nwarranted given the early stage of the deliberations.\n\n The Government strongly disagreed. The Assistant\nUnited States Attorney argued that Juror 12 “should\nabsolutely be removed” because “his demeanor ha[d]\ndemonstrated a hostility . . . both to the other jurors and to\nthe court.” JA5993. The Government also suggested that\nJuror 12’s comments that he would hang the jury meant\nthat he was not participating in the deliberations and was\nignoring the evidence and the law.\n\n Ruling from the bench, Judge Bartle announced:\n I find [the deputy clerk] to be credible. I find\n [Juror 12], not to be credible. I find that [Juror\n 12] did tell [the deputy clerk] that he was\n going to hang this jury no matter what.\n There have been only approximately\n four hours of deliberation. There’s no way in\n the world he could have reviewed and\n considered all of the evidence in the case and\n my instructions on the law.\n I instructed the jury to deliberate,\n meaning to discuss the evidence; obviously,\n to hold onto your honestly held beliefs, but at\n 52\n\f least you have to be willing to discuss the\n evidence and participate in the discussion\n with other jurors.\n Juror number 12 has delayed,\n disrupted, impeded, and obstructed the\n deliberative process and had the intent to do\n so. I base that having observed him, based on\n his words and his demeanor before me.\n He wants only to have his own voice\n heard. He has preconceived notions about the\n case. He has violated his oath as a juror.\n And I do not believe that any further\n instructions or admonitions would do any\n good. I think he’s intent on, as he said,\n hanging this jury no matter what the law is,\n no matter what the evidence is.\n Therefore, he will be excused, and I\n will replace him with the next alternate . . . .\n\nJA5994–95.\n In response, defense counsel moved for a mistrial,\nwhich the judge promptly denied. He then informed the\nreconstituted jury that deliberations would need to start\nover, and reinstructed them on certain points of law,\nincluding that the verdict slip does not constitute evidence.\n\n Judge Bartle elaborated upon his decision to remove\nJuror 12 in two post-trial memorandum opinions. In the\nfirst, ruling on a media request for the sealed transcripts,\nhe explained:\n 53\n\f Here, there is no doubt that Juror 12\n intentionally refused to deliberate when he\n declared so early in the process that he would\n hang the jury no matter what. This finding\n was predicated on the admission of Juror 12\n as reported by the court’s deputy clerk. The\n facts became clear to the court after hearing\n the credible testimony of the deputy clerk and\n the less credible testimony of Juror 12. The\n demeanor of Juror 12 before the court\n confirmed the court’s findings.\n\nGSA23–24. The second opinion addressed motions for\nbail pending appeal from Nicholas and Brand. GSA25.\nThere, Judge Bartle explained:\n\n The law is well-settled that the court has\n discretion to act as it did under these\n circumstances. See United States v. Kemp,\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\n after taking testimony, specifically found that\n the juror, following only a few hours of\n deliberation, stated to the court’s courtroom\n deputy clerk that he would hang this jury no\n matter what. He could not possibly have\n reviewed all of the law and evidence of this\n five-week trial at the time he made his\n remark. The court examined the deputy clerk\n and the juror under oath in the presence of\n counsel for all parties. The undersigned\n\n 54\n\f found the deputy clerk to be credible and the\n juror not to be credible. Based on the juror’s\n demeanor, it was clear he would not change\n his attitude and that his intent had been and\n would continue to be to refuse to deliberate\n in good faith concerning the law and the\n evidence.\n\nGSA32.\n After deliberating for approximately 15 hours, the\njury returned with its verdicts on June 21, 2016, finding\nthe defendants guilty on most counts. Fattah, Vederman,\nand Brand were convicted on all counts. The jury acquitted\nBowser on sixteen counts, but found her guilty of the\nbribery conspiracy and the associated charges of bank\nfraud, making false statements to a financial institution,\nfalsifying records, and money laundering (Counts 16, 19,\n20, 21 and 22). The jury also acquitted Nicholas of wire\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\n The following week, on June 27, the Supreme Court\nissued its opinion in McDonnell v. United States, 136 S.\nCt. 2355 (2016). McDonnell provided new limitations on\nthe definition of “official acts” as used in the honest\nservices fraud and bribery statutes under which Fattah and\nVederman had been convicted. Id. at 2369–72. Fattah and\nVederman both moved to set aside their convictions. The\nDistrict Court “acknowledge[d] that under McDonnell our\ninstructions to the jury on the meaning of official act\nturned out to be incomplete and thus erroneous.” JA103.\n 55\n\fBut the Court held that “the incomplete and thus erroneous\njury instruction on the meaning of official acts did not\ninfluence the verdict on the bribery counts” and upheld the\nverdict on Counts 16–18 and 22–23. JA107, 121.\n\n Fattah, Vederman, and Bowser had more success\nwith their other post-verdict motions. The District Court,\nin a thoughtful opinion, granted relief under Federal Rule\nof Criminal Procedure 29, acquitting Vederman of the\nRICO conspiracy (Count 1) and Fattah, Vederman, and\nBowser of bank fraud, making false statements to a\nfinancial institution, and falsifying records (Counts 19, 20,\nand 21). JA37–139.\n This appeal followed. 8 The defendants raise a\nvariety of challenges to their convictions. All defendants\nbut Bowser challenge the District Court’s decision to\ndismiss Juror 12. Fattah and Vederman argue that the\nDistrict Court erred in upholding the jury’s verdict on the\nbribery and honest services fraud counts in light of the\nSupreme Court’s decision in McDonnell. Fattah, Brand\nand Nicholas challenge the sufficiency of the evidence\nunderlying the RICO conviction. Several of the defendants\ncontend the District Court erred in its instruction on intent\nand by sending the indictment out to the jury. There are\n\n\n\n8\n Fattah, Brand, Vederman, and Nicholas each filed a\ntimely notice of appeal, but Bowser did not challenge her\nconvictions.\n 56\n\falso several evidentiary challenges.9 The Government\ncross-appeals from the District Court’s judgment\nacquitting Fattah and Vederman on Counts 19 and 20,\narguing that the District Court erred in interpreting the\ndefinition of a “mortgage lending business” under 18\nU.S.C. § 27. We address these arguments in turn.\n\n We hold that the District Court erred in upholding\nthe jury verdict in light of McDonnell, and we will\ntherefore reverse and remand for retrial on Counts 16, 17,\n18, 22, and 23. We also hold that the District Court erred\n\n9\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\nHerbert Vederman, Robert Brand, and Karen Nicholas to\nthe extent their arguments on appeal apply to Mr. Fattah.”\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\n28(i) provides that a defendant, “[i]n a case involving\nmore than one appellant . . . may adopt by reference a part\nof another’s brief.” Here, Fattah’s decision to join fails to\nspecify which of the many issues of his codefendants he\nbelieves worthy of our consideration. Rather, it appears\nthat he presumes we will scour the record and make that\ndetermination for him. This type of blanket request fails to\nsatisfy Rule 28(a)(5)’s directive requiring that the\n“appellant’s brief must contain . . . a statement of the\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\nconclude that expecting the appellate court to identify the\nissues to be adopted simply results in the abandonment and\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\n1 F.3d 176, 182 (3d Cir. 1993).\n 57\n\fin acquitting Fattah and Vederman on Counts 19 and 20.\nBecause the jury’s verdict was supported by the evidence,\nwe will reinstate the convictions as to those counts. In all\nother respects, we will affirm the judgment of the District\nCourt.\n\n III. Juror Misconduct and Dismissal of Juror 12 10\n Defendant Fattah challenges the District Court’s\ndecision to conduct an in camera inquiry into alleged juror\nmisconduct and the ultimate dismissal of Juror 12. 11 We\nreject both challenges. The record reveals credible\nallegations of juror misconduct and a sufficient basis to\nsupport the finding that Juror 12 violated his oath.\n\n A. Investigation of Alleged Juror Misconduct\n We first consider whether the District Court erred in\nits handling of the two notes from jurors. A trial court’s\nresponse to allegations of juror misconduct is reviewed\nunder an abuse of discretion standard. United States v.\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\nconclude that the District Court did not abuse its discretion\n\n\n10\n The District Court had jurisdiction under 18 U.S.C.\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\n18 U.S.C. § 3742(a).\n11\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\nreversible error concerning the dismissal of Juror 12.\n 58\n\fin addressing the issues raised in the jurors’ notes to the\nCourt.\n Trial courts are afforded discretion in responding to\nallegations of juror misconduct. This is so because “the\ntrial court is in a superior position to observe the ‘mood at\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\n690 (quoting United States v. Chiantese, 582 F.2d 974,\n980 (5th Cir. 1978)). But this discretion is not unlimited.\nOnce the jury retires to deliberate, the confidentiality of its\ndeliberations must be closely guarded. An accused is\nconstitutionally entitled to be tried before a jury of his\npeers. As ordinary citizens, jurors are “expected to speak,\ndebate, argue, and make decisions the way ordinary people\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\nagainst intrusion into a defendant’s right to be judged only\nby fellow citizens, “the door to the jury room [is] locked.”\nId. at 875.\n In Boone, this Court considered the threshold for\nintervention by a trial judge who is presented with\nallegations of juror misconduct during the course of\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\nbeyond question that the secrecy of deliberations is critical\nto the success of the jury system.” Id. at 329. But that\nsecrecy abuts a competing interest—the jury’s proper\nexecution of its duties. That is, “a juror who refuses to\ndeliberate or who commits jury nullification violates the\nsworn jury oath and prevents the jury from fulfilling its\n\n 59\n\fconstitutional role.” Id. Recognizing these competing\ninterests, we declined in Boone to adopt a sweeping\nlimitation on a trial court’s ability to investigate\nallegations of misconduct during jury deliberations. See id.\nConsistent with the standard applied at other stages of\ncriminal proceedings, Boone teaches that “where\nsubstantial evidence of jury misconduct—including\ncredible allegations of jury nullification or of a refusal to\ndeliberate—arises during deliberations, a district court\nmay, within its sound discretion, investigate the\nallegations through juror questioning or other appropriate\nmeans.” Id.\n Fattah argues that the District Court had no basis to\nquestion any of the jurors. Fattah Br. 20. We disagree. In\nBoone, notes from the jury presented substantial credible\nevidence of misconduct. 458 F.3d at 330. Here, the initial\nnote from the foreperson alleged that Juror 12 “refuse[d]\nto vote by the letter of the law,” would “not listen or reason\nwith anybody,” and that he had “an agenda or ax to grind”\nwith the Government. JA5916. The note contained\nallegations of both a refusal to deliberate and a suggestion\nof nullification. A refusal to deliberate is a violation of a\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\nsettled that jurors have a duty to deliberate.”)). Moreover,\nnullification—a juror’s refusal to follow the law—is a\nviolation of the juror’s sworn oath to render a verdict\naccording to the law and evidence. See United States v.\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\n 60\n\fboth “benevolent” and “shameful” examples of juror\nnullification, but “categorically reject[ing] the idea that, in\na society committed to the rule of law, jury nullification is\ndesirable or that courts may permit it to occur when it is\nwithin their authority to prevent”). The second jury note,\nsigned by nine jurors, supported the claim of misconduct\nby asserting that Juror 12 was “incapable of making\ndecision[s]” and was “constantly scream[ing]” at the other\njurors. JA5916–17. We conclude that the District Court\ndid not abuse its discretion in deciding to initially question\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\n\n Fattah also challenges the scope of the District\nCourt’s questioning. He argues that the rights to an\nimpartial jury and to a unanimous verdict “would be\nrendered toothless if trial courts had free rein to question\njurors during deliberations.” Fattah Br. 36. Indeed, we\nacknowledged the legitimacy of such a concern in Boone.\nDespite adopting a modest “credible allegations” standard\nfor investigating misconduct, we “ke[pt] in mind the\nimportance of maintaining deliberative secrecy.” Boone,\n458 F.3d at 329. Fattah asserts that the trial court’s\nquestions to the five jurors were “intrusive and pointed”\nand “nothing like the questioning . . . approved in Boone.”\nFattah Br. 38. But Fattah does not elaborate on how, in his\nview, the questions posed by Judge Bartle specifically\nintruded into deliberative secrecy.\n\n To be sure, Judge Bartle’s questioning of each juror\nwas more extemporaneous than the juror questioning in\n\n 61\n\fBoone. There, the district court asked a single juror four\n“concise and carefully-worded” questions. 458 F.3d at\n330. Judge Bartle’s voir dire of each of the five jurors took\non a more conversational tone. We take no issue with that\napproach. The substance of the judge’s questions was\nlimited and mirrored that of questions we deemed\nappropriate in Kemp. There, the court conducted three\nrounds of questioning. In the first round, each juror was\nasked:\n (1) “Are you personally experiencing any\n problems with how the deliberations are\n proceeding without telling us anything about\n the votes as to guilt or innocence? If yes,\n describe the problem.” (2) “Are all the jurors\n discussing the evidence or lack of evidence?”\n (3) “Are all the jurors following the court’s\n instructions on the law?”\n\nKemp, 500 F.3d at 273. In the second and third rounds,\neach juror was asked:\n (1) “Is there any juror or jurors who are\n refusing to deliberate?” (2) “Is there any juror\n who is refusing to discuss the evidence or\n lack of evidence?” (3) “Is there any juror who\n is refusing to follow the Court’s\n instructions?”\nId. at 274. Here, Judge Bartle began his voir dire of each\njuror by stating that he did not wish for the juror to discuss\n 62\n\fthe merits of the case or to reveal the content of the\ndeliberations that had taken place. He asked the jurors\nwhether screaming was occurring, whether the jurors were\ndiscussing the evidence, whether Juror 12 was placing his\nhands on other jurors, and whether Juror 12 was unwilling\nto follow his instructions.\n Fattah points to no specific question posed or topic\ndiscussed that was inappropriate, and we see little to no\nsubstantive difference between the questions here and\nthose asked by the trial judge in Kemp. As in Kemp, “the\nDistrict Court took care to limit its questions to appropriate\nmatters that did not touch on the merits of the jury’s\ndeliberation, and expressly informed each juror on\nmultiple occasions that he or she should not reveal the\nsubstance of the deliberations.” Id. at 302 (citing United\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\n Fattah also argues that once the remarks of Juror 2\nand Juror 12 revealed no further evidence of misconduct,\nthe court had no basis to question other jurors. Fattah\nReply 19. Yet, our cases make clear that a trial court may,\nin its discretion, examine each juror. Kemp, 500 F.3d at\n302 (“We have recognized that there are times in which\nindividual questioning is the optimal way in which to root\nout misconduct.”). Indeed, “the District Court must utilize\nprocedures that will ‘provide a reasonable assurance for\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\n\n\n\n 63\n\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\n(3d Cir. 1981)). 12\n\n Judge Bartle, a very able and experienced district\njudge, was in the best position to determine what type of\ninquiry was warranted under the circumstances. We\nconclude that his questioning of the five jurors was not an\nabuse of discretion. See id. at 302.\n\n B. Dismissal of Juror 12\n Fattah, joined by Vederman, Brand, and Nicholas,\nstrongly contends that the District Court committed\nreversible error by dismissing Juror 12. “We review the\ndismissal of a juror for cause for abuse of discretion.”\n\n12\n Our cases do not suggest that a trial judge confronted\nwith allegations that a jury’s deliberations are being\nobstructed by one of its members should always resort to\ninterviewing jurors. Reinstructing the jury on its duty to\ndeliberate will often be the better course at the first sign of\ntrouble. Mere disagreement among jurors—even spirited\ndisagreement—is no ground for intervention.\nFurthermore, intrusive or leading questions about the\ndeliberative process may work against the twin goals of\nprotecting that process and ensuring that jurors remain\nfaithful to their oaths. We share the Eleventh Circuit’s\npreference of “err[ing] on the side of too little inquiry as\nopposed to too much.” United States v. Oscar, 877 F.3d\n1270, 1287 (11th Cir. 2017) (quoting United States v.\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\n 64\n\fKemp, 500 F.3d at 303. That deferential standard compels\nus to affirm.\n Rule 23(b) of the Federal Rules of Criminal\nProcedure permits a trial court to excuse a deliberating\njuror for good cause. See id. (citing Fed. R. Crim. P.\n23(b)). Good cause exists where a juror refuses to apply\nthe law, refuses to follow the court’s instructions, refuses\nto deliberate with his or her fellow jurors, or demonstrates\nbias. See Kemp, 500 F.3d at 305–06; United States v.\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\nF.3d at 617. Good cause does not exist when there is\nreasonable but sustained disagreement about how a juror\nviews the evidence. The courts of appeals are emphatic\nthat trial courts “may not dismiss a juror during\ndeliberations if the request for discharge stems from\ndoubts the juror harbors about the sufficiency of the\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\nThomas, 116 F.3d at 622.\n\n To reinforce a defendant’s right to a unanimous\njury, we have adopted a high standard for juror dismissal.\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\ndischarge a juror for bias, failure to deliberate, failure to\nfollow the district court’s instructions, or jury nullification\nwhen there is no reasonable possibility that the allegations\nof misconduct stem from the juror’s view of the evidence.”\n\n 65\n\fId. at 304 (emphasis added). This “no reasonable\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\ncorresponds with the burden for establishing guilt in a\ncriminal trial.” Id.\n\n We first applied this standard in Kemp, but have not\nhad occasion to do so since. There, the evidence\nsupporting the district court’s removal decision was\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\nand consistently reported that a juror was improperly\nbiased, and did so only after three rounds of questioning\nand careful and correct instructions from the district court\nas to the distinction between appropriate skepticism and\nimpermissible bias. Id. at 304–05; see id. at 275–76\n(district court’s instruction). The testimony also showed\nthat the juror in question refused to deliberate or to discuss\nthe evidence with her fellow jurors. Id. at 305.\n Whether the evidence of misconduct in this case is\nas strong as that in Kemp is beside the point. After only\nfour hours of deliberations, Juror 12 stated unequivocally\nto the courtroom deputy that he was “going to hang” the\njury, and that it would be “11 to 1 no matter what.”\nJA5981–82 (emphasis added). These statements, coupled\nwith the District Court’s finding that Juror 12 lacked\ncredibility, provided a sufficient basis for Juror 12’s\ndismissal.\n\n As grounds for excusing Juror 12, the District Court\nfound that he refused to deliberate in good faith, “delayed,\ndisrupted, impeded, and obstructed the deliberative\n 66\n\fprocess and had the intent to do so,” JA5995, and that he\nwas “intent on . . . hanging this jury no matter what the law\nis, no matter what the evidence is.” Id. The District Court\ndetermined from this that Juror 12 had violated his oath as\na juror and that no further instructions or admonitions\ncould rehabilitate the juror. Id. The District Court based\nthese findings on personal observation, including Juror\n12’s words and demeanor, and making the specific finding\nthat Juror 12 was not credible. That finding is amply\nsupported by the record.\n\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\nCir. 2001), the Ninth Circuit recognized that “the\ndemeanor of the pertinent juror is important to juror\nmisconduct determinations” because the “juror’s\nmotivations and intentions are at issue.” That court\nemphasized, as we do, that a district judge is best situated\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\nhe could not recall putting his hand on another juror’s\nshoulder, while his fellow jurors’ testimony was consistent\non this point. Juror 12 also failed, at first, to recall his\ntroubling statements to the courtroom deputy despite\nhaving made those statements only the previous afternoon.\nWhen questioned a second time and asked directly about\nthe statements, he admitted to saying that he would hang\nthe jury but claimed he could not “really remember”\nsaying “no matter what” the day before. JA5989–90. Juror\n12’s spotty recollection of the previous day’s events\nfurther supports the District Court’s finding that he was\nnot credible.\n 67\n\f Fattah argues that the credibility determination was\nnot, by itself, a sufficient reason to dismiss the juror\nbecause the record demonstrates more than a reasonable\npossibility that the complaints about his conduct stemmed\nfrom Juror 12’s own view of the Government’s case.\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\nthe District Court abused its discretion by dismissing Juror\n12 “on the basis of, in effect, six words the juror\npurportedly said to the court’s deputy after he was verbally\nattacked by other jurors.” Fattah Br. 24. According to\nFattah, the questioning of the other jurors “confirmed that\nthere were no legitimate grounds for removing juror 12.”\nId. at 26. We conclude otherwise.\n “A district court’s finding on the question whether\na juror has impermissibly refused to participate in the\ndeliberation process is a finding of fact to which\nappropriate deference is due.” Baker, 262 F.3d at 130.\nWhile district courts must apply a high standard for juror\ndismissal, their underlying findings are afforded\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\nif the decision to dismiss a juror was “without factual\nsupport, or for a legally irrelevant reason.” Abbell, 271\nF.3d at 1302 (citation omitted).\n Here, the District Court had a legitimate reason for\nremoving Juror 12. Refusal to deliberate constitutes good\ncause for dismissal. Although the judge did not expressly\narticulate the Kemp standard when he announced that he\n\n 68\n\fwould dismiss Juror 12, he did acknowledge the “no\nreasonable possibility” standard in his discussion with\ncounsel. The unmistakable import of the District Court’s\nstatement from the bench is that there was no reasonable\npossibility that Juror 12’s intransigence was based on his\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\n Fattah contends that there is no record support for\nthe finding that Juror 12 said “he was going to hang this\njury no matter what.” Fattah Br. 29. To be sure, the\ncourtroom deputy’s testimony is not that Juror 12 used the\nwords “hang this jury” and “no matter what” in the same\nsentence. She testified that Juror 12 first stated “I am going\nto hang this jury,” then later stated “it is going to be 11 to\n1 no matter what.” JA5981–82. This is a distinction\nwithout a difference. Likewise, Fattah challenges the\nDistrict Court’s finding that Juror 12 was determined to\nhang the jury “no matter what the law is” and “no matter\nwhat the evidence is.” Fattah Br. 29. Although there is no\nevidence that Juror 12 uttered the phrases “no matter what\nthe law is” or “no matter what the evidence is,” the District\nCourt was describing the import of Juror 12’s statements.\nThis was not error.\n Fattah expresses the concern that “[i]f jurors are\nasked the right questions or interrogated long enough, it\nwould not be difficult for a trial court to elicit testimony\nfrom [a] majority [of] jurors that can be held up as\nevidence of a dissenting juror’s bias or refusal to\ndeliberate.” Fattah Br. 22. He also worries that a group of\n\n 69\n\fjurors might have an incentive to rid themselves of a juror\nwho holds a different view. Id. These are valid concerns—\nbut no basis existed for such concerns in this case. Juror\n12’s own words provided most of the support for his\neventual dismissal. Furthermore, his statements were\nmade early in the deliberations, in a complex case, before\nany juror could reasonably be expected to have reached\nfinal verdicts on the twenty-nine counts before the jury.\n\n The able District Judge did not err in finding that\nJuror 12 refused to deliberate and therefore violated his\noath.\n\n IV. The District Court’s Instructions Under\n McDonnell\n On appeal, Fattah and Vederman renew their\nchallenge to the jury instructions given on Counts 3, 16,\n17, 18, 22, and 23, concerning the meaning of the term\n“official act” as used in the bribery statute (pursuant to\nwhich both were convicted) and the honest services fraud\nstatute (pursuant to which Fattah alone was convicted).\n\n In light of the Supreme Court’s opinion in\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\nreleased the week after the jury verdict, the District Court\nconceded that its instructions were incomplete and\nerroneous, at least as to Counts 16–18. Nevertheless, the\nDistrict Court held that the erroneous jury instructions had\nnot influenced the verdict on the bribery counts, and\ndeclined to set aside Fattah and Vederman’s convictions.\n 70\n\fAs to Counts 16–18 and 22–23, we disagree, and will\nreverse the District Court’s judgment. The District Court’s\njudgment with respect to Count 3, which did not involve\nVederman, will be affirmed. JA78–79.\n\n A. The McDonnell Framework\n In McDonnell, the Supreme Court interpreted the\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\nS. Ct. at 2368. The statute defines an “official act” as “any\ndecision or action on any question, matter, cause, suit,\nproceeding or controversy, which may at any time be\npending, or which may by law be brought before any\npublic official, in such official’s official capacity, or in\nsuch official’s place of trust or profit.” 18 U.S.C.\n§ 201(a)(3). The McDonnell Court distilled this definition\ninto two requirements:\n First, the Government must identify a\n “question, matter, cause, suit, proceeding or\n controversy” that “may at any time be\n pending” or “may by law be brought” before\n a public official. Second, the Government\n must prove that the public official made a\n decision or took an action “on” that question,\n matter, cause, suit, proceeding, or\n controversy, or agreed to do so.\n\n136 S. Ct. at 2368. Applying this two-step test to Governor\nRobert McDonnell’s convictions, the Supreme Court\nconcluded that “the jury was not correctly instructed on\n 71\n\fthe meaning of ‘official act,’ ” and as a result, “may have\nconvicted Governor McDonnell for conduct that is not\nunlawful.” Id. at 2375. Given that uncertainty, the Court\n“[could not] conclude that the errors in the jury\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\nThe Supreme Court, therefore, vacated Governor\nMcDonnell’s convictions. Id.\n\n McDonnell lays out a clear path for the Government\nto follow in proving that an accused has performed an\n“official act.” First, the Government must “identify a\n‘question, matter, cause, suit, proceeding or controversy’\nthat ‘may at any time be pending’ or ‘may by law be\nbrought’ before a public official.” 136 S. Ct. at 2368\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\ninto two sub-components. In Step 1(A), the Government\nmust “identify a ‘question, matter, cause, suit, proceeding\nor controversy.’ ” Id. Step 1(B) then clarifies that the\nidentified “question, matter, cause, suit, proceeding or\ncontroversy” be one that “ ‘may at any time be pending’ or\n‘may by law be brought’ before a public official.” Id.\n\n Under Step 1(A), a “question, matter, cause, suit,\nproceeding or controversy” must be “a formal exercise of\ngovernmental power that is similar in nature to a lawsuit\nbefore a court, a determination before an agency, or a\nhearing before a committee.” Id. at 2372. Importantly, “a\ntypical meeting, telephone call, or event arranged by a\n\n\n 72\n\fpublic official” does not qualify as such a formal exercise\nof governmental power. Id. at 2368.\n Step 1(B) then requires us to ask whether the\nqualifying “question, matter, cause, suit, proceeding or\ncontroversy” was one that “ ‘may at any time be pending’\nor ‘may by law be brought’ before a public official.” Id.\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\nby law be brought’ suggest something that is relatively\ncircumscribed—the kind of thing that can be put on an\nagenda, tracked for progress, and then checked off as\ncomplete.” Id. at 2369; accord United States v. Repak, 852\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\nCt. at 2369). By contrast, matters described at a high level\nof generality—for example, “[e]conomic development,”\n“justice,” and “national security”—are not sufficiently\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\n\n In McDonnell, the Court concluded that at least\nthree questions or matters identified by the Fourth Circuit\nwere sufficiently focused:\n (1) whether researchers at any of Virginia’s\n state universities would initiate a study of [a\n drug]; (2) whether the state-created Tobacco\n Indemnification and Community\n Revitalization Commission would allocate\n grant money for the study of [a chemical\n compound]; and (3) whether the health\n insurance plan for state employees in\n\n 73\n\f Virginia would include [a specific drug] as a\n covered drug.\nId. at 2370 (internal quotations omitted) (quoting United\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\n2015)). We provided guidance in the form of a fourth\nexample in Repak, when we held that a redevelopment\nauthority’s awarding of contracts was “a concrete\ndetermination made by the [redevelopment authority’s]\nBoard of Directors.” 852 F.3d at 253.\n\n Step 2 requires the Government to prove that the\npublic official made a “decision” or took “an action” on\nthe identified “question, matter, cause, suit, proceeding or\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\nMcDonnell Court explained:\n Setting up a meeting, hosting an event, or\n calling an official (or agreeing to do so)\n merely to talk about a research study or to\n gather additional information . . . does not\n qualify as a decision or action on the pending\n question of whether to initiate the study.\n Simply expressing support for the research\n study at a meeting, event, or call—or sending\n a subordinate to such a meeting, event, or\n call—similarly does not qualify as a decision\n or action on the study, as long as the public\n official does not intend to exert pressure on\n another official or provide advice, knowing\n\n 74\n\f or intending such advice to form the basis for\n an “official act.”\nId. at 2371. The Court further clarified:\n\n If an official sets up a meeting, hosts an\n event, or makes a phone call on a question or\n matter that is or could be pending before\n another official, that could serve as evidence\n of an agreement to take an official act. A jury\n could conclude, for example, that the official\n was attempting to pressure or advise another\n official on a pending matter. And if the\n official agreed to exert that pressure or give\n that advice in exchange for a thing of value,\n that would be illegal.\nId.\n Here, Fattah was charged with engaging in three\ncategories of official acts, which we analyze in accordance\nwith the McDonnell framework. In Counts 16–18 and 22–\n23, Fattah is alleged to have set up a meeting between\nVederman and the U.S. Trade Representative, attempted\nto secure Vederman an ambassadorship, and hired\nVederman’s girlfriend, all in return for a course of conduct\nwherein Vederman provided things of value to Fattah.\n\n In this case, as in McDonnell, the jury instructions\nwere erroneous. We conclude that the first category of the\ncharged acts—setting up a meeting between Vederman\n 75\n\fand the U.S. Trade Representative—is not unlawful, and\nthat the second category—attempting to secure Vederman\nan ambassadorship—requires reconsideration by a\nproperly instructed jury. The third charged act—hiring\nVederman’s girlfriend—is clearly an official act. But\nbecause we cannot isolate the jury’s consideration of the\nhiring from the first two categories of charged acts, we\nmust reverse and remand the judgment of the District\nCourt.\n\n B. The Kirk Meeting\n We turn first to Fattah’s scheduling of a meeting\nbetween Vederman and the U.S. Trade Representative,\nRon Kirk. Under McDonnell, “setting up a meeting . . .\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\nS. Ct. at 2368. Fattah’s setting up the meeting between\nVederman and Kirk was therefore not an official act, a\nconcession implicit in the Government’s opening brief.\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\none of the “two categories” of allegedly “official acts”).\nBut the jury was not properly instructed on this point.\nWithout the benefit of the principles laid down in\nMcDonnell, the jury was free to conclude that arranging\nthe Kirk meeting was an official act—and it may have\ndone so. The District Court’s erroneous jury instructions,\ntherefore, cannot survive harmless error review.\n\n In a footnote in its brief to this Court, the\nGovernment argues that evidence about the Kirk meeting\nwas offered only “because it established the strength of\n 76\n\fVederman’s desire to be an ambassador” and not because\nthe Government was attempting to establish the meeting\nas an independent official act. Id. at79–80 n.6. But the\nrecord undercuts the Government’s post hoc justification.\n\n The indictment, provided to the jury in redacted\nform for use in its deliberations, lists Fattah’s setting up\nthe Kirk meeting as an official act under the heading\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\nUnder this heading are three distinct subheadings:\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\nof Another Executive Branch Position,” and (3) “Hiring\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\nJA494–95. The second subheading, “The Pursuit of\nAnother Executive Branch Position,” describes the\narrangement of the Kirk meeting. Quite clearly, then, this\nthree-part structure demonstrates that setting up the Kirk\nmeeting was one of three distinct categories of official acts\nalleged by the Government.\n\n Although there is some support for the\nGovernment’s argument that evidence of the Kirk meeting\nwas presented at trial only to establish the extent of\nVederman’s interest in becoming an ambassador, JA827,\n852–53 (mentioning the Kirk meeting in close proximity\nto references to Fattah’s attempts to secure Vederman an\nambassadorship), it is undermined by language in the\nredacted indictment itself, and by the way in which the\nGovernment presented its case at trial as a “pattern” of\nconnected acts.\n\n 77\n\f The redacted indictment, for example, refers to the\nKirk meeting as “The Pursuit of Another Executive\nBranch Position.” JA495 (emphasis added). The use of the\nword “Another” strongly suggests that evidence about the\nKirk meeting was not merely evidence of Fattah’s attempt\nto secure Vederman an ambassadorship, but was also\nevidence of a separate and distinct attempt to secure\nVederman a position on a federal trade-related\ncommission. The redacted indictment also notes that “[i]n\nor around May 2011, with little progress made on securing\nan ambassadorship for VEDERMAN, FATTAH turned\ntowards obtaining for VEDERMAN an appointment in the\nExecutive Branch to a federal trade commission.” Id.\n(emphasis added). The words “turned towards,” taken\nliterally, clearly convey that arranging the Kirk meeting\nwas presented as distinct from Fattah’s efforts to secure\nVederman an ambassadorship.\n\n The District Court denied Fattah and Vederman a\nnew trial on Counts 17 and 18, referring to evidence of the\nKirk meeting as “de minimis” and noting that “Kirk’s\ntestimony during this lengthy trial lasted a mere sixteen\nminutes.” JA97 n.14. In the District Court’s view,\nevidence of the Kirk meeting “played no role in the\noutcome” of the case. Id. Considering the record in light\nof McDonnell, we are not so sure.\n\n Although it is possible that evidence of the Kirk\nmeeting played a minor role at trial when compared to the\nother acts on which the Government presented evidence,\n\n 78\n\fthe redacted indictment suggests that the Kirk meeting was\na significant part of the Government’s case. The\nindictment dedicates five paragraphs to describing the\nKirk meeting, but just three paragraphs to describing the\nhiring of Vederman’s girlfriend—a hiring that, as we\nexplain below, is clearly an official act. JA495–96. While\nneither the number of minutes used at trial nor the number\nof paragraphs contained in an indictment is a dispositive\nunit of measurement for determining the significance of\nevidence, we conclude that the District Court’s erroneous\njury instructions pertaining to the Kirk meeting were not\nharmless.\n We conclude, in accordance with McDonnell, that\nFattah’s arranging a meeting between Vederman and the\nU.S. Trade Representative was not itself an official act.\nBecause the jury may have convicted Fattah for conduct\nthat is not unlawful, we cannot conclude that the error in\nthe jury instruction was harmless beyond a reasonable\ndoubt, and we must vacate and remand the convictions of\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\n\n C. Fattah’s Efforts to Secure Vederman an\n Ambassadorship\n The nature of Fattah’s efforts to secure Vederman\nan ambassadorship is less clear, and presents a closer\nquestion than the Kirk meeting. We ultimately conclude\nthat the question warrants remand so that it may be\nanswered by a properly instructed jury. On remand, the\njury must decide whether Fattah’s conduct constituted a\n 79\n\f“decision” or “action” under Step 2 of the McDonnell\nanalysis.\n At the outset, it is clear to us that, under Steps 1(A)\nand 1(B), a formal appointment of Vederman as an\nambassador would qualify as a “matter” that “may at any\ntime be pending” before a public official. The formal\nappointment of a particular person (Vederman), to a\nspecific position (an ambassadorship), constitutes a matter\nthat is sufficiently focused and concrete. The formal\nappointment of an ambassador is a matter that is “pending”\nbefore the President—the constitutional actor charged\nwith nominating ambassadors—as well Senators, who are\ncharged with confirming the President’s ambassadorial\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\nand by and with the Advice and Consent of the Senate,\nshall appoint Ambassadors . . . .”). It is beyond cavil that\nthe formal appointment of an ambassador satisfies both\nsub-components of McDonnell’s Step 1.\n Turning to Step 2, we consider whether Fattah’s\nefforts to secure Vederman an ambassadorship qualify as\nmaking a “decision” or taking “an action” on the identified\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\nAlthough those efforts—three emails, two letters, and one\nphone call—do not themselves qualify as a “question,\nmatter, cause, suit, proceeding, or controversy” under\nMcDonnell’s Step 1, they may nonetheless qualify as the\nmaking of a “decision” or taking “an action” on the\nidentified matter of appointment. Id.\n\n 80\n\f McDonnell’s Step 2 requires us to determine\nwhether Fattah’s efforts qualify as permissible attempts to\n“express[] support,” or impermissible attempts “to\npressure or advise another official on a pending matter.”\nId. at 2371. At trial, the jury was not instructed that they\nhad to place Fattah’s efforts on one side or the other of this\ndivide. The jury might even have thought they were\npermitted to find Fattah’s efforts—three emails, two\nletters, and one phone call—to themselves be official acts,\nrather than a “decision” or “action” on the properly\nidentified matter of appointment. Such a determination\nwould have been contrary to the dictates of McDonnell.\n Faced with such uncertainty, we cannot assume the\njury verdict was proper. Although the jury might not have\nconcluded that Fattah’s efforts were themselves official\nacts, and although the jury might not have concluded that\nthose efforts crossed the line into impermissible attempts\n“to pressure or advise,” we are unable to conclude that the\njury necessarily did so. Nor can we, on the cold record\nbefore us, determine whether Fattah’s efforts to secure\nVederman an ambassadorship crossed the line.\nDetermining, for example, just how forceful a strongly\nworded letter of recommendation must be before it\nbecomes impermissible “pressure or advice” is a fact-\nintensive inquiry that falls within the domain of a properly\ninstructed jury. Should the Government elect to retry these\ncounts after remand, the finder of fact will need to decide\nwhether Fattah’s efforts constituted permissible attempts\nto “express[] support,” or impermissible attempts “to\n 81\n\fpressure or advise another official on a pending matter.”\nId.\n\n D. The Zionts Hiring\n The third group of acts charged in the Fattah–\nVederman scheme involves Fattah’s decision to hire\nVederman’s girlfriend, Alexandra Zionts, as a\ncongressional staffer. We conclude that the hiring was an\nofficial act. A brief analysis of McDonnell’s two steps\nsuffices to show why this is so.\n Here, under McDonnell’s Step 1(A), the relevant\n“matter” is the decision to hire Zionts. Step 1(B) of the\nanalysis is satisfied because the hiring decision was\n“pending” before Fattah himself. And that hiring was\n“focused and concrete,” “within the specific duties of an\nofficial’s position—the function conferred by the\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\nStep 2 requires that the “Government . . . prove that the\npublic official made a decision or took an action ‘on’ [the\nidentified] question, matter, cause, suit, proceeding, or\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\ndecision to hire Zionts clearly satisfies that requirement.\nWe therefore conclude that the hiring of Zionts was an\nofficial act under McDonnell.\n\n Vederman concedes that the Zionts hiring was an\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\nhis part, maintains that “hiring someone for a routine, part-\ntime, short-term position falls well outside [the] definition\n 82\n\f[of ‘official act’] and is nothing like a lawsuit, agency\ndetermination, or committee hearing, even if each shares\nthe happenstance that federal funds will be used.” Fattah\nReply Br. 25.\n\n Fattah’s argument lacks traction. Official acts need\nnot be momentous decisions—or even notable ones.\nJudges, for example, make “routine” evidentiary rulings\nevery day, and yet it is beyond question that those rulings\nare official acts. In the realm of official acts, it is of no\nmoment that Zionts provided only “part-time, short term”\nlabor. When a public official hires an employee to work in\nhis government office, he has engaged in an official act.\n * * *\n If we could conclude that the Zionts hiring was the\nonly category of actions that the jury relied on when it\nfound that Fattah performed an official act under Counts\n16–18 and 22–23, remand would not be necessary. But, as\nwe have explained, we cannot rule out that the jury\nerroneously convicted Fattah and Vederman based on\nother actions that were not official acts under\nMcDonnell.13\n\n\n13\n More specifically, the incomplete, and therefore\nerroneous, instructions could have led the jury to commit\nat least one of three mistakes. First, the jury could have\nimproperly convicted Vederman and Fattah based on the\nKirk meeting alone, or misunderstood the Kirk meeting to\n 83\n\f The Government argues that because the Zionts\nhiring was an official act, the effect of the erroneous jury\ninstructions could be no more than harmless. The jury’s\nverdict, the Government contends, permits us to deduce\nthat the jury necessarily concluded the Zionts hiring was\nan official act, and that this conclusion alone supported\nFattah’s and Vederman’s convictions as to Counts 16–18\nand 22–23—regardless of whether the jury erroneously\nfound any unofficial acts to be official acts. We disagree.\n Fattah and Vederman objected to the definition of\n“official act” at trial. We thus apply the harmless error\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\nGovernment argues that because the jury convicted Fattah\nand Vederman of illegally laundering the proceeds of a\n“scheme to commit bribery” under Count 23, the jury\nfound that the scheme must have encompassed only the\nZionts hiring. JA531.That would mean that the jury did not\nconclude that the “scheme to commit bribery” included\n\nbe a necessary component of an impermissible “pattern”\nof official acts. Second, the jury might have concluded that\nFattah’s efforts to secure Vederman an ambassadorship\nwere themselves official acts. Third, the jury might have\nconcluded that Fattah’s efforts to secure Vederman an\nambassadorship were merely attempts to “express[]\nsupport,” rather than to “exert pressure . . . or provide\nadvice,” but nonetheless erroneously concluded that those\nexpressions of support were official acts. McDonnell, 136\nS. Ct. at 2371.\n 84\n\fany acts that McDonnell now makes clear were unofficial.\nYet the redacted indictment, jury instructions, and the fact\nthat the Government presented its case under a “pattern”\ntheory at trial compel us to reject the Government’s\nargument.\n\n The very first sentence under Count 23 of the\nredacted indictment incorporates all three categories of\n“Overt Acts” contained within paragraphs “58 through 95\nof Count One.” 14 All three of these categories fall under a\ngeneral heading within the redacted indictment titled “The\nBribery and Fraud Scheme [redacted].” JA494. The jury\nhad before it instructions for Count 23 which referred to\n“the alleged bribery scheme involving an $18,000\npayment,” JA448 (emphasis added), and the redacted\nindictment which referred to “a scheme to commit\nbribery,” JA531 (emphasis added). The parallel language\ncould well lead a rational jury to conclude that the relevant\n“scheme” included all three categories of acts listed under\nthe general heading: “The Bribery and Fraud Scheme\n[redacted].” JA494 (emphasis added).\n\n\n\n14\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\nthree categories of allegedly official acts discussed above:\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\nof Another Executive Branch Position,” and (3) the\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\nStaff.” JA494–95.\n 85\n\f Like the redacted indictment and jury instructions,\nthe Government’s trial arguments referred to patterns and\na course of conduct, and stressed that the jury need not\nconnect specific payments to particular official acts. In its\nclosing argument to the jury, the Government stated that\nthe alleged “scheme took place over a period of several\nyears. Over and over again you’re going to see the same\npattern.” JA5383 (emphasis added). Then, in its rebuttal\nargument, the Government went out of its way to\nexplicitly distinguish its “pattern” theory from an\nalternative theory that would have directly connected\nindividual payments to individual acts. As the prosecutor\nargued to the jury:\n Ms. Recker appears to argue that each thing\n of value must coincide with some specific\n official act, but that is not the law and that is\n not what Judge Bartle is going to instruct you.\n Instead what he will tell you is that the\n government is not required to prove that\n Vederman intended to influence Fattah to\n perform a set number of official acts in return\n for things of value so long as the evidence\n shows a course of conduct of giving things of\n value, things of value to Fattah in exchange\n for a pattern of official acts favorable to\n Vederman. In other words a stream of\n benefits. These for those, not this for that.\n\n\n\n 86\n\fJA5715–16 (emphases added). In closing to the jury, the\nGovernment made several other references to this\n“pattern” theory, 15 and the District Court referred to this\n“pattern” theory in its instructions to the jury. As Judge\nBartle instructed:\n\n [I]t is not necessary for the government to\n prove that a defendant intended to induce a\n public official to perform a number of official\n acts in return for things of value.\n So as long as the evidence shows a\n course of conduct of giving things of value to\n a public official in exchange for a pattern of\n official acts favorable to the giver.\n\nJA5833–34 (emphasis added). On appeal, the Government\nchanges course, asking us to assume that the jury ignored\nthese repeated references to a “pattern of official acts” and\n\n15\n See, e.g., JA5389 (“And the exchange of an official act\nfor a thing of value is called a bribe. There’s the pattern.\nFattah needs money, Vederman gets an official act.”); JA\n5393 (“That’s why you see the pattern over and over again.\nFattah needs money, Vederman gets an official act.”);\nJA5400 (“The same pattern we saw over and over again.\nFattah needs money, Vederman gets an official act.”);\nJA5409 (“[Y]ou know that these were bribes because of\nthe pattern you saw over and over and over again. Fattah\nneeds money, Vederman gets an official act, that makes\nthese things a bribe.”).\n 87\n\finstead considered the Zionts hiring and Vederman’s\n$18,000 payment to Fattah as an isolated quid pro quo.\nThis is an invitation to speculate, and we decline to do so.16\nThe jury began its deliberations accompanied by a copy of\nthe redacted indictment which alleged a pattern of official\nacts, consisting of any combination of three categories of\nacts: pursuing an ambassadorship, arranging the Kirk\nmeeting, and hiring Zionts. In light of the erroneous\ninstructions, and because only one category clearly\n\n16\n Providing some support to the Government’s ultimately\nunconvincing argument that the jury considered the Zionts\nhiring and $18,000 payment in isolation, we note that the\nredacted indictment does mention those two events side-\nby-side in paragraph 78 of the indictment’s Part V. JA497\n(“On January 13, 2012, VEDERMAN wired $18,000 to\nFATTAH, and six days later, on January 19, 2012,\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\nwelcoming her as a new employee to FATTAH’s\nCongressional Staff.”). But although paragraph 78\nmentions the $18,000 wire transfer and the Zionts hiring\nin the same breath, paragraph 78 does not instruct the jury\nto connect these two events apart from the rest of the\nevidence presented at trial. In light of the other instructions\nand arguments indicating that the jury should not consider\nthe Zionts hiring in isolation, but instead should consider\nthe hiring as one part of a three-part scheme, paragraph 78\nis not sufficient to avoid a reversal and remand on the\nconvictions of Fattah and Vederman as to Counts 16–18\nand 22–23.\n 88\n\fqualifies as an “official act,” the jury’s deliberations were\nfraught with the potential for McDonnell error. We will\nvacate the convictions of Fattah and Vederman as to\nCounts 16, 17, 18, 22, and 23, and remand to the District\nCourt.\n\nE. Vederman’s Sufficiency Challenge to Counts 16–18\n and 22–23\n Vederman argues that there is insufficient evidence\nto support a conviction, even if a jury were properly\ninstructed under McDonnell. Specifically, Vederman\nargues that there is insufficient evidence to convict him\nand Fattah, after remand, on Counts 16–18 and 22–23\nbecause “[a]t least seven of the eight alleged ‘official acts’\nwere, as a matter of law, not official at all.” Vederman Br.\n35. As to the single act that Vederman implicitly concedes\nto be an official act—the Zionts hiring—Vederman argues\nthat “[t]he only thing that even arguably associates” the\nZionts hiring with Vederman was its timing in relation to\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\nAccording to Vederman, “the undisputed chronology\nprecludes any inference that Vederman conferred this\nbenefit on his friend as an illegal bribe.” Id. (emphasis\nomitted). Vederman is wrong. Sufficient evidence was\nproduced at trial to have allowed a properly-instructed jury\nto convict Fattah and Vederman of Counts 16–18 and 22–\n23.\n To begin with, even if the Zionts hiring had been the\nsole official act to survive this Court’s interpretation of\n 89\n\fMcDonnell, there would still be sufficient evidence to\nconvict Fattah and Vederman. Zionts did not receive\nwritten notice of her official hiring until six days after the\nsham Porsche purchase. Moreover, the jury would not be\nrestricted to considering the chronology of the sham\npurchase alone. It would be free to consider Vederman’s\nentire course of conduct. Under the general heading\n“VEDERMAN’S Payments and Things of Value to\nFATTAH,” the redacted indictment not only refers to the\n$18,000 wire transaction from Vederman to Fattah as part\nof the sham Porsche purchase, but also to Vederman’s\n$3,000 payment for the college tuition of Simone Muller,\nFattah’s live-in au pair, as well as thousands of dollars in\npayments made by Vederman for Chip Fattah’s college\ntuition. JA496–97.\n And the Zionts hiring is not the only act to survive\nour application of McDonnell. As we explained, a jury\ncould find that Fattah’s efforts to secure Vederman an\nambassadorship—three emails, two letters, and a phone\ncall—were an impermissible attempt to “pressure or\nadvise” President Obama, Senator Casey, or both men.17\n\n17\n Although Fattah’s efforts to secure Vederman an\nambassadorship present a jury question that is not for us to\nanswer on appeal, we note that not one of these efforts\nalone could qualify as an official act itself. See McDonnell,\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\nanother official, or organizing an event (or agreeing to do\nso)—without more—does not fit that definition of ‘official\n 90\n\fThis means that a properly instructed jury on remand,\npresented with evidence of Fattah’s efforts to secure an\nambassadorship for Vederman and evidence of the Zionts\nhiring, could find more than a single official act.\n\n F. Blue Guardians\n In addition to the charges arising from his dealings\nwith Vederman, Fattah was charged in Count 3 with\n\n\nact.’ ”). The relevant question for a jury to consider on\nremand, then, is whether these actions constituted “a\n‘decision or action’ on a different question or matter”—to\nwit, the formal appointment of an ambassador. Id. at 2369\n(emphasis omitted).\n Even though the emails, letters, and phone call are\nnot, individually, official acts, it will be for a jury to decide\nif Fattah’s efforts to secure an ambassadorship for\nVederman crossed the line from permissible “support” to\nimpermissible “pressure or advice.” While we express\ndoubt that some of Fattah’s efforts concerning the\nambassadorship are, when considered in isolation, enough\nto cross that line, a properly instructed jury considering all\nof the facts in context might nonetheless conclude that\nother efforts—such as a hand-delivered letter to the\nPresident of the United States—indeed crossed that line.\nFurther, a jury might find that in the aggregate, three\nemails, two letters, and a phone call crossed the line and\ntherefore constituted a “decision or action” on the\nidentified matter of appointment.\n 91\n\fparticipating in a scheme with Lindenfeld to funnel money\nto a fraudulent nonprofit organization. In connection with\nthis scheme, Fattah was convicted of conspiring to commit\nhonest services fraud.\n\n Fattah owed Lindenfeld nearly $100,000 for work\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\nrepayment, Fattah suggested that Lindenfeld create an\nentity, later named Blue Guardians, to which Fattah would\ndirect $15,000,000 in public funds by using his position as\na member of the House Committee on Appropriations.\nNothing in McDonnell requires us to upset Fattah’s\nconviction on Count 3.\n Step 1(A) of our McDonnell analysis requires the\nGovernment to “identify a ‘question, matter, cause, suit,\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\n“matter” is the appropriation of millions of dollars in\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\nawarding of redevelopment funds to be an official act). In\nparticular, it was Fattah’s promise to perform this official\nact that was unlawful. As McDonnell makes clear:\n\n [A] public official is not required to actually\n make a decision or take an action on a\n “question, matter, cause, suit, proceeding or\n controversy”; it is enough that the official\n agree to do so. The agreement need not be\n explicit, and the public official need not\n specify the means that he will use to perform\n his end of the bargain.\n 92\n\f136 S. Ct. at 2370–71 (internal citations omitted). That\nFattah took steps to actually carry out his promise (e.g., by\ndrafting and sending a formal appropriations request on\nofficial congressional letterhead) is evidence of his illegal\npromise. See id. at 2371.\n\n Step 1(B) requires the Government to establish that\nthe “ ‘question, matter, cause, suit, proceeding or\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\nlaw be brought’ before a public official.” McDonnell, 136\nS. Ct. at 2368. Appropriating public funds was not only a\nmatter that was pending before Fattah as a member of the\nAppropriations Committee, it was also a matter that was\npending before the Chairman and Ranking Member of an\nAppropriations Subcommittee to whom Fattah ultimately\nsent a formal written request. See id. at 2369 (“[T]he\nmatter may be pending either before the public official\nwho is performing the official act, or before another public\nofficial.”). Appropriating millions of dollars in response to\nthe Blue Guardians request is “focused and concrete,” and\n“the kind of thing that can be put on an agenda, tracked for\nprogress, and then checked off as complete.” Id.\n\n Given Fattah’s membership on the Appropriations\nCommittee, this was “something within the specific duties\nof an official’s position—the function conferred by the\nauthority of his office.” Id. Even if we were to assume,\nagainst all reason, that an appropriation is not “something\nwithin the specific duties” of either Fattah or the Chairman\nor Ranking Member of an Appropriations Subcommittee,\n\n 93\n\fFattah’s formal request for an appropriation was\nsomething that Fattah had the authority to do. Like the\nExecutive Director in Repak, who lacked authority himself\nto award redevelopment funds but could request such\nfunds from the Board, Fattah used his position as a\nCongressman to formally request appropriations for the\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\nto, and indeed did, make recommendations to the\n[redevelopment authority.\n Step 2 of McDonnell requires the Government to\n“prove that the public official made a decision or took an\naction ‘on’ that question, matter, cause, suit, proceeding,\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\n(emphasis added). Here, Fattah agreed to request an\nappropriation for a bogus purpose. Unlike Fattah’s letters,\nemails, and phone call seeking an ambassadorship for\nVederman, there is no potential for the jury to have made\na mistake when it found Fattah’s Blue Guardians promise\nunlawful.\n Fattah argues that the Government presented “[n]o\nevidence . . . that would have allowed [the jury] to\nconclude that [he] made a decision or took an action, or\ncould have done so, on the question whether Blue\nGuardians would receive a $15 million federal grant.”\nFattah Br. 46. This argument misses the point. It was\nFattah’s agreement to engage in the official act of formally\nrequesting the appropriation that was illegal. See\nMcDonnell, 136 S. Ct. at 2371.\n\n 94\n\f Lindenfeld’s trial testimony provided sufficient\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\nFattah’s letter provided additional evidence from which\nthe jury could have concluded that Fattah illegally agreed\nto perform an official act. 18 In short, the agreement itself\nwas illegal, and the Government provided sufficient\nevidence for the jury to conclude that the illegal agreement\ntook place.\n\n The Government’s evidence in support of the Blue\nGuardians scheme meets the requirements of McDonnell,\nand the Count 3 verdict will stand.\n\n V. Sufficiency of the Evidence for the RICO\n Conspiracy Conviction\n The jury found Fattah, Vederman, Brand, and\nNicholas guilty of the RICO conspiracy charged in Count\n1 of the indictment, but acquitted Bowser. Vederman filed\na post-verdict motion, and the District Court overturned\nhis RICO conspiracy conviction.\n\n\n\n18\n Despite Fattah’s protestation to the contrary, there is\nevidence that Fattah took steps to carry out his official act.\nJA6432–33 (Letter from Congressman Fattah to House\nAppropriations Subcommittee members “request[ing]\nfunding and support for the following projects and\nprograms of critical importance,” including $3,000,000\nfor “Blue Guardians”).\n 95\n\f On appeal, Fattah, Brand, and Nicholas challenge\nthe sufficiency of the evidence supporting their RICO\nconspiracy convictions. We “review[] the sufficiency of\nthe evidence in the light most favorable to the government\nand must credit all available inferences in favor of the\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\n(3d Cir. 1998). If a rational juror could have found the\nelements of the crime beyond a reasonable doubt, we must\nsustain the verdict. United States v. Cartwright, 359 F.3d\n281, 286 (3d Cir. 2004), abrogated on other grounds by\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\nCir. 2013) (en banc).\n The indictment charged a RICO conspiracy in\nviolation of 18 U.S.C. § 1962(d), which makes it\n“unlawful for any person to conspire to violate” § 1962(c).\nSection 1962(c) provides:\n It shall be unlawful for any person . . .\n associated with any enterprise engaged in, or\n the activities of which affect, interstate . . .\n commerce, to conduct or participate, directly\n or indirectly, in the conduct of such\n enterprise’s affairs through a pattern of\n racketeering activity . . . .\n\n18 U.S.C. § 1962(c).\n\n In Salinas v. United States, 522 U.S. 52 (1997), the\ndefendant was convicted of a § 1962(d) RICO conspiracy,\nbut a jury acquitted him of the substantive RICO offense\n 96\n\funder § 1962(c). Id. at 55. The Supreme Court rejected\nSalinas’s contention that his conviction had to be set aside\nbecause he had neither committed nor agreed to commit\nthe two predicate acts required for the § 1962(c) offense.\nId. at 66. The Court declared that liability for a RICO\nconspiracy under § 1962(d), “unlike the general\nconspiracy provision applicable to federal crimes,” does\nnot require proof of an overt act. Id. at 63. A conspiracy\nmay be found, the Court explained, “even if a conspirator\ndoes not agree to commit or facilitate each and every part\nof the substantive offense. The partners in the criminal\nplan must agree to pursue the same criminal objective and\nmay divide up the work, yet each is responsible for the acts\nof each other.” Id. at 63–64 (citations omitted). This means\nthat, if a plan “calls for some conspirators to perpetrate the\ncrime and others to provide support, the supporters are as\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\nparticipating in a conspiracy may result in criminal\nliability for the acts of one’s co-conspirators. Smith v.\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\n Accordingly, liability for a RICO conspiracy may\nbe found where the conspirator intended to “further an\nendeavor which, if completed, would satisfy all of the\nelements of a substantive criminal offense, but it suffices\nthat he adopt the goal of furthering or facilitating the\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\nsubstantive criminal offense here was conducting a\n§ 1962(c) enterprise, the government had to prove:\n\n 97\n\f (1) that two or more persons agreed to\n conduct or to participate, directly or\n indirectly, in the conduct of an enterprise’s\n affairs through a pattern of racketeering\n activity; (2) that the defendant was a party to\n or member of that agreement; and (3) that the\n defendant joined the agreement or conspiracy\n knowing of its objective to conduct or\n participate, directly or indirectly, in the\n conduct of an enterprise’s affairs through a\n pattern of racketeering activity.\n\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\n2014).\n In United States v. Turkette, 452 U.S. 576 (1981),\nthe Supreme Court instructed that an enterprise is a “group\nof persons associated together for a common purpose of\nengaging in a course of conduct.” Id. at 583. The\ngovernment can prove an enterprise “by evidence of an\nongoing organization, formal or informal, and by evidence\nthat the various associates function as a continuing unit.”\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\nSupreme Court established that an “association-in-fact\nenterprise must have at least three structural features: a\npurpose, relationships among those associated with the\nenterprise, and longevity sufficient to permit these\nassociates to pursue the enterprise’s purpose.” Id. at 946.\nThe structure necessary for a § 1962(c) enterprise is not\ncomplex. Boyle explained that an enterprise\n\n 98\n\f need not have a hierarchical structure or a\n “chain of command”; decisions may be made\n on an ad hoc basis and by any number of\n methods—by majority vote, consensus, a\n show of strength, etc. Members of the group\n need not have fixed roles; different members\n may perform different roles at different\n times. The group need not have a name,\n regular meetings, dues, [or] established rules\n and regulations . . . .While the group must\n function as a continuing unit and remain in\n existence long enough to pursue a course of\n conduct, nothing in RICO exempts an\n enterprise whose associates engage in spurts\n of activity punctuated by periods of\n quiescence.\n\nId. at 948.\n\n Another element of a substantive § 1962(c) RICO\nenterprise is that the enterprise must conduct its affairs\nthrough a pattern of racketeering activity. Section 1961\ndefines racketeering activity to include various criminal\noffenses, including wire fraud, 18 U.S.C. § 1344, and\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\n§ 1961(1). A pattern of such activity “requires at least two\nacts of racketeering activity.” Id. § 1961(5). The\nracketeering predicates may establish a pattern if they\n“related and . . . amounted to, or threatened the likelihood\n\n\n 99\n\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\nCo., 492 U.S. 229, 237 (1989).\n Here, the District Court denied the post-trial\nsufficiency arguments raised by Fattah, Brand, and\nNicholas. It reasoned:\n For a RICO conspiracy to exist, the\n conspirators must agree to participate in an\n enterprise with a unity of purpose as well as\n relationships among those involved. The\n evidence demonstrates that an agreement\n among Fattah, Brand, Nicholas, Lindenfeld,\n and Naylor existed for the overall purpose of\n maintaining and enhancing Fattah as a\n political figure and of preventing his standing\n from being weakened by the failure to be able\n to pay or write down his campaign debts.\n These five persons agreed to work together as\n a continuing unit, albeit with different roles.\n The Government established that\n Fattah, Brand, and Nicholas conspired along\n with Naylor and Lindenfeld to conceal and\n repay the 2007 illegal $1,000,000 loan to the\n Fattah for Mayor campaign.\n\nJA128–29. The District Court further determined that\n [w]hile each member may not have been\n involved in every aspect of the enterprise, its\n activities were sufficiently structured and\n 100\n\f coordinated to achieve the purpose of\n maintaining and enhancing Fattah’s political\n standing and of preventing him from being\n weakened politically because of his\n campaign debts.\n A RICO conspiracy also requires an\n agreement to participate in an enterprise with\n longevity sufficient to pursue its purpose.\n This was established. In May 2007 the illegal\n loan was obtained and continued through its\n repayment in January 2008 and into at least\n 2014 when the last campaign report reducing\n a fake campaign debt to Naylor’s consulting\n firm was filed by Fattah.\nJA131.\n\n The defendants argue that the evidence is\ninsufficient to show either an enterprise for purposes of\n§ 1962(c) or an agreement as required for a § 1962(d)\nconspiracy. We disagree, and conclude that the District\nCourt’s analysis is on the mark.\n\n We begin by considering whether there was an\nagreement. The evidence showed that Fattah knew each\nmember involved in the scheme to conceal the unlawful\ncampaign loan. When Lindenfeld learned of the $1 million\nloan, he informed Fattah that it exceeded campaign\nfinance limits. In short, the transaction was unlawful, and\nthe two knew it. The transaction nonetheless went\nforward, disguised as a loan, with Lindenfeld executing\n 101\n\fthe promissory note as Strategies’ officer and obligating\nStrategies to repay Lord $1 million. The concealment\nefforts continued as Lindenfeld funneled a substantial\nportion of the loan proceeds to Naylor for get-out-the-vote\nefforts. After the losing campaign, Lindenfeld spoke with\nFattah and Naylor about accounting for the funds that had\nbeen spent. They decided not to include the amounts in the\nFFM campaign reports. Fattah instructed Naylor to\nprepare a fictitious invoice, and Naylor complied. The\nFFM campaign reports filed from 2008 to 2014 disclosed\nnothing about the unlawful $1 million loan. Instead, they\nfalsely showed that Naylor’s consulting firm made yearly\nin-kind contributions of $20,000 in debt forgiveness, when\nin reality there was no debt to forgive.\n As Lindenfeld fretted over repaying the $600,000\nbalance of the Lord loan, Naylor assured him that Fattah\nhad promised to take care of the repayment. And the\nevidence supports an inference that Fattah recruited both\nNicholas and Brand in doing so. As EAA’s director,\nNicholas could fund the repayment. Brand, through his\ncompany, Solutions, acted as the middleman: he received\nthe payment from EAA pursuant to a fictitious contract,\nand then forwarded the balance due to Strategies pursuant\nto yet another fictitious contract. Nicholas and Brand\ncontinued in the spring and summer of 2008 to hide the\nfictitious agreement and the $600,000 payment to\nLindenfeld to satisfy the Lord loan.\n\n\n\n 102\n\f In short, this evidence shows that Fattah,\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\nparticipate in Fattah’s plan to conceal the unlawful\ncampaign loan to maintain his political stature. Nicholas\nand Brand claim that they had no knowledge of the false\ncampaign reporting aspect of the plan. But as Salinas\ninstructs, conspirators need not “agree to commit or\nfacilitate each and every part of the” conspiracy. 522 U.S.\nat 63. Rather, they “must agree to pursue the same criminal\nobjective and may divide up the work, yet each [be]\nresponsible for the acts of each other.” Id. at 63–64. Thus,\na conspirator may agree to “facilitate only some of the acts\nleading to the substantive offense” yet still be criminally\nliable. Id. at 65.\n The evidence showed that a substantial amount of\nmoney was needed to repay Lord, and that the source of\nthe repayment was EAA, a non-profit organization whose\nfunds could be spent only for purposes consistent with the\nterms of the grants it received. It also showed that Nicholas\nwas presented with a sham contract to legitimize the\nEAA–Solutions transaction. We conclude that the\nevidence is sufficient to support an inference that Nicholas\nknew at the start that the plan was unlawful. Yet she still\nagreed to provide the requisite funds and to play a role in\nconcealing the illegal campaign loan so that Fattah could\nmaintain his political stature.\n\n As to Brand, even if he did not know that false\ncampaign reports were being filed, the evidence is\n\n 103\n\fsufficient to show he played a key role in the enterprise.\nFrom the outset, Brand worked to disguise the repayment\nof the Lord loan as the consideration in a sham contract\nbetween EAA and Solutions. He then arranged for the\ntransfer of funds to Strategies in satisfaction of a\ncontractual term in another purported business agreement\nbetween Solutions and Strategies. The evidence reveals\nthat Brand was the point man in the effort to meet the\nJanuary 31, 2008 deadline to repay the Lord loan, and it\namply shows that Brand also agreed to participate in the\nplan to hide the illegal campaign loan and its repayment to\nbenefit Fattah politically.\n Fattah, Brand, and Nicholas attack their RICO\nconspiracy convictions on another front. They argue that\nthose verdicts should be set aside because the evidence\nfails to show that the various schemes alleged in the\nindictment as part of the RICO conspiracy are connected.\nThe RICO count, they assert, charges a hub-and-spoke\nconspiracy that is unconnected by a rim. In their view,\nFattah is the hub, and the spokes consist of a series of\nindependent schemes: the Vederman bribery scheme, the\npayment of the outstanding tuition debt of Fattah’s son\nChip, the Blue Guardians plan, and the repayment of the\nillegal Lord loan to maintain Fattah’s political stature.\nThey argue that, without a unifying rim, their actions\ncannot constitute an enterprise. Again, we disagree.\n\n In In re Insurance Brokerage Antitrust Litigation,\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\n\n 104\n\fone of plaintiffs’ RICO claims, that the alleged hub-and-\nspoke enterprise—comprised of broker hubs and insurer\nspokes—could not withstand a motion to dismiss because\nit did not have a unifying rim. Id. at 374. We explained\nthat the allegations did “not plausibly imply concerted\naction—as opposed to merely parallel conduct—by the\ninsurers, and therefore cannot provide a ‘rim’ enclosing\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\nenterprises.” Id. Thus, the allegations did not “adequately\nplead an association-in-fact enterprise” because the hub-\nand-spoke conspiracy failed to “function as a unit.” Id.\n\n That is not the case here. The evidence showed that\nFattah, Brand, and Nicholas agreed to conceal the illegal\nLord loan. Each acted for the common purpose of\nfurthering Fattah’s political interests. In short, they\nengaged in concerted activity and functioned as a unit. The\njury convicted Fattah, Brand, and Nicholas of the RICO\nconspiracy based on the racketeering activity of wire fraud\nand obstruction of justice to conceal the unlawful\ntransaction. Because the evidence shows that Fattah,\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\nFattah’s political status by acting to maintain the secrecy\nof the unlawful Lord loan, the alleged lack of a unifying\n“rim” is not fatal to this RICO enterprise. What matters in\nanalyzing the structure of this enterprise is that it\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\nrequirement” was met. Id.\n\n 105\n\f We turn next to the contention that the evidence\nfails to establish other components of an enterprise. We\nconclude that much of the evidence supporting the\nexistence of an agreement also shows that there was an\nassociation-in-fact enterprise.\n\n Boyle made clear that an association-in-fact\nenterprise must have “a purpose, relationships among\nthose associated with the enterprise, and longevity\nsufficient to permit these associates to pursue the\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\nhave repeatedly observed, was to maintain and preserve\nFattah’s political stature by concealing the illegal loan and\nits repayment. Though informal, there were relationships\namong those associated with the enterprise. Fattah was at\nthe center of this association and he directed its activity.\nHe knew each of the association’s members, and the\nmembers knew each other (except, perhaps, for Nicholas,\nwho may not have known Lindenfeld).19\n\n\n19\n Nicholas’s lack of familiarity with Lindenfeld does not\nundermine her membership in this association-in-fact\nenterprise. We have previously explained that “[i]t is well-\nestablished that one conspirator need not know the\nidentities of all his co-conspirators, nor be aware of all the\ndetails of the conspiracy in order to be found to have\nagreed to participate in it.” United States v. Riccobene, 709\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\nby Griffin v. United States, 502 U.S. 46 (1991).\n 106\n\f The Government also adduced sufficient proof of\nthe longevity component required for an enterprise. The\nscheme began in mid-2007, when Lord made the\ncampaign loan, directing the proceeds of the loan to\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\nall knew they needed to conceal this illegal transaction.\nThey began by fabricating an explanation for the source of\nthe funds they spent on election day. SLA created a fake\ninvoice for the campaign, showing a fictitious debt that\nNaylor could later forgive by fictitious in-kind\ncontributions existing only on Fattah’s campaign finance\nreports.\n The effort to disguise the Lord loan was not limited\nto filing false campaign reports. Nicholas and Brand, who\njoined the conspiracy a few months later than the other\nmembers, understood that they too had to make the\nfraudulent $600,000 payment by EAA to Solutions appear\nlegitimate. Nicholas and Brand tried to disguise the sham\ncontract as an ordinary transaction (even though it called\nfor a six-figure upfront payment simply to support\nSolutions’ various projects), and they succeeded in\nkeeping it out of the DOJ auditors’ view until August\n2008. The ruse continued as Solutions funneled the\n$600,000 payment to Strategies under the guise of another\nsham contract (which also required an upfront six-figure\npayment). The scheme then continued as Fattah submitted\nfalse FFM campaign reports from 2008 through 2014.\n\n\n\n 107\n\f Finally, we consider whether the enterprise\nconducted its affairs through a pattern of racketeering\nactivity, as required for a § 1962(c) enterprise. Wire fraud\nand obstruction of justice may constitute “racketeering\nactivity” under § 1961(1). As the Supreme Court\ninstructed in H.J. Inc., the “multiple predicates within a\nsingle scheme” must be related and “amount[] to, or\nthreaten[] the likelihood of, continued criminal activity.”\n492 U.S. at 237. Here, the amount of the illegal loan to be\nconcealed was substantial. The enterprise needed to write\noff the fictitious debt to Naylor’s consulting firm, and it\nwas urgent that both the EAA–Solutions contract and the\nSolutions–Strategies contract be legitimized. We conclude\nthe evidence was sufficient to establish that this enterprise\nconducted its affairs through a pattern of racketeering\nactivity and that the predicate acts of wire fraud and\nobstruction of justice were related. The racketeering\nactivity furthered the goals of maintaining the secrecy of\nthis $1 million illicit campaign loan and of preserving\nFattah’s political stature.\n Nicholas contends that the evidence fails to\nestablish a pattern of racketeering activity because the\nactions to which she agreed did not “extend[] over a\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\nat 242. That case indeed instructs that the continuity\nrequirement of a pattern is a “temporal concept,” and that\n“[p]redicate acts extending over a few weeks or months”\ndo not satisfy the continuity concept. Id. But the Supreme\nCourt explained that continuity may also be established by\n 108\n\fshowing that there is a “threat of continued racketeering\nactivity.” Id. Here, the course of fraudulent conduct\nundertaken to secure and to conceal the $1 million Lord\nloan consisted of the creation of sham debts, fictitious\ncontracts, and false accounting entries over the course of\nabout a year. But because Fattah needed to appear able to\nretire his campaign debt, the enterprise needed to continue\nfiling false campaign reports for several years, allowing\nthe annual $20,000 in-kind debt forgiveness contributions\nto appear to satisfy Naylor’s fake $193,000 invoice. That\nevidence was sufficient to establish the requisite threat of\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\n43.\n We conclude that the Government met its burden in\nproving that Fattah, Brand, and Nicholas 20 engaged in a\nRICO conspiracy in violation of § 1962(d).\n\n\n20\n Nicholas also asserts, in passing, that that her conviction\nunder § 1962(d) should be set aside because that statutory\nprovision is unconstitutionally vague as applied to her.\nAccording to Nicholas, a person of ordinary intelligence\nwould not know that her actions constituted an agreement\nto participate in a RICO enterprise. See United States v.\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\ncontrary, a person of ordinary intelligence, who had been\nemployed by a prominent politician and then became the\nCEO of a nonprofit organization which that politician had\nfounded (and, to some extent, continued to direct), would\n 109\n\f VI. Variance from the Indictment and Sufficiency of\n the Evidence for Count 2\n Brand and Nicholas challenge their convictions for\nconspiracy to commit wire fraud by arguing that the\nGovernment’s evidence at trial impermissibly varied from\nthe indictment. Nicholas also challenges the sufficiency of\nthe evidence to support her conviction for conspiracy to\ncommit wire fraud. We address these contentions\ntogether. 21\n\n Count 2 of the indictment alleged a single\nconspiracy. JA277–79. Brand and Nicholas assert that the\nGovernment’s evidence at trial did not support the\nexistence of a single conspiracy but instead showed two\nindependent conspiracies, only one of which involved the\ntwo of them. According to Brand and Nicholas, the only\nconspiracy with which they were involved ended more\nthan five years before the Government charged them. That\nwould mean that all their conduct falls outside the five-\nyear limitations period for wire fraud conspiracy under 18\nU.S.C. § 3282.\n\n\nrealize that agreeing to participate with others in hiding an\nunlawful campaign loan of $1 million could constitute an\nunlawful RICO conspiracy.\n21\n In her briefing, Nicholas discusses variance in far less\ndetail than Brand, so we refer primarily to Brand’s\narguments. See Nicholas Br. 54–56. Her variance\narguments fail for the same reasons that Brand’s fail.\n 110\n\f “A conviction must be vacated when (1) there is a\nvariance between the indictment and the proof presented\nat trial and (2) the variance prejudices a substantial right\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\nno variance, and will affirm the District Court.\n A variance exists “if the indictment charges a single\nconspiracy while the evidence presented at trial proves\nonly the existence of multiple conspiracies.” Id. “We must\ndetermine ‘whether there was sufficient evidence from\nwhich the jury could have concluded that the government\nproved the single conspiracy alleged in the indictment.’ ”\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\nthe light most favorable to the Government, we consider\nthree factors: (1) “whether there was a common goal\namong the conspirators”; (2) “whether the agreement\ncontemplated bringing to pass a continuous result that will\nnot continue without the continuous cooperation of the\nconspirators”; and (3) “the extent to which the participants\noverlap in the various dealings.” Id. (quoting Kelly, 892\nF.2d at 259).\n\n Brand argues that the Government failed to\nestablish a common goal among the conspirators. To\ndetermine whether the conspirators shared a common\ngoal, “we look to the underlying purpose of the alleged\ncriminal activity” in a fairly broad sense. United States v.\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\nRigas, we described the common goal of the defendants as\n\n 111\n\f“enriching [themselves] through the plunder of [their\ncorporate employer],” id., and we have similarly\narticulated the common goal in fairly general terms\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\n93 (3d Cir. 2007) (“There was certainly evidence of a\ncommon goal among these co-conspirators: to make\nmoney by depositing stolen and altered corporate checks\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\ncommon goal of all the participants was simply to make\nmoney selling ‘speed.’ ”). Importantly, a common goal\nmay exist even when “conspirators individually or in\ngroups perform different tasks in pursuing the common\ngoal,” and a single conspiracy may “attract[] different\nmembers at different times” or “involve[] different sub-\ngroups committing acts in furtherance of the overall plan.”\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\n\n Here, the indictment described the purpose of the\nunified conspiracy in Count 2 at length:\n\n It was a purpose of the conspiracy to obtain\n an illegal campaign loan and to fraudulently\n repay that loan with hundreds of thousands of\n dollars of misappropriated charitable funds\n from Sallie Mae and federal grant funds from\n NASA which were intended for educational\n purposes.\n\n . . . . It was further a purpose of the\n conspiracy to present FATTAH to the public\n as a perennially viable candidate for public\n 112\n\f office who honored his obligations to his\n creditors and was able to retire his publicly\n reported campaign debts.\n . . . . It was further a purpose of the\n conspiracy to promote FATTAH’s political\n and financial goals through deception by\n concealing and protecting the conspirators’\n activities from detection and prosecution by\n law enforcement officials and the federal\n judiciary, as well as from exposure by the\n news media, through means that included\n obstruction of justice and the falsification of\n documents, including Campaign Finance\n Reports, false invoices, contracts, and other\n documents and records.\n\nJA277–78, ¶¶ 3–5.\n Brand characterizes the evidence at trial as\nestablishing two distinct conspiracies. The first he labels\nthe “diversion of funds scheme,” covering the\nmisappropriation of funds by Nicholas, Brand,\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\n34. Brand calls the second conspiracy the “CFR scheme,”\nin which Fattah and Naylor filed the false campaign\nfinance reports showing Naylor gradually forgiving a non-\nexistent debt. Id.\n Brand argues that the only goal of the CFR scheme\nwas to cover up how the funds from the illegal campaign\n 113\n\floan were spent, a goal he distinguishes from that of the\ndiversion of funds scheme, which he characterizes as a\nplan to cover up the repayment of the loan with stolen\nfunds. He also argues that the evidence does not establish\nhe was involved in, or even aware of, the false campaign\nfinance reports filed by Fattah. In Brand’s view, that\nnecessarily means the evidence showed two separate\nconspiracies.\n\n In considering these arguments, we begin by noting\nthat one conspiracy can involve multiple subsidiary\nschemes. Rigas, 605 F.3d at 214. It is true that the false\ncampaign finance reports, in the narrowest sense, had the\nspecific purpose of covering up how the illegal loan funds\nwere used during the election. But the false campaign\nfinance reports were also filed in furtherance of a broader\ngoal shared by the conspirators involved in repayment of\nthe Lord loan. They sought to promote Fattah’s political\nand financial goals by preserving his image as a viable\ncandidate and making him appear able to repay or\notherwise service his campaign debts without resorting to\nillegal means in doing so. The two subsidiary schemes\nworked in concert in furtherance of this overarching goal,\nand both were directed at covering up how the loan was\ntruly repaid. The “diversion of funds scheme” hid the\nillegal (but real) loan repayment through the use of fake\ncontracts; the “CFR scheme” showed the seemingly legal\n(but fake) loan forgiveness installments through the\ncreation of fake invoices and campaign finance reports.\nThe existence of two concealment schemes acting in\n 114\n\fconcert does not undermine the unity of the conspiracy of\nwhich they were both a part. We have no difficulty\nconcluding that the false campaign finance reports and the\nconcealed use of stolen funds to repay the Lord loan\noperated together in furtherance of a common goal.\n\n As for Brand’s argument that he was unaware of the\nfalse campaign finance reports and therefore could not be\na part of any conspiracy involving them, it is well-settled\nthat “each member of the charged conspiracy is liable for\nthe substantive crimes his coconspirators commit in\nfurtherance of the conspiracy even if he neither\nparticipates in his co-conspirators’ crimes nor has any\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\nU.S. 640 (1946)). The exceptions to that rule allow a\ndefendant to escape liability for a co-conspirator’s crime\nif: (1) “the substantive offense committed by one of the\nconspirators was not in fact done in furtherance of the\nconspiracy,” (2) “the substantive offense committed by\none of the conspirators ‘did not fall within the scope of the\nunlawful project,’ ” or (3) “the substantive offense\ncommitted by one of the conspirators ‘could not be\nreasonably foreseen as a necessary or natural consequence\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\nU.S. at 647–48). There was, as we have concluded, a unity\nof purpose between the co-conspirators to further Fattah’s\npolitical and financial goals by secretly obtaining and\nrepaying an illegal campaign loan with stolen funds. The\nfiling of false campaign reports does not fit within any of\n 115\n\fthe recognized exceptions to co-conspirator liability, as it\nwas in furtherance of the conspiracy’s shared goal, within\nthe scope of the agreement to conceal the loan, and\nforeseeable to Brand and Nicholas.\n\n Neither Brand nor Nicholas briefed the other two\nfactors we consider when determining whether the\nevidence impermissibly varied from the evidence,\n“whether the agreement contemplated bringing to pass a\ncontinuous result that will not continue without the\ncontinuous cooperation of the conspirators,” and “the\nextent to which the participants overlap in the various\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\nat 258). The unified goal of promoting Fattah’s political\ncareer and maintaining secrecy surrounding the illegal\nloan and the misappropriated funds used to repay it\nrequired the continuous cooperation of the conspirators.\nIndeed, the efforts of several of them overlapped in every\naspect of the scheme. And Lindenfeld and Fattah were, at\na minimum, involved in some way in nearly every aspect\nof the origination of the loan, the false campaign finance\nreports, and the use of misappropriated funds to repay the\nloan. For his part, Naylor was involved in the use of the\nfunds, the false campaign finance reports, and to a lesser\nextent, the repayment of the loan.\n Brand (as part of his variance argument) and\nNicholas (as part of her sufficiency argument) argue that\nthe Government did not prove they agreed to conceal their\nactions, and thus the false campaign reports would not be\n\n 116\n\fsufficient to extend the duration of the conspiracy so that\nit fell within the statute of limitations. Acts of\nconcealment, such as the false campaign reports, are not\nautomatically “in furtherance” of a conspiracy. We must\ndetermine whether there was “an express original\nagreement among the conspirators to continue to act in\nconcert in order to cover up, for their own self-protection,\ntraces of the crime after its commission,” as opposed to “a\nconspiracy to conceal . . . being implied from elements\nwhich will be present in virtually every conspiracy case,\nthat is, secrecy plus overt acts of concealment.”\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\nthe indictment “specifically alleges a continuing\nconspiracy” to conceal the crime after the completion of\nthe wire fraud, and such a conspiracy can be proven, the\nstatute of limitations does not begin to run until the last\novert act of concealment. United States v. Moses, 148 F.3d\n277, 282 (3d Cir. 1998).\n\n Here, the evidence shows that the conspirators\nexpressly agreed to conceal the loan and its repayment. As\nan initial matter, Brand’s only role in the conspiracy was\nto cover up the use of stolen funds by (1) serving as an\nintermediary between Nicholas and Lindenfeld; and\n(2) agreeing to create false documentation (the contracts)\nwith both EAA and Strategies for the sole purpose of\ndisguising the payments and covering up the wire fraud\nconspiracy. Nicholas could simply have paid Lindenfeld\nherself (or paid Lord) if she and Brand had not agreed to\nconceal the crime from the start. Additionally, and as\n 117\n\fBrand acknowledges, the false campaign finance reports\nbegan before the loan was repaid, proving that\nconcealment of the crime was contemplated and begun as\na direct purpose of the conspiracy before Brand and\nNicholas became involved in the repayment. Nicholas too\nagreed to conceal the repayment, as she implicitly\nacknowledged in her emails with Brand and Fattah. GSA2.\nFinally, when Lindenfeld briefly strayed from the\nconspiracy’s commitment to secrecy by mentioning the\nrepayment in front of others who did not know of the\nscheme, Brand became “angry,” “took [Lindenfeld] out in\nthe hallway,” and chastised him, saying that “[Lindenfeld]\ncouldn’t say that sort of []thing” in front of other people.\nJA1670–71. We conclude that the evidence is consistent\nwith the allegations in the indictment, which charge a\nsingle conspiracy consisting of an original agreement to\nconceal the illegal loan and its subsequent illegal\nrepayment to further Fattah’s political career.\n\n Nicholas makes several arguments in passing. She\nsuggests that the District Court upheld the conviction after\ntrial “on a theory not submitted to the jury.” Nicholas Br.\n51. This argument is, essentially, that the indictment and\nthe District Court’s post-trial ruling described the\nconspiracy one way, but that the jury charge described the\nconspiracy differently. Nicholas argues that the jury was\npresented with the theory that the sole purpose of the false\ncampaign reports under Count 2 was to “conceal[] the\nalleged scheme to defraud,” JA5849, rather than to support\n\n 118\n\fFattah’s political career, as the District Court described the\npurpose after trial, see JA74.\n Nicholas ignores that part of the jury charge which\ninstructed that Count 2 required a finding “[t]hat two or\nmore persons agreed to commit wire fraud as charged in\nthe indictment.” JA5845 (emphasis added). The jury had\naccess to the indictment, and as Nicholas points out,\nNicholas Br. 45–46, the indictment outlines the offense in\nthe same way the District Court later described it in its\npost-trial ruling. The District Court consistently described\nthe count, and we see no reversible error.\n Nicholas also argues that the conspiracy charged in\nCount 2 has an objective—“to ‘present Fattah’ as\n‘perennially viable’ ”—and that such an objective is not\nillegal. Nicholas Br. 53. But, of course, the jury was not\ninstructed that it was illegal to be a Fattah supporter, or\neven to work on his campaign. The jury was charged\nspecifically on the crime of wire fraud.\n\n We conclude that there was no impermissible\nvariance between the indictment and the Government’s\nevidence at trial, and that there was sufficient evidence to\nsupport the convictions. We will affirm the convictions of\nBrand and Nicholas for conspiracy to commit wire fraud\nunder Count 2.\n\n\n\n\n 119\n\f VII. The District Court’s Instruction to the Jury on\n the Meaning of Intent\n Nicholas contends that the District Court\nimproperly instructed the jury by using the disjunctive\nrather than the conjunctive at one point in its definition of\nintent. When providing its final charge to the jury, the\nDistrict Court explained:\n Certain of the offenses charged in the\n indictment require that the government prove\n that the charged defendant acted intentionally\n or with intent. This means that the\n government must prove either that (1), it was\n the defendant’s conscious desire or purpose\n to act in a certain way or to cause a certain\n result; or (2), the defendant knew that he or\n she was acting in that way or it would be\n practically certain to cause that result.\n\nJA5787 (emphasis added). According to Nicholas, an\naccurate definition of intent required that the final “or” be\nan “and.” Nicholas argues that this was an error so\ngrievous as to “effectively eliminate[] the intent element\nfrom each offense of conviction.” 22 Nicholas Br. 26.\n\n\n22\n The Comment to Third Circuit Model Criminal Jury\nInstruction 5.03 makes clear that the definition of intent\nencapsulates both “specific intent” (acting “purposely” or\nwith “conscious object”) and “general intent” (acting\n 120\n\f Our review of whether a jury instruction stated the\nproper legal standard is plenary. United States v. Petersen,\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\nfailed to object to this portion of the jury charge.\nAccordingly, our review must be for plain error. See\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\n2014) (en banc).\n\n To prevail on plain error review, Nicholas must\nestablish that there was an error, that it was plain (i.e., clear\nunder current law), and that it affected her substantial\nrights (i.e., whether there is a reasonable likelihood that\nthe jury applied the challenged instruction in an\nimpermissible manner). United States v. Olano, 507 U.S.\n\n“knowingly” or “with awareness”). Although Nicholas\ndescribes the alleged error as “essentially eliminating” the\nelement of intent, we think Nicholas’s argument is better\nunderstood as a claim that the instruction given could have\npermitted a jury to conclude that she acted with only\ngeneral intent (that she was aware of what she was doing),\nwhen her crimes require specific intent (that she had an\nillegal purpose). As her brief states, “[p]lainly she\n‘knowingly’ wrote checks from EAA to [Solutions] and\nmade record entries about them; the question was whether\nshe intended to defraud EAA and NASA, or to obstruct\njustice, by doing so.” Nicholas Br. 24. We cannot agree\nwith her characterization that the instruction resulted in the\n“effective omission” of the intent element from the jury\ninstructions.\n 121\n\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\n231, 239–40 (3d Cir. 2005). If these requirements are met,\nwe may then exercise our discretion to address the error,\nbut only if we conclude that the error seriously affected the\nfairness, integrity, or public reputation of the judicial\nproceeding. United States v. Andrews, 681 F.3d 509, 517\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\n461, 467 (1997)). A failure to instruct the jury on a\nnecessary element of an offense ordinarily constitutes\nplain error, unless the instructions as a whole otherwise\nmake clear to the jury all the necessary elements of the\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\nCir. 2017).\n Nicholas acknowledges, as she must, that the\ninstruction given was a verbatim recitation of Instruction\n5.03 of the Third Circuit’s Model Criminal Jury\nInstructions. She nonetheless contends that our Model\nInstruction is erroneous. Even if we were to accept\nNicholas’s contention that the instruction is incorrect, a\nproposition we consider as highly doubtful, see Petersen,\n622 F.3d at 208 (“We have a hard time concluding that the\nuse of our own model jury instruction can constitute error\n. . . .”), we conclude that, considering the instructions as a\nwhole, the District Court clearly and specifically\ninstructed the jury on the intent element as it applied to\neach of Nicholas’s charged crimes.\n\n The disputed intent instruction was given at the\nbeginning of the final charge, explaining the general\n\n 122\n\fmeaning of the intent applicable to “[c]ertain of the\noffenses charged.”23 JA5787. The District Court went on\nto instruct the jury in specific detail on the elements of\neach of the crimes of which Nicholas was accused,\n\n\n\n\n23\n The introductory definition did not end with the\nlanguage Nicholas cites. The District Court elaborated that\nacting in good faith is a complete defense to the charges:\n\n The offenses charged in the indictment\n require proof that the charged defendants\n acted with criminal intent. If you find that a\n defendant acted in good faith that would be a\n complete defense to such a charge, because\n good faith on the part of the defendant would\n be inconsistent with his or her acting\n knowingly, willfully, corruptly, or with intent\n to defraud or intent to impede, obstruct, or\n wrongfully influence.\n\nJA5788–89 (emphasis added). This instruction\nundermines Nicholas’s claim that the jury could have\nreasonably concluded that she “ ‘knowingly’ wrote\nchecks” but did not “intend[] to defraud . . . or to obstruct\njustice[] by doing so,” Nicholas Br. 24, as this instruction\nleaves little room for doubt that good faith is at odds with\n“criminal intent.”\n\n 123\n\fexplaining also the intent element of each. 24 See JA5791\n(describing the third element of the RICO conspiracy\ncharge as: “the particular defendant and at least one other\nalleged conspirator shared a unity of purpose and the intent\nto achieve the objective of conducting or participating in\nthe conduct of an enterprise’s affairs through a pattern of\nracketeering activity”); JA5823 (regarding wire fraud,\ninstructing that the government must prove “[t]hat the\ndefendant under consideration acted with the intent to\ndefraud”); JA5838–39 (regarding obstruction of justice,\ninstructing that the defendant must have acted “with the\nintent to impair the record, document, or object’s integrity\nor availability for use in an official proceeding,” and must\nhave acted corruptly “with the purpose of wrongfully\nimpeding the due administration of justice”); JA5860\n(explaining that falsification of records requires that “the\ndefendant under consideration acted with the intent to\nimpede, obstruct or influence the investigation or proper\nadministration of a matter”). These instructions are\nconsistent with both our Model Jury Instructions and our\ncase law concerning the elements of these crimes. See\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\nof justice); United States v. Sussman, 709 F.3d 155, 168\n(3d Cir. 2013) (obstruction of justice); United States v.\n\n24\n Nicholas did not object to the knowledge and intent\ninstructions when the District Court discussed each of the\nindividual charges, and does not identify a disagreement\nwith any specific instruction on any particular charge.\n 124\n\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\n193, 216 (3d Cir. 1992) (wire fraud).\n The District Court also provided a separate\ndefinition of the knowledge element of each charge,\nillustrating the difference between knowledge and intent.\nSee JA5793 (explaining that the evidence must show that\na RICO defendant “knowingly agreed to facilitate or\nfurther a course of conduct, which if completed would\ninclude a pattern of racketeering activity”); JA5823 (wire\nfraud means that the defendant “knowingly devised a\nscheme to defraud a victim . . . by materially false or\nfraudulent pretenses”); JA5860 (falsification of records\nhas as an element “[t]hat the defendant under\nconsideration knowingly concealed, covered up, falsified\nor made false entries in a document or record”). These\ninstructions made clear that knowledge and intent are\nseparate considerations, undermining Nicholas’s\ncontention that the jury was led to believe that “knowledge\nis sufficient to prove intent.” Nicholas Br. 24.\n The District Court provided each member of the\njury with more than 100 pages of instructions before\ndeliberations began. Viewing those instructions as a\nwhole, we are satisfied that the jury was apprised of the\ncorrect meaning of intent as an element of the crimes with\nwhich Nicholas was charged, as well as the distinction\nbetween knowledge and intent. We perceive no error,\n\n\n 125\n\fmuch less error that is plain, in the District Court’s\ninstructions to the jury. 25\n\n VIII. Sending the Indictment to the Jury\n At trial, Vederman, Nicholas, and Brand objected to\nthe District Court’s decision to give the jury a redacted\ncopy of the indictment to use during its deliberations. Only\nNicholas and Brand raise this issue on appeal. In\nNicholas’s view, sending the indictment to the jury\nunfairly prejudiced her because it contained unsupported\nallegations that she had obstructed federal agencies and\nreferred to a nonexistent certification requirement for\nSallie Mae funds. Brand argues that he was prejudiced by\nthe indictment’s references to “schemes” and “fake”\ncontracts, and because it mentioned Brand’s spouse and\nthat she was a former member of Fattah’s congressional\nstaff. Nicholas and Brand together assert that the\nindictment included legal theories on which the jury was\nnot instructed. They contend that the indictment’s\nnarrative of the Government’s case set out a roadmap that\nomitted any averments relating to the defense theory and\nallowed the Government to yet again present its case. To\nbuttress that argument, Nicholas and Brand cite the\ntestimony of Juror 12, who described the jury’s initial\n\n\n\n25\n Accordingly, we need not consider the merits of\nNicholas’s argument that Model Criminal Jury Instruction\n5.03 is erroneous.\n 126\n\fdeliberations and alleged that the jurors viewed the\nindictment as evidence.\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\n1971), we held that the decision to allow “jurors to have a\ncopy of the indictment with them during their\ndeliberations . . . is a matter within the discretion of the\nDistrict Judge, subject to a limiting instruction that the\nindictment does not constitute evidence, but is an\naccusation only.” Subsequently, in United States v.\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\nacknowledged that the District Court has the power to\nredact the indictment if doing so would be appropriate to\navoid prejudice to the defendant. See also United States v.\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\ncourt may redact an indictment before submitting it to the\njury).\n\n While both Nicholas and Brand objected in general\nterms to the District Court’s decision to provide the\nindictment to the jury, they have not directed us to any\nspecific request to redact the information they now claim\nis prejudicial. And the District Court provided a limiting\ninstruction on four occasions during its charge, repeatedly\nemphasizing that the indictment was not evidence.\nJA5765, 5767, 5782, 5880. The Court instructed the jury\non its duty to base its verdict “solely upon the evidence in\nthe case.” JA5764. Just before the jury retired to\ndeliberate, the Court reiterated that the purpose of the\n\n\n 127\n\findictment is to set forth the charges, and that it is “merely\nan accusation.” JA5909.\n “[J]uries are presumed to follow their instructions\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\nour view, Juror 12’s assertion that the indictment was\nbeing considered evidence does not, standing alone,\nestablish that his fellow jurors actually did so. We reject\nthe notion that the jury, after hearing weeks of testimony\nand having viewed substantial documentary evidence,\nwent on to ignore the Court’s limiting instruction\nconcerning the indictment. 26 Accordingly, we conclude\n\n\n26\n We acknowledge that our case law provides minimal\nguidance to district courts concerning the practice of\nsending an indictment to the jury for their use during\ndeliberations. We are also aware that some courts have\ndisapproved the practice of sending the indictment out\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\nemphasize that this practice is committed to the sound\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\nour view, such an exercise of a judge’s discretion should\nbe informed by considering the nature of the case, the\nnumber of defendants, the length of the indictment, the\nextent of the factual recitation supporting the criminal\ncharges, and most importantly, whether the indictment\n(especially if lengthy and fact-laden) will be useful to the\njury, in light of the judge’s own carefully tailored jury\n 128\n\fthat the District Court did not abuse its discretion in\nsending the indictment out to the jury.\n\n IX. The District Court’s Evidentiary Rulings\n Vederman, Nicholas, and Brand each challenge\nevidentiary rulings by the District Court. We conclude that\nnone of these contentions warrants setting aside their\nconvictions.\n\n A. The District Court’s Application of Rule 404(b)\n Vederman argues that the District Court misapplied\nFederal Rule of Evidence 404(b) when it excluded\nevidence of Vederman’s prior gift-giving. 27 This Court\nreviews a district court’s application of Rule 404(b) for\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\n\ninstruction, as supplemented by a verdict slip. See Esso,\n684 F.3d at 352 n.5.\n27\n Although Rule 404(b) determinations are usually in\nresponse to attempts to introduce “bad” acts evidence,\nVederman’s attempt to introduce “good” acts of gift-\ngiving is properly analyzed under the same rule. Ansell v.\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\n2003) (“The evidence admitted in this case differs from\ngarden variety Rule 404(b) matter because it is evidence,\nnot of a prior bad act in a criminal case, but of a subsequent\ngood act in a civil case. Nonetheless, this evidence is\nencompassed by the plain text of Rule 404(b) which\naddresses ‘other . . . acts,’ not just prior bad acts.”).\n 129\n\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\n“[a]n abuse of discretion . . . when [the] district court’s\ndecision rests upon a clearly erroneous finding of fact, an\nerrant conclusion of law or an improper application of law\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\n\n Federal Rule of Evidence 404(b) provides in part:\n (b) Crimes, Wrongs, or Other Acts.\n\n (1) Prohibited Uses. Evidence of a\n crime, wrong, or other act is not\n admissible to prove a person’s\n character in order to show that on a\n particular occasion the person\n acted in accordance with the\n character.\n\n (2) Permitted Uses; Notice in a\n Criminal Case. This evidence may\n be admissible for another purpose,\n such as proving motive,\n opportunity, intent, preparation,\n plan, knowledge, identity, absence\n of mistake, or lack of accident.\nFed. R. Evid. 404(b)(1)–(2).\n\n 130\n\f At trial, Vederman sought to present a witness from\nAmerican University who would have testified that\n“Vederman agreed, on more than fifty instances, to\nfinancially assist students [at American] who needed help\nwith tuition, book money, or travel funds to visit their\nfamilies.” Vederman Br. 42 (emphasis omitted).\nAccording to Vederman, the testimony was relevant to\nrefuting the Government’s argument that he agreed to\nguarantee the tuition expenses of Fattah’s au pair as a way\nof bribing the congressman. In excluding this evidence\nunder Rule 404(b), the District Court stated at sidebar:\n\n I sustain the government’s objection to\n calling a representative of American\n University to testify on behalf of Herbert\n Vederman.\n\n In my view the testimony runs afoul of\n Rule 404(b)(1) of the Federal Rules of\n Evidence. I find it to be propensity evidence.\n He or she would be testifying about Mr.\n Vederman’s financial generosity with respect\n to students of American University.\n The issue here is payment of partial\n tuition of a student at the Philadelphia\n University. I see no connection between the\n generosity at American University and the\n situation with Philadelphia University.\n\n\n 131\n\fJA4459–60. Vederman argues that because the proposed\nevidence related to Vederman’s intent, and not solely his\npropensity to perform good acts, we should conclude that\nthe District Court abused its discretion. We see no error in\nthe District Court’s ruling.\n\n Vederman challenges as arbitrary the District\nCourt’s “assertion that support for American University\nstudents is too remote from support for Philadelphia\nUniversity students” such that it constitutes inadmissible\nevidence. Vederman Reply Br. 23. This distinction was far\nfrom arbitrary. Vederman may well have financially\nsupported American University students because of\nconnections he had to that school or to the D.C.\ncommunity at large—connections Vederman did not have\nto Philadelphia University. And the excluded testimony\nappears to have described support for students Vederman\ndid not previously know. By supporting Fattah’s au pair,\nVederman was helping an employee of a man whom he\nknew quite well. JA889 (“[Fattah and Vederman] spent a\nlot of time together traveling back and forth to\nWashington, in the case of a death in the family attending\ncertain ceremonies that were important, and above all\nspending time with each other and their families\ntogether.”). Vederman’s decision to help Fattah’s au pair,\nwho wished to attend Philadelphia University, seems more\nlike a departure from, rather than a continuation of, his\npattern of support for American University students.\n\n\n\n 132\n\f As the party seeking admission of evidence under\nRule 404(b), Vederman bore “the burden of demonstrating\nits applicability” and “identifying a proper purpose.”\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\n2014). By failing to explain sufficiently why the factual\ndistinctions discussed above were not material, Vederman\nfailed to meet his burden. In particular, although\nVederman argues that he offered evidence of his prior gift-\ngiving to prove intent—“a proper non-propensity\npurpose”—he failed to show why the proposed testimony\nwas “relevant to that identified purpose.” Id. at 277. 28 As\nwe noted in Ansell v. Green Acres Contracting, an\nemployment discrimination case on which Vederman\nheavily relies, “[t]here is. . . no bright line rule for\ndetermining when evidence is too remote to be relevant.”\n347 F.3d at 525. As such, a district court’s determination\nunder Rule 404(b) “will not be disturbed on appeal unless\nit amounts to an abuse of discretion.” Id. The District\n\n\n\n28\n Under Rule 404(b), “prior act evidence is inadmissible\nunless the evidence is (1) offered for a proper non-\npropensity purpose that is at issue in the case; (2) relevant\nto that identified purpose; (3) sufficiently probative under\nRule 403 such that its probative value is not outweighed\nby any inherent danger of unfair prejudice; and\n(4) accompanied by a limiting instruction, if requested.”\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\n2014).\n 133\n\fCourt did not abuse its discretion in excluding evidence of\nVederman’s support for students at American University.\n\nB. Evidentiary Rulings Regarding Nicholas’s Defense\n Nicholas argues that the District Court rendered\nthree erroneous evidentiary rulings that prejudiced her\ndefense. We do not find any of her arguments convincing.\n\n 1. The EAA Board Minutes\n In support of its theory that Nicholas defrauded\nEAA, the Government introduced minutes from EAA’s\nBoard. Minutes from 2005 revealed that the Board limited\nNicholas’s signing authority to $100,000. Minutes from\nDecember 2007, February 2008, and May 2008 failed to\nreference either the EAA–Solutions contract or the checks,\ndrawn from EAA’s account for $500,000 and $100,000,\nthat were purportedly paid pursuant to the contract.\nNicholas contends that the Board minutes were\nerroneously admitted because they constituted improper\nhearsay which failed to satisfy either the exception for\nbusiness records under Federal Rule of Evidence 803(6)\nor the absence of records exception under Federal Rule of\nEvidence 803(7). “We review the District Court’s\nevidentiary ruling[s] for abuse of discretion, but also\n‘exercise plenary review . . . to the extent [the rulings] are\nbased on a legal interpretation of the Federal Rules of\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\n(second alteration in original).\n\n 134\n\f Applying those standards here,29 we conclude there\nwas sufficient basis to admit exhibit EAA-48 under\nFederal Rule of Evidence 803(6) as a business record.\nAlthough allowing the prosecution to inquire over\nNicholas’s earlier objection based on Federal Rule of\nEvidence 803(7) to the absence of any mention of the\n$500,000 check in the 2008 Board Minutes was error, it\nwas not reversible error. Other evidence in the record\noverwhelmingly showed that Nicholas made the $500,000\nand $100,000 payments to Solutions with the requisite\nfraudulent intent. That evidence included the 2005 policy\nlimiting Nicholas’s authority to approve expenditures to\n$100,000, the accountant’s testimony about the\ndisbursement policy requiring the completion of a check\nrequest form for the issuance of a check, and Jones’\ntestimony that he never saw a request for the $500,000\ncheck. That evidence, coupled with Nicholas’s tendering\nof the upfront half-million dollar payment before the terms\nof the purported agreement had been finalized or executed,\nher failure to mention the $600,000 in payments to\nSolutions during her interview with FBI Agent\n\n29\n We note that the argument section of Nicholas’s brief on\nthis issue specifically cited to the page in the record where\nexhibit EAA-48 was admitted without objection by any\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\n82). Nonetheless, there was an earlier objection to the\nadmission of exhibit EAA-48 that was preserved and that\nwas referenced in a string citation elsewhere in Nicholas’s\nbrief.\n 135\n\fDieffenbach, and her alteration of EAA’s general ledger\nto conceal the $100,000 payment, makes it “highly\nprobable” that the jury would have reached the same\nresult. See United States v. Friedman, 658 F.3d 342, 352\n(3d Cir. 2011).\n\n Nicholas also asserts that the Board minutes were\nunfairly prejudicial. We disagree. Any possible prejudice\nwas minimized by the fact that the Board minutes make no\nreference to either the EAA–Solutions contract or to any\nfinancial matters whatsoever. Indeed, given these lacunae\nin the Government’s proof, a reasonable factfinder might\nwell have concluded that the Board’s intention to limit\nNicholas’s signing authority had not been implemented\nand that Nicholas had not concealed the contract from the\nBoard.\n\n 2. Jones’ Memory Regarding Other Contracts\n Nicholas next asserts that the District Court erred\nduring her cross-examination of Board Chairman Jones by\nsustaining the prosecution’s objection to her inquiry into\nwhether he remembered other contracts in excess of\n$100,000 being brought to the Board. See JA1386–87. The\nbasis of the prosecution’s objection seemed to be that\nNicholas’s line of inquiry was beyond the scope of the\ndirect testimony. JA1387 (“I showed checks concerning\nwhat’s going on, not other programs.”); see Fed. R. Evid.\n611(b). The District Court sustained the objection,\ndeclaring that “it has absolutely nothing to do with this\ncase.” JA1387. Nicholas contends that if Jones did not\n 136\n\frecall whether other large contracts had been presented to\nthe Board, his inability to recall the EAA–Solutions\ncontract would have been “unremarkable rather than\nevidence of fraud or concealment.” Nicholas Br. 61.\n\n We acknowledge that whether Jones remembered\nother large contracts requiring Board approval had some\nrelevance under Rule 401. Yet any error by the District\nCourt in prohibiting Nicholas’s counsel from pursuing this\nline of inquiry is harmless. Jones admitted that he did not\nknow if the Board ever implemented the policy requiring\nits approval of contracts exceeding $100,000. He also\nconceded that the EAA Board focused less on the financial\nside of EAA than on its programs. JA1383–85. Nicholas\ncould not have been prejudiced by the District Court’s\nruling.\n\n 3. Exclusion of NOAA Evidence\n Nicholas defended against the criminal charges\narising out of the non-existent October 2012 conference\nby asserting that she acted in “good faith in spending the\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\ndifference in the dates in the paperwork was not material,\nand that NOAA had received the benefits of the\nsponsorship because its logo was displayed on the signage\nused at the February conference. Nicholas succeeded in\npresenting testimony and introducing photographs that\nshowed NOAA’s logo on the February 2012 annual\nconference bags, padfolios, and name tags. The Court\nexcluded a photograph of a NOAA intern at the February\n 137\n\f2012 conference, other photographs of the February\nconference signage, and some checks that pertained to the\nFebruary conference. Nicholas claims that her inability to\nintroduce those exhibits frustrated her ability to present\nher good faith defense. We are not persuaded.\n\n The photographs were excluded as cumulative, the\nsort of ruling to which we afford trial judges very broad\ndiscretion. See Fed. R. Evid. 403; United States v.\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\nerror to exclude the student intern’s photograph. The\nconference brochure included photographs from previous\nconferences, and the witness from NOAA was unable to\ntestify to the year the student served as an intern. Finally,\nthe checks tendered for the travel expenses incurred for the\nFebruary conference were excluded as irrelevant to\nwhether Nicholas had a good faith belief that NOAA\nsponsored the October conference.\n\nC. The Cooperating Witness’s Mental Health Records\n During discovery, Brand learned that a cooperating\nwitness was diagnosed with bipolar II disorder and was\ntaking medication to treat that condition. Brand\nsubpoenaed mental health records kept by the witness’s\ncurrent and former psychiatrists in hopes of using those\nrecords to attack the witness’s memory, truthfulness, and\ncredibility. The witness and the Government both filed\nmotions to quash the subpoena, arguing that the witness’s\nmental health records were protected by the\npsychotherapist–patient privilege recognized by the\n 138\n\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\nThe Government also filed a motion in limine seeking to\nrestrict the scope of cross-examination to prevent Brand\nfrom questioning the witness about his mental health.\n\n Alongside his motion to quash, the witness\nvoluntarily produced for the Court his mental health\nrecords. The Court concluded that the psychotherapist–\npatient privilege would ordinarily apply to the mental\nhealth records, but that the privilege was not absolute,\nespecially when invoked in response to a criminal\ndefendant’s efforts to obtain through discovery evidence\nthat is favorable to his case. Following the procedure set\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\nDistrict Court conducted an in camera review of the\nmental health records to determine if they contained\nmaterial evidence—that is, evidence that would “give[]\nrise to a reasonable probability that it [would] affect the\noutcome of the case.” JA149. The District Court found\n“nothing in the mental health records of the [witness] . . .\nmaterial for this criminal action,” noting that “[t]he\nrecords reveal nothing that calls into question [the\nwitness’s] memory, perception, competence, or veracity.”\nJA150. Accordingly, the Court entered an order granting\nthe motions to quash the subpoena.\n The District Court also granted the Government’s\nmotion in limine and restricted the scope of cross-\nexamination, ruling that “no reference may be made to [the\nwitness’s] bipolar disorder or the medications he takes to\n\n 139\n\fmanage it.” JA142, 156. The Court reasoned that bipolar\ndisorder varied in its effects from person to person, and\nconcluded that Brand had not shown that the effects of the\ndisorder had any bearing on the witness’s credibility. The\nDistrict Court ruled that cross-examination would not\nserve any valid impeachment purpose.\n Brand claims that the District Court’s order ran\nafoul of the Due Process Clause of the Fifth Amendment\nand the Confrontation Clause of the Sixth Amendment.\nWe review a district court’s rulings to quash a subpoena\nand to limit the scope of cross-examination for abuse of\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\nCir. 1992). Here, the District Court did not abuse that\ndiscretion.\n\n1. The District Court’s Denial of Access to the Mental\n Health Records\n In claiming that the District Court’s decision to\nreview the mental health records in camera before ruling\non their admissibility violated his rights under both the\nFifth and Sixth Amendments, Brand specifically argues\nthat his right to confront the witness was impeded because\nhe was denied access to records he could have used to\nimpeach the witness. This very argument was considered\nand rejected by a plurality of the Supreme Court in Ritchie,\nwhich noted that “the effect [of the argument] would be to\ntransform the Confrontation Clause into a constitutionally\ncompelled rule of pretrial discovery. . . . [T]he right to\n 140\n\fconfrontation is a trial right, designed to prevent improper\nrestrictions on the types of questions that defense counsel\nmay ask during cross-examination.” 480 U.S. at 52. We\nfollow the Ritchie plurality, and conclude that the\nConfrontation Clause did not require the District Court to\ngrant Brand access to the witness’s mental health records.\n Brand next challenges the District Court’s decision\nto quash the subpoena as a violation of the Fifth\nAmendment’s Due Process Clause. He concedes that\nRitchie’s Due Process holding allowed the District Court\nto review the mental health records in camera without\ndisclosing them to him. See id. at 59–60 (“A defendant’s\nright to discover exculpatory evidence does not include the\nunsupervised authority to search through [the\nGovernment’s] files. . . . We find that [the defendant’s]\ninterest . . . in ensuring a fair trial can be protected fully by\nrequiring that the [privileged] files be submitted only to\nthe trial court for in camera review.”). Brand instead\nargues that the District Court abused its discretion by\nfocusing on “irrelevant facts and spurious symptoms. . . .\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\nevidence of cognitive impairment and memory issues.”\nBrand Br. 30. The record reveals, however, that the\nDistrict Court reviewed the mental health records and\ndetermined that they “reveal[ed] nothing that calls into\nquestion [the witness’s] memory, perception, competence,\nor veracity.” JA150. This hardly amounts to a refusal to\nconsider evidence of cognitive impairment or memory\nissues.\n 141\n\f Brand also challenges the legal standard applied by\nthe District Court, arguing that the court “focused solely\non whether disclosure would ‘change the outcome’ of\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\nconsidering “whether the ultimate verdict is one ‘worthy\nof confidence.’ ” Id. (quoting United States v. Robinson,\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\nmisleadingly quotes from the District Court’s opinion. The\nDistrict Court considered, in accordance with Ritchie,\n“whether there is a reasonable probability that disclosure\nwould change the outcome” of Brand’s trial, JA148\n(emphasis added), not whether disclosure would\nnecessarily change the outcome. As articulated in Ritchie,\na “ ‘reasonable probability’ is a probability sufficient to\nundermine confidence in the outcome.” 480 U.S. at 57\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\n(Blackmun, J.)). The District Court applied the correct\nstandard.\n\n2. The District Court’s Grant of the Motion in Limine\n In granting the Government’s motion in limine, the\nDistrict Court ruled that Brand could not “reference . . .\n[the witness’s] bipolar disorder or the medications he takes\nto manage it.” JA156. Yet that ruling placed no restriction\non Brand’s ability to cross-examine the witness with\nrespect to “his memory, competence, or truthfulness.” Id.\nBrand argues, nevertheless, that his Sixth Amendment\nright “to be confronted with the witnesses against him”\nwas violated. U.S. Const. amend. VI.\n\n 142\n\f The Confrontation Clause protects a defendant’s\nright to cross-examine a witness with respect to any\ntestimonial statements made by that witness. United States\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\nthe scope of cross-examination is not unlimited, and “[a]\ndistrict court retains ‘wide latitude insofar as the\nConfrontation Clause is concerned to impose reasonable\nlimits on such cross-examination based on concerns about\n. . . harassment, prejudice, confusion of the issues, the\nwitness’ safety, or interrogation that is repetitive or only\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\nCir. 2005)). We review limitations on cross-examination\nfor abuse of discretion, and reverse “only when the\nrestriction ‘is so severe as to constitute a denial of the\ndefendant’s right to confront witnesses against him and . . .\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\nin original) (quoting United States v. Conley, 92 F.3d 157,\n169 (3d Cir. 1996)).\n In United States v. Chandler, 326 F.3d 210, 219 (3d\nCir. 2003), we analyzed whether a district court’s decision\nto limit cross-examination with respect to a witness’s\nmotivation for testifying violated the Confrontation\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\n747 F.3d at 211–12. Consistent with Delaware v. Van\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\nexposure of a witness’ motivation in testifying is a proper\n 143\n\fand important function of the constitutionally protected\nright of cross-examination.” Chandler, 326 F.3d at 219–\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\nnoted that the Confrontation Clause does not prevent a trial\njudge from imposing reasonable limits on cross-\nexamination. Id. In reviewing a district judge’s imposition\nof such limitations, we apply a two-part analysis. As we\nhave since described, “we inquire into: ‘(1) whether the\nlimitation significantly limited the defendant’s right to\ninquire into a witness’s motivation for testifying; and\n(2) whether the constraints imposed fell within the\nreasonable limits that a district court has the authority to\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\nMussare, 405 F.3d at 169).\n The same analytical framework is appropriate when\ndetermining whether a restriction on the cross-\nexamination of a witness with respect to his memory and\nperception violates the Confrontation Clause. See Davis v.\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\n578, 582 (3d Cir. 1976). Memory and perception, like\nmotivation for testifying, are central issues affecting the\ncredibility of any witness, and unreasonable limitations on\nthe right to cross-examine on those subjects cannot be\ncountenanced. We therefore ask, paraphrasing Chandler:\n(1) whether the District Court’s decision to put the\nwitness’s diagnosis and medications off limits\nsignificantly impaired Brand’s right to inquire into the\nwitness’s memory and perception; and (2) whether the\n 144\n\fruling fell within the reasonable limits that the District\nCourt has the authority to impose.\n We conclude that the District Court did not err. As\nan initial matter, the District Court permitted Brand to\ncross-examine the witness about his memory and\nperception, and limited cross-examination only with\nrespect to the witness’s bipolar disorder and the\nmedications he was taking to treat that condition. Brand\nwas free to question the witness about his memory and\nperception, and indeed did so. The restriction on asking\nthe witness about his bipolar disorder was not a significant\nlimitation of Brand’s right to inquire into the witness’s\nmemory or perception. Moreover, as the District Court\npointed out, Brand failed to show how inquiry into the\nwitness’s bipolar disorder would be useful for\nimpeachment purposes. See JA154.\n\n Given that failure, the District Court’s limits on\ncross-examination were reasonable. The Court concluded,\nafter reviewing the evidence submitted by Brand and the\nwitness’s mental health records, that any mention of the\nwitness’s bipolar disorder would “only be designed to\nconfuse the jury or to stigmatize him unfairly because of a\n‘mental problem’ without any countervailing probative\nvalue.” JA155. The District Court did not abuse its\ndiscretion in limiting Brand’s cross-examination on a topic\nthat would be far more prejudicial than probative. See\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\n\n\n 145\n\fwell within its discretion to restrict irrelevant and\nconfusing testimony.”).\n All of this is not to suggest that a witness’s mental\nhealth is always off limits. The appropriate course in any\ngiven case must be determined from the facts and\ncircumstances surrounding that case and the witness’s\nparticular condition. See United States v. George, 532 F.3d\n933, 937 (D.C. Cir. 2008) (“The days are long past when\nany mental illness was presumed to undermine a witness’s\ncompetence to testify. . . . [M]ental illness [is] potentially\nrelevant in a broad[] range of circumstances . . . . [But]\nsome indication is needed that a particular witness’s\nmedical history throws some doubt on the witness’s\ncompetence or credibility.”). Here, Brand failed to show,\nthrough mental health records or otherwise, any\nparticularized reason to doubt the credibility of the witness\nfor medical reasons.\n\n Brand states that the witness provided “the only\nevidence offered” on the intent element of his conspiracy\nconviction and that he should therefore be entitled to\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\nmatter the importance of a witness to any party, a district\ncourt may always place reasonable limits on cross-\nexamination to avoid “harassment, prejudice, confusion of\nthe issues, the witness’ safety, or interrogation that is\nrepetitive or only marginally relevant.” John-Baptiste, 747\nF.3d at 211 (citation omitted).\n\n\n 146\n\f We conclude that the District Court did not abuse\nits discretion in restricting the scope of Brand’s cross-\nexamination of the cooperating witness.\n\n X. The Government’s Cross-Appeal\n The jury convicted Fattah, Vederman, and Bowser\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\nfalse statements to a financial institution, 18 U.S.C.\n§ 1014 31 (Count 20). In response to post-trial motions, the\nDistrict Court granted a judgment of acquittal on both\ncounts under Fed. R. Crim. P. 29, concluding that the\n\n30\n “Whoever knowingly executes, or attempts to execute,\na scheme or artifice . . . to defraud a financial institution\n. . . shall be fined not more than $1,000,000 or imprisoned\nnot more than 30 years, or both.” The definition of\n“financial institution” for purposes of § 1344 is set forth at\n18 U.S.C. § 20, and includes “a credit union with accounts\ninsured by the National Credit Union Share Insurance\nFund” and “a mortgage lending business (as defined in\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\n31\n “Whoever knowingly makes any false statement or\nreport, or willfully overvalues any land, property or\nsecurity, for the purpose of influencing in any way the\naction of . . . a Federal credit union . . . any institution the\naccounts of which are insured by . . . the National Credit\nUnion Administration Board . . . or a mortgage lending\nbusiness . . . shall be fined not more than $1,000,000 or\nimprisoned not more than 30 years, or both.”\n 147\n\fevidence was insufficient to establish that the Credit\nUnion Mortgage Association (CUMA), the entity to whom\nFattah, Vederman, and Bowser made the false statements,\nis a “financial institution,” or, more specifically, a\n“mortgage lending business” as defined in 18 U.S.C. § 27.\nThe Government claims that, viewing the evidence in the\nlight most favorable to it, the District Court erred and that\nCUMA is, indeed, a “mortgage lending business.” We\nagree. Because the evidence is sufficient to support the\njury’s verdict, we will remand so Fattah and Vederman\nmay be resentenced on these charges.32\n\n A. CUMA is a Mortgage Lending Business\n In reviewing the District Court’s post-verdict\njudgment of acquittal under Rule 29 of the Federal Rules\nof Civil Procedure, we consider whether the evidence,\nwhen viewed in a light most favorable to the government,\nsupports the jury’s verdict. United States v. Dixon, 658\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\nsame as that applied by the District Court, and we must\nuphold the jury’s verdict unless no reasonable juror could\naccept the evidence as sufficient to support the defendant’s\nguilt beyond a reasonable doubt. United States v.\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\n\n32\n Because the Government did not file an appeal as to\nBowser, the cross-appeal is limited to Fattah and\nVederman. The judgment of acquittal as to Bowser is\ntherefore unaffected by our ruling today.\n 148\n\f Initially, the grand jury’s indictment alleged that\nCUMA is a financial institution because it is federally\ninsured. JA302–03. At trial, however, the jury was\ninstructed that CUMA could qualify as a financial\ninstitution either because it is federally insured or because\nit is a “mortgage lending business.” See JA111, 401–02. A\n“mortgage lending business” is “an organization which\nfinances or refinances any debt secured by an interest in\nreal estate, including private mortgage companies and any\nsubsidiaries of such organizations, and whose activities\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\n\n At trial, CUMA’s president and CEO, Eddie Scott\nToler, testified that CUMA is not federally insured.\nJA4235. The Government therefore attempted to prove\nthat CUMA is a “mortgage lending business” by\npresenting evidence that CUMA funds mortgages and then\nsells them in a secondary market.\n\n Toler also testified that CUMA is a “credit union\nservice organization”—a for-profit company owned by 48\ncredit unions, which serves small credit unions that do not\nhave the infrastructure or in-house expertise to handle\nmortgage loans themselves. JA4235. According to Toler,\n“[CUMA] exclusively provide[s] First Trust Residential\nMortgage loaning [sic] services, all the way from the\norigination of the mortgage loan through processing,\nunderwriting, closing and access to the secondary market\nwhere—and we’re selling the mortgage loan on the\nsecondary market.” JA4236–37. In jurisdictions in which\n\n 149\n\fCUMA is licensed, 33 CUMA holds the mortgage for a\nlimited period, generally from two to thirty days, and then\nsells the mortgage either to a partner credit union or on the\nsecondary market. JA4240.\n\n The District Court concluded that CUMA is not a\n“mortgage lending business” because “[t]he record is\ndevoid of any evidence that CUMA finances or refinances\nany debt.” JA113. Concluding that CUMA “simply is a\nloan processor for various credit unions which do the\nfinancing or refinancing,” id., the District Court ruled that\nCUMA’s “activity does not constitute the financing or\nrefinancing of any debt. CUMA is not the mortgagee. It is\nmerely selling the debt instrument to a third party.” JA114.\n We cannot agree with the District Court’s view of\nthe evidence. Toler testified that in “Maryland, D.C., and\nVirginia . . . all of the loans are closed in the name of\nCUMA.” JA4238–39. As Toler described it, CUMA\nborrows on a line of credit to fund the loan, and when the\nloan is sold, CUMA pays off its line of credit. JA4239–40.\nSo contrary to the District Court’s assessment, the\nevidence, viewed in a light most favorable to the\nGovernment, shows that CUMA is indeed the\nmortgagee—at least during the time from closing until the\nloan is sold to a partner credit union or on the secondary\nmarket. The fact that CUMA funds the closing and then\n\n33\n CUMA is licensed in Maryland, Washington, D.C., and\nVirginia. JA4238.\n 150\n\fholds the mortgage, even for a brief time, is sufficient to\nsupport a conclusion that CUMA is “an organization\nwhich finances or refinances any debt secured by an\ninterest in real estate.” 18 U.S.C. § 27.\n\n Fattah and Vederman attempt to refute the argument\nthat CUMA engages in financing mortgages by focusing\non Toler’s testimony that CUMA “doesn’t actually have\nany money to fund these mortgage loans.” JA4239; see\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\ntestified that CUMA employs a credit line to borrow the\nfunds necessary to close on mortgages. See JA4239. That\nCUMA incurs debt to finance mortgages hardly\nundermines a conclusion that CUMA finances mortgages.\nIndeed, it is the very nature of modern banking that\nfinancial institutions do not hold cash reserves equal to the\nfull amount of their liabilities. See, e.g., Timothy C.\nHarker, Bailment Ailment: An Analysis of the Legal Status\nof Ordinary Demand Deposits in the Shadow of the\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\nde facto standard for all modern banks.”).\n\n Vederman also argues that, even if CUMA acts as a\nmortgage lending business in some transactions, it was not\nacting as a mortgage lending business in this transaction.\nVederman points to Toler’s testimony that, in a state in\nwhich CUMA is not licensed, the mortgage is closed in the\nname of a credit union. In such cases, the credit union, and\nnot CUMA, owns the mortgage for the short period before\n\n 151\n\fthe loan is sold on the secondary market. JA4241. CUMA\nis not licensed in the Commonwealth of Pennsylvania. See\nid. Thus, according to Vederman, CUMA was acting in its\ncapacity as a mortgage servicing company for Fattah’s\nvacation home purchase and did not—and could not—\nfinance Fattah’s mortgage. That would mean that CUMA\ncould not have been a victim of a crime against a financial\ninstitution in this instance: “When an entity is not\nfunctioning as a mortgage lender, the ‘pertinent federal\ninterest’ behind the statutes is not implicated.” Vederman\nReply Br. 38 (citation omitted).\n\n The Government responds that neither of the\nstatutes of conviction requires that the fraud or false\nstatement occur in connection with the same transaction\nthat places the entity within the definition of “financial\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\nGovernment.\n\n Both § 1344 and § 1014 protect entities that fall\nwithin the definition of “financial institution” and are\notherwise quite broad in their application. See Loughrin v.\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\n§ 1344 as not requiring specific intent to defraud a bank);\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\n(“[Section 1014’s] reach is not limited to false statements\nmade with regard to loans, but extends to any application,\ncommitment or other specified transaction.”). Neither\nstatute is expressly limited in the manner that Vederman\nsuggests. Williams v. United States, 458 U.S. 279, 284\n\n 152\n\f(1982) (“To obtain a conviction under § 1014, the\nGovernment must establish two propositions: it must\ndemonstrate (1) that the defendant made a ‘false statement\nor report,’ . . . and (2) that he did so ‘for the purpose of\ninfluencing in any way the action of [a described financial\ninstitution] upon any application, advance, . . .\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\nstatute is to protect the ‘financial integrity of [banking]\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\nother grounds by Loughrin, 134 S. Ct. at 2389.\n In support of his position, Vederman relies on\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\nwhich the Fifth Circuit concluded that § 1014 (false\nstatements to a financial institution) is not intended to\ncapture fraud unrelated to an entity’s lending activities,\nand therefore held that it “applies only to actions involving\nlending transactions.” Id. at 580. The Fifth Circuit stated:\n [W]e are not persuaded that the statute\n imposes liability whenever a defendant’s\n false statement was intended to interfere with\n any activity of a financial institution; such a\n broad interpretation of section 1014\n presumably would encompass fraud or false\n representations having nothing to do with\n financial transactions, such as fraud in an\n employment contract or, for example, in a\n\n 153\n\f contract to provide goods or services for\n custodial care, premises repair, or renovation.\nId.\n\n Yet a majority of circuits, including our own, have\ndeclined to follow Devoll’s suggestion that § 1014 is\nrestricted to lending transactions. As the Ninth Circuit has\nheld, “we join at least six of our sister circuits—the First,\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\n18 U.S.C. § 1014 is not limited to lending transactions,\nand reject the minority rule to the contrary.” Boren, 278\nF.3d at 915. And even if we were to adopt Devoll’s narrow\nconstruction of § 1014 to lending transactions, that would\nnot resolve the more specific question of whether the\ndefrauded entity must be defined as a “mortgage lending\nbusiness” by virtue of the specific transaction in which the\nfalse statements arose.\n Recently, the Eighth Circuit addressed precisely\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\nCir. 2017), that Court considered the defendant’s appeal\nfrom the district court’s denial of a Rule 29 motion on\ngrounds that GMAC, the entity defrauded, was not a\n“financial institution.” The Court upheld the district\ncourt’s determination that the evidence was sufficient to\nestablish that GMAC is in the mortgage lending business\nbecause there was testimony that “it had made hundreds or\nthousands of loans secured by mortgages in 2010 and 2011\nin states all across the country,” which established that its\nactivities affect interstate commerce. Id. at 953. It was not\n 154\n\fdeterminative that GMAC did not own the specific loan at\nissue in the case: “we discern no requirement in the\ndefinition of ‘mortgage lending business’ that the business\nown the particular loan in question; it need only finance or\nrefinance any debt secured by an interest in real estate, or,\nin other words, be in the interstate mortgage lending\nbusiness in general.” Id.\n\n In our view, the Eighth Circuit’s analysis is correct.\nWe therefore adopt that Court’s reasoning in Springer and\nconclude that it is of no moment that CUMA did not\nfinance the mortgage at issue in Fattah’s case. CUMA is a\n“mortgage lending business,” and that alone suffices to\nsupport the convictions under §§ 1014 and 1344.\n\n B. Sufficiency of the Evidence\n Finally, Vederman argues that, even if CUMA is a\nfinancial institution, the judgment of acquittal should\nstand because the Government did not put forth any\nevidence that he made a false representation to CUMA.34\nSpecifically, Vederman argues that the title to the Porsche\nwas actually changed to his name, making it a “true sale”\nas a matter of law, without regard to whether Fattah’s wife\n\n34\n Although Vederman presented this argument in his Rule\n29 motion, the District Court did not need to reach it in the\ncontext of Counts 19 and 20 because the Court granted the\nmotion on the ground that CUMA is not a financial\ninstitution. The District Court rejected the argument as to\nCounts 16, 17, and 18. See JA100–02.\n 155\n\fcontinued to retain possession. See United States v.\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\nanother context that “the government must be able to show\nthat [the defendant] made a statement to government\nagents that was untrue, and the government cannot satisfy\nthat burden by showing that the defendant intended to\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\nCons. Stat. § 102 (defining “owner” as “[a] person, other\nthan a lienholder, having the property right in or title to a\nvehicle”).\n\n The Government responds that, regardless of\nwhether it is legally possible for one person to hold a title\nwhile a different person possesses the vehicle, the jury was\npermitted to consider all the circumstances in deciding\nwhether the Porsche sale was a sham. We agree.\n\n First, as the District Court observed, it was unclear\nas to whether the title had been properly executed under\nPennsylvania law. For instance, Fattah’s wife never\nappeared before a notary. 35 JA101. In addition, title 75,\nsection 1111(a) of the Pennsylvania Consolidated Statutes\nrequires that, “[i]n the event of the sale or transfer of the\nownership of a vehicle within this Commonwealth, the\nowner shall . . . deliver the certificate to the transferee at\n\n35\n Vederman argues that it is of no significance that the\nparties did not appear before a notary as the statute\nrequires, but he offers cases only from states other than\nPennsylvania to support this proposition.\n 156\n\fthe time of the delivery of the vehicle.” And, the transferee\nmust, within twenty days of the assignment of the vehicle,\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\nNeither of these requirements was fulfilled. Finally,\nVederman never registered the Porsche in his name with\nthe Department of Motor Vehicles. See id.; JA4254.\n Second, and more importantly, even if the title had\nbeen properly transferred to Vederman, the title provisions\nof the Pennsylvania Motor Vehicle Code “were [not]\ndesigned to establish conclusively the ownership of an\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\na certificate of title is not to conclusively establish\nownership in a motor vehicle, but rather to establish the\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\nprovides evidence of ownership; it is not dispositive of the\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\n(Pa. Super. Ct. 1967).\n Vederman’s argument that the title in his name\nconstitutes conclusive evidence of ownership rests upon\nan erroneous conclusion that the jury was prohibited from\nconsidering all the circumstances of the transfer. As the\nDistrict Court observed, though, Pennsylvania’s\nCommonwealth Court has held that “[w]hether a\ntransferor has transferred ownership of a motor vehicle to\na transferee is a factual determination to be made by the\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\n\n 157\n\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\nof title was appropriately treated as one piece of evidence\nfor the jury to consider in assessing the validity of the\nvehicle transfer. Considered in the light most favorable to\nthe Government, the totality of the evidence is sufficient\nto support the jury’s conclusion that the Porsche sale was\na sham.\n\n XI. Prejudicial Spillover\n Finally, Fattah, Vederman, Nicholas, and Brand\neach contend that their convictions on various counts\nresulted from prejudicial spillover. We are not persuaded.\n We exercise plenary review over a district court’s\ndenial of a claim of prejudicial spillover, United States v.\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\ntwo-step test when reviewing such a claim. United States\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\nmust consider “whether the jury heard evidence that would\nhave been inadmissible at a trial limited to the remaining\nvalid count[s].” Id. (quoting United States v. Cross, 308\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\nthat we “ask whether that evidence (the ‘spillover\nevidence’) was prejudicial.” Id. We consider four factors:\n“whether (1) the charges are intertwined with each other;\n(2) the evidence for the remaining counts is sufficiently\ndistinct to support the verdict on these counts; (3) the\nelimination of the invalid count [will] significantly\nchange[] the strategy of the trial; and (4) the prosecution\nused language of the sort to arouse a jury.” Id. (quoting\n 158\n\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\n2003)); see also United States v. Pelullo (Pellulo II), 14\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\nconsidered in a light “somewhat favorable to the\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\nF.3d at 122); see also Gov’t Br. 198 (same).\n\n A. Fattah’s Claim of Prejudicial Spillover\n Fattah argues that he suffered prejudicial spillover\non the remaining counts of conviction in light of (1)\nevidence pertinent to the alleged Vederman bribery\nschemes that is now arguably inadmissible under\nMcDonnell; and (2) “the government’s flawed RICO\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\nis undercut substantially because of our determination that\nMcDonnell requires a new trial for Counts 16, 17, 22, and\n23 and our decision to affirm the RICO conspiracy\nconviction. The only possible spillover left to consider is\nthe evidence pertaining to Fattah’s arranging a meeting\nbetween Vederman and the U.S. Trade Representative,\nRon Kirk, which in light of McDonnell is now arguably\ninadmissible.36\n\n The evidence of the Kirk meeting admitted during\nthis five-week trial was limited. Although this evidence\n\n36\n Nothing in this opinion is intended to foreclose the\npossibility that evidence of the Kirk meeting may be\nadmissible on retrial for some purpose other than as proof\nof an official act.\n 159\n\fwas part of the Government’s proof as to both the RICO\nand the bribery related charges, there is more than\nsufficient—and distinct —evidence to support Fattah’s\nconviction on all the other counts. In our view, eliminating\nany evidence of the Kirk meeting would not have altered\nthe strategy of the trial, nor should it significantly change\nthe strategy for any new trial that may be held. Because\nFattah has not pointed us to any argument by the\nprosecution relating to this meeting that could have\ninflamed the jury, we conclude that Fattah’s prejudicial\nspillover claim fails. Like the District Court, we presume\nthat the jury followed the Court’s instructions to consider\nand weigh separately the evidence on each count as to each\ndefendant and not to be swayed by evidence pertaining to\nother defendants. 37\n\n B. Vederman’s Assertion of Prejudicial Spillover\n Because the District Court acquitted Vederman of\nthe RICO charge, Vederman argues that he was “severely\nprejudiced by the presentation to the jury of a legally\nflawed racketeering conspiracy charge,” and as a\nconsequence his bribery and money laundering\n\n37\n We likewise reject Brand’s prejudicial spillover\narguments. See Brand Br. 6 (“Brand adopts the significant\nissue advanced by his co-appellant pursuant to Fed. R.\nApp. P. 28(i) that improper jury instructions and the\nresulting spillover of related improperly admitted\nevidence and argument unfairly prejudiced Brand.”).\n 160\n\fconvictions should be overturned. Vederman Br. 46. In\nresponse to the Government’s appeal of the District\nCourt’s Rule 29 acquittal on Counts 19–20 involving\nCUMA, Vederman asserts that these two counts also were\naffected by spillover evidence because the Government’s\ntheory tied the bribery charges to the actions taken to\ndefraud CUMA. In that we are vacating Vederman’s\nconvictions of Counts 16–18 and 22–23 based on\nMcDonnell and remanding for further proceedings, we\nneed address only Vederman’s argument of prejudicial\nspillover as it relates to the charges involving CUMA in\nCounts 19–20, charges that we will reinstate.\n The District Court’s acquittal of Vederman on the\nRICO count establishes that step one of the Wright\nspillover test has been met. “[T]he jury heard evidence that\nwould have been inadmissible at a trial limited” to the\nbribery and CUMA-related counts. Wright, 665 F.3d at\n575 (quoting Cross, 308 F.3d at 317).\n\n Wright’s second step requires “ask[ing] whether\nthat evidence (the ‘spillover evidence’) was prejudicial.”\nId. Vederman submits that the RICO, bribery, and CUMA-\nrelated charges were intertwined “in that the acts relating\nto the alleged bribery scheme were also charged as\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\n\n To be sure, the RICO, bribery, and CUMA Counts\nare related to one another. But in this instance, mere\nrelatedness is not enough to demonstrate the foundation\nnecessary for spillover. This is so because the bribery\n 161\n\fcharges were a predicate to the RICO charge. In other\nwords, the jury had to determine if Vederman was guilty\nof bribery, and the jury then used that “predicate” to\nconsider whether he was also guilty of the RICO\nconspiracy. Thus, the necessarily tiered structure of the\nquestions presented to the jury refute Vederman’s\nargument that the counts were intertwined.\n\n That the bribery charges were predicates for the\nRICO conspiracy further demonstrates that the “evidence\nfor the different counts was sufficiently distinct to support\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\n898. Regardless of the evidence pertaining solely to the\nRICO conviction, the evidence supporting both the bribery\ncharges and the charges involving CUMA in Counts 19–\n20 would have remained the same.\n\n The next factor we address is “whether the\nelimination of the count on which the defendant was\ninvalidly convicted would have significantly changed the\n[defendant’s] strategy of the trial.” Id. As Vederman\nargues, “the RICO charge interfered with Vederman’s\ncentral defense to the bribery charge—that his gestures\ntoward Fattah ‘were motivated purely by friendship.’ ”\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\nwords, the “RICO count made it dangerous to unduly\nemphasize [Vederman’s] close friendship” with Fattah. Id.\nFrom Vederman’s perspective, “a bribery-only trial would\nhave reduced this danger and allowed a freer presentation\nof the defense.” Id.\n\n 162\n\f It is quite likely that Vederman’s claim of friendship\nwould have been less risky as a litigation strategy if he had\nnot been facing a RICO charge. But Vederman\nnevertheless chose to take that risk and fully presented his\nfriendship argument to the jury. Moreover, while\nVederman’s reliance on friendship might have helped him\ndefend against the bribery charges, that friendship would\nnot have altered the evidence pertaining to Counts 19–20\ninvolving CUMA. Whether done for friendship or some\nother reason, submitting fraudulent information to a\nfinancial institution is unlawful.\n\n Finally, we “examine the charges, the language that\nthe government used, and the evidence introduced during\nthe trial to see whether they are ‘of the sort to arouse a\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\nthat Fattah was presented as “a backslapping, corrupt party\nboss,” with “predictable spillover to his friend and\nassociate, Vederman.” Vederman Br. 50 (quoting United\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\nthis description was of Fattah, not Vederman. Vederman\ncites other examples of prejudicial, pejorative language in\nthe Government’s closing arguments. At one point, the\nGovernment referred to “conspirators engaged in what can\nonly be described as a white collar crime spree from\nPhiladelphia all the way to Washington, D.C.” and\npromised “to untangle the webs of lies and deception that\nthese conspirators spun.” Vederman Br. 51 (quoting\nJA5295, 5297). Whatever rhetorical flair these words\n 163\n\fcontained, they did not obscure the evidence which\nindependently supported the convictions for bank fraud at\nCount 19 and for making false statements to CUMA at\nCount 20. Accordingly, because we presume that the jury\nfollowed the District Court’s instruction to consider and to\nweigh separately the evidence on each count and as to each\ndefendant, and because the evidence supporting the\nCUMA-related charges in Counts 19–20 is sufficiently\ndistinct from the RICO conspiracy, we conclude that\nVederman’s spillover argument is unavailing.38\n\n XII. Conclusion\n We will vacate the convictions of Chaka Fattah, Sr.\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\n\n38\n Nicholas adopted “pertinent portions” of the prejudicial\nspillover arguments advanced by Vederman and Fattah.\nNicholas Br. 65. Her spillover claim has no more merit\nthan theirs. Nicholas’s involvement in the RICO\nconspiracy was distinct from the bribery charges, which\ndid not unfairly influence the other counts. As to\nNicholas’s assertion that the NOAA charges did not\nbelong in the indictment and should have been tried\nseparately, we fail to see how this relates to a claim of\nprejudicial spillover. To the extent it challenges the\nDistrict Court’s denial of Nicholas’s motion for a\nseverance, Nicholas has failed to provide legal support for\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\n 164\n\fFattah and Vederman may be retried on these counts\nbefore a properly instructed jury. We will also reverse the\nDistrict Court’s judgment of acquittal on Counts 19 and\n20. The convictions of Chaka Fattah, Sr. and Herbert\nVederman will be reinstated, and the case will be\nremanded for sentencing on those counts. In all other\nrespects, the judgments of the District Court will be\naffirmed.\n\n\n\n\n 165\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Appellant in 17-1346 v. Chaka FATTAH, Sr., Appellant in 16-4397 Karen Nicholas, Appellant in 16-4410 Robert Brand, Appellant in 16-4411 Herbert Vederman, Appellant in 16-4427\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n Nos. 16-4397, 16-4410, 16-4411,\\n 16-4427, 17-1346\\n _____________\\n\\n UNITED STATES OF AMERICA\\n Appellant in 17-1346\\n\\n v.\\n\\n CHAKA FATTAH, SR.,\\n Appellant in 16-4397\\n\\n KAREN NICHOLAS,\\n Appellant in 16-4410\\n\\n ROBERT BRAND,\\n Appellant in 16-4411\\n\\n HERBERT VEDERMAN,\\n Appellant in 16-4427\\n _____________\\n\\nOn Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n District Court Nos. 2-15-cr-00346-001,\\n\\f 2-15-cr-00346-002, 2-15-cr-00346-003,\\n 2-15-cr-00346-004\\n District Judge: The Honorable Harvey Bartle III\\n\\n Argued January 18, 2018\\n\\nBefore: SMITH, Chief Judge, GREENAWAY, JR., and\\n KRAUSE, Circuit Judges\\n\\n (Filed: January 16, 2019)\\n\\nAndrea G. Foulkes\\nEric L. Gibson\\nPaul L. Gray\\nRobert A. Zauzmer\\nOffice of United States Attorney\\n615 Chestnut Street\\nSuite 1250\\nPhiladelphia, PA 19106\\n\\nJonathan Ian Kravis [ARGUED]\\nUnited States Department of Justice\\nCriminal Division, Public Integrity Section\\n1400 New York Avenue, N.W.\\nWashington, DC 20005\\n Counsel for the United States\\n\\nMark M. Lee\\nBruce P. Merenstein [ARGUED]\\nSamuel W. Silver\\n 2\\n\\fSchnader Harrison Segal & Lewis\\n1600 Market Street\\nSuite 3600\\nPhiladelphia, PA 19103\\n Counsel for Appellant Fattah\\n\\nAnn C. Flannery [ARGUED]\\nSuite 2700\\n1835 Market Street\\nPhiladelphia, PA 19103\\n\\nLisa A. Mathewson\\nSuite 810\\n123 South Broad Street\\nPhiladelphia, PA 19109\\n Counsel for Appellant Nicholas\\n\\nAlan Silber\\nPashman Stein Walder Hayden\\n21 Main Street\\nSuite 200\\nHackensack, NJ 07601\\n Counsel for National Association of Criminal\\n Defense Lawyers, Amicus Appellant Nicholas\\n\\nMira E. Baylson\\nBarry Gross [ARGUED]\\nMeredith C. Slawe\\nDrinker Biddle & Reath\\nOne Logan Square\\n 3\\n\\fSuite 2000\\nPhiladelphia, PA 19103\\n Counsel for Appellant Brand\\n\\nHenry W. Asbill\\nBuckley Sandler\\n1250 24th Street, N.W.\\nSuite 700\\nWashington, DC 20037\\n\\nGlen D. Nager [ARGUED]\\nJacob M. Roth\\nJulia W. M. F. Sheketoff\\nJones Day\\n51 Louisiana Avenue, N.W.\\nWashington, DC 20001\\n Counsel for Appellant Vederman\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nSMITH, Chief Judge.\\n\\n\\n\\n\\n 4\\n\\f Table of Contents\\nI. Introduction ................................................................... 8\\nII. Background .................................................................. 9\\n A. The Fattah for Mayor Scheme ................................. 9\\n 1. The Lord Loan and Its Repayment ..................... 10\\n 2. The College Tuition Component of the FFM\\n Scheme ................................................................ 27\\n 3. The NOAA Grant and the Phantom Conference 28\\n B. The Blue Guardians Scheme.................................. 31\\n C. The Fattah–Vederman Bribery Scheme................. 33\\n D. The Indictment and Trial ....................................... 39\\nIII. Juror Misconduct and Dismissal of Juror 12 ........... 58\\n A. Investigation of Alleged Juror Misconduct ........... 58\\n B. Dismissal of Juror 12 ............................................. 64\\nIV. The District Court’s Instructions Under McDonnell 70\\n A. The McDonnell Framework................................... 71\\n B. The Kirk Meeting ................................................... 76\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship.......................................................... 79\\n D. The Zionts Hiring .................................................. 82\\n E. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23.................................................................... 89\\n F. Blue Guardians ....................................................... 91\\n\\n 5\\n\\fV. Sufficiency of the Evidence for the RICO Conspiracy\\nConviction ...................................................................... 95\\nVI. Variance from the Indictment and Sufficiency of the\\nEvidence for Count 2.................................................... 110\\nVII. The District Court’s Instruction to the Jury on the\\nMeaning of Intent ......................................................... 120\\nVIII. Sending the Indictment to the Jury ...................... 126\\nIX. The District Court’s Evidentiary Rulings .............. 129\\n A. The District Court’s Application of Rule 404(b) 129\\n B. Evidentiary Rulings Regarding Nicholas’s\\n Defense ..................................................................... 134\\n 1. The EAA Board Minutes .................................. 134\\n 2. Jones’ Memory Regarding Other Contracts ..... 136\\n 3. Exclusion of NOAA Evidence.......................... 137\\n C. The Cooperating Witness’s Mental Health\\n Records ..................................................................... 138\\n 1. The District Court’s Denial of Access to the\\n Mental Health Records ..................................... 140\\n 2. The District Court’s Grant of the Motion in\\n Limine ............................................................... 142\\nX. The Government’s Cross-Appeal ............................ 147\\n A. CUMA is a Mortgage Lending Business............. 148\\n B. Sufficiency of the Evidence ................................. 155\\nXI. Prejudicial Spillover ............................................... 158\\n A. Fattah’s Claim of Prejudicial Spillover ............... 159\\n 6\\n\\f B. Vederman’s Assertion of Prejudicial Spillover ... 160\\nXII. Conclusion ............................................................ 164\\n\\n\\n\\n\\n 7\\n\\f I. Introduction\\n Chaka Fattah, Sr., a powerful and prominent fixture\\nin Philadelphia politics, financially overextended himself\\nin both his personal life and his professional career during\\nan ultimately unsuccessful run for mayor. Fattah received\\na substantial illicit loan to his mayoral campaign and used\\nhis political influence and personal connections to engage\\nfriends, employees, and others in an elaborate series of\\nschemes aimed at preserving his political status by hiding\\nthe source of the illicit loan and its repayment. In so doing,\\nFattah and his allies engaged in shady and, at times, illegal\\nbehavior, including the misuse of federal grant money and\\nfederal appropriations, the siphoning of money from\\nnonprofit organizations to pay campaign debts, and the\\nmisappropriation of campaign funds to pay personal\\nobligations.\\n Based upon their actions, Fattah and four of his\\nassociates—Herbert Vederman, Robert Brand, Bonnie\\nBowser, and Karen Nicholas—were charged with\\nnumerous criminal acts in a twenty-nine count indictment.\\nAfter a jury trial, each was convicted on multiple counts.\\nAll but Bowser appealed. As we explain below, the\\nDistrict Court’s judgment will be affirmed in part and\\nreversed in part.\\n\\n\\n\\n\\n 8\\n\\f II. Background1\\n During the 1980s and ’90s, Fattah served in both\\nhouses of the Pennsylvania General Assembly, first as a\\nmember of the House of Representatives and later as a\\nSenator. In 1995, Fattah was elected to the United States\\nHouse of Representatives for Pennsylvania’s Second\\nCongressional District. In 2006, Fattah launched an\\nunsuccessful run for Mayor of Philadelphia, setting in\\nmotion the events that would lead to his criminal\\nconviction and resignation from Congress ten years later.\\n\\n A. The Fattah for Mayor Scheme\\n Fattah declared his candidacy for mayor in\\nNovember of 2006. Thomas Lindenfeld, a political\\nconsultant on Fattah’s exploratory committee, believed\\nthat “[a]t the beginning of the campaign, [Fattah] was a\\nconsiderable . . . candidate and somebody who had a very\\nlikely chance of success.” JA1618. But Fattah’s campaign\\nsoon began to experience difficulties, particularly with\\nfundraising. Philadelphia had adopted its first-ever\\ncampaign contribution limits, which limited contributions\\nto $2,500 from individuals and $10,000 from political\\naction committees and certain types of business\\norganizations. Fattah’s fundraising difficulties led him to\\n\\n\\n\\n1\\n The facts are drawn from the trial record unless otherwise\\nnoted.\\n 9\\n\\fseek a substantial loan, far in excess of the new\\ncontribution limits.\\n\\n 1. The Lord Loan and Its Repayment\\n While serving in Congress, Fattah became\\nacquainted with Albert Lord, II. The two first met around\\n1998, when Lord was a member of the Board of Directors\\nof Sallie Mae.\\n As the May 15, 2007 primary date for the\\nPhiladelphia mayoral race approached, Fattah met Lord to\\nask for assistance, telling Lord that the Fattah for Mayor\\n(FFM) campaign was running low on funds. Fattah asked\\nLord to meet with Thomas Lindenfeld, a political\\nconsultant in Washington, D.C., and part-owner of LSG\\nStrategies, Inc. (Strategies), a company that was working\\nwith the FFM campaign and that specialized in direct voter\\ncontact initiatives. Lindenfeld had been part of the\\nexploratory group that initially considered Fattah’s\\nviability as a candidate for mayor. Lindenfeld had known\\nFattah since 1999, when Fattah endorsed Philadelphia\\nMayor John Street. Through Fattah, Lindenfeld had also\\ngotten to know several of Fattah’s associates, including\\nHerbert Vederman, Robert Brand, and Bonnie Bowser.\\nHerbert Vederman, a businessman and former state\\nofficial, was the finance director for the FFM campaign.\\nRobert Brand owned Solutions for Progress (Solutions), a\\n“Philadelphia-based public policy technology company,\\nwhose mission [was] to deliver technology that directly\\nassists low and middle income families [in obtaining]\\n 10\\n\\fpublic benefits.” JA6551. Bowser was Fattah’s Chief of\\nStaff and campaign treasurer, and served in his district\\noffice in Philadelphia.\\n Lord’s assistant contacted Lindenfeld to arrange a\\nmeeting, and Lindenfeld informed Fattah that he would be\\nmeeting with Lord. Lindenfeld, along with his partner,\\nMichael Matthews, met with Lord and discussed Fattah’s\\nneed for funds to mount an intensive media campaign.\\nAfter that meeting, Lindenfeld reported to Fattah that Lord\\nwanted to help, but that they had not discussed a specific\\ndollar amount. Approximately a week later, Fattah\\ninstructed Lindenfeld to meet with Lord a second time.\\nLord “wanted to know if he could give a substantial\\namount of money, a million dollars” to Fattah’s campaign.\\nJA1630. That prompted Lindenfeld to reply that the\\namount “would be beyond the campaign finance limits.”\\nId.\\n\\n Lord proposed a solution: he offered to instead give\\na million dollars to Strategies in the form of a loan. To that\\nend, Lindenfeld had a promissory note drafted which\\nspecified that Lord was lending Strategies $1 million, and\\nthat Strategies promised to repay the $1 million at 9.25%\\ninterest, with repayment to commence January 31, 2008.\\nLindenfeld later acknowledged that the promissory note\\nwould make it appear as though Lord’s $1 million was not\\na contribution directly to the Congressman, although he\\nknew that it was actually a loan to the FFM campaign.\\nIndeed, Lindenfeld confirmed with Fattah that neither\\n\\n 11\\n\\fLindenfeld nor Strategies would be responsible for\\nrepayment. With that understanding, Lindenfeld executed\\nboth the note and a security agreement purporting to\\nencumber Strategies’ accounts receivable and all its assets.\\n\\n On May 1, shortly before the primary election, Lord\\nwired $1 million to Lindenfeld. Lindenfeld held the money\\nin Strategies’ operating account until Fattah told him how\\nit was to be spent. Some of the money was eventually used\\nfor print materials mailed directly to voters. And, at\\nFattah’s direction, Lindenfeld wired a substantial sum to\\nSydney Lei and Associates (SLA), a company owned by\\nGregory Naylor which specialized in “get out the vote”\\nefforts.\\n Naylor had known Fattah for more than 30 years.2\\nDuring the campaign, Naylor worked as the field director\\nand was in charge of getting out the vote on election day.\\n\\n2\\n Naylor first worked with Fattah when he was in the state\\nlegislature. When Fattah was elected to Congress, Naylor\\nworked in his Philadelphia office. Naylor met Nicholas\\nwhen she joined Fattah’s staff at some point in the 1990s.\\nAfter concluding her employment with Fattah’s office,\\nNicholas worked with the Educational Advancement\\nAlliance (EAA), an education nonprofit entity founded by\\nFattah. This entity helped to recruit underrepresented\\nstudents for scholarship and college opportunities. Around\\n2009, Naylor left Fattah’s office to work exclusively with\\nSLA. Naylor also knew Brand.\\n 12\\n\\fOn the final day of the campaign, Naylor worked with\\nVederman, who allowed Naylor to use his credit card to\\nrent vans that would transport Fattah voters to the polls.\\n As the primary date neared, Fattah and Naylor knew\\nthe campaign was running out of money. The campaign\\nwas unable to finance “media buys,” and Naylor needed\\nmoney for field operations to cover Philadelphia’s more\\nthan one thousand polling places. In early May,\\nLindenfeld called Naylor to say that Lindenfeld “would be\\nsending some money [Naylor’s] way.” JA3057. Within\\ndays, SLA received a six-figure sum for Naylor to use in\\nthe campaign and on election day. Naylor used the money\\nto pay some outstanding bills, including salaries for FFM\\nemployees, and allocated $200,000 to field operations for\\nelection day.\\n\\n Fattah lost the mayoral primary on May 15, 2007.\\nAfterward, Lindenfeld spoke with Fattah, Naylor and\\nBowser about accounting for the FFM campaign money\\nfrom Lord that had been spent. They decided that the\\namounts should not appear in the FFM campaign finance\\nreports, and Fattah instructed Naylor to have his firm,\\nSLA, create an invoice. Naylor did so, creating an invoice\\ndated June 1, 2007 from SLA to FFM, seeking payment of\\n$193,580.19. Naylor later acknowledged that the FFM\\ncampaign did not actually owe money to SLA, and that the\\nfalse invoice was created to “hide the transaction that took\\nplace earlier” and “make it look like [SLA] was owed\\nmoney.” JA3075–76. Although FFM did not owe SLA\\n\\n 13\\n\\fanything for the election day expenses, the FFM campaign\\nfinance reports from 2009 through 2013 listed a $20,000\\nin-kind contribution from SLA for each year, thereby\\nlowering FFM’s alleged outstanding debt to SLA.\\n\\n Of the total $1 million Lord loan, $400,000 had not\\nbeen spent. Lindenfeld returned that sum to Lord on June\\n3, 2007. He included a cover letter which stated: “As it\\nturns out the business opportunities we had contemplated\\ndo not seem to be as fruitful as previously expected.”\\nJA1254. Lindenfeld later admitted that there were no such\\n“business opportunities” and that the letter was simply an\\neffort to conceal the loan.\\n In late 2007, faced with financial pressures, Lord\\nasked his son, Albert Lord, III, to collect the outstanding\\n$600,000 balance on the loan to Strategies. Lord III\\ncontacted Lindenfeld about repayment and expressed a\\nwillingness to forgive the interest owed if the principal\\nwas paid. Lindenfeld immediately called Fattah and\\ninformed him that repayment could not be put off any\\nlonger. Fattah told Lindenfeld more than once that “[h]e\\nwould take care of it,” JA1652, but Fattah did not act.\\nNeeding someone who might have Fattah’s ear,\\nLindenfeld reached out to Naylor and Bowser. Naylor\\ntalked to Fattah on several occasions and told him that\\nLindenfeld was under considerable pressure to repay the\\nloan. Fattah told Naylor more than once that he was\\n“working on it.” JA3082–83.\\n\\n\\n 14\\n\\f During his political career, Fattah had focused on\\neducation, especially for the underprivileged. Indeed,\\nFattah founded two nonprofit organizations: College\\nOpportunity Resources for Education (CORE), and the\\nEducational Advancement Alliance (EAA).\\n\\n EAA held the annual Fattah Conference on Higher\\nEducation (the “annual conference”) to acquaint high\\nschool students with higher education options. JA3079.\\nSallie Mae regularly sponsored the conference. According\\nto Raymond Jones, EAA’s chairman of the board from\\n2004 through 2007, EAA offered a variety of programs to\\nprovide “marginalized students with educational\\nopportunities so they could continue and go to college.”\\nJA1360. EAA was funded with federal grant money which\\ncould only be spent for the purposes described in the\\nparticular grant. Karen Nicholas served as EAA’s\\nexecutive director, handling the organization’s day-to-day\\nadministrative responsibilities. Nicholas had previously\\nbeen a staffer for Fattah when he was a member of\\nPennsylvania’s House of Representatives.\\n CORE was an organization that awarded\\nscholarships to graduating high school students in\\nPhiladelphia who had gained admission to a state\\nuniversity or the Community College of Philadelphia.\\nCORE received funding from a variety of sources,\\nincluding Sallie Mae. Because CORE also received\\nfederal funds, and because EAA had experience working\\nwith federal grants, EAA received and handled the federal\\n\\n 15\\n\\ffunds awarded to CORE. In short, EAA functioned as a\\nfiduciary for CORE. When money became a problem for\\nthe FFM campaign, Fattah’s involvement with EAA and\\nCORE soon became less about helping underprivileged\\nstudents, and more about providing an avenue for\\ndisguising efforts to repay the illicit campaign funds from\\nLord.\\n\\n On January 7, 2008, Robert Brand contacted Fattah\\nby telephone. Shortly thereafter, Lindenfeld received an\\nunexpected call from Brand proposing an arrangement for\\nBrand’s company, Solutions, to work with Strategies.\\nSolutions had developed a software tool called “The\\nBenefit Bank,” which was designed to “assist low and\\nmoderate income families to have enhanced access to\\nbenefits and taxes.” JA1993. During the telephone call,\\nBrand referred to The Benefit Bank and suggested a\\ncontract under which Strategies would be paid $600,000\\nupfront. JA1666. Shortly thereafter, on January 9, 2008,\\nBrand followed up on his call to Lindenfeld with an email\\nabout “develop[ing] a working relationship where you\\ncould help us to grow The Benefit Bank and our process\\nof civic engagement. While I know this is not your core\\nbusiness I would like to try to convince you to take us on\\nas a client.” JA6427. Lindenfeld responded that he was\\ninterested. To Lindenfeld, “this was the way that\\nCongressman Fattah was going to repay the debt to Al\\nLord.” JA1654. When Lindenfeld called Fattah and told\\nhim of the contact from Brand, Fattah simply replied that\\nLindenfeld “should just proceed.” JA1666–67.\\n 16\\n\\f A few days later, Brand emailed Nicholas at EAA a\\nproposal from Solutions concerning The Benefit Bank,\\nwhich sought EAA’s support in developing an education\\nedition of The Benefit Bank and a $900,000 upfront\\npayment.\\n\\n As the January 31 date for repayment of the balance\\nof the $1 million Lord loan approached, a flurry of activity\\ntook place. On January 24, both Raymond Jones, chair of\\nthe EAA Board, and Nicholas signed a check from EAA\\nmade out to Solutions in the amount of $500,000.\\nAlthough no contract existed between EAA and Solutions,\\nthe memo line of the check indicated that it was for a\\ncontract, and Nicholas entered it into EAA’s ledger.3\\n\\n That same day, Ivy Butts, an employee of\\nStrategies, emailed Lindenfeld the instructions Brand\\nwould need to wire the $600,000 balance on the Lord loan.\\n\\n3\\n Raymond Jones, who was EAA’s Chairman of the Board\\nfrom 2004 through 2007, recalled at trial that the Board\\nhad a limit on the amount that Nicholas could spend\\nwithout board approval. JA1358, 1369. Nicholas was\\nauthorized to sign contracts on behalf of EAA for no more\\nthan $100,000. JA1369–71. Jones did not recall the\\ncontract between EAA and Solutions, nor did the EAA\\nboard minutes for December 2007, February 2008, or May\\n2008 refer to the EAA–Solutions contract or to the\\nsubstantial upfront payment of half a million dollars upon\\nexecution of the agreement. JA6358–63; 6567.\\n 17\\n\\fWithin minutes, Lindenfeld forwarded that email to Brand\\nat Solutions. Brand then made two telephone calls to\\nFattah. By late afternoon, Brand emailed Nicholas,\\ninforming her that he had “met with all the people I need\\nto meet with and have a pretty clear schedule of what\\nworks best for us. I am also seeing what line of credit we\\nhave to stretch out the payments until you get your line of\\ncredit in place.” JA6558. Brand asked if they could talk\\nand “finalize this effort.” JA6558. On January 25 and 26,\\nthere were a number of calls between Fattah, Brand, and\\nNicholas.\\n\\n On Sunday January 27, at 5:46 pm, Brand\\ntelephoned Fattah. At 10:59 pm, Brand emailed Nicholas\\na revised contract between EAA and Solutions for the\\nengagement of services. Brand indicated he would send\\nsomeone to pick up the check at about 1:00 pm the\\nfollowing day. The revised contract called for the same\\n$900,000 payment from EAA to Solutions, yet specified\\nthat $500,000 was to be paid on signing, with $100,000\\ndue three weeks later, and another $100,000 to be paid six\\nweeks out. No due date for the $200,000 balance was\\nspecified. The terms of the contract called for EAA to\\nassist Solutions with further developing The Benefit Bank.\\nIn addition, under the contract, EAA would receive certain\\n\\n\\n\\n\\n 18\\n\\ffunds from the Commonwealth of Pennsylvania for a\\nprogram relating to FAFSA applications. 4\\n\\n The same evening, Brand sent Lindenfeld a contract\\nentitled “Cooperative Development Agreement to Provide\\nServices to Solutions for Progress, Inc. for Growth of The\\nBenefit Bank.” JA6569. The agreement proposed a\\nworking partnership in which Strategies would work with\\nSolutions to identify and secure a Benefit Bank affiliate in\\nthe District of Columbia and two other states, and to\\nfacilitate introductions to key officials in other states\\nwhere The Benefit Bank might expand. The terms of the\\nagreement provided that Solutions would pay $600,000 to\\nStrategies by January 31, 2008, which would “enable\\n[Strategies’] team to assess opportunities and develop\\ndetailed work plans for each area.” JA6572. Brand copied\\nSolutions’ Chief Financial Officer, Michael Golden.\\nLindenfeld responded to Brand’s email within a minute,\\nasking if Brand had received the wiring instructions.\\nBrand immediately confirmed that he had.\\n\\n Concerned that Solutions did not have $600,000 to\\npay Strategies, Golden talked to Brand, who informed him\\nthat Solutions would be receiving a check for $500,000\\nfrom EAA. Early the next morning, Nicholas responded to\\nBrand’s email from the night before. She advised Brand\\nthat he could pick up the check, “but as I stated I am not\\n\\n4\\n FAFSA is an acronym for Free Application for Federal\\nStudent Aid.\\n 19\\n\\fin a position to sign a contract committing funds that I am\\nnot sure that I will have.” Gov’t Supp. App. (GSA) 1. That\\nsame day, a $540,000 transfer was made from the\\nconference account, which EAA handled, into EAA’s\\nchecking account. The conference account was maintained\\nto handle expenses for Fattah’s annual higher education\\nconference. Prior to this transfer, EAA had only\\n$23,170.95 in its account. EAA then tendered a $500,000\\ncheck to Solutions, which promptly deposited the check\\nbefore the close of that day’s business. EAA never\\nreplenished the $540,000 withdrawal from the conference\\naccount.\\n Brand received the executed contract between\\nSolutions and Strategies on January 28. Even though the\\ncontract called for Strategies to perform services in\\nexchange for the $600,000 payment, Lindenfeld neither\\nexpected to do any work for the $600,000, nor did he in\\nfact do any work.\\n\\n In sum, by January 28, Solutions had received\\n$500,000 from EAA, but it still had to come up with\\n$100,000 to provide Strategies with the entire amount\\nneeded to repay the Lord loan. Golden obtained the needed\\nfunds the following day by drawing $150,000 on a line of\\ncredit held by Brand’s wife. Brand and Fattah spoke four\\nmore times on the telephone on January 29. Trial evidence\\nlater showed that, during the month of January 2008,\\nneither the FFM campaign bank account nor Fattah’s\\n\\n\\n 20\\n\\fpersonal account had a sufficient balance to fund a\\n$600,000 payment.\\n On the morning of January 30, frustrated by the\\ndelay, Lindenfeld sent Brand an email with a subject line\\n“You are killing me.” JA6430. Lindenfeld stated that he\\nhad “made a commitment based on yours to me. Please\\ndon’t drag this out. I have a lot on the line.” Id. Brand\\nresponded late in the afternoon, stating: “just met with\\nMichael. He does the transfer at 8 AM tomorrow. It should\\nbe in your account ($600K) early tomorrow morning.” Id.\\nLindenfeld replied: “The earlier the better.” Id. The\\nfollowing morning, Golden wired $600,000 from\\nSolutions’ Pennsylvania bank account into Strategies’\\nWashington D.C. bank account. JA2745, 2874. Strategies\\nin turn, wired the same amount from its Washington D.C.\\nbank account to Lord’s bank account in Virginia. JA2874,\\n6549. Around noon, Brand telephoned Lindenfeld.\\n\\n In the days following the exhaustive efforts to meet\\nthe January 31 loan repayment deadline, four more\\ntelephone calls took place between Brand and Fattah.5\\nNaylor learned at some point that the loan had been paid\\noff. When Naylor asked Fattah about details of the\\nrepayment, Fattah simply replied “[t]hat it went through\\nEAA to Solutions and it was done.” JA3088.\\n\\n5\\n By contrast, between October to December 2007, Brand\\nand Fattah spoke by telephone only “once or twice [a]\\nmonth.” JA2734.\\n 21\\n\\f Meanwhile, at some point in January, EAA received\\nnotice that the Department of Justice Office of the\\nInspector General (DOJ) intended to audit its books.6 DOJ\\nauditors told EAA to provide, at the “entrance\\nconference,” documentation containing budgetary and\\naccounting information. EAA failed to produce any\\naccounting information.\\n Although Lindenfeld was no longer making\\ndemands of Brand, Brand was still owed the remaining\\n$100,000 that Solutions had paid to satisfy the Lord loan.\\nOn March 23, 2008, Brand sent Nicholas an email\\noutlining his efforts to contact her over the previous two\\nweeks about documentation on the CORE work, how to\\nproceed with the paperwork for the Commonwealth of\\nPennsylvania, and “how we can get our proposed contract\\nsigned and the outstanding payments made.” JA2749.\\nNicholas responded that evening, writing:\\n\\n I can appreciate your urgency however I do\\n have EAA work that I continue to do,\\n including the [usual] facilitation of programs,\\n our financial audit, the start-up of two new\\n programs[,] and of course the DOJ audit. I am\\n still trying to obtain a line of credit without a\\n completed 2007 audit and things are getting a\\n\\n\\n\\n6\\n One of the terms and conditions of a federal grant is that\\nthe recipient “be readily prepared for an audit.” JA2314.\\n 22\\n\\f little uncomfortable now as I try to keep us\\n afloat.\\nJA6576. Nicholas told Brand that the DOJ auditors were\\nmaking demands and would soon be on site. She noted that\\n“[t]hey are still very uncomfortable with your contract\\namongst other things and depending on their findings\\nsome of the funding received may have to be returned.” Id.\\nNicholas said that she had submitted the paperwork to the\\nstate, and she told Brand that “in the future . . . as a result\\nof the DOJ audit I will not be in a position to do another\\ncontract such as this.” Id.\\n Shortly after Nicholas’s reply to Brand, Nicholas\\nforwarded the Brand–Nicholas email chain to Fattah. The\\nbody of the email stated, in its entirety: “I really don’t\\nappreciate the tone of Bob’s email. I can appreciate that he\\nhas some things going on however I am doing my best to\\nassist him. Some other things are a priority. He needs to\\nback off.” GSA2. Later that night, Bowser sent Fattah an\\nemail with a subject line that read “Karen N” and a\\ntelephone number. JA2752.\\n\\n As the audit continued, the auditors found other\\ndeficiencies. During April of 2008, DOJ issued a notice of\\nirregularity to EAA, which resulted in the audit being\\nreferred to DOJ’s Investigations Division for a more\\ncomprehensive review.\\n\\n On April 24, 2008, Brand emailed Nicholas asking\\nfor a time to update her on The Benefit Bank. In early May,\\n 23\\n\\fBrand sent another email to Nicholas attaching a revised\\nEAA–Solutions contract proposal, which decreased the\\ninitial upfront cost from $900,000 to $700,000.\\n Although Solutions and EAA had still not signed a\\ncontract, EAA paid Solutions another $100,000 in May.\\nThat money was obtained via a loan to EAA from CORE.\\nThomas Butler, who had worked for Fattah both when\\nFattah was in Congress and when he was in the General\\nAssembly, was CORE’s executive director. Butler had\\nbeen contacted in mid-May by Jackie Barnett, a member\\nof CORE’s Board who had also worked with\\nCongressman Fattah. Barnett informed Butler that\\nNicholas had requested a loan from CORE to EAA, and\\nthat Fattah, as Chairman of CORE’s Board, had approved\\nit. Butler and Barnett withdrew funds from two CORE\\nbank accounts and obtained a cashier’s check, dated May\\n19, in the amount of $225,000 and made payable to EAA.\\nThe withdrawals were from accounts used for Sallie Mae\\nfunds and other scholarship money.\\n After EAA received the $225,000 check, EAA\\ntendered a $100,000 check to Solutions. The check bore\\nthe notation “Commonwealth of Pennsylvania.” EAA\\nrepaid CORE the following month. Because EAA lacked\\nsufficient funds of its own to cover this payment, EAA\\ndrew on grant money that it had received from NASA.\\n\\n Brand and Lindenfeld continued to communicate\\nconcerning The Benefit Bank. In July of 2008, a meeting\\nwas held at Solutions with Brand, Lindenfeld, Golden, and\\n 24\\n\\fother Solutions employees to discuss “an enormous\\namount of work” that Brand wanted Strategies to do.\\nJA1670. Lindenfeld said in response “we’d be glad to do\\nthat, but . . . we would have to be paid.” Id. At that point,\\nsomeone in the meeting stated that Strategies “had already\\nbeen paid” $600,000. Id. Lindenfeld replied: “well, that\\nwas for Congressman Fattah, . . . that’s not for us. So if\\nyou want us to do work, we have to get paid for it\\nseparately.” Id. Brand became upset with Lindenfeld over\\nhis comment about being paid because his colleagues at\\nSolutions were not aware of the reason for the $600,000\\npayment.\\n Meanwhile, EAA was attempting to meet the\\ndemands of the DOJ auditors, who were focused on the\\nrelationship between EAA and CORE. DOJ served a\\nsubpoena upon Solutions to produce “[a]ny and all\\ndocuments including, but not limited to, contract\\ndocuments, invoices, correspondence, timesheets,\\ndeliverables and proof of payment related to any services\\nprovided to or payments received” from CORE or EAA.\\nJA2350.\\n\\n Special Agent Dieffenbach, from the DOJ,\\ninterviewed Nicholas on July 14, 2008. During that\\ninterview, Nicholas discussed the relationship between\\nEAA and CORE, how invoices were paid, and how\\nconsultants were handled. Nicholas also answered\\nquestions about EAA’s relationship with Solutions,\\nincluding the payment of invoices. She did not inform\\n\\n 25\\n\\fAgent Dieffenbach of the $500,000 payment in January or\\nthe subsequent $100,000 payment in May. Nor did the\\ninterview address the EAA–Solutions contract that\\npurportedly required those payments, because the contract\\nhad yet to be produced.\\n\\n Solutions failed to comply with the subpoena,\\nprompting an email from Agent Dieffenbach on August 26\\nasking for an update concerning Solutions’ reply to the\\nDOJ subpoena. Solutions then produced an undated\\nversion of the EAA–Solutions contract that required the\\n$600,000 upfront payment. Neither Brand nor Nicholas\\nprovided the auditors with the January and May checks\\nfrom EAA to Solutions.\\n Efforts to conceal the repayment of the Lord loan\\nand to promote the political and financial interests of\\nFattah continued. The FFM campaign reports indicated in-\\nkind contributions of debt forgiveness by SLA even\\nthough there had been no actual debt. In September of\\n2009, with EAA’s ledgers still under scrutiny, Nicholas\\naltered the description of the entry for the $100,000 check\\nto Solutions from “professional fees consulting” to\\n“CORE Philly.” JA2546. Other FFM campaign debt was\\nreduced further after Vederman negotiated with creditors.\\n\\n EAA never fully recovered from its payment of the\\n$600,000 balance on the Lord loan and the audits that took\\nplace in 2008. It began laying off employees in 2011, and\\nby June of 2012, only four employees remained. JA3659.\\nEAA ceased operations at some point in 2012. JA1530.\\n 26\\n\\f 2. The College Tuition Component of the FFM\\n Scheme\\n Although the FFM campaign was close to insolvent,\\nit nevertheless made tuition payments for Fattah’s son,\\nChaka Fattah Jr., also known as Chip. Chip attended\\nDrexel University, but had yet to complete his coursework\\nbecause he had failed to pay an outstanding tuition\\nbalance. As the FFM campaign got underway in 2007,\\nFattah wanted Chip to re-enroll in classes at Drexel and\\nget a degree. Fattah asked Naylor to help financially, and\\nhe did so by writing checks from SLA to Drexel toward\\nChip’s outstanding tuition. By October of 2007, Chip was\\npermitted to re-enroll in classes.\\n Although Naylor never directly addressed the issue\\nwith Fattah, he agreed to assist with Chip’s outstanding\\ntuition with the expectation that SLA would be repaid. The\\nfirst check to Drexel in the amount of $5,000 was sent in\\nAugust of 2007, with $400 payments in the months that\\nfollowed until August of 2008. At some point, Chip\\ninformed Naylor that the payee was no longer Drexel, but\\nSallie Mae. Naylor then began sending monthly checks\\nfrom SLA to Sallie Mae. Those payments, in the amount\\nof $525.52, began in March of 2009 and continued until\\nApril of 2011, after which Fattah told Naylor he no longer\\nneeded to make them. SLA’s payments to Drexel and\\nSallie Mae totaled $23,063.52.\\n\\n Naylor’s expectation of repayment was eventually\\nrealized. Beginning in January of 2008 and continuing\\n 27\\n\\funtil November 2010, Bowser sporadically sent SLA\\nreimbursement checks from the FFM campaign with a\\nnotation that payment was for “election day operation\\nexpenses.” JA3136. The FFM funds had been transferred\\nfrom the Fattah for Congress campaign. These\\nreimbursement checks totaled $25,400. In an effort to\\nconceal the source of the payments to Drexel and Sallie\\nMae, and to make it appear that the younger Fattah had\\nperformed services for SLA, Naylor created false tax\\nforms for Chip. Chip, however, had never performed\\nservices for SLA.\\n\\n 3. The NOAA Grant and the Phantom Conference\\n In mid-December 2011, when EAA was\\nexperiencing serious financial difficulties, Nicholas\\nsubmitted an email request to the educational partnership\\nprogram of the National Oceanic & Atmospheric\\nAdministration (NOAA) for a grant “designed to provide\\ntraining opportunities and funding to students at minority\\nserving institutions” interested in science, technology,\\nengineering, and math fields related to NOAA’s mission.\\nJA3354–55. The request sought $409,000 to fund EAA’s\\nannual conference scheduled for February 17–19, 2012.\\nJacqueline Rousseau, a supervisory program manager at\\nNOAA, participated in a conference call with Nicholas\\nshortly thereafter and advised Nicholas that the agency\\ncould not afford the $409,000 request but would consider\\na smaller grant. Rousseau advised Nicholas that EAA\\n\\n\\n 28\\n\\fwould need to submit an application if it wished to be\\nconsidered for a grant.\\n Before submitting a grant application, Nicholas\\nemailed Rousseau about sponsoring the conference. On\\nJanuary 11, 2012, Rousseau informed Nicholas that the\\n“NOAA Office of Education, Scholarship Programs has\\nagreed to participate and provide sponsorship funds of\\n$50K to support the referenced conference.” JA6453.\\nRousseau also informed Nicholas that Chantell Haskins,\\nwho also worked with the student scholarship program,\\nwould be the point of contact for NOAA.\\n In February 2012, EAA held its annual conference\\nat the Sheraton Hotel in downtown Philadelphia. The\\nconference had been held at the same location each year\\nsince 2008.\\n\\n Nicholas contacted Haskins at some point in early\\n2012, inquiring about the $50,000 grant. On May 8, 2012,\\nHaskins sent Nicholas an e-mail which included\\ninformation about submitting proposals to fund a\\nconference for students. EAA then submitted a grant\\napplication, which Haskins reviewed. She advised\\nNicholas on June 28, 2012 that the grant could not be used\\nto provide meals, and that the date of the conference would\\nhave to be pushed back, with the new date included in a\\nmodified application. When Nicholas asked if expenses\\nfrom a previous conference could be paid from the new\\ngrant, Haskins informed her that this was not allowed.\\n\\n 29\\n\\f In early July 2012, Nicholas sent a modified grant\\nproposal to Haskins. It eliminated the budget item for food\\nand changed the date of the 2012 conference to October\\n19–21, 2012 at the same Sheraton Hotel in Philadelphia\\nwhere EAA’s annual conference had taken place earlier in\\nthe year. NOAA approved a $50,000 grant for the October\\n2012 conference—a conference that would never be held.\\n\\n Unaware that no October 2012 conference had\\ntaken place, NOAA allowed Nicholas access to the\\n$50,000 grant in March of 2013. She then transferred the\\nentire amount from NOAA to EAA’s bank account a few\\ndays later. Naylor had performed services for EAA for\\nwhich he was still owed $116,590. JA3119. In discussions\\nwith Naylor, Nicholas had informed him that the\\nlikelihood of EAA’s being able to pay him was “[n]ot very\\ngood.” JA3120. Yet several days after EAA had received\\nthe $50,000 from NOAA, Nicholas sent Naylor a check\\nfor $20,000. JA3120, 4283.\\n\\n On April 3, 2013, Nicholas submitted a final report\\nto NOAA concerning EAA’s use of the grant. Notably,\\npage 4 of the report stated the conference had been held in\\nFebruary 2012, while page 17 stated that the conference\\nhad been held from October 19 to 21, 2012. NOAA issued\\na notice asking for clarification and for a list of students\\nwho had been supported at the conference. Nicholas failed\\nto file either a clarifying report regarding the date of the\\nconference or a timely report regarding the disbursement\\nof the grant. Finally, in November of 2013, Nicholas\\n\\n 30\\n\\fsubmitted the final Federal Financial Report in which she\\ncertified, falsely, that the $50,000 had been used for a\\nproject during the period from August 1, 2012 to\\nDecember 30, 2012.\\n\\n B. The Blue Guardians Scheme\\n In addition to functioning as the conduit for Lord’s\\n$1 million loan to Fattah’s campaign, Lindenfeld’s\\ncompany, Strategies, also performed services for the\\ncampaign. The work resulted in indebtedness from FFM\\nto Strategies of approximately $95,000. Fattah made\\nseveral small payments, but failed to pay the full amount\\ndue. Although Lindenfeld spoke to Fattah, Naylor and\\nBowser about the debt, no payments were forthcoming.\\nDuring a meeting in Fattah’s D.C. office, Fattah told\\nLindenfeld “that [repayment] really wasn’t going to be\\npossible because the campaign had been over for a long\\ntime” and the funds were not available. JA1693. Fattah\\nthen asked Lindenfeld if he could write off the debt on his\\nFFM campaign finance reports. Id. Lindenfeld told Fattah\\nthat as long as he was paid, it was not his business how\\nFattah disclosed it on the campaign finance reports.\\nJA1694.\\n In lieu of repayment, Fattah suggested that\\nStrategies could claim to be interested in setting up an\\nentity to address environmental issues and ocean pollution\\nalong the coastline and in the Caribbean. Fattah explained\\nthat creating such an entity would make it possible to\\nobtain an appropriation from the government. Hearing\\n 31\\n\\fthis, Lindenfeld knew he was not going to be paid by the\\nFFM campaign, and was amenable to receiving money\\nfrom an appropriation instead. At a later meeting,\\nLindenfeld told Fattah that the name of the entity would\\nbe “Blue Guardians.” Lindenfeld consulted with an\\nattorney about creating Blue Guardians as an entity to\\nreceive the federal grant. He emailed Fattah, asking\\nquestions about how to complete an application to the\\nHouse Appropriations Committee. Fattah provided\\nsuggestions, and an application was eventually completed.\\nIt indicated that Blue Guardians would be “in operation for\\na minimum of ten years,” and, in accordance with Fattah’s\\nguidance, requested $15 million in federal funds. JA1711–\\n13.\\n Lindenfeld submitted the application to Fattah’s\\noffice in April of 2009. Afterward, a Fattah staffer\\ncontacted Lindenfeld to suggest that he change his\\nWashington, D.C., address to Philadelphia because that\\nwas the location of Fattah’s district. Fattah later suggested\\nto Lindenfeld that Brand might allow the use of his\\nPhiladelphia office address, a plan to which Brand agreed.\\n\\n In February 2010, Lindenfeld submitted a second\\napplication to the Appropriations Committee. In March,\\nFattah submitted a project request using his congressional\\nletterhead and seeking $3,000,000 for the “Blue\\nGuardians, Coastal Environmental Education Outreach\\nProgram.” JA6432. Within a month, Blue Guardians had\\nboth articles of incorporation and a bank account. Around\\n\\n 32\\n\\fthat time, a news reporter contacted Lindenfeld to discuss\\nthe new Blue Guardians entity. The inquiry made\\nLindenfeld uncomfortable, and he ultimately decided to\\nabandon the Blue Guardians project. He continued to seek\\npayment from Fattah, to no avail.\\n\\n Nonetheless, having obtained Lindenfeld’s\\nacquiescence to writing off the campaign’s debt to\\nStrategies, Fattah started falsifying FFM’s campaign\\nreports. Beginning in 2009 and extending through 2013,\\nthe FFM campaign reports executed by Fattah and Bowser\\nstated that Strategies made in-kind contributions of\\n$20,000, until the debt appeared to have been paid in full.\\n\\n C. The Fattah–Vederman Bribery Scheme\\n Vederman and Fattah were personal friends.\\nVederman was a successful businessman who had also\\nserved in prominent roles in the administrations of Ed\\nRendell when he was Mayor of Philadelphia and Governor\\nof Pennsylvania. In November of 2008, Vederman was a\\nsenior consultant in the government and public affairs\\npractice group of a Philadelphia law firm. His assistance\\nto the FFM campaign included paying for rented vans used\\nin the get-out-the-vote effort.\\n\\n After Fattah’s electoral defeat, the campaign still\\nowed more than $84,000 to a different law firm for\\nservices performed for the campaign. Vederman\\napproached that firm in the summer of 2008 asking if it\\nwould forgive FFM’s debt. Negotiations resulted in a\\n 33\\n\\fcommitment from FFM to pay the firm $30,000 by the end\\nof 2008 in exchange for forgiveness of $20,000, all of\\nwhich would appear on the FFM campaign finance report.\\nVederman’s efforts also led to payment by Fattah of an\\nadditional $10,000 in 2009 to the law firm, in exchange\\nfor additional forgiveness of $20,000 of debt. It was not\\nlong after Vederman’s successful efforts to lower Fattah’s\\ncampaign debt, that Fattah wrote a letter to U.S. Senator\\nRobert P. Casey recommending Vederman for an\\nambassadorship.\\n\\n At some point in 2010, Vederman again intervened\\non behalf of the FFM campaign. FFM remained in debt to\\nan advertising and public relations firm owned by Robert\\nDilella. By late 2011, Vederman and Dilella had worked\\nout a settlement to resolve the outstanding debt. Pursuant\\nto that settlement, Dilella received partial payment from\\nthe FFM campaign: $25,000 in satisfaction of a $55,000\\ndebt. Dilella testified at trial that he would not have agreed\\nto retire a portion of the debt had he known the FFM\\ncampaign was paying college tuition for Fattah’s son.\\n Vederman helped Fattah financially in other ways.\\nBefore the 2006 FFM campaign, Fattah and his wife,\\nRenee Chenault-Fattah, sponsored a young woman named\\nSimone Muller to live with them as an au pair exchange\\nvisitor. Muller was from South Africa, and her J-1 visa\\nallowed her to serve as a nanny and to study in the United\\nStates. Muller later applied for and received a second visa,\\nan F-1 student visa that indicated she had been accepted as\\n\\n 34\\n\\fan international student at the Community College of\\nPhiladelphia. The application indicated that Muller would\\nagain be residing with the Fattahs. Notwithstanding this\\nliving arrangement, Fattah identified Vederman as the\\nperson who would be paying for Muller’s trip to the\\nUnited States.\\n By the beginning of 2010, Muller wished to transfer\\nto Philadelphia University. This required her to submit\\nverification that funds were available to pay for her study.\\nAlthough the Fattahs were Muller’s sponsors, Fattah\\nexplained to the University’s Dean of Enrollment Services\\nthat he was submitting a letter of secondary support from\\nVederman. JA3754, 3763–65, 6504. Without Vederman’s\\nJanuary 2010 letter of support, the University would not\\nhave admitted Muller. In addition to this pledge of support,\\nVederman paid $3,000 of Muller’s tuition. Shortly\\nthereafter, Fattah resumed his efforts to secure an\\nambassadorship for Vederman.\\n\\n In February of 2010, Fattah staffer Maisha Leek\\ncontacted Katherine Kochman, a scheduler for White\\nHouse Chief of Staff Rahm Emanuel. Leek requested a\\ntelephone conference with Emanuel, Rendell, and Fattah\\nto discuss Vederman’s “serving his country in an\\ninternational capacity.” JA2893. In a follow-up email on\\nMarch 26, Leek sent documents to Kristin Sheehy, a\\nsecretary to White House Deputy Chief of Staff James\\nMessina. The documents included Fattah’s 2008 letter to\\nSenator Casey and Vederman’s biography. After\\n\\n 35\\n\\fparticipating in a telephone conference about Vederman\\nwith Fattah and Rendell, Messina sent Vederman’s\\nbiography to the White House personnel office for\\nconsideration.\\n\\n As the April 2010 tax deadline approached, Fattah\\nstill owed the City of Philadelphia earned income tax in\\nthe amount of $2,381. Just days before the filing deadline,\\nVederman gave a check to Chip Fattah for $3,500. The\\nyounger Fattah quickly deposited $2,310 into his father’s\\nbank account. Fattah paid his tax bill on April 15. Without\\nChip’s deposit into his father’s bank account, the older\\nFattah would not have had sufficient funds to pay his tax\\nbill.\\n On October 30, 2010, Vederman gave Chip another\\ncheck, this one for $2,800. That same day, Fattah hand-\\ndelivered a letter to President Obama recommending\\nVederman for an ambassadorship. A few weeks later,\\nFattah’s staffer, Leek, sent the letter that Fattah had given\\nto President Obama to Messina’s office. That letter\\npointed out that both Rendell and Fattah had sent letters\\non behalf of Vederman, and that he was an\\n“unquestionably exceptional candidate for an\\nambassadorship.” JA6291–92.\\n\\n Fattah’s efforts to secure Vederman an\\nambassadorship were unsuccessful. Fattah then shifted\\ngears and sought to secure Vederman a position on a\\nfederal trade committee. Fattah approached Ron Kirk, who\\nserved as U.S. Trade Representative, and asked him to\\n 36\\n\\fspeak with a constituent. In May of 2011, Leek followed\\nup on that discussion by emailing Kirk and asking him to\\nmeet with Vederman. Kirk met with Vederman on June 5,\\n2011 and explained to him the role of the trade advisory\\ncommittees. Although the two men “had a very nice\\nconversation,” JA 3566, it soon became “pretty apparent\\nto [Kirk and his staff] that [serving on a trade advisory\\ncommittee was] not what Mr. Vederman was interested\\nin.” JA3567. As Kirk put it, “it was obvious that\\n[Vederman] was looking for something perhaps more\\nrobust in his mind or . . . higher profile than one of our\\nadvisory committees.” Id. Given Vederman’s lukewarm\\ninterest, no appointment to an advisory committee was\\nforthcoming.\\n In late December 2011, the Fattahs applied for a\\nmortgage so they could purchase a second home in the\\nPoconos. Shortly after applying for the mortgage, Fattah\\nemailed Vederman, offering to sell him his wife’s 1989\\nPorsche for $18,000. Vederman accepted the offer. The\\nnext day, Vederman wired $18,000 to Fattah’s Wright\\nPatman Federal Credit Union account.\\n\\n The Credit Union Mortgage Association (CUMA)\\nacted as the loan processing organization for the home\\nmortgage. Because CUMA is required to verify the source\\nof any large deposits, CUMA’s mortgage loan processor,\\nVictoria Souza, contacted Fattah on January 17, 2012, to\\nconfirm the source of the $18,000. Fattah informed Souza\\nthat the $18,000 represented the proceeds of the Porsche\\n\\n 37\\n\\fsale. Souza requested documentation, including a signed\\nbill of sale and title.\\n That same day, Bowser emailed Vederman a blank\\nbill of sale for the Porsche. After Vederman signed the bill\\nof sale, Fattah forwarded it to Souza. The bill of sale was\\ndated January 16, 2012, which was the day before Souza\\nhad requested the documentation. It bore the signatures of\\nRenee Chenault-Fattah and Herbert Vederman, with\\nBonnie Bowser as a witness.\\n\\n Fattah also provided Souza with a copy of the\\nPorsche’s title. It was dated the same day it was sent to\\nSouza, and bore signatures of Chenault-Fattah as the seller\\nand Vederman as buyer, along with a notary’s stamp.\\nNeither Vederman nor Chenault-Fattah actually appeared\\nbefore the notary.\\n\\n Vederman never took possession of the Porsche.\\nRenee Chenault-Fattah continued to have the Porsche\\nserviced and insured long after the purported sale had\\ntaken place. Moreover, the Porsche remained registered in\\nChenault-Fattah’s name, and was never registered to\\nHerbert Vederman. When FBI agents searched the\\nFattahs’ home in 2014, the Porsche was discovered in the\\nFattahs’ garage.\\n\\n On January 24, 2012, the Fattahs wired $25,000 to\\nthe attorney handling the escrow account for the purchase\\nof the vacation home. Without the $18,000 transfer from\\n\\n 38\\n\\fVederman, the Fattahs would not have had sufficient funds\\nin their bank accounts to close on the home.\\n Around the same time that the Fattahs were\\npurchasing the house in the Poconos, Fattah’s Philadelphia\\noffice hired Vederman’s longtime girlfriend, Alexandra\\nZionts. Zionts had long worked for a federal magistrate\\njudge in Florida. Near the end of 2011, the magistrate\\njudge retired, leaving Zionts ten months shy of obtaining\\nthe necessary service required to receive retirement\\nbenefits. If Zionts could find another job in the federal\\ngovernment, her benefits and pension would not be\\nadversely affected. Vederman assisted Zionts in her job\\nsearch, which included calling Fattah. Fattah hired her, a\\nmove that put his congressional office overbudget. Zionts\\nworked in Fattah’s office for only about two months,\\nleaving to work for a congressman from Florida.\\n\\n Tia Watson, who performed constituent services for\\nFattah and worked on the same floor as Zionts in Fattah’s\\ndistrict office, testified she had no idea what work Zionts\\nperformed. Although Zionts contacted Temple University\\nabout archiving Fattah’s papers from his career in both the\\nstate and federal government, an employee from Temple\\nUniversity observed that Zionts’ work contributed nothing\\nof value to the papers project.\\n\\n D. The Indictment and Trial\\n Fattah’s schemes eventually unraveled. On July 29,\\n2015, a federal grand jury in the Eastern District of\\n 39\\n\\fPennsylvania returned a twenty-nine count indictment\\nalleging that Fattah and his associates had engaged in a\\nvariety of criminal acts. Fattah, Vederman, Nicholas,\\nBrand, and Bowser were charged with unlawfully\\nconspiring to violate the Racketeer Influenced and Corrupt\\nOrganizations Act (RICO), 18 U.S.C. § 1962(d). In\\naddition to the RICO charge, the indictment alleged that\\nFattah and certain co-defendants had unlawfully conspired\\nto commit wire fraud, 18 U.S.C. §§ 1343, 1349; honest\\nservices fraud, 18 U.S.C. §§ 1343, 1346, 1349; mail fraud,\\n18 U.S.C. §§ 1341, 1349; money laundering, 18 U.S.C.\\n§ 1956; and to defraud the United States, 18 U.S.C. § 371.\\nSeveral defendants were also charged with making false\\nstatements to banks, 18 U.S.C. § 1014; falsifying records,\\n18 U.S.C. § 1519; laundering money, 18 U.S.C. § 1957;\\nand engaging in mail, wire, and bank fraud, 18 U.S.C.\\n§§ 1341, 1343, and 1344.\\n\\n The RICO charge alleged that the defendants and\\nother co-conspirators constituted an enterprise aimed at\\nsupporting and promoting Fattah’s political and financial\\ninterests. The efforts to conceal the $1 million Lord loan\\nand its repayment are at the heart of the RICO conspiracy\\nand the Fattah for Mayor scheme. The indictment further\\nalleged that the RICO enterprise involved: (1) the scheme\\nto satisfy an outstanding campaign debt by creating the\\nfake “Blue Guardians” nonprofit; and (2) the bribery\\nscheme to obtain payments and things of value from\\nVederman in exchange for Fattah’s efforts to secure\\nVederman an appointment as a United States Ambassador.\\n 40\\n\\f A jury trial, before the Honorable Harvey Bartle III\\nof the Eastern District of Pennsylvania, began on May 16,\\n2016, and lasted about a month. 7 Judge Bartle charged the\\njury on Wednesday, June 15, 2016, and deliberations\\nbegan late that afternoon. The following day, after\\ndeliberating for only four hours, the jury sent a note to the\\njudge. Written by the foreperson, the note read:\\n Juror Number 12 refuses to vote by the letter\\n of the law. He will not, after proof, still\\n change his vote. His answer will not change.\\n He has the 11 of us a total wreck knowing that\\n we are not getting anywhere in the hour of\\n deliberation yesterday and the three hours\\n today. We have zero verdicts at this time all\\n due to Juror Number 12. He will not listen or\\n reason with anybody. He is killing every\\n other juror’s experience. We showed him all\\n the proof. He doesn’t care. Juror Number 12\\n has an agenda or ax to grind w/govt.\\nJA5916.\\n\\n Shortly after receiving the foreperson’s note, the\\nCourt received a second communication—a note signed\\n\\n\\n\\n 7\\n The District Court dismissed one charge prior to\\ntrial: an individual money laundering count against\\nNicholas.\\n 41\\n\\fby nine jurors, including the foreperson. The second note\\nread:\\n We feel that [Juror 12] is argumentative,\\n incapable of making decision. He constantly\\n scream [sic] at all of us.\\nId.\\n Judge Bartle met with counsel in his chambers and\\nadvised them of his intention to voir dire both the\\nforeperson and Juror 12 in an effort to determine whether\\nthe juror was deliberating as required by his oath. The\\nJudge also indicated that he would “stay away from the\\nmerits of the case,” and that whether he would voir dire\\nmore jurors “remain[ed] to be seen.” JA5917.\\n Counsel for the defendants objected to the Court’s\\nproposed inquiry. As a group, they indicated that while the\\nnote could be read as suggesting “a flat refusal to\\ndeliberate,” they were of the opinion that it sounded “more\\nin the manner of a disagreement over the evidence.”\\nJA5918. Nicholas’s counsel specifically argued that\\nquestioning the jurors so quickly after the start of\\ndeliberations would send a message that differences of\\nopinion among a block of jurors could be resolved by\\ncomplaining to the Court. Defense counsel acknowledged\\nthat the case law gave Judge Bartle wide discretion on how\\nto proceed, but suggested that a “less intrusive” course of\\naction was preferred. JA5918–19. They collectively urged\\n\\n 42\\n\\fthe Court to do nothing more than remind the jurors of\\ntheir duty to deliberate.\\n The Government agreed with Judge Bartle’s\\nproposed voir dire. In the prosecution’s view, the Court\\nhad already given proper instructions to the jury on their\\nduty to deliberate. The Government further argued that if\\nJuror 12 had exhibited bias, as suggested in the notes, he\\nwould have lied during the voir dire process and his\\nrefusal to deliberate would be “further evidence of that and\\nhis unsuitability as a juror.” JA5921.\\n\\n With all counsel present, and over defense counsel’s\\nobjections, Judge Bartle ultimately questioned five jurors\\nin chambers. He questioned Juror 2 (the foreperson), Juror\\n12 (the subject of the complaints), Juror 3, Juror 6, and\\nJuror 1.\\n\\n Judge Bartle began each voir dire by informing the\\njuror that he would ask a series of questions, but would not\\ninquire into the merits of the case or how any juror was\\nvoting. Each juror was placed under oath, and Judge Bartle\\nasked, among other questions, whether screaming was\\noccurring; whether the jurors were discussing the\\nevidence; whether Juror 12 was placing his hands on other\\njurors; and whether Juror 12 was unwilling to follow his\\ninstructions.\\n The foreperson acknowledged that he had written\\nthe initial note during lunch earlier that day. He stated that\\nJuror 12 was not willing to follow the law, but instead\\n 43\\n\\f“want[ed] to add his own piece of the law . . . which has\\nnothing to do with it.” JA5927–28. The foreperson further\\ntestified that Juror 12 “was standing up screaming” and\\nthat “[i]t was everybody pretty much against [Juror 12].”\\nJA5929. He testified that Juror 12 “has his own agenda,”\\nand that Juror 12 put his hand on another juror. JA5930.\\nThe foreperson also stated that the jury had discussed only\\na single count since the day before, and that they were still\\ndiscussing it. When the District Court responded that the\\njurors should understand that they could take as much time\\nas they needed, the foreperson responded: “I understand\\nthat. . . . [W]e all understand it. But we feel that he’s just—\\nhe’s got another agenda.” JA5934.\\n Judge Bartle advised counsel that he considered this\\n“a very serious situation” and that he would proceed to\\nvoir dire Juror 12. JA5937. Fattah’s counsel renewed his\\nobjection to questioning Juror 12, which the Court\\noverruled. Brand’s counsel argued that because the Court\\nhad decided to voir dire Juror 12, it should also voir dire\\nan additional juror. The Court agreed to do so.\\n When the Court questioned Juror 12, he admitted to\\nhaving “yelled back” at others, but only when they raised\\ntheir voices to him. JA5939. Juror 12 contended that he, in\\nfact, was “the only one” deliberating. Id. When an initial\\nvote was taken the previous afternoon, his vote “was\\ndifferent than everybody else’s.” Id. Juror 12 explained to\\nthe other jurors why his vote was different, bringing up\\nspecific evidence. In response, the other jurors said “that\\n\\n 44\\n\\fdoesn’t mean anything” and “pointed to the indictment.”\\nJA5940. Juror 12 told the other jurors that the indictment\\nis not evidence. Id. In response, the others “threatened to\\nhave [him] thrown off.” Id.\\n\\n Juror 12 testified that a similar sequence of events\\nhad taken place that morning. After a brief period of\\ndeliberations, another vote was taken, and with the same\\nresult as the previous afternoon. A discussion ensued, and\\nthe other jurors again “point[ed] to the indictment.” Id.\\nJuror 12 told them to “read the charge,” “[t]he indictment\\nis not evidence.” Id. They read the charge, and Juror 12\\nagain attempted to explain his view, but the other jurors\\npaid little attention. Accordingly, Juror 12 told the others\\nthat if they did not want him there, he “[didn’t] want to be\\n[there]”—he would be “[o]kay with it” if they wanted him\\ntaken off the jury. JA5941.\\n Upon hearing this testimony, Judge Bartle again\\nasked about the tone of deliberations. Juror 12 repeated\\nthat he raised his voice only in response to others who did\\nso—he did “not want to yell at anybody.” JA5942. Judge\\nBartle then asked whether he had touched other jurors.\\nJuror 12 replied that he had not hurt anyone. When asked\\nif he had put his hand on anybody’s shoulder, Juror 12\\nanswered: “I couldn’t remember to be honest with you.”\\nJA5946.\\n\\n Following Juror 12’s voir dire, the Court summoned\\nJuror 3 to chambers. Juror 3 testified that, after discussion\\nof a particular count, there was one juror at odds with the\\n 45\\n\\fothers. According to Juror 3, “the rest of the jurors\\npounced on the gentleman with the . . . dissenting\\nopinion.” JA5948. Juror 3 testified that Juror 12 “got very\\ndefensive and just a little bit [] impatient” and that “the\\nother jurors were very impatient with him.” Id. Juror 3 did\\nnot recall witnessing Juror 12 putting his hand on any\\nother jurors.\\n\\n The Government requested that the Court voir dire\\nanother juror. Defense counsel objected, claiming that the\\nquestioning “threaten[ed] . . . the entire deliberative\\nprocess.” JA5949–50. Judge Bartle reminded counsel that\\nhe had the authority to question each juror, and called for\\nvoir dire of Juror 6.\\n Juror 6 testified that the jury had been discussing the\\ncase and reviewing the evidence, but that Juror 12 “wants\\nto be seen” and was “being obstinate.” JA5951–52.\\nAccording to Juror 6, Juror 12 “may not agree” with the\\nconclusion of other jurors but “doesn’t give valid reasons\\nas to why he may disagree with the charge.” JA5952. Juror\\n6 also revealed that Juror 12 was the first to raise his voice,\\nand that he may have touched her and another juror. When\\nasked to clarify what she meant by Juror 12 disagreeing\\nwith “the charge,” Juror 6 testified that Juror 12 was\\n“reading maybe too deeply into it and putting his own\\nemotions into it instead of just looking at what it says [and]\\nwhat the facts are.” JA5952, 5955. According to Juror 6,\\nJuror 12 “just continues to read past that into his own mind\\nof what he feels it should be.” JA5955. Juror 6 testified\\n\\n 46\\n\\fthat Juror 12’s “justification for some of his responses [did\\nnot] seem to relate to what the matter [was] before\\n[them].” JA5957.\\n Judge Bartle chose to hear from yet another juror.\\nJuror 1 was called and informed the Court and counsel that\\nthe jury “really [hadn’t] been able to even start the\\ndeliberation process” in light of the disruptive behavior of\\n“one particular individual.” JA5958–59. The particular\\nindividual, according to Juror 1, was “very opinionated”\\nand “[came] into the process with his view already\\nestablished, refusing to even listen to any of the evidence\\n. . . [being] very forceful . . . standing up, yelling, pointing\\nhis finger.” JA5959. When asked if this individual was\\nwilling to follow the Court’s instructions, Juror 1 testified\\nthat he “pours [sic] over the documents very well” but that\\nhe was adding other factors to answer the question on the\\nverdict form, such as “what did this person feel.” JA5961.\\nWhen Judge Bartle advised that intent was an appropriate\\nconsideration, Juror 1 agreed but said that Juror 12 was\\n“trying to investigate . . . going way beyond the scope” of\\nthe evidence before them. JA5961–62. Juror 12, he said,\\n“has an opinion and that opinion is established.” JA5962.\\nHe stated that Juror 12 was “not willing to listen to any\\nsort of reason or any sort of what everyone else is saying”\\nbut instead, was “trying to force everyone else to get to his\\npoint of view.” Id. “[I]f he feels like he’s not getting there,\\nhe gets louder and louder and points and puts his hand on\\nyour shoulder . . . .” Id.\\n\\n 47\\n\\f After questioning the five jurors (Jurors 1, 2, 3, 6,\\nand 12), Judge Bartle heard argument from counsel. The\\nattorney for the Government pointed out that the Court\\nwould have to make a credibility determination because\\nJuror 12 stated that he did not recall touching anyone. In\\nthe Government’s view, Juror 12 was disrupting the\\nprocess and should be removed. Defense counsel\\ndisagreed. They argued that Juror 12 was conscientious\\nand was engaging with the evidence. They pointed out that\\ndespite the testimony that Juror 12 was reading too deeply\\ninto the instructions or introducing new factors for the jury\\nto consider, Juror 6 had testified that the jurors “talked it\\nthrough” and resolved the concern. JA5965. Defense\\ncounsel argued that the jury was discussing intent, an issue\\nthat was at the heart of the case. Defense counsel perceived\\nno breakdown in deliberations and argued that dismissal\\nwould be premature. They suggested, instead, that the\\nCourt provide a supplemental instruction.\\n\\n Judge Bartle decided to adjourn for the afternoon.\\nBut before he left the courtroom, defense counsel brought\\ntwo matters to his attention. First, in light of testimony\\nduring the voir dire, they asked that the jury be\\nreinstructed that the verdict form and indictment were not\\nevidence. Second, they apprised the Judge of the standard\\nfor juror dismissal set forth in United States v. Kemp, 500\\nF.3d 257 (3d Cir. 2007). Defense counsel stated that under\\nKemp, a request to discharge a juror must be denied if there\\nis a possibility that the request stems from the juror’s view\\nof the evidence. Judge Bartle expressed hesitation on\\n 48\\n\\freinstructing the jury, but agreed that Kemp would control\\nhis determination as to whether dismissal was appropriate.\\n With the following morning came a new revelation.\\nWith counsel in chambers, the Judge informed them that\\n“additional significant evidence” had come to light since\\nthe previous day’s recess. JA5980. He placed his\\ncourtroom deputy under oath, and she proceeded to testify\\nto an exchange that had occurred the previous day as she\\nwas escorting Juror 12 back to the jury room after he had\\nbeen voir dired. According to the deputy, Juror 12 stopped\\nher in the hallway, placed his hand on her shoulder, and\\nlooked her “straight in the eye.” JA5981. He then said:\\n“I’m going to hang this jury.” Id. The deputy then related\\nthat before any further conversation could take place\\nbetween Juror 12 and the deputy, Judge Bartle summoned\\nJuror 12 back to his chambers. Later that day, however,\\nJuror 12 and the courtroom deputy had another exchange.\\nShe testified that after all five jurors had been questioned,\\nJuror 12 emerged from the jury room and told her “I really\\nneed to talk to you.” JA5982. She informed Judge Bartle\\nand counsel that Juror 12 “said more about how they’re\\ntreating him and what he’s saying to them.” Id. He flatly\\nstated that “it’s going to be 11 to 1 no matter what.” Id.\\n\\n There were no follow-up questions for the deputy.\\nInstead, defense counsel suggested that what Juror 12 may\\nhave meant was that he was willing to hang the jury\\nbecause of a lack of evidence. They requested that Juror\\n12 be asked about his comments to the deputy.\\n\\n 49\\n\\f After once again summoning Juror 12 to his\\nchambers, the Judge advised him that “[s]ome questions\\nhave arisen” about what he may have done after being voir\\ndired the previous day. JA5985. Juror 12 acknowledged\\nhaving conversations with the courtroom deputy. When\\nasked “what happened” and “[w]hat occurred,” Juror 12\\nresponded: “Basically, I said that there was a lot of name\\ncalling going on.” JA5985. He said comments had been\\nmade by other jurors about his service in the military. He\\nspecifically referred to other jurors’ suggesting that he had\\npossibly “hit [his] head . . . hard a few times” while\\nserving in a parachute regiment. JA5986. He testified he\\nhad conveyed these comments to the deputy and that he\\nfound them offensive. When asked if he said anything else\\nto the deputy, Juror 12 responded: “I may have. I really\\ncan’t recall.” JA5987. And when Judge Bartle followed up\\nby asking if he could recall anything else that he said to\\nthe deputy, Juror 12 simply replied: “No. To me, that was\\nthe most important thing.” Id. Juror 12 was then excused\\nfrom chambers.\\n Defense counsel next requested that the juror be\\nasked directly whether he told the courtroom deputy that\\nhe was going to “hang this jury.” JA5988. Juror 12 was\\nrecalled to chambers, and the following back and forth\\ntook place:\\n\\n The Court: You may be seated. And, of\\n course, [Juror 12], you know you’re under\\n oath here from yesterday?\\n\\n 50\\n\\f Juror 12: Yes, sir.\\n The Court: . . . Did you say to [the courtroom\\n deputy] that you’re going to hang this jury?\\n Juror 12: I said I would.\\n The Court: You did?\\n Juror 12: I did. I said—I told her—I said, we\\n don’t agree; I’m not just going to say guilty\\n because everybody wants me to, and if that\\n hangs this jury, so be it.\\n ....\\n Juror 12: I did say that, sir.\\n The Court: You didn’t remember that before?\\n Juror 12: I’m more concerned about people\\n spitting on my military record.\\n The Court: Did you say that you’d hang the\\n jury no matter what?\\n Juror 12: If they do—if we cannot come to—\\n The Court: No. The question is what you said\\n to her. Did you say to her you would hang the\\n jury no matter what?\\n Juror 12: I can’t really remember that. I did\\n say that if we didn’t—a person—no matter\\n what, I can’t recall that exactly.\\n The Court: All right. Thank you very much.\\n You can wait just out there in the anteroom.\\nJA5989–90.\\n\\n Defense counsel continued to oppose Juror 12’s\\ndismissal. They argued that the juror’s concern was about\\n\\n 51\\n\\fthe evidence, and that his comments to the courtroom\\ndeputy reflected a conviction that “he’s not going to agree\\njust because others want him to agree.” JA5991. They also\\nargued that nothing should be made of Juror 12’s failure\\nto mention the comments when initially questioned by the\\nCourt, and that a supplemental instruction was all that was\\nwarranted given the early stage of the deliberations.\\n\\n The Government strongly disagreed. The Assistant\\nUnited States Attorney argued that Juror 12 “should\\nabsolutely be removed” because “his demeanor ha[d]\\ndemonstrated a hostility . . . both to the other jurors and to\\nthe court.” JA5993. The Government also suggested that\\nJuror 12’s comments that he would hang the jury meant\\nthat he was not participating in the deliberations and was\\nignoring the evidence and the law.\\n\\n Ruling from the bench, Judge Bartle announced:\\n I find [the deputy clerk] to be credible. I find\\n [Juror 12], not to be credible. I find that [Juror\\n 12] did tell [the deputy clerk] that he was\\n going to hang this jury no matter what.\\n There have been only approximately\\n four hours of deliberation. There’s no way in\\n the world he could have reviewed and\\n considered all of the evidence in the case and\\n my instructions on the law.\\n I instructed the jury to deliberate,\\n meaning to discuss the evidence; obviously,\\n to hold onto your honestly held beliefs, but at\\n 52\\n\\f least you have to be willing to discuss the\\n evidence and participate in the discussion\\n with other jurors.\\n Juror number 12 has delayed,\\n disrupted, impeded, and obstructed the\\n deliberative process and had the intent to do\\n so. I base that having observed him, based on\\n his words and his demeanor before me.\\n He wants only to have his own voice\\n heard. He has preconceived notions about the\\n case. He has violated his oath as a juror.\\n And I do not believe that any further\\n instructions or admonitions would do any\\n good. I think he’s intent on, as he said,\\n hanging this jury no matter what the law is,\\n no matter what the evidence is.\\n Therefore, he will be excused, and I\\n will replace him with the next alternate . . . .\\n\\nJA5994–95.\\n In response, defense counsel moved for a mistrial,\\nwhich the judge promptly denied. He then informed the\\nreconstituted jury that deliberations would need to start\\nover, and reinstructed them on certain points of law,\\nincluding that the verdict slip does not constitute evidence.\\n\\n Judge Bartle elaborated upon his decision to remove\\nJuror 12 in two post-trial memorandum opinions. In the\\nfirst, ruling on a media request for the sealed transcripts,\\nhe explained:\\n 53\\n\\f Here, there is no doubt that Juror 12\\n intentionally refused to deliberate when he\\n declared so early in the process that he would\\n hang the jury no matter what. This finding\\n was predicated on the admission of Juror 12\\n as reported by the court’s deputy clerk. The\\n facts became clear to the court after hearing\\n the credible testimony of the deputy clerk and\\n the less credible testimony of Juror 12. The\\n demeanor of Juror 12 before the court\\n confirmed the court’s findings.\\n\\nGSA23–24. The second opinion addressed motions for\\nbail pending appeal from Nicholas and Brand. GSA25.\\nThere, Judge Bartle explained:\\n\\n The law is well-settled that the court has\\n discretion to act as it did under these\\n circumstances. See United States v. Kemp,\\n 500 F.3d 257, 304 (3d Cir. 2007). The court,\\n after taking testimony, specifically found that\\n the juror, following only a few hours of\\n deliberation, stated to the court’s courtroom\\n deputy clerk that he would hang this jury no\\n matter what. He could not possibly have\\n reviewed all of the law and evidence of this\\n five-week trial at the time he made his\\n remark. The court examined the deputy clerk\\n and the juror under oath in the presence of\\n counsel for all parties. The undersigned\\n\\n 54\\n\\f found the deputy clerk to be credible and the\\n juror not to be credible. Based on the juror’s\\n demeanor, it was clear he would not change\\n his attitude and that his intent had been and\\n would continue to be to refuse to deliberate\\n in good faith concerning the law and the\\n evidence.\\n\\nGSA32.\\n After deliberating for approximately 15 hours, the\\njury returned with its verdicts on June 21, 2016, finding\\nthe defendants guilty on most counts. Fattah, Vederman,\\nand Brand were convicted on all counts. The jury acquitted\\nBowser on sixteen counts, but found her guilty of the\\nbribery conspiracy and the associated charges of bank\\nfraud, making false statements to a financial institution,\\nfalsifying records, and money laundering (Counts 16, 19,\\n20, 21 and 22). The jury also acquitted Nicholas of wire\\nfraud (Count 24). See Nicholas Supp. App. (NSA) 36.\\n The following week, on June 27, the Supreme Court\\nissued its opinion in McDonnell v. United States, 136 S.\\nCt. 2355 (2016). McDonnell provided new limitations on\\nthe definition of “official acts” as used in the honest\\nservices fraud and bribery statutes under which Fattah and\\nVederman had been convicted. Id. at 2369–72. Fattah and\\nVederman both moved to set aside their convictions. The\\nDistrict Court “acknowledge[d] that under McDonnell our\\ninstructions to the jury on the meaning of official act\\nturned out to be incomplete and thus erroneous.” JA103.\\n 55\\n\\fBut the Court held that “the incomplete and thus erroneous\\njury instruction on the meaning of official acts did not\\ninfluence the verdict on the bribery counts” and upheld the\\nverdict on Counts 16–18 and 22–23. JA107, 121.\\n\\n Fattah, Vederman, and Bowser had more success\\nwith their other post-verdict motions. The District Court,\\nin a thoughtful opinion, granted relief under Federal Rule\\nof Criminal Procedure 29, acquitting Vederman of the\\nRICO conspiracy (Count 1) and Fattah, Vederman, and\\nBowser of bank fraud, making false statements to a\\nfinancial institution, and falsifying records (Counts 19, 20,\\nand 21). JA37–139.\\n This appeal followed. 8 The defendants raise a\\nvariety of challenges to their convictions. All defendants\\nbut Bowser challenge the District Court’s decision to\\ndismiss Juror 12. Fattah and Vederman argue that the\\nDistrict Court erred in upholding the jury’s verdict on the\\nbribery and honest services fraud counts in light of the\\nSupreme Court’s decision in McDonnell. Fattah, Brand\\nand Nicholas challenge the sufficiency of the evidence\\nunderlying the RICO conviction. Several of the defendants\\ncontend the District Court erred in its instruction on intent\\nand by sending the indictment out to the jury. There are\\n\\n\\n\\n8\\n Fattah, Brand, Vederman, and Nicholas each filed a\\ntimely notice of appeal, but Bowser did not challenge her\\nconvictions.\\n 56\\n\\falso several evidentiary challenges.9 The Government\\ncross-appeals from the District Court’s judgment\\nacquitting Fattah and Vederman on Counts 19 and 20,\\narguing that the District Court erred in interpreting the\\ndefinition of a “mortgage lending business” under 18\\nU.S.C. § 27. We address these arguments in turn.\\n\\n We hold that the District Court erred in upholding\\nthe jury verdict in light of McDonnell, and we will\\ntherefore reverse and remand for retrial on Counts 16, 17,\\n18, 22, and 23. We also hold that the District Court erred\\n\\n9\\n Pursuant to Rule 28(i), “Fattah joins in the arguments of\\nHerbert Vederman, Robert Brand, and Karen Nicholas to\\nthe extent their arguments on appeal apply to Mr. Fattah.”\\nFattah Br. 19 n.69. Federal Rule of Appellate Procedure\\n28(i) provides that a defendant, “[i]n a case involving\\nmore than one appellant . . . may adopt by reference a part\\nof another’s brief.” Here, Fattah’s decision to join fails to\\nspecify which of the many issues of his codefendants he\\nbelieves worthy of our consideration. Rather, it appears\\nthat he presumes we will scour the record and make that\\ndetermination for him. This type of blanket request fails to\\nsatisfy Rule 28(a)(5)’s directive requiring that the\\n“appellant’s brief must contain . . . a statement of the\\nissues presented for review.” Fed. R. App. P. 28(a)(5). We\\nconclude that expecting the appellate court to identify the\\nissues to be adopted simply results in the abandonment and\\nwaiver of the unspecified issues. See Kost v. Kozakiewicz,\\n1 F.3d 176, 182 (3d Cir. 1993).\\n 57\\n\\fin acquitting Fattah and Vederman on Counts 19 and 20.\\nBecause the jury’s verdict was supported by the evidence,\\nwe will reinstate the convictions as to those counts. In all\\nother respects, we will affirm the judgment of the District\\nCourt.\\n\\n III. Juror Misconduct and Dismissal of Juror 12 10\\n Defendant Fattah challenges the District Court’s\\ndecision to conduct an in camera inquiry into alleged juror\\nmisconduct and the ultimate dismissal of Juror 12. 11 We\\nreject both challenges. The record reveals credible\\nallegations of juror misconduct and a sufficient basis to\\nsupport the finding that Juror 12 violated his oath.\\n\\n A. Investigation of Alleged Juror Misconduct\\n We first consider whether the District Court erred in\\nits handling of the two notes from jurors. A trial court’s\\nresponse to allegations of juror misconduct is reviewed\\nunder an abuse of discretion standard. United States v.\\nBoone, 458 F.3d 321, 326 (3d Cir. 2006) (citing United\\nStates v. Resko, 3 F.3d 684, 690 (3d Cir. 1993)). We\\nconclude that the District Court did not abuse its discretion\\n\\n\\n10\\n The District Court had jurisdiction under 18 U.S.C.\\n§ 3231. We have jurisdiction under 28 U.S.C. § 1291 and\\n18 U.S.C. § 3742(a).\\n11\\n Vederman, Nicholas, and Brand adopt Fattah’s claim of\\nreversible error concerning the dismissal of Juror 12.\\n 58\\n\\fin addressing the issues raised in the jurors’ notes to the\\nCourt.\\n Trial courts are afforded discretion in responding to\\nallegations of juror misconduct. This is so because “the\\ntrial court is in a superior position to observe the ‘mood at\\ntrial and the predilections of the jury.’ ” Resko, 3 F.3d at\\n690 (quoting United States v. Chiantese, 582 F.2d 974,\\n980 (5th Cir. 1978)). But this discretion is not unlimited.\\nOnce the jury retires to deliberate, the confidentiality of its\\ndeliberations must be closely guarded. An accused is\\nconstitutionally entitled to be tried before a jury of his\\npeers. As ordinary citizens, jurors are “expected to speak,\\ndebate, argue, and make decisions the way ordinary people\\ndo in their daily lives.” Pena-Rodriguez v. Colorado, 137\\nS. Ct. 855, 874 (2017) (Alito, J., dissenting). To protect\\nagainst intrusion into a defendant’s right to be judged only\\nby fellow citizens, “the door to the jury room [is] locked.”\\nId. at 875.\\n In Boone, this Court considered the threshold for\\nintervention by a trial judge who is presented with\\nallegations of juror misconduct during the course of\\ndeliberations. 458 F.3d at 327. We recognized that “[i]t is\\nbeyond question that the secrecy of deliberations is critical\\nto the success of the jury system.” Id. at 329. But that\\nsecrecy abuts a competing interest—the jury’s proper\\nexecution of its duties. That is, “a juror who refuses to\\ndeliberate or who commits jury nullification violates the\\nsworn jury oath and prevents the jury from fulfilling its\\n\\n 59\\n\\fconstitutional role.” Id. Recognizing these competing\\ninterests, we declined in Boone to adopt a sweeping\\nlimitation on a trial court’s ability to investigate\\nallegations of misconduct during jury deliberations. See id.\\nConsistent with the standard applied at other stages of\\ncriminal proceedings, Boone teaches that “where\\nsubstantial evidence of jury misconduct—including\\ncredible allegations of jury nullification or of a refusal to\\ndeliberate—arises during deliberations, a district court\\nmay, within its sound discretion, investigate the\\nallegations through juror questioning or other appropriate\\nmeans.” Id.\\n Fattah argues that the District Court had no basis to\\nquestion any of the jurors. Fattah Br. 20. We disagree. In\\nBoone, notes from the jury presented substantial credible\\nevidence of misconduct. 458 F.3d at 330. Here, the initial\\nnote from the foreperson alleged that Juror 12 “refuse[d]\\nto vote by the letter of the law,” would “not listen or reason\\nwith anybody,” and that he had “an agenda or ax to grind”\\nwith the Government. JA5916. The note contained\\nallegations of both a refusal to deliberate and a suggestion\\nof nullification. A refusal to deliberate is a violation of a\\njuror’s oath. Boone, 458 F.3d at 329 (citing United States\\nv. Baker, 262 F.3d 124, 130 (2d Cir. 2001) (“It is well-\\nsettled that jurors have a duty to deliberate.”)). Moreover,\\nnullification—a juror’s refusal to follow the law—is a\\nviolation of the juror’s sworn oath to render a verdict\\naccording to the law and evidence. See United States v.\\nThomas, 116 F.3d 606, 614–18 (2d Cir. 1997) (discussing\\n 60\\n\\fboth “benevolent” and “shameful” examples of juror\\nnullification, but “categorically reject[ing] the idea that, in\\na society committed to the rule of law, jury nullification is\\ndesirable or that courts may permit it to occur when it is\\nwithin their authority to prevent”). The second jury note,\\nsigned by nine jurors, supported the claim of misconduct\\nby asserting that Juror 12 was “incapable of making\\ndecision[s]” and was “constantly scream[ing]” at the other\\njurors. JA5916–17. We conclude that the District Court\\ndid not abuse its discretion in deciding to initially question\\nJuror 2, and subsequently, Jurors 12, 3, 6 and 1.\\n\\n Fattah also challenges the scope of the District\\nCourt’s questioning. He argues that the rights to an\\nimpartial jury and to a unanimous verdict “would be\\nrendered toothless if trial courts had free rein to question\\njurors during deliberations.” Fattah Br. 36. Indeed, we\\nacknowledged the legitimacy of such a concern in Boone.\\nDespite adopting a modest “credible allegations” standard\\nfor investigating misconduct, we “ke[pt] in mind the\\nimportance of maintaining deliberative secrecy.” Boone,\\n458 F.3d at 329. Fattah asserts that the trial court’s\\nquestions to the five jurors were “intrusive and pointed”\\nand “nothing like the questioning . . . approved in Boone.”\\nFattah Br. 38. But Fattah does not elaborate on how, in his\\nview, the questions posed by Judge Bartle specifically\\nintruded into deliberative secrecy.\\n\\n To be sure, Judge Bartle’s questioning of each juror\\nwas more extemporaneous than the juror questioning in\\n\\n 61\\n\\fBoone. There, the district court asked a single juror four\\n“concise and carefully-worded” questions. 458 F.3d at\\n330. Judge Bartle’s voir dire of each of the five jurors took\\non a more conversational tone. We take no issue with that\\napproach. The substance of the judge’s questions was\\nlimited and mirrored that of questions we deemed\\nappropriate in Kemp. There, the court conducted three\\nrounds of questioning. In the first round, each juror was\\nasked:\\n (1) “Are you personally experiencing any\\n problems with how the deliberations are\\n proceeding without telling us anything about\\n the votes as to guilt or innocence? If yes,\\n describe the problem.” (2) “Are all the jurors\\n discussing the evidence or lack of evidence?”\\n (3) “Are all the jurors following the court’s\\n instructions on the law?”\\n\\nKemp, 500 F.3d at 273. In the second and third rounds,\\neach juror was asked:\\n (1) “Is there any juror or jurors who are\\n refusing to deliberate?” (2) “Is there any juror\\n who is refusing to discuss the evidence or\\n lack of evidence?” (3) “Is there any juror who\\n is refusing to follow the Court’s\\n instructions?”\\nId. at 274. Here, Judge Bartle began his voir dire of each\\njuror by stating that he did not wish for the juror to discuss\\n 62\\n\\fthe merits of the case or to reveal the content of the\\ndeliberations that had taken place. He asked the jurors\\nwhether screaming was occurring, whether the jurors were\\ndiscussing the evidence, whether Juror 12 was placing his\\nhands on other jurors, and whether Juror 12 was unwilling\\nto follow his instructions.\\n Fattah points to no specific question posed or topic\\ndiscussed that was inappropriate, and we see little to no\\nsubstantive difference between the questions here and\\nthose asked by the trial judge in Kemp. As in Kemp, “the\\nDistrict Court took care to limit its questions to appropriate\\nmatters that did not touch on the merits of the jury’s\\ndeliberation, and expressly informed each juror on\\nmultiple occasions that he or she should not reveal the\\nsubstance of the deliberations.” Id. at 302 (citing United\\nStates v. Edwards, 303 F.3d 606, 634 n.16 (5th Cir. 2002)).\\n Fattah also argues that once the remarks of Juror 2\\nand Juror 12 revealed no further evidence of misconduct,\\nthe court had no basis to question other jurors. Fattah\\nReply 19. Yet, our cases make clear that a trial court may,\\nin its discretion, examine each juror. Kemp, 500 F.3d at\\n302 (“We have recognized that there are times in which\\nindividual questioning is the optimal way in which to root\\nout misconduct.”). Indeed, “the District Court must utilize\\nprocedures that will ‘provide a reasonable assurance for\\nthe discovery of prejudice.’ ” Id. (quoting Martin v.\\n\\n\\n\\n 63\\n\\fWarden, Huntingdon State Corr. Inst., 653 F.2d 799, 807\\n(3d Cir. 1981)). 12\\n\\n Judge Bartle, a very able and experienced district\\njudge, was in the best position to determine what type of\\ninquiry was warranted under the circumstances. We\\nconclude that his questioning of the five jurors was not an\\nabuse of discretion. See id. at 302.\\n\\n B. Dismissal of Juror 12\\n Fattah, joined by Vederman, Brand, and Nicholas,\\nstrongly contends that the District Court committed\\nreversible error by dismissing Juror 12. “We review the\\ndismissal of a juror for cause for abuse of discretion.”\\n\\n12\\n Our cases do not suggest that a trial judge confronted\\nwith allegations that a jury’s deliberations are being\\nobstructed by one of its members should always resort to\\ninterviewing jurors. Reinstructing the jury on its duty to\\ndeliberate will often be the better course at the first sign of\\ntrouble. Mere disagreement among jurors—even spirited\\ndisagreement—is no ground for intervention.\\nFurthermore, intrusive or leading questions about the\\ndeliberative process may work against the twin goals of\\nprotecting that process and ensuring that jurors remain\\nfaithful to their oaths. We share the Eleventh Circuit’s\\npreference of “err[ing] on the side of too little inquiry as\\nopposed to too much.” United States v. Oscar, 877 F.3d\\n1270, 1287 (11th Cir. 2017) (quoting United States v.\\nAugustin, 661 F.3d 1105, 1133 (11th Cir. 2011)).\\n 64\\n\\fKemp, 500 F.3d at 303. That deferential standard compels\\nus to affirm.\\n Rule 23(b) of the Federal Rules of Criminal\\nProcedure permits a trial court to excuse a deliberating\\njuror for good cause. See id. (citing Fed. R. Crim. P.\\n23(b)). Good cause exists where a juror refuses to apply\\nthe law, refuses to follow the court’s instructions, refuses\\nto deliberate with his or her fellow jurors, or demonstrates\\nbias. See Kemp, 500 F.3d at 305–06; United States v.\\nOscar, 877 F.3d 1270, 1287 (11th Cir. 2017); Thomas, 116\\nF.3d at 617. Good cause does not exist when there is\\nreasonable but sustained disagreement about how a juror\\nviews the evidence. The courts of appeals are emphatic\\nthat trial courts “may not dismiss a juror during\\ndeliberations if the request for discharge stems from\\ndoubts the juror harbors about the sufficiency of the\\ngovernment’s evidence.” Kemp, 500 F.3d at 303 (quoting\\nUnited States v. Brown, 823 F.2d 591, 596 (D.C. Cir.\\n1987)); see also Oscar, 877 F.3d at 1287 (same); United\\nStates v. Symington, 195 F.3d 1080, 1087 (9th Cir. 1999);\\nThomas, 116 F.3d at 622.\\n\\n To reinforce a defendant’s right to a unanimous\\njury, we have adopted a high standard for juror dismissal.\\nKemp, 500 F.3d at 304 & n.26. “[D]istrict courts may\\ndischarge a juror for bias, failure to deliberate, failure to\\nfollow the district court’s instructions, or jury nullification\\nwhen there is no reasonable possibility that the allegations\\nof misconduct stem from the juror’s view of the evidence.”\\n\\n 65\\n\\fId. at 304 (emphasis added). This “no reasonable\\npossibility” standard is “by no means lax.” Id. Rather, “[i]t\\ncorresponds with the burden for establishing guilt in a\\ncriminal trial.” Id.\\n\\n We first applied this standard in Kemp, but have not\\nhad occasion to do so since. There, the evidence\\nsupporting the district court’s removal decision was\\n“overwhelming.” 500 F.3d at 304. Ten jurors separately\\nand consistently reported that a juror was improperly\\nbiased, and did so only after three rounds of questioning\\nand careful and correct instructions from the district court\\nas to the distinction between appropriate skepticism and\\nimpermissible bias. Id. at 304–05; see id. at 275–76\\n(district court’s instruction). The testimony also showed\\nthat the juror in question refused to deliberate or to discuss\\nthe evidence with her fellow jurors. Id. at 305.\\n Whether the evidence of misconduct in this case is\\nas strong as that in Kemp is beside the point. After only\\nfour hours of deliberations, Juror 12 stated unequivocally\\nto the courtroom deputy that he was “going to hang” the\\njury, and that it would be “11 to 1 no matter what.”\\nJA5981–82 (emphasis added). These statements, coupled\\nwith the District Court’s finding that Juror 12 lacked\\ncredibility, provided a sufficient basis for Juror 12’s\\ndismissal.\\n\\n As grounds for excusing Juror 12, the District Court\\nfound that he refused to deliberate in good faith, “delayed,\\ndisrupted, impeded, and obstructed the deliberative\\n 66\\n\\fprocess and had the intent to do so,” JA5995, and that he\\nwas “intent on . . . hanging this jury no matter what the law\\nis, no matter what the evidence is.” Id. The District Court\\ndetermined from this that Juror 12 had violated his oath as\\na juror and that no further instructions or admonitions\\ncould rehabilitate the juror. Id. The District Court based\\nthese findings on personal observation, including Juror\\n12’s words and demeanor, and making the specific finding\\nthat Juror 12 was not credible. That finding is amply\\nsupported by the record.\\n\\n In United States v. Abbell, 271 F.3d 1286, 1303 (9th\\nCir. 2001), the Ninth Circuit recognized that “the\\ndemeanor of the pertinent juror is important to juror\\nmisconduct determinations” because the “juror’s\\nmotivations and intentions are at issue.” That court\\nemphasized, as we do, that a district judge is best situated\\nto assess the demeanor of a juror. Id. Here, Juror 12 stated\\nhe could not recall putting his hand on another juror’s\\nshoulder, while his fellow jurors’ testimony was consistent\\non this point. Juror 12 also failed, at first, to recall his\\ntroubling statements to the courtroom deputy despite\\nhaving made those statements only the previous afternoon.\\nWhen questioned a second time and asked directly about\\nthe statements, he admitted to saying that he would hang\\nthe jury but claimed he could not “really remember”\\nsaying “no matter what” the day before. JA5989–90. Juror\\n12’s spotty recollection of the previous day’s events\\nfurther supports the District Court’s finding that he was\\nnot credible.\\n 67\\n\\f Fattah argues that the credibility determination was\\nnot, by itself, a sufficient reason to dismiss the juror\\nbecause the record demonstrates more than a reasonable\\npossibility that the complaints about his conduct stemmed\\nfrom Juror 12’s own view of the Government’s case.\\nFattah Reply Br. 11; Fattah Br. 25, 28. Fattah claims that\\nthe District Court abused its discretion by dismissing Juror\\n12 “on the basis of, in effect, six words the juror\\npurportedly said to the court’s deputy after he was verbally\\nattacked by other jurors.” Fattah Br. 24. According to\\nFattah, the questioning of the other jurors “confirmed that\\nthere were no legitimate grounds for removing juror 12.”\\nId. at 26. We conclude otherwise.\\n “A district court’s finding on the question whether\\na juror has impermissibly refused to participate in the\\ndeliberation process is a finding of fact to which\\nappropriate deference is due.” Baker, 262 F.3d at 130.\\nWhile district courts must apply a high standard for juror\\ndismissal, their underlying findings are afforded\\nconsiderable deference on appeal. Kemp, 500 F.3d at 304\\n(citing Abbell, 271 F.3d at 1302–03). We will reverse only\\nif the decision to dismiss a juror was “without factual\\nsupport, or for a legally irrelevant reason.” Abbell, 271\\nF.3d at 1302 (citation omitted).\\n Here, the District Court had a legitimate reason for\\nremoving Juror 12. Refusal to deliberate constitutes good\\ncause for dismissal. Although the judge did not expressly\\narticulate the Kemp standard when he announced that he\\n\\n 68\\n\\fwould dismiss Juror 12, he did acknowledge the “no\\nreasonable possibility” standard in his discussion with\\ncounsel. The unmistakable import of the District Court’s\\nstatement from the bench is that there was no reasonable\\npossibility that Juror 12’s intransigence was based on his\\nview of the evidence. See Oscar, 877 F.3d at 1288 n.16.\\n Fattah contends that there is no record support for\\nthe finding that Juror 12 said “he was going to hang this\\njury no matter what.” Fattah Br. 29. To be sure, the\\ncourtroom deputy’s testimony is not that Juror 12 used the\\nwords “hang this jury” and “no matter what” in the same\\nsentence. She testified that Juror 12 first stated “I am going\\nto hang this jury,” then later stated “it is going to be 11 to\\n1 no matter what.” JA5981–82. This is a distinction\\nwithout a difference. Likewise, Fattah challenges the\\nDistrict Court’s finding that Juror 12 was determined to\\nhang the jury “no matter what the law is” and “no matter\\nwhat the evidence is.” Fattah Br. 29. Although there is no\\nevidence that Juror 12 uttered the phrases “no matter what\\nthe law is” or “no matter what the evidence is,” the District\\nCourt was describing the import of Juror 12’s statements.\\nThis was not error.\\n Fattah expresses the concern that “[i]f jurors are\\nasked the right questions or interrogated long enough, it\\nwould not be difficult for a trial court to elicit testimony\\nfrom [a] majority [of] jurors that can be held up as\\nevidence of a dissenting juror’s bias or refusal to\\ndeliberate.” Fattah Br. 22. He also worries that a group of\\n\\n 69\\n\\fjurors might have an incentive to rid themselves of a juror\\nwho holds a different view. Id. These are valid concerns—\\nbut no basis existed for such concerns in this case. Juror\\n12’s own words provided most of the support for his\\neventual dismissal. Furthermore, his statements were\\nmade early in the deliberations, in a complex case, before\\nany juror could reasonably be expected to have reached\\nfinal verdicts on the twenty-nine counts before the jury.\\n\\n The able District Judge did not err in finding that\\nJuror 12 refused to deliberate and therefore violated his\\noath.\\n\\n IV. The District Court’s Instructions Under\\n McDonnell\\n On appeal, Fattah and Vederman renew their\\nchallenge to the jury instructions given on Counts 3, 16,\\n17, 18, 22, and 23, concerning the meaning of the term\\n“official act” as used in the bribery statute (pursuant to\\nwhich both were convicted) and the honest services fraud\\nstatute (pursuant to which Fattah alone was convicted).\\n\\n In light of the Supreme Court’s opinion in\\nMcDonnell v. United States, 136 S. Ct. 2355 (2016),\\nreleased the week after the jury verdict, the District Court\\nconceded that its instructions were incomplete and\\nerroneous, at least as to Counts 16–18. Nevertheless, the\\nDistrict Court held that the erroneous jury instructions had\\nnot influenced the verdict on the bribery counts, and\\ndeclined to set aside Fattah and Vederman’s convictions.\\n 70\\n\\fAs to Counts 16–18 and 22–23, we disagree, and will\\nreverse the District Court’s judgment. The District Court’s\\njudgment with respect to Count 3, which did not involve\\nVederman, will be affirmed. JA78–79.\\n\\n A. The McDonnell Framework\\n In McDonnell, the Supreme Court interpreted the\\nterm “official act” as defined in 18 U.S.C. § 201(a)(3). 136\\nS. Ct. at 2368. The statute defines an “official act” as “any\\ndecision or action on any question, matter, cause, suit,\\nproceeding or controversy, which may at any time be\\npending, or which may by law be brought before any\\npublic official, in such official’s official capacity, or in\\nsuch official’s place of trust or profit.” 18 U.S.C.\\n§ 201(a)(3). The McDonnell Court distilled this definition\\ninto two requirements:\\n First, the Government must identify a\\n “question, matter, cause, suit, proceeding or\\n controversy” that “may at any time be\\n pending” or “may by law be brought” before\\n a public official. Second, the Government\\n must prove that the public official made a\\n decision or took an action “on” that question,\\n matter, cause, suit, proceeding, or\\n controversy, or agreed to do so.\\n\\n136 S. Ct. at 2368. Applying this two-step test to Governor\\nRobert McDonnell’s convictions, the Supreme Court\\nconcluded that “the jury was not correctly instructed on\\n 71\\n\\fthe meaning of ‘official act,’ ” and as a result, “may have\\nconvicted Governor McDonnell for conduct that is not\\nunlawful.” Id. at 2375. Given that uncertainty, the Court\\n“[could not] conclude that the errors in the jury\\ninstructions were ‘harmless beyond a reasonable doubt.’ ”\\nId. (quoting Neder v. United States, 527 U.S. 1, 16 (1999)).\\nThe Supreme Court, therefore, vacated Governor\\nMcDonnell’s convictions. Id.\\n\\n McDonnell lays out a clear path for the Government\\nto follow in proving that an accused has performed an\\n“official act.” First, the Government must “identify a\\n‘question, matter, cause, suit, proceeding or controversy’\\nthat ‘may at any time be pending’ or ‘may by law be\\nbrought’ before a public official.” 136 S. Ct. at 2368\\n(quoting 18 U.S.C. § 201(a)(3)). This first step is divided\\ninto two sub-components. In Step 1(A), the Government\\nmust “identify a ‘question, matter, cause, suit, proceeding\\nor controversy.’ ” Id. Step 1(B) then clarifies that the\\nidentified “question, matter, cause, suit, proceeding or\\ncontroversy” be one that “ ‘may at any time be pending’ or\\n‘may by law be brought’ before a public official.” Id.\\n\\n Under Step 1(A), a “question, matter, cause, suit,\\nproceeding or controversy” must be “a formal exercise of\\ngovernmental power that is similar in nature to a lawsuit\\nbefore a court, a determination before an agency, or a\\nhearing before a committee.” Id. at 2372. Importantly, “a\\ntypical meeting, telephone call, or event arranged by a\\n\\n\\n 72\\n\\fpublic official” does not qualify as such a formal exercise\\nof governmental power. Id. at 2368.\\n Step 1(B) then requires us to ask whether the\\nqualifying “question, matter, cause, suit, proceeding or\\ncontroversy” was one that “ ‘may at any time be pending’\\nor ‘may by law be brought’ before a public official.” Id.\\nAs the McDonnell Court clarified, “ ‘[p]ending’ and ‘may\\nby law be brought’ suggest something that is relatively\\ncircumscribed—the kind of thing that can be put on an\\nagenda, tracked for progress, and then checked off as\\ncomplete.” Id. at 2369; accord United States v. Repak, 852\\nF.3d 230, 252 (3d Cir. 2017) (quoting McDonnell, 136 S.\\nCt. at 2369). By contrast, matters described at a high level\\nof generality—for example, “[e]conomic development,”\\n“justice,” and “national security”—are not sufficiently\\n“focused and concrete.” McDonnell, 136 S. Ct. at 2369.\\n\\n In McDonnell, the Court concluded that at least\\nthree questions or matters identified by the Fourth Circuit\\nwere sufficiently focused:\\n (1) whether researchers at any of Virginia’s\\n state universities would initiate a study of [a\\n drug]; (2) whether the state-created Tobacco\\n Indemnification and Community\\n Revitalization Commission would allocate\\n grant money for the study of [a chemical\\n compound]; and (3) whether the health\\n insurance plan for state employees in\\n\\n 73\\n\\f Virginia would include [a specific drug] as a\\n covered drug.\\nId. at 2370 (internal quotations omitted) (quoting United\\nStates v. McDonnell, 792 F.3d 478, 515–16 (4th Cir.\\n2015)). We provided guidance in the form of a fourth\\nexample in Repak, when we held that a redevelopment\\nauthority’s awarding of contracts was “a concrete\\ndetermination made by the [redevelopment authority’s]\\nBoard of Directors.” 852 F.3d at 253.\\n\\n Step 2 requires the Government to prove that the\\npublic official made a “decision” or took “an action” on\\nthe identified “question, matter, cause, suit, proceeding or\\ncontroversy.” McDonnell, 136 S. Ct. at 2368. The\\nMcDonnell Court explained:\\n Setting up a meeting, hosting an event, or\\n calling an official (or agreeing to do so)\\n merely to talk about a research study or to\\n gather additional information . . . does not\\n qualify as a decision or action on the pending\\n question of whether to initiate the study.\\n Simply expressing support for the research\\n study at a meeting, event, or call—or sending\\n a subordinate to such a meeting, event, or\\n call—similarly does not qualify as a decision\\n or action on the study, as long as the public\\n official does not intend to exert pressure on\\n another official or provide advice, knowing\\n\\n 74\\n\\f or intending such advice to form the basis for\\n an “official act.”\\nId. at 2371. The Court further clarified:\\n\\n If an official sets up a meeting, hosts an\\n event, or makes a phone call on a question or\\n matter that is or could be pending before\\n another official, that could serve as evidence\\n of an agreement to take an official act. A jury\\n could conclude, for example, that the official\\n was attempting to pressure or advise another\\n official on a pending matter. And if the\\n official agreed to exert that pressure or give\\n that advice in exchange for a thing of value,\\n that would be illegal.\\nId.\\n Here, Fattah was charged with engaging in three\\ncategories of official acts, which we analyze in accordance\\nwith the McDonnell framework. In Counts 16–18 and 22–\\n23, Fattah is alleged to have set up a meeting between\\nVederman and the U.S. Trade Representative, attempted\\nto secure Vederman an ambassadorship, and hired\\nVederman’s girlfriend, all in return for a course of conduct\\nwherein Vederman provided things of value to Fattah.\\n\\n In this case, as in McDonnell, the jury instructions\\nwere erroneous. We conclude that the first category of the\\ncharged acts—setting up a meeting between Vederman\\n 75\\n\\fand the U.S. Trade Representative—is not unlawful, and\\nthat the second category—attempting to secure Vederman\\nan ambassadorship—requires reconsideration by a\\nproperly instructed jury. The third charged act—hiring\\nVederman’s girlfriend—is clearly an official act. But\\nbecause we cannot isolate the jury’s consideration of the\\nhiring from the first two categories of charged acts, we\\nmust reverse and remand the judgment of the District\\nCourt.\\n\\n B. The Kirk Meeting\\n We turn first to Fattah’s scheduling of a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk. Under McDonnell, “setting up a meeting . . .\\ndoes not, standing alone, qualify as an ‘official act.’ ” 136\\nS. Ct. at 2368. Fattah’s setting up the meeting between\\nVederman and Kirk was therefore not an official act, a\\nconcession implicit in the Government’s opening brief.\\nSee Gov’t Br. 32 (failing to mention the Kirk meeting as\\none of the “two categories” of allegedly “official acts”).\\nBut the jury was not properly instructed on this point.\\nWithout the benefit of the principles laid down in\\nMcDonnell, the jury was free to conclude that arranging\\nthe Kirk meeting was an official act—and it may have\\ndone so. The District Court’s erroneous jury instructions,\\ntherefore, cannot survive harmless error review.\\n\\n In a footnote in its brief to this Court, the\\nGovernment argues that evidence about the Kirk meeting\\nwas offered only “because it established the strength of\\n 76\\n\\fVederman’s desire to be an ambassador” and not because\\nthe Government was attempting to establish the meeting\\nas an independent official act. Id. at79–80 n.6. But the\\nrecord undercuts the Government’s post hoc justification.\\n\\n The indictment, provided to the jury in redacted\\nform for use in its deliberations, lists Fattah’s setting up\\nthe Kirk meeting as an official act under the heading\\n“FATTAH’s Official Acts for VEDERMAN.” JA494.\\nUnder this heading are three distinct subheadings:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) “Hiring\\nthe Lobbyist’s Girlfriend to the Congressional Staff.”\\nJA494–95. The second subheading, “The Pursuit of\\nAnother Executive Branch Position,” describes the\\narrangement of the Kirk meeting. Quite clearly, then, this\\nthree-part structure demonstrates that setting up the Kirk\\nmeeting was one of three distinct categories of official acts\\nalleged by the Government.\\n\\n Although there is some support for the\\nGovernment’s argument that evidence of the Kirk meeting\\nwas presented at trial only to establish the extent of\\nVederman’s interest in becoming an ambassador, JA827,\\n852–53 (mentioning the Kirk meeting in close proximity\\nto references to Fattah’s attempts to secure Vederman an\\nambassadorship), it is undermined by language in the\\nredacted indictment itself, and by the way in which the\\nGovernment presented its case at trial as a “pattern” of\\nconnected acts.\\n\\n 77\\n\\f The redacted indictment, for example, refers to the\\nKirk meeting as “The Pursuit of Another Executive\\nBranch Position.” JA495 (emphasis added). The use of the\\nword “Another” strongly suggests that evidence about the\\nKirk meeting was not merely evidence of Fattah’s attempt\\nto secure Vederman an ambassadorship, but was also\\nevidence of a separate and distinct attempt to secure\\nVederman a position on a federal trade-related\\ncommission. The redacted indictment also notes that “[i]n\\nor around May 2011, with little progress made on securing\\nan ambassadorship for VEDERMAN, FATTAH turned\\ntowards obtaining for VEDERMAN an appointment in the\\nExecutive Branch to a federal trade commission.” Id.\\n(emphasis added). The words “turned towards,” taken\\nliterally, clearly convey that arranging the Kirk meeting\\nwas presented as distinct from Fattah’s efforts to secure\\nVederman an ambassadorship.\\n\\n The District Court denied Fattah and Vederman a\\nnew trial on Counts 17 and 18, referring to evidence of the\\nKirk meeting as “de minimis” and noting that “Kirk’s\\ntestimony during this lengthy trial lasted a mere sixteen\\nminutes.” JA97 n.14. In the District Court’s view,\\nevidence of the Kirk meeting “played no role in the\\noutcome” of the case. Id. Considering the record in light\\nof McDonnell, we are not so sure.\\n\\n Although it is possible that evidence of the Kirk\\nmeeting played a minor role at trial when compared to the\\nother acts on which the Government presented evidence,\\n\\n 78\\n\\fthe redacted indictment suggests that the Kirk meeting was\\na significant part of the Government’s case. The\\nindictment dedicates five paragraphs to describing the\\nKirk meeting, but just three paragraphs to describing the\\nhiring of Vederman’s girlfriend—a hiring that, as we\\nexplain below, is clearly an official act. JA495–96. While\\nneither the number of minutes used at trial nor the number\\nof paragraphs contained in an indictment is a dispositive\\nunit of measurement for determining the significance of\\nevidence, we conclude that the District Court’s erroneous\\njury instructions pertaining to the Kirk meeting were not\\nharmless.\\n We conclude, in accordance with McDonnell, that\\nFattah’s arranging a meeting between Vederman and the\\nU.S. Trade Representative was not itself an official act.\\nBecause the jury may have convicted Fattah for conduct\\nthat is not unlawful, we cannot conclude that the error in\\nthe jury instruction was harmless beyond a reasonable\\ndoubt, and we must vacate and remand the convictions of\\nFattah and Vederman as to Counts 16, 17, 18, 22 and 23.\\n\\n C. Fattah’s Efforts to Secure Vederman an\\n Ambassadorship\\n The nature of Fattah’s efforts to secure Vederman\\nan ambassadorship is less clear, and presents a closer\\nquestion than the Kirk meeting. We ultimately conclude\\nthat the question warrants remand so that it may be\\nanswered by a properly instructed jury. On remand, the\\njury must decide whether Fattah’s conduct constituted a\\n 79\\n\\f“decision” or “action” under Step 2 of the McDonnell\\nanalysis.\\n At the outset, it is clear to us that, under Steps 1(A)\\nand 1(B), a formal appointment of Vederman as an\\nambassador would qualify as a “matter” that “may at any\\ntime be pending” before a public official. The formal\\nappointment of a particular person (Vederman), to a\\nspecific position (an ambassadorship), constitutes a matter\\nthat is sufficiently focused and concrete. The formal\\nappointment of an ambassador is a matter that is “pending”\\nbefore the President—the constitutional actor charged\\nwith nominating ambassadors—as well Senators, who are\\ncharged with confirming the President’s ambassadorial\\nnominations. U.S. Const. art. II § 2 (“[H]e shall nominate,\\nand by and with the Advice and Consent of the Senate,\\nshall appoint Ambassadors . . . .”). It is beyond cavil that\\nthe formal appointment of an ambassador satisfies both\\nsub-components of McDonnell’s Step 1.\\n Turning to Step 2, we consider whether Fattah’s\\nefforts to secure Vederman an ambassadorship qualify as\\nmaking a “decision” or taking “an action” on the identified\\n“matter” of appointment. McDonnell, 136 S. Ct. at 2368.\\nAlthough those efforts—three emails, two letters, and one\\nphone call—do not themselves qualify as a “question,\\nmatter, cause, suit, proceeding, or controversy” under\\nMcDonnell’s Step 1, they may nonetheless qualify as the\\nmaking of a “decision” or taking “an action” on the\\nidentified matter of appointment. Id.\\n\\n 80\\n\\f McDonnell’s Step 2 requires us to determine\\nwhether Fattah’s efforts qualify as permissible attempts to\\n“express[] support,” or impermissible attempts “to\\npressure or advise another official on a pending matter.”\\nId. at 2371. At trial, the jury was not instructed that they\\nhad to place Fattah’s efforts on one side or the other of this\\ndivide. The jury might even have thought they were\\npermitted to find Fattah’s efforts—three emails, two\\nletters, and one phone call—to themselves be official acts,\\nrather than a “decision” or “action” on the properly\\nidentified matter of appointment. Such a determination\\nwould have been contrary to the dictates of McDonnell.\\n Faced with such uncertainty, we cannot assume the\\njury verdict was proper. Although the jury might not have\\nconcluded that Fattah’s efforts were themselves official\\nacts, and although the jury might not have concluded that\\nthose efforts crossed the line into impermissible attempts\\n“to pressure or advise,” we are unable to conclude that the\\njury necessarily did so. Nor can we, on the cold record\\nbefore us, determine whether Fattah’s efforts to secure\\nVederman an ambassadorship crossed the line.\\nDetermining, for example, just how forceful a strongly\\nworded letter of recommendation must be before it\\nbecomes impermissible “pressure or advice” is a fact-\\nintensive inquiry that falls within the domain of a properly\\ninstructed jury. Should the Government elect to retry these\\ncounts after remand, the finder of fact will need to decide\\nwhether Fattah’s efforts constituted permissible attempts\\nto “express[] support,” or impermissible attempts “to\\n 81\\n\\fpressure or advise another official on a pending matter.”\\nId.\\n\\n D. The Zionts Hiring\\n The third group of acts charged in the Fattah–\\nVederman scheme involves Fattah’s decision to hire\\nVederman’s girlfriend, Alexandra Zionts, as a\\ncongressional staffer. We conclude that the hiring was an\\nofficial act. A brief analysis of McDonnell’s two steps\\nsuffices to show why this is so.\\n Here, under McDonnell’s Step 1(A), the relevant\\n“matter” is the decision to hire Zionts. Step 1(B) of the\\nanalysis is satisfied because the hiring decision was\\n“pending” before Fattah himself. And that hiring was\\n“focused and concrete,” “within the specific duties of an\\nofficial’s position—the function conferred by the\\nauthority of his office.” Id. at 2369. Finally, McDonnell’s\\nStep 2 requires that the “Government . . . prove that the\\npublic official made a decision or took an action ‘on’ [the\\nidentified] question, matter, cause, suit, proceeding, or\\ncontroversy, or agreed to do so.” Id. at 2368. Fattah’s\\ndecision to hire Zionts clearly satisfies that requirement.\\nWe therefore conclude that the hiring of Zionts was an\\nofficial act under McDonnell.\\n\\n Vederman concedes that the Zionts hiring was an\\nofficial act. Oral Argument Transcript at 5–6. Fattah, for\\nhis part, maintains that “hiring someone for a routine, part-\\ntime, short-term position falls well outside [the] definition\\n 82\\n\\f[of ‘official act’] and is nothing like a lawsuit, agency\\ndetermination, or committee hearing, even if each shares\\nthe happenstance that federal funds will be used.” Fattah\\nReply Br. 25.\\n\\n Fattah’s argument lacks traction. Official acts need\\nnot be momentous decisions—or even notable ones.\\nJudges, for example, make “routine” evidentiary rulings\\nevery day, and yet it is beyond question that those rulings\\nare official acts. In the realm of official acts, it is of no\\nmoment that Zionts provided only “part-time, short term”\\nlabor. When a public official hires an employee to work in\\nhis government office, he has engaged in an official act.\\n * * *\\n If we could conclude that the Zionts hiring was the\\nonly category of actions that the jury relied on when it\\nfound that Fattah performed an official act under Counts\\n16–18 and 22–23, remand would not be necessary. But, as\\nwe have explained, we cannot rule out that the jury\\nerroneously convicted Fattah and Vederman based on\\nother actions that were not official acts under\\nMcDonnell.13\\n\\n\\n13\\n More specifically, the incomplete, and therefore\\nerroneous, instructions could have led the jury to commit\\nat least one of three mistakes. First, the jury could have\\nimproperly convicted Vederman and Fattah based on the\\nKirk meeting alone, or misunderstood the Kirk meeting to\\n 83\\n\\f The Government argues that because the Zionts\\nhiring was an official act, the effect of the erroneous jury\\ninstructions could be no more than harmless. The jury’s\\nverdict, the Government contends, permits us to deduce\\nthat the jury necessarily concluded the Zionts hiring was\\nan official act, and that this conclusion alone supported\\nFattah’s and Vederman’s convictions as to Counts 16–18\\nand 22–23—regardless of whether the jury erroneously\\nfound any unofficial acts to be official acts. We disagree.\\n Fattah and Vederman objected to the definition of\\n“official act” at trial. We thus apply the harmless error\\nstandard of review. McDonnell, 136 S. Ct. at 2375. The\\nGovernment argues that because the jury convicted Fattah\\nand Vederman of illegally laundering the proceeds of a\\n“scheme to commit bribery” under Count 23, the jury\\nfound that the scheme must have encompassed only the\\nZionts hiring. JA531.That would mean that the jury did not\\nconclude that the “scheme to commit bribery” included\\n\\nbe a necessary component of an impermissible “pattern”\\nof official acts. Second, the jury might have concluded that\\nFattah’s efforts to secure Vederman an ambassadorship\\nwere themselves official acts. Third, the jury might have\\nconcluded that Fattah’s efforts to secure Vederman an\\nambassadorship were merely attempts to “express[]\\nsupport,” rather than to “exert pressure . . . or provide\\nadvice,” but nonetheless erroneously concluded that those\\nexpressions of support were official acts. McDonnell, 136\\nS. Ct. at 2371.\\n 84\\n\\fany acts that McDonnell now makes clear were unofficial.\\nYet the redacted indictment, jury instructions, and the fact\\nthat the Government presented its case under a “pattern”\\ntheory at trial compel us to reject the Government’s\\nargument.\\n\\n The very first sentence under Count 23 of the\\nredacted indictment incorporates all three categories of\\n“Overt Acts” contained within paragraphs “58 through 95\\nof Count One.” 14 All three of these categories fall under a\\ngeneral heading within the redacted indictment titled “The\\nBribery and Fraud Scheme [redacted].” JA494. The jury\\nhad before it instructions for Count 23 which referred to\\n“the alleged bribery scheme involving an $18,000\\npayment,” JA448 (emphasis added), and the redacted\\nindictment which referred to “a scheme to commit\\nbribery,” JA531 (emphasis added). The parallel language\\ncould well lead a rational jury to conclude that the relevant\\n“scheme” included all three categories of acts listed under\\nthe general heading: “The Bribery and Fraud Scheme\\n[redacted].” JA494 (emphasis added).\\n\\n\\n\\n14\\n JA531. Paragraphs 58 through 95 of Count 1 refer to the\\nthree categories of allegedly official acts discussed above:\\n(1) “The Pursuit of an Ambassadorship,” (2) “The Pursuit\\nof Another Executive Branch Position,” and (3) the\\n“Hiring of the Lobbyist’s Girlfriend to the Congressional\\nStaff.” JA494–95.\\n 85\\n\\f Like the redacted indictment and jury instructions,\\nthe Government’s trial arguments referred to patterns and\\na course of conduct, and stressed that the jury need not\\nconnect specific payments to particular official acts. In its\\nclosing argument to the jury, the Government stated that\\nthe alleged “scheme took place over a period of several\\nyears. Over and over again you’re going to see the same\\npattern.” JA5383 (emphasis added). Then, in its rebuttal\\nargument, the Government went out of its way to\\nexplicitly distinguish its “pattern” theory from an\\nalternative theory that would have directly connected\\nindividual payments to individual acts. As the prosecutor\\nargued to the jury:\\n Ms. Recker appears to argue that each thing\\n of value must coincide with some specific\\n official act, but that is not the law and that is\\n not what Judge Bartle is going to instruct you.\\n Instead what he will tell you is that the\\n government is not required to prove that\\n Vederman intended to influence Fattah to\\n perform a set number of official acts in return\\n for things of value so long as the evidence\\n shows a course of conduct of giving things of\\n value, things of value to Fattah in exchange\\n for a pattern of official acts favorable to\\n Vederman. In other words a stream of\\n benefits. These for those, not this for that.\\n\\n\\n\\n 86\\n\\fJA5715–16 (emphases added). In closing to the jury, the\\nGovernment made several other references to this\\n“pattern” theory, 15 and the District Court referred to this\\n“pattern” theory in its instructions to the jury. As Judge\\nBartle instructed:\\n\\n [I]t is not necessary for the government to\\n prove that a defendant intended to induce a\\n public official to perform a number of official\\n acts in return for things of value.\\n So as long as the evidence shows a\\n course of conduct of giving things of value to\\n a public official in exchange for a pattern of\\n official acts favorable to the giver.\\n\\nJA5833–34 (emphasis added). On appeal, the Government\\nchanges course, asking us to assume that the jury ignored\\nthese repeated references to a “pattern of official acts” and\\n\\n15\\n See, e.g., JA5389 (“And the exchange of an official act\\nfor a thing of value is called a bribe. There’s the pattern.\\nFattah needs money, Vederman gets an official act.”); JA\\n5393 (“That’s why you see the pattern over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5400 (“The same pattern we saw over and over again.\\nFattah needs money, Vederman gets an official act.”);\\nJA5409 (“[Y]ou know that these were bribes because of\\nthe pattern you saw over and over and over again. Fattah\\nneeds money, Vederman gets an official act, that makes\\nthese things a bribe.”).\\n 87\\n\\finstead considered the Zionts hiring and Vederman’s\\n$18,000 payment to Fattah as an isolated quid pro quo.\\nThis is an invitation to speculate, and we decline to do so.16\\nThe jury began its deliberations accompanied by a copy of\\nthe redacted indictment which alleged a pattern of official\\nacts, consisting of any combination of three categories of\\nacts: pursuing an ambassadorship, arranging the Kirk\\nmeeting, and hiring Zionts. In light of the erroneous\\ninstructions, and because only one category clearly\\n\\n16\\n Providing some support to the Government’s ultimately\\nunconvincing argument that the jury considered the Zionts\\nhiring and $18,000 payment in isolation, we note that the\\nredacted indictment does mention those two events side-\\nby-side in paragraph 78 of the indictment’s Part V. JA497\\n(“On January 13, 2012, VEDERMAN wired $18,000 to\\nFATTAH, and six days later, on January 19, 2012,\\nBOWSER emailed VEDERMAN’s girlfriend, A.Z.,\\nwelcoming her as a new employee to FATTAH’s\\nCongressional Staff.”). But although paragraph 78\\nmentions the $18,000 wire transfer and the Zionts hiring\\nin the same breath, paragraph 78 does not instruct the jury\\nto connect these two events apart from the rest of the\\nevidence presented at trial. In light of the other instructions\\nand arguments indicating that the jury should not consider\\nthe Zionts hiring in isolation, but instead should consider\\nthe hiring as one part of a three-part scheme, paragraph 78\\nis not sufficient to avoid a reversal and remand on the\\nconvictions of Fattah and Vederman as to Counts 16–18\\nand 22–23.\\n 88\\n\\fqualifies as an “official act,” the jury’s deliberations were\\nfraught with the potential for McDonnell error. We will\\nvacate the convictions of Fattah and Vederman as to\\nCounts 16, 17, 18, 22, and 23, and remand to the District\\nCourt.\\n\\nE. Vederman’s Sufficiency Challenge to Counts 16–18\\n and 22–23\\n Vederman argues that there is insufficient evidence\\nto support a conviction, even if a jury were properly\\ninstructed under McDonnell. Specifically, Vederman\\nargues that there is insufficient evidence to convict him\\nand Fattah, after remand, on Counts 16–18 and 22–23\\nbecause “[a]t least seven of the eight alleged ‘official acts’\\nwere, as a matter of law, not official at all.” Vederman Br.\\n35. As to the single act that Vederman implicitly concedes\\nto be an official act—the Zionts hiring—Vederman argues\\nthat “[t]he only thing that even arguably associates” the\\nZionts hiring with Vederman was its timing in relation to\\nVederman’s sham purchase of the Fattahs’ Porsche. Id.\\nAccording to Vederman, “the undisputed chronology\\nprecludes any inference that Vederman conferred this\\nbenefit on his friend as an illegal bribe.” Id. (emphasis\\nomitted). Vederman is wrong. Sufficient evidence was\\nproduced at trial to have allowed a properly-instructed jury\\nto convict Fattah and Vederman of Counts 16–18 and 22–\\n23.\\n To begin with, even if the Zionts hiring had been the\\nsole official act to survive this Court’s interpretation of\\n 89\\n\\fMcDonnell, there would still be sufficient evidence to\\nconvict Fattah and Vederman. Zionts did not receive\\nwritten notice of her official hiring until six days after the\\nsham Porsche purchase. Moreover, the jury would not be\\nrestricted to considering the chronology of the sham\\npurchase alone. It would be free to consider Vederman’s\\nentire course of conduct. Under the general heading\\n“VEDERMAN’S Payments and Things of Value to\\nFATTAH,” the redacted indictment not only refers to the\\n$18,000 wire transaction from Vederman to Fattah as part\\nof the sham Porsche purchase, but also to Vederman’s\\n$3,000 payment for the college tuition of Simone Muller,\\nFattah’s live-in au pair, as well as thousands of dollars in\\npayments made by Vederman for Chip Fattah’s college\\ntuition. JA496–97.\\n And the Zionts hiring is not the only act to survive\\nour application of McDonnell. As we explained, a jury\\ncould find that Fattah’s efforts to secure Vederman an\\nambassadorship—three emails, two letters, and a phone\\ncall—were an impermissible attempt to “pressure or\\nadvise” President Obama, Senator Casey, or both men.17\\n\\n17\\n Although Fattah’s efforts to secure Vederman an\\nambassadorship present a jury question that is not for us to\\nanswer on appeal, we note that not one of these efforts\\nalone could qualify as an official act itself. See McDonnell,\\n136 S. Ct. at 2372 (“Setting up a meeting, talking to\\nanother official, or organizing an event (or agreeing to do\\nso)—without more—does not fit that definition of ‘official\\n 90\\n\\fThis means that a properly instructed jury on remand,\\npresented with evidence of Fattah’s efforts to secure an\\nambassadorship for Vederman and evidence of the Zionts\\nhiring, could find more than a single official act.\\n\\n F. Blue Guardians\\n In addition to the charges arising from his dealings\\nwith Vederman, Fattah was charged in Count 3 with\\n\\n\\nact.’ ”). The relevant question for a jury to consider on\\nremand, then, is whether these actions constituted “a\\n‘decision or action’ on a different question or matter”—to\\nwit, the formal appointment of an ambassador. Id. at 2369\\n(emphasis omitted).\\n Even though the emails, letters, and phone call are\\nnot, individually, official acts, it will be for a jury to decide\\nif Fattah’s efforts to secure an ambassadorship for\\nVederman crossed the line from permissible “support” to\\nimpermissible “pressure or advice.” While we express\\ndoubt that some of Fattah’s efforts concerning the\\nambassadorship are, when considered in isolation, enough\\nto cross that line, a properly instructed jury considering all\\nof the facts in context might nonetheless conclude that\\nother efforts—such as a hand-delivered letter to the\\nPresident of the United States—indeed crossed that line.\\nFurther, a jury might find that in the aggregate, three\\nemails, two letters, and a phone call crossed the line and\\ntherefore constituted a “decision or action” on the\\nidentified matter of appointment.\\n 91\\n\\fparticipating in a scheme with Lindenfeld to funnel money\\nto a fraudulent nonprofit organization. In connection with\\nthis scheme, Fattah was convicted of conspiring to commit\\nhonest services fraud.\\n\\n Fattah owed Lindenfeld nearly $100,000 for work\\nperformed on Fattah’s 2007 mayoral campaign. In lieu of\\nrepayment, Fattah suggested that Lindenfeld create an\\nentity, later named Blue Guardians, to which Fattah would\\ndirect $15,000,000 in public funds by using his position as\\na member of the House Committee on Appropriations.\\nNothing in McDonnell requires us to upset Fattah’s\\nconviction on Count 3.\\n Step 1(A) of our McDonnell analysis requires the\\nGovernment to “identify a ‘question, matter, cause, suit,\\nproceeding or controversy.’ ” 136 S. Ct. at 2368. Here, the\\n“matter” is the appropriation of millions of dollars in\\npublic funds. See Repak, 852 F.3d at 253–54 (holding the\\nawarding of redevelopment funds to be an official act). In\\nparticular, it was Fattah’s promise to perform this official\\nact that was unlawful. As McDonnell makes clear:\\n\\n [A] public official is not required to actually\\n make a decision or take an action on a\\n “question, matter, cause, suit, proceeding or\\n controversy”; it is enough that the official\\n agree to do so. The agreement need not be\\n explicit, and the public official need not\\n specify the means that he will use to perform\\n his end of the bargain.\\n 92\\n\\f136 S. Ct. at 2370–71 (internal citations omitted). That\\nFattah took steps to actually carry out his promise (e.g., by\\ndrafting and sending a formal appropriations request on\\nofficial congressional letterhead) is evidence of his illegal\\npromise. See id. at 2371.\\n\\n Step 1(B) requires the Government to establish that\\nthe “ ‘question, matter, cause, suit, proceeding or\\ncontroversy’ . . . ‘may at any time be pending’ or ‘may by\\nlaw be brought’ before a public official.” McDonnell, 136\\nS. Ct. at 2368. Appropriating public funds was not only a\\nmatter that was pending before Fattah as a member of the\\nAppropriations Committee, it was also a matter that was\\npending before the Chairman and Ranking Member of an\\nAppropriations Subcommittee to whom Fattah ultimately\\nsent a formal written request. See id. at 2369 (“[T]he\\nmatter may be pending either before the public official\\nwho is performing the official act, or before another public\\nofficial.”). Appropriating millions of dollars in response to\\nthe Blue Guardians request is “focused and concrete,” and\\n“the kind of thing that can be put on an agenda, tracked for\\nprogress, and then checked off as complete.” Id.\\n\\n Given Fattah’s membership on the Appropriations\\nCommittee, this was “something within the specific duties\\nof an official’s position—the function conferred by the\\nauthority of his office.” Id. Even if we were to assume,\\nagainst all reason, that an appropriation is not “something\\nwithin the specific duties” of either Fattah or the Chairman\\nor Ranking Member of an Appropriations Subcommittee,\\n\\n 93\\n\\fFattah’s formal request for an appropriation was\\nsomething that Fattah had the authority to do. Like the\\nExecutive Director in Repak, who lacked authority himself\\nto award redevelopment funds but could request such\\nfunds from the Board, Fattah used his position as a\\nCongressman to formally request appropriations for the\\nBlue Guardians. 852 F.3d at 254 (“Repak had the power\\nto, and indeed did, make recommendations to the\\n[redevelopment authority.\\n Step 2 of McDonnell requires the Government to\\n“prove that the public official made a decision or took an\\naction ‘on’ that question, matter, cause, suit, proceeding,\\nor controversy, or agreed to do so.” 136 S. Ct. at 2368\\n(emphasis added). Here, Fattah agreed to request an\\nappropriation for a bogus purpose. Unlike Fattah’s letters,\\nemails, and phone call seeking an ambassadorship for\\nVederman, there is no potential for the jury to have made\\na mistake when it found Fattah’s Blue Guardians promise\\nunlawful.\\n Fattah argues that the Government presented “[n]o\\nevidence . . . that would have allowed [the jury] to\\nconclude that [he] made a decision or took an action, or\\ncould have done so, on the question whether Blue\\nGuardians would receive a $15 million federal grant.”\\nFattah Br. 46. This argument misses the point. It was\\nFattah’s agreement to engage in the official act of formally\\nrequesting the appropriation that was illegal. See\\nMcDonnell, 136 S. Ct. at 2371.\\n\\n 94\\n\\f Lindenfeld’s trial testimony provided sufficient\\nevidence of Fattah’s illegal agreement. JA1694–96, 1954.\\nFattah’s letter provided additional evidence from which\\nthe jury could have concluded that Fattah illegally agreed\\nto perform an official act. 18 In short, the agreement itself\\nwas illegal, and the Government provided sufficient\\nevidence for the jury to conclude that the illegal agreement\\ntook place.\\n\\n The Government’s evidence in support of the Blue\\nGuardians scheme meets the requirements of McDonnell,\\nand the Count 3 verdict will stand.\\n\\n V. Sufficiency of the Evidence for the RICO\\n Conspiracy Conviction\\n The jury found Fattah, Vederman, Brand, and\\nNicholas guilty of the RICO conspiracy charged in Count\\n1 of the indictment, but acquitted Bowser. Vederman filed\\na post-verdict motion, and the District Court overturned\\nhis RICO conspiracy conviction.\\n\\n\\n\\n18\\n Despite Fattah’s protestation to the contrary, there is\\nevidence that Fattah took steps to carry out his official act.\\nJA6432–33 (Letter from Congressman Fattah to House\\nAppropriations Subcommittee members “request[ing]\\nfunding and support for the following projects and\\nprograms of critical importance,” including $3,000,000\\nfor “Blue Guardians”).\\n 95\\n\\f On appeal, Fattah, Brand, and Nicholas challenge\\nthe sufficiency of the evidence supporting their RICO\\nconspiracy convictions. We “review[] the sufficiency of\\nthe evidence in the light most favorable to the government\\nand must credit all available inferences in favor of the\\ngovernment.” United States v. Riddick, 156 F.3d 505, 509\\n(3d Cir. 1998). If a rational juror could have found the\\nelements of the crime beyond a reasonable doubt, we must\\nsustain the verdict. United States v. Cartwright, 359 F.3d\\n281, 286 (3d Cir. 2004), abrogated on other grounds by\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418 (3d\\nCir. 2013) (en banc).\\n The indictment charged a RICO conspiracy in\\nviolation of 18 U.S.C. § 1962(d), which makes it\\n“unlawful for any person to conspire to violate” § 1962(c).\\nSection 1962(c) provides:\\n It shall be unlawful for any person . . .\\n associated with any enterprise engaged in, or\\n the activities of which affect, interstate . . .\\n commerce, to conduct or participate, directly\\n or indirectly, in the conduct of such\\n enterprise’s affairs through a pattern of\\n racketeering activity . . . .\\n\\n18 U.S.C. § 1962(c).\\n\\n In Salinas v. United States, 522 U.S. 52 (1997), the\\ndefendant was convicted of a § 1962(d) RICO conspiracy,\\nbut a jury acquitted him of the substantive RICO offense\\n 96\\n\\funder § 1962(c). Id. at 55. The Supreme Court rejected\\nSalinas’s contention that his conviction had to be set aside\\nbecause he had neither committed nor agreed to commit\\nthe two predicate acts required for the § 1962(c) offense.\\nId. at 66. The Court declared that liability for a RICO\\nconspiracy under § 1962(d), “unlike the general\\nconspiracy provision applicable to federal crimes,” does\\nnot require proof of an overt act. Id. at 63. A conspiracy\\nmay be found, the Court explained, “even if a conspirator\\ndoes not agree to commit or facilitate each and every part\\nof the substantive offense. The partners in the criminal\\nplan must agree to pursue the same criminal objective and\\nmay divide up the work, yet each is responsible for the acts\\nof each other.” Id. at 63–64 (citations omitted). This means\\nthat, if a plan “calls for some conspirators to perpetrate the\\ncrime and others to provide support, the supporters are as\\nguilty as the perpetrators.” Id. at 64. Thus, opting into and\\nparticipating in a conspiracy may result in criminal\\nliability for the acts of one’s co-conspirators. Smith v.\\nBerg, 247 F.3d 532, 537 (3d Cir. 2001).\\n Accordingly, liability for a RICO conspiracy may\\nbe found where the conspirator intended to “further an\\nendeavor which, if completed, would satisfy all of the\\nelements of a substantive criminal offense, but it suffices\\nthat he adopt the goal of furthering or facilitating the\\ncriminal endeavor.” Salinas, 522 U.S. at 65. Because the\\nsubstantive criminal offense here was conducting a\\n§ 1962(c) enterprise, the government had to prove:\\n\\n 97\\n\\f (1) that two or more persons agreed to\\n conduct or to participate, directly or\\n indirectly, in the conduct of an enterprise’s\\n affairs through a pattern of racketeering\\n activity; (2) that the defendant was a party to\\n or member of that agreement; and (3) that the\\n defendant joined the agreement or conspiracy\\n knowing of its objective to conduct or\\n participate, directly or indirectly, in the\\n conduct of an enterprise’s affairs through a\\n pattern of racketeering activity.\\n\\nUnited States v. John-Baptiste, 747 F.3d 186, 207 (3d Cir.\\n2014).\\n In United States v. Turkette, 452 U.S. 576 (1981),\\nthe Supreme Court instructed that an enterprise is a “group\\nof persons associated together for a common purpose of\\nengaging in a course of conduct.” Id. at 583. The\\ngovernment can prove an enterprise “by evidence of an\\nongoing organization, formal or informal, and by evidence\\nthat the various associates function as a continuing unit.”\\nId. In Boyle v. United States, 556 U.S. 938 (2009), the\\nSupreme Court established that an “association-in-fact\\nenterprise must have at least three structural features: a\\npurpose, relationships among those associated with the\\nenterprise, and longevity sufficient to permit these\\nassociates to pursue the enterprise’s purpose.” Id. at 946.\\nThe structure necessary for a § 1962(c) enterprise is not\\ncomplex. Boyle explained that an enterprise\\n\\n 98\\n\\f need not have a hierarchical structure or a\\n “chain of command”; decisions may be made\\n on an ad hoc basis and by any number of\\n methods—by majority vote, consensus, a\\n show of strength, etc. Members of the group\\n need not have fixed roles; different members\\n may perform different roles at different\\n times. The group need not have a name,\\n regular meetings, dues, [or] established rules\\n and regulations . . . .While the group must\\n function as a continuing unit and remain in\\n existence long enough to pursue a course of\\n conduct, nothing in RICO exempts an\\n enterprise whose associates engage in spurts\\n of activity punctuated by periods of\\n quiescence.\\n\\nId. at 948.\\n\\n Another element of a substantive § 1962(c) RICO\\nenterprise is that the enterprise must conduct its affairs\\nthrough a pattern of racketeering activity. Section 1961\\ndefines racketeering activity to include various criminal\\noffenses, including wire fraud, 18 U.S.C. § 1344, and\\nobstruction of justice, 18 U.S.C. § 1511. See 18 U.S.C.\\n§ 1961(1). A pattern of such activity “requires at least two\\nacts of racketeering activity.” Id. § 1961(5). The\\nracketeering predicates may establish a pattern if they\\n“related and . . . amounted to, or threatened the likelihood\\n\\n\\n 99\\n\\fof, continued criminal activity.” H.J. Inc. v. Nw. Bell Tel.\\nCo., 492 U.S. 229, 237 (1989).\\n Here, the District Court denied the post-trial\\nsufficiency arguments raised by Fattah, Brand, and\\nNicholas. It reasoned:\\n For a RICO conspiracy to exist, the\\n conspirators must agree to participate in an\\n enterprise with a unity of purpose as well as\\n relationships among those involved. The\\n evidence demonstrates that an agreement\\n among Fattah, Brand, Nicholas, Lindenfeld,\\n and Naylor existed for the overall purpose of\\n maintaining and enhancing Fattah as a\\n political figure and of preventing his standing\\n from being weakened by the failure to be able\\n to pay or write down his campaign debts.\\n These five persons agreed to work together as\\n a continuing unit, albeit with different roles.\\n The Government established that\\n Fattah, Brand, and Nicholas conspired along\\n with Naylor and Lindenfeld to conceal and\\n repay the 2007 illegal $1,000,000 loan to the\\n Fattah for Mayor campaign.\\n\\nJA128–29. The District Court further determined that\\n [w]hile each member may not have been\\n involved in every aspect of the enterprise, its\\n activities were sufficiently structured and\\n 100\\n\\f coordinated to achieve the purpose of\\n maintaining and enhancing Fattah’s political\\n standing and of preventing him from being\\n weakened politically because of his\\n campaign debts.\\n A RICO conspiracy also requires an\\n agreement to participate in an enterprise with\\n longevity sufficient to pursue its purpose.\\n This was established. In May 2007 the illegal\\n loan was obtained and continued through its\\n repayment in January 2008 and into at least\\n 2014 when the last campaign report reducing\\n a fake campaign debt to Naylor’s consulting\\n firm was filed by Fattah.\\nJA131.\\n\\n The defendants argue that the evidence is\\ninsufficient to show either an enterprise for purposes of\\n§ 1962(c) or an agreement as required for a § 1962(d)\\nconspiracy. We disagree, and conclude that the District\\nCourt’s analysis is on the mark.\\n\\n We begin by considering whether there was an\\nagreement. The evidence showed that Fattah knew each\\nmember involved in the scheme to conceal the unlawful\\ncampaign loan. When Lindenfeld learned of the $1 million\\nloan, he informed Fattah that it exceeded campaign\\nfinance limits. In short, the transaction was unlawful, and\\nthe two knew it. The transaction nonetheless went\\nforward, disguised as a loan, with Lindenfeld executing\\n 101\\n\\fthe promissory note as Strategies’ officer and obligating\\nStrategies to repay Lord $1 million. The concealment\\nefforts continued as Lindenfeld funneled a substantial\\nportion of the loan proceeds to Naylor for get-out-the-vote\\nefforts. After the losing campaign, Lindenfeld spoke with\\nFattah and Naylor about accounting for the funds that had\\nbeen spent. They decided not to include the amounts in the\\nFFM campaign reports. Fattah instructed Naylor to\\nprepare a fictitious invoice, and Naylor complied. The\\nFFM campaign reports filed from 2008 to 2014 disclosed\\nnothing about the unlawful $1 million loan. Instead, they\\nfalsely showed that Naylor’s consulting firm made yearly\\nin-kind contributions of $20,000 in debt forgiveness, when\\nin reality there was no debt to forgive.\\n As Lindenfeld fretted over repaying the $600,000\\nbalance of the Lord loan, Naylor assured him that Fattah\\nhad promised to take care of the repayment. And the\\nevidence supports an inference that Fattah recruited both\\nNicholas and Brand in doing so. As EAA’s director,\\nNicholas could fund the repayment. Brand, through his\\ncompany, Solutions, acted as the middleman: he received\\nthe payment from EAA pursuant to a fictitious contract,\\nand then forwarded the balance due to Strategies pursuant\\nto yet another fictitious contract. Nicholas and Brand\\ncontinued in the spring and summer of 2008 to hide the\\nfictitious agreement and the $600,000 payment to\\nLindenfeld to satisfy the Lord loan.\\n\\n\\n\\n 102\\n\\f In short, this evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas all agreed to\\nparticipate in Fattah’s plan to conceal the unlawful\\ncampaign loan to maintain his political stature. Nicholas\\nand Brand claim that they had no knowledge of the false\\ncampaign reporting aspect of the plan. But as Salinas\\ninstructs, conspirators need not “agree to commit or\\nfacilitate each and every part of the” conspiracy. 522 U.S.\\nat 63. Rather, they “must agree to pursue the same criminal\\nobjective and may divide up the work, yet each [be]\\nresponsible for the acts of each other.” Id. at 63–64. Thus,\\na conspirator may agree to “facilitate only some of the acts\\nleading to the substantive offense” yet still be criminally\\nliable. Id. at 65.\\n The evidence showed that a substantial amount of\\nmoney was needed to repay Lord, and that the source of\\nthe repayment was EAA, a non-profit organization whose\\nfunds could be spent only for purposes consistent with the\\nterms of the grants it received. It also showed that Nicholas\\nwas presented with a sham contract to legitimize the\\nEAA–Solutions transaction. We conclude that the\\nevidence is sufficient to support an inference that Nicholas\\nknew at the start that the plan was unlawful. Yet she still\\nagreed to provide the requisite funds and to play a role in\\nconcealing the illegal campaign loan so that Fattah could\\nmaintain his political stature.\\n\\n As to Brand, even if he did not know that false\\ncampaign reports were being filed, the evidence is\\n\\n 103\\n\\fsufficient to show he played a key role in the enterprise.\\nFrom the outset, Brand worked to disguise the repayment\\nof the Lord loan as the consideration in a sham contract\\nbetween EAA and Solutions. He then arranged for the\\ntransfer of funds to Strategies in satisfaction of a\\ncontractual term in another purported business agreement\\nbetween Solutions and Strategies. The evidence reveals\\nthat Brand was the point man in the effort to meet the\\nJanuary 31, 2008 deadline to repay the Lord loan, and it\\namply shows that Brand also agreed to participate in the\\nplan to hide the illegal campaign loan and its repayment to\\nbenefit Fattah politically.\\n Fattah, Brand, and Nicholas attack their RICO\\nconspiracy convictions on another front. They argue that\\nthose verdicts should be set aside because the evidence\\nfails to show that the various schemes alleged in the\\nindictment as part of the RICO conspiracy are connected.\\nThe RICO count, they assert, charges a hub-and-spoke\\nconspiracy that is unconnected by a rim. In their view,\\nFattah is the hub, and the spokes consist of a series of\\nindependent schemes: the Vederman bribery scheme, the\\npayment of the outstanding tuition debt of Fattah’s son\\nChip, the Blue Guardians plan, and the repayment of the\\nillegal Lord loan to maintain Fattah’s political stature.\\nThey argue that, without a unifying rim, their actions\\ncannot constitute an enterprise. Again, we disagree.\\n\\n In In re Insurance Brokerage Antitrust Litigation,\\n618 F.3d 300 (3d Cir. 2010), we concluded, in analyzing\\n\\n 104\\n\\fone of plaintiffs’ RICO claims, that the alleged hub-and-\\nspoke enterprise—comprised of broker hubs and insurer\\nspokes—could not withstand a motion to dismiss because\\nit did not have a unifying rim. Id. at 374. We explained\\nthat the allegations did “not plausibly imply concerted\\naction—as opposed to merely parallel conduct—by the\\ninsurers, and therefore cannot provide a ‘rim’ enclosing\\nthe ‘spokes’ of these alleged ‘hub-and-spoke’\\nenterprises.” Id. Thus, the allegations did not “adequately\\nplead an association-in-fact enterprise” because the hub-\\nand-spoke conspiracy failed to “function as a unit.” Id.\\n\\n That is not the case here. The evidence showed that\\nFattah, Brand, and Nicholas agreed to conceal the illegal\\nLord loan. Each acted for the common purpose of\\nfurthering Fattah’s political interests. In short, they\\nengaged in concerted activity and functioned as a unit. The\\njury convicted Fattah, Brand, and Nicholas of the RICO\\nconspiracy based on the racketeering activity of wire fraud\\nand obstruction of justice to conceal the unlawful\\ntransaction. Because the evidence shows that Fattah,\\nLindenfeld, Naylor, Brand, and Nicholas agreed to protect\\nFattah’s political status by acting to maintain the secrecy\\nof the unlawful Lord loan, the alleged lack of a unifying\\n“rim” is not fatal to this RICO enterprise. What matters in\\nanalyzing the structure of this enterprise is that it\\nfunctioned as a unit. Boyle, 556 U.S. at 945; In re Ins.\\nBrokerage Antitrust Litig., 618 F.3d at 374. That “basic\\nrequirement” was met. Id.\\n\\n 105\\n\\f We turn next to the contention that the evidence\\nfails to establish other components of an enterprise. We\\nconclude that much of the evidence supporting the\\nexistence of an agreement also shows that there was an\\nassociation-in-fact enterprise.\\n\\n Boyle made clear that an association-in-fact\\nenterprise must have “a purpose, relationships among\\nthose associated with the enterprise, and longevity\\nsufficient to permit these associates to pursue the\\nenterprise’s purpose.” 556 U.S. at 946. The purpose, as we\\nhave repeatedly observed, was to maintain and preserve\\nFattah’s political stature by concealing the illegal loan and\\nits repayment. Though informal, there were relationships\\namong those associated with the enterprise. Fattah was at\\nthe center of this association and he directed its activity.\\nHe knew each of the association’s members, and the\\nmembers knew each other (except, perhaps, for Nicholas,\\nwho may not have known Lindenfeld).19\\n\\n\\n19\\n Nicholas’s lack of familiarity with Lindenfeld does not\\nundermine her membership in this association-in-fact\\nenterprise. We have previously explained that “[i]t is well-\\nestablished that one conspirator need not know the\\nidentities of all his co-conspirators, nor be aware of all the\\ndetails of the conspiracy in order to be found to have\\nagreed to participate in it.” United States v. Riccobene, 709\\nF.2d 214, 225 (3d Cir. 1983), abrogated on other grounds\\nby Griffin v. United States, 502 U.S. 46 (1991).\\n 106\\n\\f The Government also adduced sufficient proof of\\nthe longevity component required for an enterprise. The\\nscheme began in mid-2007, when Lord made the\\ncampaign loan, directing the proceeds of the loan to\\nStrategies. From the outset, Fattah, Lindenfeld, and Naylor\\nall knew they needed to conceal this illegal transaction.\\nThey began by fabricating an explanation for the source of\\nthe funds they spent on election day. SLA created a fake\\ninvoice for the campaign, showing a fictitious debt that\\nNaylor could later forgive by fictitious in-kind\\ncontributions existing only on Fattah’s campaign finance\\nreports.\\n The effort to disguise the Lord loan was not limited\\nto filing false campaign reports. Nicholas and Brand, who\\njoined the conspiracy a few months later than the other\\nmembers, understood that they too had to make the\\nfraudulent $600,000 payment by EAA to Solutions appear\\nlegitimate. Nicholas and Brand tried to disguise the sham\\ncontract as an ordinary transaction (even though it called\\nfor a six-figure upfront payment simply to support\\nSolutions’ various projects), and they succeeded in\\nkeeping it out of the DOJ auditors’ view until August\\n2008. The ruse continued as Solutions funneled the\\n$600,000 payment to Strategies under the guise of another\\nsham contract (which also required an upfront six-figure\\npayment). The scheme then continued as Fattah submitted\\nfalse FFM campaign reports from 2008 through 2014.\\n\\n\\n\\n 107\\n\\f Finally, we consider whether the enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity, as required for a § 1962(c) enterprise. Wire fraud\\nand obstruction of justice may constitute “racketeering\\nactivity” under § 1961(1). As the Supreme Court\\ninstructed in H.J. Inc., the “multiple predicates within a\\nsingle scheme” must be related and “amount[] to, or\\nthreaten[] the likelihood of, continued criminal activity.”\\n492 U.S. at 237. Here, the amount of the illegal loan to be\\nconcealed was substantial. The enterprise needed to write\\noff the fictitious debt to Naylor’s consulting firm, and it\\nwas urgent that both the EAA–Solutions contract and the\\nSolutions–Strategies contract be legitimized. We conclude\\nthe evidence was sufficient to establish that this enterprise\\nconducted its affairs through a pattern of racketeering\\nactivity and that the predicate acts of wire fraud and\\nobstruction of justice were related. The racketeering\\nactivity furthered the goals of maintaining the secrecy of\\nthis $1 million illicit campaign loan and of preserving\\nFattah’s political stature.\\n Nicholas contends that the evidence fails to\\nestablish a pattern of racketeering activity because the\\nactions to which she agreed did not “extend[] over a\\nsubstantial period of time” as H.J. Inc. requires. 492 U.S.\\nat 242. That case indeed instructs that the continuity\\nrequirement of a pattern is a “temporal concept,” and that\\n“[p]redicate acts extending over a few weeks or months”\\ndo not satisfy the continuity concept. Id. But the Supreme\\nCourt explained that continuity may also be established by\\n 108\\n\\fshowing that there is a “threat of continued racketeering\\nactivity.” Id. Here, the course of fraudulent conduct\\nundertaken to secure and to conceal the $1 million Lord\\nloan consisted of the creation of sham debts, fictitious\\ncontracts, and false accounting entries over the course of\\nabout a year. But because Fattah needed to appear able to\\nretire his campaign debt, the enterprise needed to continue\\nfiling false campaign reports for several years, allowing\\nthe annual $20,000 in-kind debt forgiveness contributions\\nto appear to satisfy Naylor’s fake $193,000 invoice. That\\nevidence was sufficient to establish the requisite threat of\\ncontinued criminal activity. See H.J. Inc., 492 U.S. at 242–\\n43.\\n We conclude that the Government met its burden in\\nproving that Fattah, Brand, and Nicholas 20 engaged in a\\nRICO conspiracy in violation of § 1962(d).\\n\\n\\n20\\n Nicholas also asserts, in passing, that that her conviction\\nunder § 1962(d) should be set aside because that statutory\\nprovision is unconstitutionally vague as applied to her.\\nAccording to Nicholas, a person of ordinary intelligence\\nwould not know that her actions constituted an agreement\\nto participate in a RICO enterprise. See United States v.\\nPungitore, 910 F.2d 1084, 1104–05 (3d Cir. 1990). To the\\ncontrary, a person of ordinary intelligence, who had been\\nemployed by a prominent politician and then became the\\nCEO of a nonprofit organization which that politician had\\nfounded (and, to some extent, continued to direct), would\\n 109\\n\\f VI. Variance from the Indictment and Sufficiency of\\n the Evidence for Count 2\\n Brand and Nicholas challenge their convictions for\\nconspiracy to commit wire fraud by arguing that the\\nGovernment’s evidence at trial impermissibly varied from\\nthe indictment. Nicholas also challenges the sufficiency of\\nthe evidence to support her conviction for conspiracy to\\ncommit wire fraud. We address these contentions\\ntogether. 21\\n\\n Count 2 of the indictment alleged a single\\nconspiracy. JA277–79. Brand and Nicholas assert that the\\nGovernment’s evidence at trial did not support the\\nexistence of a single conspiracy but instead showed two\\nindependent conspiracies, only one of which involved the\\ntwo of them. According to Brand and Nicholas, the only\\nconspiracy with which they were involved ended more\\nthan five years before the Government charged them. That\\nwould mean that all their conduct falls outside the five-\\nyear limitations period for wire fraud conspiracy under 18\\nU.S.C. § 3282.\\n\\n\\nrealize that agreeing to participate with others in hiding an\\nunlawful campaign loan of $1 million could constitute an\\nunlawful RICO conspiracy.\\n21\\n In her briefing, Nicholas discusses variance in far less\\ndetail than Brand, so we refer primarily to Brand’s\\narguments. See Nicholas Br. 54–56. Her variance\\narguments fail for the same reasons that Brand’s fail.\\n 110\\n\\f “A conviction must be vacated when (1) there is a\\nvariance between the indictment and the proof presented\\nat trial and (2) the variance prejudices a substantial right\\nof the defendant.” Kemp, 500 F.3d at 287 (quoting United\\nStates v. Kelly, 892 F.2d 255, 258 (3d Cir. 1989)). We see\\nno variance, and will affirm the District Court.\\n A variance exists “if the indictment charges a single\\nconspiracy while the evidence presented at trial proves\\nonly the existence of multiple conspiracies.” Id. “We must\\ndetermine ‘whether there was sufficient evidence from\\nwhich the jury could have concluded that the government\\nproved the single conspiracy alleged in the indictment.’ ”\\nId. (quoting Kelly, 892 F.2d at 258). Viewing the record in\\nthe light most favorable to the Government, we consider\\nthree factors: (1) “whether there was a common goal\\namong the conspirators”; (2) “whether the agreement\\ncontemplated bringing to pass a continuous result that will\\nnot continue without the continuous cooperation of the\\nconspirators”; and (3) “the extent to which the participants\\noverlap in the various dealings.” Id. (quoting Kelly, 892\\nF.2d at 259).\\n\\n Brand argues that the Government failed to\\nestablish a common goal among the conspirators. To\\ndetermine whether the conspirators shared a common\\ngoal, “we look to the underlying purpose of the alleged\\ncriminal activity” in a fairly broad sense. United States v.\\nRigas, 605 F.3d 194, 214 (3d Cir. 2010) (en banc). In\\nRigas, we described the common goal of the defendants as\\n\\n 111\\n\\f“enriching [themselves] through the plunder of [their\\ncorporate employer],” id., and we have similarly\\narticulated the common goal in fairly general terms\\nelsewhere. See United States v. Greenidge, 495 F.3d 85,\\n93 (3d Cir. 2007) (“There was certainly evidence of a\\ncommon goal among these co-conspirators: to make\\nmoney by depositing stolen and altered corporate checks\\ninto business accounts.”); Kelly, 892 F.2d at 259 (“[T]he\\ncommon goal of all the participants was simply to make\\nmoney selling ‘speed.’ ”). Importantly, a common goal\\nmay exist even when “conspirators individually or in\\ngroups perform different tasks in pursuing the common\\ngoal,” and a single conspiracy may “attract[] different\\nmembers at different times” or “involve[] different sub-\\ngroups committing acts in furtherance of the overall plan.”\\nUnited States v. Boyd, 595 F.2d 120, 123 (3d Cir. 1978).\\n\\n Here, the indictment described the purpose of the\\nunified conspiracy in Count 2 at length:\\n\\n It was a purpose of the conspiracy to obtain\\n an illegal campaign loan and to fraudulently\\n repay that loan with hundreds of thousands of\\n dollars of misappropriated charitable funds\\n from Sallie Mae and federal grant funds from\\n NASA which were intended for educational\\n purposes.\\n\\n . . . . It was further a purpose of the\\n conspiracy to present FATTAH to the public\\n as a perennially viable candidate for public\\n 112\\n\\f office who honored his obligations to his\\n creditors and was able to retire his publicly\\n reported campaign debts.\\n . . . . It was further a purpose of the\\n conspiracy to promote FATTAH’s political\\n and financial goals through deception by\\n concealing and protecting the conspirators’\\n activities from detection and prosecution by\\n law enforcement officials and the federal\\n judiciary, as well as from exposure by the\\n news media, through means that included\\n obstruction of justice and the falsification of\\n documents, including Campaign Finance\\n Reports, false invoices, contracts, and other\\n documents and records.\\n\\nJA277–78, ¶¶ 3–5.\\n Brand characterizes the evidence at trial as\\nestablishing two distinct conspiracies. The first he labels\\nthe “diversion of funds scheme,” covering the\\nmisappropriation of funds by Nicholas, Brand,\\nLindenfeld, and Fattah to repay the Lord loan. Brand Br.\\n34. Brand calls the second conspiracy the “CFR scheme,”\\nin which Fattah and Naylor filed the false campaign\\nfinance reports showing Naylor gradually forgiving a non-\\nexistent debt. Id.\\n Brand argues that the only goal of the CFR scheme\\nwas to cover up how the funds from the illegal campaign\\n 113\\n\\floan were spent, a goal he distinguishes from that of the\\ndiversion of funds scheme, which he characterizes as a\\nplan to cover up the repayment of the loan with stolen\\nfunds. He also argues that the evidence does not establish\\nhe was involved in, or even aware of, the false campaign\\nfinance reports filed by Fattah. In Brand’s view, that\\nnecessarily means the evidence showed two separate\\nconspiracies.\\n\\n In considering these arguments, we begin by noting\\nthat one conspiracy can involve multiple subsidiary\\nschemes. Rigas, 605 F.3d at 214. It is true that the false\\ncampaign finance reports, in the narrowest sense, had the\\nspecific purpose of covering up how the illegal loan funds\\nwere used during the election. But the false campaign\\nfinance reports were also filed in furtherance of a broader\\ngoal shared by the conspirators involved in repayment of\\nthe Lord loan. They sought to promote Fattah’s political\\nand financial goals by preserving his image as a viable\\ncandidate and making him appear able to repay or\\notherwise service his campaign debts without resorting to\\nillegal means in doing so. The two subsidiary schemes\\nworked in concert in furtherance of this overarching goal,\\nand both were directed at covering up how the loan was\\ntruly repaid. The “diversion of funds scheme” hid the\\nillegal (but real) loan repayment through the use of fake\\ncontracts; the “CFR scheme” showed the seemingly legal\\n(but fake) loan forgiveness installments through the\\ncreation of fake invoices and campaign finance reports.\\nThe existence of two concealment schemes acting in\\n 114\\n\\fconcert does not undermine the unity of the conspiracy of\\nwhich they were both a part. We have no difficulty\\nconcluding that the false campaign finance reports and the\\nconcealed use of stolen funds to repay the Lord loan\\noperated together in furtherance of a common goal.\\n\\n As for Brand’s argument that he was unaware of the\\nfalse campaign finance reports and therefore could not be\\na part of any conspiracy involving them, it is well-settled\\nthat “each member of the charged conspiracy is liable for\\nthe substantive crimes his coconspirators commit in\\nfurtherance of the conspiracy even if he neither\\nparticipates in his co-conspirators’ crimes nor has any\\nknowledge of them.” United States v. Bailey, 840 F.3d 99,\\n112 (3d Cir. 2016) (citing Pinkerton v. United States, 328\\nU.S. 640 (1946)). The exceptions to that rule allow a\\ndefendant to escape liability for a co-conspirator’s crime\\nif: (1) “the substantive offense committed by one of the\\nconspirators was not in fact done in furtherance of the\\nconspiracy,” (2) “the substantive offense committed by\\none of the conspirators ‘did not fall within the scope of the\\nunlawful project,’ ” or (3) “the substantive offense\\ncommitted by one of the conspirators ‘could not be\\nreasonably foreseen as a necessary or natural consequence\\nof the unlawful agreement.’ ” Id. (quoting Pinkerton, 328\\nU.S. at 647–48). There was, as we have concluded, a unity\\nof purpose between the co-conspirators to further Fattah’s\\npolitical and financial goals by secretly obtaining and\\nrepaying an illegal campaign loan with stolen funds. The\\nfiling of false campaign reports does not fit within any of\\n 115\\n\\fthe recognized exceptions to co-conspirator liability, as it\\nwas in furtherance of the conspiracy’s shared goal, within\\nthe scope of the agreement to conceal the loan, and\\nforeseeable to Brand and Nicholas.\\n\\n Neither Brand nor Nicholas briefed the other two\\nfactors we consider when determining whether the\\nevidence impermissibly varied from the evidence,\\n“whether the agreement contemplated bringing to pass a\\ncontinuous result that will not continue without the\\ncontinuous cooperation of the conspirators,” and “the\\nextent to which the participants overlap in the various\\ndealings.” Kemp, 500 F.3d at 287 (quoting Kelly, 892 F.2d\\nat 258). The unified goal of promoting Fattah’s political\\ncareer and maintaining secrecy surrounding the illegal\\nloan and the misappropriated funds used to repay it\\nrequired the continuous cooperation of the conspirators.\\nIndeed, the efforts of several of them overlapped in every\\naspect of the scheme. And Lindenfeld and Fattah were, at\\na minimum, involved in some way in nearly every aspect\\nof the origination of the loan, the false campaign finance\\nreports, and the use of misappropriated funds to repay the\\nloan. For his part, Naylor was involved in the use of the\\nfunds, the false campaign finance reports, and to a lesser\\nextent, the repayment of the loan.\\n Brand (as part of his variance argument) and\\nNicholas (as part of her sufficiency argument) argue that\\nthe Government did not prove they agreed to conceal their\\nactions, and thus the false campaign reports would not be\\n\\n 116\\n\\fsufficient to extend the duration of the conspiracy so that\\nit fell within the statute of limitations. Acts of\\nconcealment, such as the false campaign reports, are not\\nautomatically “in furtherance” of a conspiracy. We must\\ndetermine whether there was “an express original\\nagreement among the conspirators to continue to act in\\nconcert in order to cover up, for their own self-protection,\\ntraces of the crime after its commission,” as opposed to “a\\nconspiracy to conceal . . . being implied from elements\\nwhich will be present in virtually every conspiracy case,\\nthat is, secrecy plus overt acts of concealment.”\\nGrunewald v. United States, 353 U.S. 391, 404 (1957). If\\nthe indictment “specifically alleges a continuing\\nconspiracy” to conceal the crime after the completion of\\nthe wire fraud, and such a conspiracy can be proven, the\\nstatute of limitations does not begin to run until the last\\novert act of concealment. United States v. Moses, 148 F.3d\\n277, 282 (3d Cir. 1998).\\n\\n Here, the evidence shows that the conspirators\\nexpressly agreed to conceal the loan and its repayment. As\\nan initial matter, Brand’s only role in the conspiracy was\\nto cover up the use of stolen funds by (1) serving as an\\nintermediary between Nicholas and Lindenfeld; and\\n(2) agreeing to create false documentation (the contracts)\\nwith both EAA and Strategies for the sole purpose of\\ndisguising the payments and covering up the wire fraud\\nconspiracy. Nicholas could simply have paid Lindenfeld\\nherself (or paid Lord) if she and Brand had not agreed to\\nconceal the crime from the start. Additionally, and as\\n 117\\n\\fBrand acknowledges, the false campaign finance reports\\nbegan before the loan was repaid, proving that\\nconcealment of the crime was contemplated and begun as\\na direct purpose of the conspiracy before Brand and\\nNicholas became involved in the repayment. Nicholas too\\nagreed to conceal the repayment, as she implicitly\\nacknowledged in her emails with Brand and Fattah. GSA2.\\nFinally, when Lindenfeld briefly strayed from the\\nconspiracy’s commitment to secrecy by mentioning the\\nrepayment in front of others who did not know of the\\nscheme, Brand became “angry,” “took [Lindenfeld] out in\\nthe hallway,” and chastised him, saying that “[Lindenfeld]\\ncouldn’t say that sort of []thing” in front of other people.\\nJA1670–71. We conclude that the evidence is consistent\\nwith the allegations in the indictment, which charge a\\nsingle conspiracy consisting of an original agreement to\\nconceal the illegal loan and its subsequent illegal\\nrepayment to further Fattah’s political career.\\n\\n Nicholas makes several arguments in passing. She\\nsuggests that the District Court upheld the conviction after\\ntrial “on a theory not submitted to the jury.” Nicholas Br.\\n51. This argument is, essentially, that the indictment and\\nthe District Court’s post-trial ruling described the\\nconspiracy one way, but that the jury charge described the\\nconspiracy differently. Nicholas argues that the jury was\\npresented with the theory that the sole purpose of the false\\ncampaign reports under Count 2 was to “conceal[] the\\nalleged scheme to defraud,” JA5849, rather than to support\\n\\n 118\\n\\fFattah’s political career, as the District Court described the\\npurpose after trial, see JA74.\\n Nicholas ignores that part of the jury charge which\\ninstructed that Count 2 required a finding “[t]hat two or\\nmore persons agreed to commit wire fraud as charged in\\nthe indictment.” JA5845 (emphasis added). The jury had\\naccess to the indictment, and as Nicholas points out,\\nNicholas Br. 45–46, the indictment outlines the offense in\\nthe same way the District Court later described it in its\\npost-trial ruling. The District Court consistently described\\nthe count, and we see no reversible error.\\n Nicholas also argues that the conspiracy charged in\\nCount 2 has an objective—“to ‘present Fattah’ as\\n‘perennially viable’ ”—and that such an objective is not\\nillegal. Nicholas Br. 53. But, of course, the jury was not\\ninstructed that it was illegal to be a Fattah supporter, or\\neven to work on his campaign. The jury was charged\\nspecifically on the crime of wire fraud.\\n\\n We conclude that there was no impermissible\\nvariance between the indictment and the Government’s\\nevidence at trial, and that there was sufficient evidence to\\nsupport the convictions. We will affirm the convictions of\\nBrand and Nicholas for conspiracy to commit wire fraud\\nunder Count 2.\\n\\n\\n\\n\\n 119\\n\\f VII. The District Court’s Instruction to the Jury on\\n the Meaning of Intent\\n Nicholas contends that the District Court\\nimproperly instructed the jury by using the disjunctive\\nrather than the conjunctive at one point in its definition of\\nintent. When providing its final charge to the jury, the\\nDistrict Court explained:\\n Certain of the offenses charged in the\\n indictment require that the government prove\\n that the charged defendant acted intentionally\\n or with intent. This means that the\\n government must prove either that (1), it was\\n the defendant’s conscious desire or purpose\\n to act in a certain way or to cause a certain\\n result; or (2), the defendant knew that he or\\n she was acting in that way or it would be\\n practically certain to cause that result.\\n\\nJA5787 (emphasis added). According to Nicholas, an\\naccurate definition of intent required that the final “or” be\\nan “and.” Nicholas argues that this was an error so\\ngrievous as to “effectively eliminate[] the intent element\\nfrom each offense of conviction.” 22 Nicholas Br. 26.\\n\\n\\n22\\n The Comment to Third Circuit Model Criminal Jury\\nInstruction 5.03 makes clear that the definition of intent\\nencapsulates both “specific intent” (acting “purposely” or\\nwith “conscious object”) and “general intent” (acting\\n 120\\n\\f Our review of whether a jury instruction stated the\\nproper legal standard is plenary. United States v. Petersen,\\n622 F.3d 196, 207 n.7 (3d Cir. 2010). At trial, Nicholas\\nfailed to object to this portion of the jury charge.\\nAccordingly, our review must be for plain error. See\\nUnited States v. Flores-Mejia, 759 F.3d 253, 258 (3d Cir.\\n2014) (en banc).\\n\\n To prevail on plain error review, Nicholas must\\nestablish that there was an error, that it was plain (i.e., clear\\nunder current law), and that it affected her substantial\\nrights (i.e., whether there is a reasonable likelihood that\\nthe jury applied the challenged instruction in an\\nimpermissible manner). United States v. Olano, 507 U.S.\\n\\n“knowingly” or “with awareness”). Although Nicholas\\ndescribes the alleged error as “essentially eliminating” the\\nelement of intent, we think Nicholas’s argument is better\\nunderstood as a claim that the instruction given could have\\npermitted a jury to conclude that she acted with only\\ngeneral intent (that she was aware of what she was doing),\\nwhen her crimes require specific intent (that she had an\\nillegal purpose). As her brief states, “[p]lainly she\\n‘knowingly’ wrote checks from EAA to [Solutions] and\\nmade record entries about them; the question was whether\\nshe intended to defraud EAA and NASA, or to obstruct\\njustice, by doing so.” Nicholas Br. 24. We cannot agree\\nwith her characterization that the instruction resulted in the\\n“effective omission” of the intent element from the jury\\ninstructions.\\n 121\\n\\f725, 733–34 (1993); United States v. Dobson, 419 F.3d\\n231, 239–40 (3d Cir. 2005). If these requirements are met,\\nwe may then exercise our discretion to address the error,\\nbut only if we conclude that the error seriously affected the\\nfairness, integrity, or public reputation of the judicial\\nproceeding. United States v. Andrews, 681 F.3d 509, 517\\n(3d Cir. 2012) (quoting Johnson v. United States, 520 U.S.\\n461, 467 (1997)). A failure to instruct the jury on a\\nnecessary element of an offense ordinarily constitutes\\nplain error, unless the instructions as a whole otherwise\\nmake clear to the jury all the necessary elements of the\\noffense. United States v. Stimler, 864 F.3d 253, 270 (3d\\nCir. 2017).\\n Nicholas acknowledges, as she must, that the\\ninstruction given was a verbatim recitation of Instruction\\n5.03 of the Third Circuit’s Model Criminal Jury\\nInstructions. She nonetheless contends that our Model\\nInstruction is erroneous. Even if we were to accept\\nNicholas’s contention that the instruction is incorrect, a\\nproposition we consider as highly doubtful, see Petersen,\\n622 F.3d at 208 (“We have a hard time concluding that the\\nuse of our own model jury instruction can constitute error\\n. . . .”), we conclude that, considering the instructions as a\\nwhole, the District Court clearly and specifically\\ninstructed the jury on the intent element as it applied to\\neach of Nicholas’s charged crimes.\\n\\n The disputed intent instruction was given at the\\nbeginning of the final charge, explaining the general\\n\\n 122\\n\\fmeaning of the intent applicable to “[c]ertain of the\\noffenses charged.”23 JA5787. The District Court went on\\nto instruct the jury in specific detail on the elements of\\neach of the crimes of which Nicholas was accused,\\n\\n\\n\\n\\n23\\n The introductory definition did not end with the\\nlanguage Nicholas cites. The District Court elaborated that\\nacting in good faith is a complete defense to the charges:\\n\\n The offenses charged in the indictment\\n require proof that the charged defendants\\n acted with criminal intent. If you find that a\\n defendant acted in good faith that would be a\\n complete defense to such a charge, because\\n good faith on the part of the defendant would\\n be inconsistent with his or her acting\\n knowingly, willfully, corruptly, or with intent\\n to defraud or intent to impede, obstruct, or\\n wrongfully influence.\\n\\nJA5788–89 (emphasis added). This instruction\\nundermines Nicholas’s claim that the jury could have\\nreasonably concluded that she “ ‘knowingly’ wrote\\nchecks” but did not “intend[] to defraud . . . or to obstruct\\njustice[] by doing so,” Nicholas Br. 24, as this instruction\\nleaves little room for doubt that good faith is at odds with\\n“criminal intent.”\\n\\n 123\\n\\fexplaining also the intent element of each. 24 See JA5791\\n(describing the third element of the RICO conspiracy\\ncharge as: “the particular defendant and at least one other\\nalleged conspirator shared a unity of purpose and the intent\\nto achieve the objective of conducting or participating in\\nthe conduct of an enterprise’s affairs through a pattern of\\nracketeering activity”); JA5823 (regarding wire fraud,\\ninstructing that the government must prove “[t]hat the\\ndefendant under consideration acted with the intent to\\ndefraud”); JA5838–39 (regarding obstruction of justice,\\ninstructing that the defendant must have acted “with the\\nintent to impair the record, document, or object’s integrity\\nor availability for use in an official proceeding,” and must\\nhave acted corruptly “with the purpose of wrongfully\\nimpeding the due administration of justice”); JA5860\\n(explaining that falsification of records requires that “the\\ndefendant under consideration acted with the intent to\\nimpede, obstruct or influence the investigation or proper\\nadministration of a matter”). These instructions are\\nconsistent with both our Model Jury Instructions and our\\ncase law concerning the elements of these crimes. See\\nThird Circuit Model Criminal Jury Instruction 6.18.1962D\\n(RICO), 6.18.1343 (wire fraud), 6.18.1512A2 (obstruction\\nof justice); United States v. Sussman, 709 F.3d 155, 168\\n(3d Cir. 2013) (obstruction of justice); United States v.\\n\\n24\\n Nicholas did not object to the knowledge and intent\\ninstructions when the District Court discussed each of the\\nindividual charges, and does not identify a disagreement\\nwith any specific instruction on any particular charge.\\n 124\\n\\fMoyer, 674 F.3d 192, 208–09 (3d Cir. 2012) (falsification\\nof records); United States v. Pelullo (Pelullo I), 964 F.2d\\n193, 216 (3d Cir. 1992) (wire fraud).\\n The District Court also provided a separate\\ndefinition of the knowledge element of each charge,\\nillustrating the difference between knowledge and intent.\\nSee JA5793 (explaining that the evidence must show that\\na RICO defendant “knowingly agreed to facilitate or\\nfurther a course of conduct, which if completed would\\ninclude a pattern of racketeering activity”); JA5823 (wire\\nfraud means that the defendant “knowingly devised a\\nscheme to defraud a victim . . . by materially false or\\nfraudulent pretenses”); JA5860 (falsification of records\\nhas as an element “[t]hat the defendant under\\nconsideration knowingly concealed, covered up, falsified\\nor made false entries in a document or record”). These\\ninstructions made clear that knowledge and intent are\\nseparate considerations, undermining Nicholas’s\\ncontention that the jury was led to believe that “knowledge\\nis sufficient to prove intent.” Nicholas Br. 24.\\n The District Court provided each member of the\\njury with more than 100 pages of instructions before\\ndeliberations began. Viewing those instructions as a\\nwhole, we are satisfied that the jury was apprised of the\\ncorrect meaning of intent as an element of the crimes with\\nwhich Nicholas was charged, as well as the distinction\\nbetween knowledge and intent. We perceive no error,\\n\\n\\n 125\\n\\fmuch less error that is plain, in the District Court’s\\ninstructions to the jury. 25\\n\\n VIII. Sending the Indictment to the Jury\\n At trial, Vederman, Nicholas, and Brand objected to\\nthe District Court’s decision to give the jury a redacted\\ncopy of the indictment to use during its deliberations. Only\\nNicholas and Brand raise this issue on appeal. In\\nNicholas’s view, sending the indictment to the jury\\nunfairly prejudiced her because it contained unsupported\\nallegations that she had obstructed federal agencies and\\nreferred to a nonexistent certification requirement for\\nSallie Mae funds. Brand argues that he was prejudiced by\\nthe indictment’s references to “schemes” and “fake”\\ncontracts, and because it mentioned Brand’s spouse and\\nthat she was a former member of Fattah’s congressional\\nstaff. Nicholas and Brand together assert that the\\nindictment included legal theories on which the jury was\\nnot instructed. They contend that the indictment’s\\nnarrative of the Government’s case set out a roadmap that\\nomitted any averments relating to the defense theory and\\nallowed the Government to yet again present its case. To\\nbuttress that argument, Nicholas and Brand cite the\\ntestimony of Juror 12, who described the jury’s initial\\n\\n\\n\\n25\\n Accordingly, we need not consider the merits of\\nNicholas’s argument that Model Criminal Jury Instruction\\n5.03 is erroneous.\\n 126\\n\\fdeliberations and alleged that the jurors viewed the\\nindictment as evidence.\\n In United States v. Todaro, 448 F.2d 64, 66 (3d Cir.\\n1971), we held that the decision to allow “jurors to have a\\ncopy of the indictment with them during their\\ndeliberations . . . is a matter within the discretion of the\\nDistrict Judge, subject to a limiting instruction that the\\nindictment does not constitute evidence, but is an\\naccusation only.” Subsequently, in United States v.\\nPungitore, 910 F.2d 1084, 1142 n.83 (3d Cir. 1990), we\\nacknowledged that the District Court has the power to\\nredact the indictment if doing so would be appropriate to\\navoid prejudice to the defendant. See also United States v.\\nRoy, 473 F.3d 1232, 1237 n.2 (D.C. Cir. 2007) (noting that\\ncourt may redact an indictment before submitting it to the\\njury).\\n\\n While both Nicholas and Brand objected in general\\nterms to the District Court’s decision to provide the\\nindictment to the jury, they have not directed us to any\\nspecific request to redact the information they now claim\\nis prejudicial. And the District Court provided a limiting\\ninstruction on four occasions during its charge, repeatedly\\nemphasizing that the indictment was not evidence.\\nJA5765, 5767, 5782, 5880. The Court instructed the jury\\non its duty to base its verdict “solely upon the evidence in\\nthe case.” JA5764. Just before the jury retired to\\ndeliberate, the Court reiterated that the purpose of the\\n\\n\\n 127\\n\\findictment is to set forth the charges, and that it is “merely\\nan accusation.” JA5909.\\n “[J]uries are presumed to follow their instructions\\n. . . .” Richardson v. Marsh, 481 U.S. 200, 211 (1987). In\\nour view, Juror 12’s assertion that the indictment was\\nbeing considered evidence does not, standing alone,\\nestablish that his fellow jurors actually did so. We reject\\nthe notion that the jury, after hearing weeks of testimony\\nand having viewed substantial documentary evidence,\\nwent on to ignore the Court’s limiting instruction\\nconcerning the indictment. 26 Accordingly, we conclude\\n\\n\\n26\\n We acknowledge that our case law provides minimal\\nguidance to district courts concerning the practice of\\nsending an indictment to the jury for their use during\\ndeliberations. We are also aware that some courts have\\ndisapproved the practice of sending the indictment out\\nwith the jury. See United States v. Esso, 684 F.3d 347, 352\\nn.5 (2d Cir. 2012); Roy, 473 F.3d at 1237 n.2. We\\nemphasize that this practice is committed to the sound\\ndiscretion of the district judge. Todaro, 448 F.2d at 66. In\\nour view, such an exercise of a judge’s discretion should\\nbe informed by considering the nature of the case, the\\nnumber of defendants, the length of the indictment, the\\nextent of the factual recitation supporting the criminal\\ncharges, and most importantly, whether the indictment\\n(especially if lengthy and fact-laden) will be useful to the\\njury, in light of the judge’s own carefully tailored jury\\n 128\\n\\fthat the District Court did not abuse its discretion in\\nsending the indictment out to the jury.\\n\\n IX. The District Court’s Evidentiary Rulings\\n Vederman, Nicholas, and Brand each challenge\\nevidentiary rulings by the District Court. We conclude that\\nnone of these contentions warrants setting aside their\\nconvictions.\\n\\n A. The District Court’s Application of Rule 404(b)\\n Vederman argues that the District Court misapplied\\nFederal Rule of Evidence 404(b) when it excluded\\nevidence of Vederman’s prior gift-giving. 27 This Court\\nreviews a district court’s application of Rule 404(b) for\\nabuse of discretion. United States v. Daraio, 445 F.3d 253,\\n\\ninstruction, as supplemented by a verdict slip. See Esso,\\n684 F.3d at 352 n.5.\\n27\\n Although Rule 404(b) determinations are usually in\\nresponse to attempts to introduce “bad” acts evidence,\\nVederman’s attempt to introduce “good” acts of gift-\\ngiving is properly analyzed under the same rule. Ansell v.\\nGreen Acres Contracting Co., 347 F.3d 515, 520 (3d Cir.\\n2003) (“The evidence admitted in this case differs from\\ngarden variety Rule 404(b) matter because it is evidence,\\nnot of a prior bad act in a criminal case, but of a subsequent\\ngood act in a civil case. Nonetheless, this evidence is\\nencompassed by the plain text of Rule 404(b) which\\naddresses ‘other . . . acts,’ not just prior bad acts.”).\\n 129\\n\\f259 (3d Cir. 2006); Ansell v. Green Acres Contracting Co.,\\n347 F.3d 515, 519 (3d Cir. 2003). A trial court commits\\n“[a]n abuse of discretion . . . when [the] district court’s\\ndecision rests upon a clearly erroneous finding of fact, an\\nerrant conclusion of law or an improper application of law\\nto fact.” Pardini v. Allegheny Intermediate Unit, 524 F.3d\\n419, 422 (3d Cir. 2008) (quoting P.N. v. Clementon Bd. of\\nEduc., 442 F.3d 848, 852 (3d Cir. 2006)).\\n\\n Federal Rule of Evidence 404(b) provides in part:\\n (b) Crimes, Wrongs, or Other Acts.\\n\\n (1) Prohibited Uses. Evidence of a\\n crime, wrong, or other act is not\\n admissible to prove a person’s\\n character in order to show that on a\\n particular occasion the person\\n acted in accordance with the\\n character.\\n\\n (2) Permitted Uses; Notice in a\\n Criminal Case. This evidence may\\n be admissible for another purpose,\\n such as proving motive,\\n opportunity, intent, preparation,\\n plan, knowledge, identity, absence\\n of mistake, or lack of accident.\\nFed. R. Evid. 404(b)(1)–(2).\\n\\n 130\\n\\f At trial, Vederman sought to present a witness from\\nAmerican University who would have testified that\\n“Vederman agreed, on more than fifty instances, to\\nfinancially assist students [at American] who needed help\\nwith tuition, book money, or travel funds to visit their\\nfamilies.” Vederman Br. 42 (emphasis omitted).\\nAccording to Vederman, the testimony was relevant to\\nrefuting the Government’s argument that he agreed to\\nguarantee the tuition expenses of Fattah’s au pair as a way\\nof bribing the congressman. In excluding this evidence\\nunder Rule 404(b), the District Court stated at sidebar:\\n\\n I sustain the government’s objection to\\n calling a representative of American\\n University to testify on behalf of Herbert\\n Vederman.\\n\\n In my view the testimony runs afoul of\\n Rule 404(b)(1) of the Federal Rules of\\n Evidence. I find it to be propensity evidence.\\n He or she would be testifying about Mr.\\n Vederman’s financial generosity with respect\\n to students of American University.\\n The issue here is payment of partial\\n tuition of a student at the Philadelphia\\n University. I see no connection between the\\n generosity at American University and the\\n situation with Philadelphia University.\\n\\n\\n 131\\n\\fJA4459–60. Vederman argues that because the proposed\\nevidence related to Vederman’s intent, and not solely his\\npropensity to perform good acts, we should conclude that\\nthe District Court abused its discretion. We see no error in\\nthe District Court’s ruling.\\n\\n Vederman challenges as arbitrary the District\\nCourt’s “assertion that support for American University\\nstudents is too remote from support for Philadelphia\\nUniversity students” such that it constitutes inadmissible\\nevidence. Vederman Reply Br. 23. This distinction was far\\nfrom arbitrary. Vederman may well have financially\\nsupported American University students because of\\nconnections he had to that school or to the D.C.\\ncommunity at large—connections Vederman did not have\\nto Philadelphia University. And the excluded testimony\\nappears to have described support for students Vederman\\ndid not previously know. By supporting Fattah’s au pair,\\nVederman was helping an employee of a man whom he\\nknew quite well. JA889 (“[Fattah and Vederman] spent a\\nlot of time together traveling back and forth to\\nWashington, in the case of a death in the family attending\\ncertain ceremonies that were important, and above all\\nspending time with each other and their families\\ntogether.”). Vederman’s decision to help Fattah’s au pair,\\nwho wished to attend Philadelphia University, seems more\\nlike a departure from, rather than a continuation of, his\\npattern of support for American University students.\\n\\n\\n\\n 132\\n\\f As the party seeking admission of evidence under\\nRule 404(b), Vederman bore “the burden of demonstrating\\nits applicability” and “identifying a proper purpose.”\\nUnited States v. Caldwell, 760 F.3d 267, 276 (3d Cir.\\n2014). By failing to explain sufficiently why the factual\\ndistinctions discussed above were not material, Vederman\\nfailed to meet his burden. In particular, although\\nVederman argues that he offered evidence of his prior gift-\\ngiving to prove intent—“a proper non-propensity\\npurpose”—he failed to show why the proposed testimony\\nwas “relevant to that identified purpose.” Id. at 277. 28 As\\nwe noted in Ansell v. Green Acres Contracting, an\\nemployment discrimination case on which Vederman\\nheavily relies, “[t]here is. . . no bright line rule for\\ndetermining when evidence is too remote to be relevant.”\\n347 F.3d at 525. As such, a district court’s determination\\nunder Rule 404(b) “will not be disturbed on appeal unless\\nit amounts to an abuse of discretion.” Id. The District\\n\\n\\n\\n28\\n Under Rule 404(b), “prior act evidence is inadmissible\\nunless the evidence is (1) offered for a proper non-\\npropensity purpose that is at issue in the case; (2) relevant\\nto that identified purpose; (3) sufficiently probative under\\nRule 403 such that its probative value is not outweighed\\nby any inherent danger of unfair prejudice; and\\n(4) accompanied by a limiting instruction, if requested.”\\nUnited States v. Caldwell, 760 F.3d 267, 277–78 (3d Cir.\\n2014).\\n 133\\n\\fCourt did not abuse its discretion in excluding evidence of\\nVederman’s support for students at American University.\\n\\nB. Evidentiary Rulings Regarding Nicholas’s Defense\\n Nicholas argues that the District Court rendered\\nthree erroneous evidentiary rulings that prejudiced her\\ndefense. We do not find any of her arguments convincing.\\n\\n 1. The EAA Board Minutes\\n In support of its theory that Nicholas defrauded\\nEAA, the Government introduced minutes from EAA’s\\nBoard. Minutes from 2005 revealed that the Board limited\\nNicholas’s signing authority to $100,000. Minutes from\\nDecember 2007, February 2008, and May 2008 failed to\\nreference either the EAA–Solutions contract or the checks,\\ndrawn from EAA’s account for $500,000 and $100,000,\\nthat were purportedly paid pursuant to the contract.\\nNicholas contends that the Board minutes were\\nerroneously admitted because they constituted improper\\nhearsay which failed to satisfy either the exception for\\nbusiness records under Federal Rule of Evidence 803(6)\\nor the absence of records exception under Federal Rule of\\nEvidence 803(7). “We review the District Court’s\\nevidentiary ruling[s] for abuse of discretion, but also\\n‘exercise plenary review . . . to the extent [the rulings] are\\nbased on a legal interpretation of the Federal Rules of\\nEvidence.’ ” Repak, 852 F.3d at 240 (citations omitted)\\n(second alteration in original).\\n\\n 134\\n\\f Applying those standards here,29 we conclude there\\nwas sufficient basis to admit exhibit EAA-48 under\\nFederal Rule of Evidence 803(6) as a business record.\\nAlthough allowing the prosecution to inquire over\\nNicholas’s earlier objection based on Federal Rule of\\nEvidence 803(7) to the absence of any mention of the\\n$500,000 check in the 2008 Board Minutes was error, it\\nwas not reversible error. Other evidence in the record\\noverwhelmingly showed that Nicholas made the $500,000\\nand $100,000 payments to Solutions with the requisite\\nfraudulent intent. That evidence included the 2005 policy\\nlimiting Nicholas’s authority to approve expenditures to\\n$100,000, the accountant’s testimony about the\\ndisbursement policy requiring the completion of a check\\nrequest form for the issuance of a check, and Jones’\\ntestimony that he never saw a request for the $500,000\\ncheck. That evidence, coupled with Nicholas’s tendering\\nof the upfront half-million dollar payment before the terms\\nof the purported agreement had been finalized or executed,\\nher failure to mention the $600,000 in payments to\\nSolutions during her interview with FBI Agent\\n\\n29\\n We note that the argument section of Nicholas’s brief on\\nthis issue specifically cited to the page in the record where\\nexhibit EAA-48 was admitted without objection by any\\ndefense counsel. See Appellant’s Br. at 57 (citing JA4381-\\n82). Nonetheless, there was an earlier objection to the\\nadmission of exhibit EAA-48 that was preserved and that\\nwas referenced in a string citation elsewhere in Nicholas’s\\nbrief.\\n 135\\n\\fDieffenbach, and her alteration of EAA’s general ledger\\nto conceal the $100,000 payment, makes it “highly\\nprobable” that the jury would have reached the same\\nresult. See United States v. Friedman, 658 F.3d 342, 352\\n(3d Cir. 2011).\\n\\n Nicholas also asserts that the Board minutes were\\nunfairly prejudicial. We disagree. Any possible prejudice\\nwas minimized by the fact that the Board minutes make no\\nreference to either the EAA–Solutions contract or to any\\nfinancial matters whatsoever. Indeed, given these lacunae\\nin the Government’s proof, a reasonable factfinder might\\nwell have concluded that the Board’s intention to limit\\nNicholas’s signing authority had not been implemented\\nand that Nicholas had not concealed the contract from the\\nBoard.\\n\\n 2. Jones’ Memory Regarding Other Contracts\\n Nicholas next asserts that the District Court erred\\nduring her cross-examination of Board Chairman Jones by\\nsustaining the prosecution’s objection to her inquiry into\\nwhether he remembered other contracts in excess of\\n$100,000 being brought to the Board. See JA1386–87. The\\nbasis of the prosecution’s objection seemed to be that\\nNicholas’s line of inquiry was beyond the scope of the\\ndirect testimony. JA1387 (“I showed checks concerning\\nwhat’s going on, not other programs.”); see Fed. R. Evid.\\n611(b). The District Court sustained the objection,\\ndeclaring that “it has absolutely nothing to do with this\\ncase.” JA1387. Nicholas contends that if Jones did not\\n 136\\n\\frecall whether other large contracts had been presented to\\nthe Board, his inability to recall the EAA–Solutions\\ncontract would have been “unremarkable rather than\\nevidence of fraud or concealment.” Nicholas Br. 61.\\n\\n We acknowledge that whether Jones remembered\\nother large contracts requiring Board approval had some\\nrelevance under Rule 401. Yet any error by the District\\nCourt in prohibiting Nicholas’s counsel from pursuing this\\nline of inquiry is harmless. Jones admitted that he did not\\nknow if the Board ever implemented the policy requiring\\nits approval of contracts exceeding $100,000. He also\\nconceded that the EAA Board focused less on the financial\\nside of EAA than on its programs. JA1383–85. Nicholas\\ncould not have been prejudiced by the District Court’s\\nruling.\\n\\n 3. Exclusion of NOAA Evidence\\n Nicholas defended against the criminal charges\\narising out of the non-existent October 2012 conference\\nby asserting that she acted in “good faith in spending the\\nNOAA funds on EAA expenses,” Nicholas Br. 64, that the\\ndifference in the dates in the paperwork was not material,\\nand that NOAA had received the benefits of the\\nsponsorship because its logo was displayed on the signage\\nused at the February conference. Nicholas succeeded in\\npresenting testimony and introducing photographs that\\nshowed NOAA’s logo on the February 2012 annual\\nconference bags, padfolios, and name tags. The Court\\nexcluded a photograph of a NOAA intern at the February\\n 137\\n\\f2012 conference, other photographs of the February\\nconference signage, and some checks that pertained to the\\nFebruary conference. Nicholas claims that her inability to\\nintroduce those exhibits frustrated her ability to present\\nher good faith defense. We are not persuaded.\\n\\n The photographs were excluded as cumulative, the\\nsort of ruling to which we afford trial judges very broad\\ndiscretion. See Fed. R. Evid. 403; United States v.\\nDalfonso, 707 F.2d 757, 762 (3d Cir. 1983). It was not\\nerror to exclude the student intern’s photograph. The\\nconference brochure included photographs from previous\\nconferences, and the witness from NOAA was unable to\\ntestify to the year the student served as an intern. Finally,\\nthe checks tendered for the travel expenses incurred for the\\nFebruary conference were excluded as irrelevant to\\nwhether Nicholas had a good faith belief that NOAA\\nsponsored the October conference.\\n\\nC. The Cooperating Witness’s Mental Health Records\\n During discovery, Brand learned that a cooperating\\nwitness was diagnosed with bipolar II disorder and was\\ntaking medication to treat that condition. Brand\\nsubpoenaed mental health records kept by the witness’s\\ncurrent and former psychiatrists in hopes of using those\\nrecords to attack the witness’s memory, truthfulness, and\\ncredibility. The witness and the Government both filed\\nmotions to quash the subpoena, arguing that the witness’s\\nmental health records were protected by the\\npsychotherapist–patient privilege recognized by the\\n 138\\n\\fSupreme Court in Jaffee v. Redmond, 518 U.S. 1 (1996).\\nThe Government also filed a motion in limine seeking to\\nrestrict the scope of cross-examination to prevent Brand\\nfrom questioning the witness about his mental health.\\n\\n Alongside his motion to quash, the witness\\nvoluntarily produced for the Court his mental health\\nrecords. The Court concluded that the psychotherapist–\\npatient privilege would ordinarily apply to the mental\\nhealth records, but that the privilege was not absolute,\\nespecially when invoked in response to a criminal\\ndefendant’s efforts to obtain through discovery evidence\\nthat is favorable to his case. Following the procedure set\\nforth in Pennsylvania v. Ritchie, 480 U.S. 39 (1987), the\\nDistrict Court conducted an in camera review of the\\nmental health records to determine if they contained\\nmaterial evidence—that is, evidence that would “give[]\\nrise to a reasonable probability that it [would] affect the\\noutcome of the case.” JA149. The District Court found\\n“nothing in the mental health records of the [witness] . . .\\nmaterial for this criminal action,” noting that “[t]he\\nrecords reveal nothing that calls into question [the\\nwitness’s] memory, perception, competence, or veracity.”\\nJA150. Accordingly, the Court entered an order granting\\nthe motions to quash the subpoena.\\n The District Court also granted the Government’s\\nmotion in limine and restricted the scope of cross-\\nexamination, ruling that “no reference may be made to [the\\nwitness’s] bipolar disorder or the medications he takes to\\n\\n 139\\n\\fmanage it.” JA142, 156. The Court reasoned that bipolar\\ndisorder varied in its effects from person to person, and\\nconcluded that Brand had not shown that the effects of the\\ndisorder had any bearing on the witness’s credibility. The\\nDistrict Court ruled that cross-examination would not\\nserve any valid impeachment purpose.\\n Brand claims that the District Court’s order ran\\nafoul of the Due Process Clause of the Fifth Amendment\\nand the Confrontation Clause of the Sixth Amendment.\\nWe review a district court’s rulings to quash a subpoena\\nand to limit the scope of cross-examination for abuse of\\ndiscretion. United States v. Tykarsky, 446 F.3d 458, 475\\n(3d Cir. 2006); NLRB v. Frazier, 966 F.2d 812, 815 (3d\\nCir. 1992). Here, the District Court did not abuse that\\ndiscretion.\\n\\n1. The District Court’s Denial of Access to the Mental\\n Health Records\\n In claiming that the District Court’s decision to\\nreview the mental health records in camera before ruling\\non their admissibility violated his rights under both the\\nFifth and Sixth Amendments, Brand specifically argues\\nthat his right to confront the witness was impeded because\\nhe was denied access to records he could have used to\\nimpeach the witness. This very argument was considered\\nand rejected by a plurality of the Supreme Court in Ritchie,\\nwhich noted that “the effect [of the argument] would be to\\ntransform the Confrontation Clause into a constitutionally\\ncompelled rule of pretrial discovery. . . . [T]he right to\\n 140\\n\\fconfrontation is a trial right, designed to prevent improper\\nrestrictions on the types of questions that defense counsel\\nmay ask during cross-examination.” 480 U.S. at 52. We\\nfollow the Ritchie plurality, and conclude that the\\nConfrontation Clause did not require the District Court to\\ngrant Brand access to the witness’s mental health records.\\n Brand next challenges the District Court’s decision\\nto quash the subpoena as a violation of the Fifth\\nAmendment’s Due Process Clause. He concedes that\\nRitchie’s Due Process holding allowed the District Court\\nto review the mental health records in camera without\\ndisclosing them to him. See id. at 59–60 (“A defendant’s\\nright to discover exculpatory evidence does not include the\\nunsupervised authority to search through [the\\nGovernment’s] files. . . . We find that [the defendant’s]\\ninterest . . . in ensuring a fair trial can be protected fully by\\nrequiring that the [privileged] files be submitted only to\\nthe trial court for in camera review.”). Brand instead\\nargues that the District Court abused its discretion by\\nfocusing on “irrelevant facts and spurious symptoms. . . .\\nsuch as ‘hallucinations,’ ” and by “refus[ing] to consider\\nevidence of cognitive impairment and memory issues.”\\nBrand Br. 30. The record reveals, however, that the\\nDistrict Court reviewed the mental health records and\\ndetermined that they “reveal[ed] nothing that calls into\\nquestion [the witness’s] memory, perception, competence,\\nor veracity.” JA150. This hardly amounts to a refusal to\\nconsider evidence of cognitive impairment or memory\\nissues.\\n 141\\n\\f Brand also challenges the legal standard applied by\\nthe District Court, arguing that the court “focused solely\\non whether disclosure would ‘change the outcome’ of\\nBrand’s trial,” Brand Br. 29 (quoting JA148), rather than\\nconsidering “whether the ultimate verdict is one ‘worthy\\nof confidence.’ ” Id. (quoting United States v. Robinson,\\n583 F.3d 1265, 1270 (10th Cir. 2009)). Brand\\nmisleadingly quotes from the District Court’s opinion. The\\nDistrict Court considered, in accordance with Ritchie,\\n“whether there is a reasonable probability that disclosure\\nwould change the outcome” of Brand’s trial, JA148\\n(emphasis added), not whether disclosure would\\nnecessarily change the outcome. As articulated in Ritchie,\\na “ ‘reasonable probability’ is a probability sufficient to\\nundermine confidence in the outcome.” 480 U.S. at 57\\n(quoting United States v. Bagley, 473 U.S. 667, 682 (1985)\\n(Blackmun, J.)). The District Court applied the correct\\nstandard.\\n\\n2. The District Court’s Grant of the Motion in Limine\\n In granting the Government’s motion in limine, the\\nDistrict Court ruled that Brand could not “reference . . .\\n[the witness’s] bipolar disorder or the medications he takes\\nto manage it.” JA156. Yet that ruling placed no restriction\\non Brand’s ability to cross-examine the witness with\\nrespect to “his memory, competence, or truthfulness.” Id.\\nBrand argues, nevertheless, that his Sixth Amendment\\nright “to be confronted with the witnesses against him”\\nwas violated. U.S. Const. amend. VI.\\n\\n 142\\n\\f The Confrontation Clause protects a defendant’s\\nright to cross-examine a witness with respect to any\\ntestimonial statements made by that witness. United States\\nv. Berrios, 676 F.3d 118, 125–26 (3d Cir. 2012) (citing\\nCrawford v. Washington, 541 U.S. 36, 51 (2004), and\\nDavis v. Washington, 547 U.S. 813, 823–24 (2006)). But\\nthe scope of cross-examination is not unlimited, and “[a]\\ndistrict court retains ‘wide latitude insofar as the\\nConfrontation Clause is concerned to impose reasonable\\nlimits on such cross-examination based on concerns about\\n. . . harassment, prejudice, confusion of the issues, the\\nwitness’ safety, or interrogation that is repetitive or only\\nmarginally relevant.’ ” John-Baptiste, 747 F.3d at 211\\n(quoting United States v. Mussare, 405 F.3d 161, 169 (3d\\nCir. 2005)). We review limitations on cross-examination\\nfor abuse of discretion, and reverse “only when the\\nrestriction ‘is so severe as to constitute a denial of the\\ndefendant’s right to confront witnesses against him and . . .\\nis prejudicial to [his] substantial rights.’ ” Id. (alternation\\nin original) (quoting United States v. Conley, 92 F.3d 157,\\n169 (3d Cir. 1996)).\\n In United States v. Chandler, 326 F.3d 210, 219 (3d\\nCir. 2003), we analyzed whether a district court’s decision\\nto limit cross-examination with respect to a witness’s\\nmotivation for testifying violated the Confrontation\\nClause. See also Mussare, 405 F.3d at 169; John-Baptiste,\\n747 F.3d at 211–12. Consistent with Delaware v. Van\\nArsdall, 475 U.S. 673 (1986), we first concluded that “the\\nexposure of a witness’ motivation in testifying is a proper\\n 143\\n\\fand important function of the constitutionally protected\\nright of cross-examination.” Chandler, 326 F.3d at 219–\\n20 (quoting Van Arsdall, 475 U.S. at 678–79). We also\\nnoted that the Confrontation Clause does not prevent a trial\\njudge from imposing reasonable limits on cross-\\nexamination. Id. In reviewing a district judge’s imposition\\nof such limitations, we apply a two-part analysis. As we\\nhave since described, “we inquire into: ‘(1) whether the\\nlimitation significantly limited the defendant’s right to\\ninquire into a witness’s motivation for testifying; and\\n(2) whether the constraints imposed fell within the\\nreasonable limits that a district court has the authority to\\nimpose.’ ” John-Baptiste, 747 F.3d at 211–12 (quoting\\nMussare, 405 F.3d at 169).\\n The same analytical framework is appropriate when\\ndetermining whether a restriction on the cross-\\nexamination of a witness with respect to his memory and\\nperception violates the Confrontation Clause. See Davis v.\\nAlaska, 415 U.S. 308, 316 (1974); Greene v. McElroy, 360\\nU.S. 474, 496 (1959); United States v. Segal, 534 F.2d\\n578, 582 (3d Cir. 1976). Memory and perception, like\\nmotivation for testifying, are central issues affecting the\\ncredibility of any witness, and unreasonable limitations on\\nthe right to cross-examine on those subjects cannot be\\ncountenanced. We therefore ask, paraphrasing Chandler:\\n(1) whether the District Court’s decision to put the\\nwitness’s diagnosis and medications off limits\\nsignificantly impaired Brand’s right to inquire into the\\nwitness’s memory and perception; and (2) whether the\\n 144\\n\\fruling fell within the reasonable limits that the District\\nCourt has the authority to impose.\\n We conclude that the District Court did not err. As\\nan initial matter, the District Court permitted Brand to\\ncross-examine the witness about his memory and\\nperception, and limited cross-examination only with\\nrespect to the witness’s bipolar disorder and the\\nmedications he was taking to treat that condition. Brand\\nwas free to question the witness about his memory and\\nperception, and indeed did so. The restriction on asking\\nthe witness about his bipolar disorder was not a significant\\nlimitation of Brand’s right to inquire into the witness’s\\nmemory or perception. Moreover, as the District Court\\npointed out, Brand failed to show how inquiry into the\\nwitness’s bipolar disorder would be useful for\\nimpeachment purposes. See JA154.\\n\\n Given that failure, the District Court’s limits on\\ncross-examination were reasonable. The Court concluded,\\nafter reviewing the evidence submitted by Brand and the\\nwitness’s mental health records, that any mention of the\\nwitness’s bipolar disorder would “only be designed to\\nconfuse the jury or to stigmatize him unfairly because of a\\n‘mental problem’ without any countervailing probative\\nvalue.” JA155. The District Court did not abuse its\\ndiscretion in limiting Brand’s cross-examination on a topic\\nthat would be far more prejudicial than probative. See\\nTykarsky, 446 F.3d at 476–77 (“[T]he District Court acted\\n\\n\\n 145\\n\\fwell within its discretion to restrict irrelevant and\\nconfusing testimony.”).\\n All of this is not to suggest that a witness’s mental\\nhealth is always off limits. The appropriate course in any\\ngiven case must be determined from the facts and\\ncircumstances surrounding that case and the witness’s\\nparticular condition. See United States v. George, 532 F.3d\\n933, 937 (D.C. Cir. 2008) (“The days are long past when\\nany mental illness was presumed to undermine a witness’s\\ncompetence to testify. . . . [M]ental illness [is] potentially\\nrelevant in a broad[] range of circumstances . . . . [But]\\nsome indication is needed that a particular witness’s\\nmedical history throws some doubt on the witness’s\\ncompetence or credibility.”). Here, Brand failed to show,\\nthrough mental health records or otherwise, any\\nparticularized reason to doubt the credibility of the witness\\nfor medical reasons.\\n\\n Brand states that the witness provided “the only\\nevidence offered” on the intent element of his conspiracy\\nconviction and that he should therefore be entitled to\\nunrestricted cross-examination. Brand Br. 12 n.3. Yet no\\nmatter the importance of a witness to any party, a district\\ncourt may always place reasonable limits on cross-\\nexamination to avoid “harassment, prejudice, confusion of\\nthe issues, the witness’ safety, or interrogation that is\\nrepetitive or only marginally relevant.” John-Baptiste, 747\\nF.3d at 211 (citation omitted).\\n\\n\\n 146\\n\\f We conclude that the District Court did not abuse\\nits discretion in restricting the scope of Brand’s cross-\\nexamination of the cooperating witness.\\n\\n X. The Government’s Cross-Appeal\\n The jury convicted Fattah, Vederman, and Bowser\\nof bank fraud, 18 U.S.C. § 134430 (Count 19) and making\\nfalse statements to a financial institution, 18 U.S.C.\\n§ 1014 31 (Count 20). In response to post-trial motions, the\\nDistrict Court granted a judgment of acquittal on both\\ncounts under Fed. R. Crim. P. 29, concluding that the\\n\\n30\\n “Whoever knowingly executes, or attempts to execute,\\na scheme or artifice . . . to defraud a financial institution\\n. . . shall be fined not more than $1,000,000 or imprisoned\\nnot more than 30 years, or both.” The definition of\\n“financial institution” for purposes of § 1344 is set forth at\\n18 U.S.C. § 20, and includes “a credit union with accounts\\ninsured by the National Credit Union Share Insurance\\nFund” and “a mortgage lending business (as defined in\\nsection 27 of this Title).” 18 U.S.C. §§ 20(2), (10).\\n31\\n “Whoever knowingly makes any false statement or\\nreport, or willfully overvalues any land, property or\\nsecurity, for the purpose of influencing in any way the\\naction of . . . a Federal credit union . . . any institution the\\naccounts of which are insured by . . . the National Credit\\nUnion Administration Board . . . or a mortgage lending\\nbusiness . . . shall be fined not more than $1,000,000 or\\nimprisoned not more than 30 years, or both.”\\n 147\\n\\fevidence was insufficient to establish that the Credit\\nUnion Mortgage Association (CUMA), the entity to whom\\nFattah, Vederman, and Bowser made the false statements,\\nis a “financial institution,” or, more specifically, a\\n“mortgage lending business” as defined in 18 U.S.C. § 27.\\nThe Government claims that, viewing the evidence in the\\nlight most favorable to it, the District Court erred and that\\nCUMA is, indeed, a “mortgage lending business.” We\\nagree. Because the evidence is sufficient to support the\\njury’s verdict, we will remand so Fattah and Vederman\\nmay be resentenced on these charges.32\\n\\n A. CUMA is a Mortgage Lending Business\\n In reviewing the District Court’s post-verdict\\njudgment of acquittal under Rule 29 of the Federal Rules\\nof Civil Procedure, we consider whether the evidence,\\nwhen viewed in a light most favorable to the government,\\nsupports the jury’s verdict. United States v. Dixon, 658\\nF.2d 181, 188 (3d Cir. 1981). Our standard of review is the\\nsame as that applied by the District Court, and we must\\nuphold the jury’s verdict unless no reasonable juror could\\naccept the evidence as sufficient to support the defendant’s\\nguilt beyond a reasonable doubt. United States v.\\nColeman, 811 F.2d 804, 807 (3d Cir. 1987).\\n\\n32\\n Because the Government did not file an appeal as to\\nBowser, the cross-appeal is limited to Fattah and\\nVederman. The judgment of acquittal as to Bowser is\\ntherefore unaffected by our ruling today.\\n 148\\n\\f Initially, the grand jury’s indictment alleged that\\nCUMA is a financial institution because it is federally\\ninsured. JA302–03. At trial, however, the jury was\\ninstructed that CUMA could qualify as a financial\\ninstitution either because it is federally insured or because\\nit is a “mortgage lending business.” See JA111, 401–02. A\\n“mortgage lending business” is “an organization which\\nfinances or refinances any debt secured by an interest in\\nreal estate, including private mortgage companies and any\\nsubsidiaries of such organizations, and whose activities\\naffect interstate or foreign commerce.” 18 U.S.C. § 27.\\n\\n At trial, CUMA’s president and CEO, Eddie Scott\\nToler, testified that CUMA is not federally insured.\\nJA4235. The Government therefore attempted to prove\\nthat CUMA is a “mortgage lending business” by\\npresenting evidence that CUMA funds mortgages and then\\nsells them in a secondary market.\\n\\n Toler also testified that CUMA is a “credit union\\nservice organization”—a for-profit company owned by 48\\ncredit unions, which serves small credit unions that do not\\nhave the infrastructure or in-house expertise to handle\\nmortgage loans themselves. JA4235. According to Toler,\\n“[CUMA] exclusively provide[s] First Trust Residential\\nMortgage loaning [sic] services, all the way from the\\norigination of the mortgage loan through processing,\\nunderwriting, closing and access to the secondary market\\nwhere—and we’re selling the mortgage loan on the\\nsecondary market.” JA4236–37. In jurisdictions in which\\n\\n 149\\n\\fCUMA is licensed, 33 CUMA holds the mortgage for a\\nlimited period, generally from two to thirty days, and then\\nsells the mortgage either to a partner credit union or on the\\nsecondary market. JA4240.\\n\\n The District Court concluded that CUMA is not a\\n“mortgage lending business” because “[t]he record is\\ndevoid of any evidence that CUMA finances or refinances\\nany debt.” JA113. Concluding that CUMA “simply is a\\nloan processor for various credit unions which do the\\nfinancing or refinancing,” id., the District Court ruled that\\nCUMA’s “activity does not constitute the financing or\\nrefinancing of any debt. CUMA is not the mortgagee. It is\\nmerely selling the debt instrument to a third party.” JA114.\\n We cannot agree with the District Court’s view of\\nthe evidence. Toler testified that in “Maryland, D.C., and\\nVirginia . . . all of the loans are closed in the name of\\nCUMA.” JA4238–39. As Toler described it, CUMA\\nborrows on a line of credit to fund the loan, and when the\\nloan is sold, CUMA pays off its line of credit. JA4239–40.\\nSo contrary to the District Court’s assessment, the\\nevidence, viewed in a light most favorable to the\\nGovernment, shows that CUMA is indeed the\\nmortgagee—at least during the time from closing until the\\nloan is sold to a partner credit union or on the secondary\\nmarket. The fact that CUMA funds the closing and then\\n\\n33\\n CUMA is licensed in Maryland, Washington, D.C., and\\nVirginia. JA4238.\\n 150\\n\\fholds the mortgage, even for a brief time, is sufficient to\\nsupport a conclusion that CUMA is “an organization\\nwhich finances or refinances any debt secured by an\\ninterest in real estate.” 18 U.S.C. § 27.\\n\\n Fattah and Vederman attempt to refute the argument\\nthat CUMA engages in financing mortgages by focusing\\non Toler’s testimony that CUMA “doesn’t actually have\\nany money to fund these mortgage loans.” JA4239; see\\nFattah Reply Br. 38, Vederman Reply Br. 36. But Toler\\ntestified that CUMA employs a credit line to borrow the\\nfunds necessary to close on mortgages. See JA4239. That\\nCUMA incurs debt to finance mortgages hardly\\nundermines a conclusion that CUMA finances mortgages.\\nIndeed, it is the very nature of modern banking that\\nfinancial institutions do not hold cash reserves equal to the\\nfull amount of their liabilities. See, e.g., Timothy C.\\nHarker, Bailment Ailment: An Analysis of the Legal Status\\nof Ordinary Demand Deposits in the Shadow of the\\nFinancial Crisis of 2008, 19 Fordham J. Corp. & Fin. L.\\n543, 561 (2014) (“[F]ractional reserve banking . . . is the\\nde facto standard for all modern banks.”).\\n\\n Vederman also argues that, even if CUMA acts as a\\nmortgage lending business in some transactions, it was not\\nacting as a mortgage lending business in this transaction.\\nVederman points to Toler’s testimony that, in a state in\\nwhich CUMA is not licensed, the mortgage is closed in the\\nname of a credit union. In such cases, the credit union, and\\nnot CUMA, owns the mortgage for the short period before\\n\\n 151\\n\\fthe loan is sold on the secondary market. JA4241. CUMA\\nis not licensed in the Commonwealth of Pennsylvania. See\\nid. Thus, according to Vederman, CUMA was acting in its\\ncapacity as a mortgage servicing company for Fattah’s\\nvacation home purchase and did not—and could not—\\nfinance Fattah’s mortgage. That would mean that CUMA\\ncould not have been a victim of a crime against a financial\\ninstitution in this instance: “When an entity is not\\nfunctioning as a mortgage lender, the ‘pertinent federal\\ninterest’ behind the statutes is not implicated.” Vederman\\nReply Br. 38 (citation omitted).\\n\\n The Government responds that neither of the\\nstatutes of conviction requires that the fraud or false\\nstatement occur in connection with the same transaction\\nthat places the entity within the definition of “financial\\ninstitution.” Gov’t Fourth Step Br. 4. We agree with the\\nGovernment.\\n\\n Both § 1344 and § 1014 protect entities that fall\\nwithin the definition of “financial institution” and are\\notherwise quite broad in their application. See Loughrin v.\\nUnited States, 134 S. Ct. 2384, 2389 (2014) (interpreting\\n§ 1344 as not requiring specific intent to defraud a bank);\\nUnited States v. Boren, 278 F.3d 911, 914 (9th Cir. 2002)\\n(“[Section 1014’s] reach is not limited to false statements\\nmade with regard to loans, but extends to any application,\\ncommitment or other specified transaction.”). Neither\\nstatute is expressly limited in the manner that Vederman\\nsuggests. Williams v. United States, 458 U.S. 279, 284\\n\\n 152\\n\\f(1982) (“To obtain a conviction under § 1014, the\\nGovernment must establish two propositions: it must\\ndemonstrate (1) that the defendant made a ‘false statement\\nor report,’ . . . and (2) that he did so ‘for the purpose of\\ninfluencing in any way the action of [a described financial\\ninstitution] upon any application, advance, . . .\\ncommitment, or loan.’ ”); United States v. Leahy, 445 F.3d\\n634, 646 (3d Cir. 2006) (“The purpose of the bank fraud\\nstatute is to protect the ‘financial integrity of [banking]\\ninstitutions.’ ”) (citing S. Rep. No. 98-225, at 377 (1983),\\nas reprinted in 1984 U.S.C.C.A.N. 3517), abrogated on\\nother grounds by Loughrin, 134 S. Ct. at 2389.\\n In support of his position, Vederman relies on\\nUnited States v. Devoll, 39 F.3d 575 (5th Cir. 1994), in\\nwhich the Fifth Circuit concluded that § 1014 (false\\nstatements to a financial institution) is not intended to\\ncapture fraud unrelated to an entity’s lending activities,\\nand therefore held that it “applies only to actions involving\\nlending transactions.” Id. at 580. The Fifth Circuit stated:\\n [W]e are not persuaded that the statute\\n imposes liability whenever a defendant’s\\n false statement was intended to interfere with\\n any activity of a financial institution; such a\\n broad interpretation of section 1014\\n presumably would encompass fraud or false\\n representations having nothing to do with\\n financial transactions, such as fraud in an\\n employment contract or, for example, in a\\n\\n 153\\n\\f contract to provide goods or services for\\n custodial care, premises repair, or renovation.\\nId.\\n\\n Yet a majority of circuits, including our own, have\\ndeclined to follow Devoll’s suggestion that § 1014 is\\nrestricted to lending transactions. As the Ninth Circuit has\\nheld, “we join at least six of our sister circuits—the First,\\nThird, Fourth, Sixth, Seventh, and Tenth—in holding that\\n18 U.S.C. § 1014 is not limited to lending transactions,\\nand reject the minority rule to the contrary.” Boren, 278\\nF.3d at 915. And even if we were to adopt Devoll’s narrow\\nconstruction of § 1014 to lending transactions, that would\\nnot resolve the more specific question of whether the\\ndefrauded entity must be defined as a “mortgage lending\\nbusiness” by virtue of the specific transaction in which the\\nfalse statements arose.\\n Recently, the Eighth Circuit addressed precisely\\nthis issue. In United States v. Springer, 866 F.3d 949 (8th\\nCir. 2017), that Court considered the defendant’s appeal\\nfrom the district court’s denial of a Rule 29 motion on\\ngrounds that GMAC, the entity defrauded, was not a\\n“financial institution.” The Court upheld the district\\ncourt’s determination that the evidence was sufficient to\\nestablish that GMAC is in the mortgage lending business\\nbecause there was testimony that “it had made hundreds or\\nthousands of loans secured by mortgages in 2010 and 2011\\nin states all across the country,” which established that its\\nactivities affect interstate commerce. Id. at 953. It was not\\n 154\\n\\fdeterminative that GMAC did not own the specific loan at\\nissue in the case: “we discern no requirement in the\\ndefinition of ‘mortgage lending business’ that the business\\nown the particular loan in question; it need only finance or\\nrefinance any debt secured by an interest in real estate, or,\\nin other words, be in the interstate mortgage lending\\nbusiness in general.” Id.\\n\\n In our view, the Eighth Circuit’s analysis is correct.\\nWe therefore adopt that Court’s reasoning in Springer and\\nconclude that it is of no moment that CUMA did not\\nfinance the mortgage at issue in Fattah’s case. CUMA is a\\n“mortgage lending business,” and that alone suffices to\\nsupport the convictions under §§ 1014 and 1344.\\n\\n B. Sufficiency of the Evidence\\n Finally, Vederman argues that, even if CUMA is a\\nfinancial institution, the judgment of acquittal should\\nstand because the Government did not put forth any\\nevidence that he made a false representation to CUMA.34\\nSpecifically, Vederman argues that the title to the Porsche\\nwas actually changed to his name, making it a “true sale”\\nas a matter of law, without regard to whether Fattah’s wife\\n\\n34\\n Although Vederman presented this argument in his Rule\\n29 motion, the District Court did not need to reach it in the\\ncontext of Counts 19 and 20 because the Court granted the\\nmotion on the ground that CUMA is not a financial\\ninstitution. The District Court rejected the argument as to\\nCounts 16, 17, and 18. See JA100–02.\\n 155\\n\\fcontinued to retain possession. See United States v.\\nCastro, 704 F.3d 125, 139 (3d Cir. 2013) (holding in\\nanother context that “the government must be able to show\\nthat [the defendant] made a statement to government\\nagents that was untrue, and the government cannot satisfy\\nthat burden by showing that the defendant intended to\\ndeceive, if in fact he told the literal truth”); see also 75 Pa.\\nCons. Stat. § 102 (defining “owner” as “[a] person, other\\nthan a lienholder, having the property right in or title to a\\nvehicle”).\\n\\n The Government responds that, regardless of\\nwhether it is legally possible for one person to hold a title\\nwhile a different person possesses the vehicle, the jury was\\npermitted to consider all the circumstances in deciding\\nwhether the Porsche sale was a sham. We agree.\\n\\n First, as the District Court observed, it was unclear\\nas to whether the title had been properly executed under\\nPennsylvania law. For instance, Fattah’s wife never\\nappeared before a notary. 35 JA101. In addition, title 75,\\nsection 1111(a) of the Pennsylvania Consolidated Statutes\\nrequires that, “[i]n the event of the sale or transfer of the\\nownership of a vehicle within this Commonwealth, the\\nowner shall . . . deliver the certificate to the transferee at\\n\\n35\\n Vederman argues that it is of no significance that the\\nparties did not appear before a notary as the statute\\nrequires, but he offers cases only from states other than\\nPennsylvania to support this proposition.\\n 156\\n\\fthe time of the delivery of the vehicle.” And, the transferee\\nmust, within twenty days of the assignment of the vehicle,\\napply for a new title. See 75 Pa. Cons. Stat. § 1111(b).\\nNeither of these requirements was fulfilled. Finally,\\nVederman never registered the Porsche in his name with\\nthe Department of Motor Vehicles. See id.; JA4254.\\n Second, and more importantly, even if the title had\\nbeen properly transferred to Vederman, the title provisions\\nof the Pennsylvania Motor Vehicle Code “were [not]\\ndesigned to establish conclusively the ownership of an\\nautomobile.” Weigelt v. Factors Credit Corp., 101 A.2d\\n404, 404 (Pa. Super. Ct. 1953). Indeed, “[t]he purpose of\\na certificate of title is not to conclusively establish\\nownership in a motor vehicle, but rather to establish the\\nperson entitled to possession.” Speck Cadillac-Olds, Inc.\\nv. Goodman, 95 A.2d 191, 193 (Pa. 1953). Thus, a title\\nprovides evidence of ownership; it is not dispositive of the\\nissue. Wasilko v. Home Mut. Cas. Co., 232 A.2d 60, 61\\n(Pa. Super. Ct. 1967).\\n Vederman’s argument that the title in his name\\nconstitutes conclusive evidence of ownership rests upon\\nan erroneous conclusion that the jury was prohibited from\\nconsidering all the circumstances of the transfer. As the\\nDistrict Court observed, though, Pennsylvania’s\\nCommonwealth Court has held that “[w]hether a\\ntransferor has transferred ownership of a motor vehicle to\\na transferee is a factual determination to be made by the\\ncourt below.” Dep’t. of Transp. v. Walker, 584 A.2d 1080,\\n\\n 157\\n\\f1082 (Pa. Commw. Ct. 1990). Thus, the signed certificate\\nof title was appropriately treated as one piece of evidence\\nfor the jury to consider in assessing the validity of the\\nvehicle transfer. Considered in the light most favorable to\\nthe Government, the totality of the evidence is sufficient\\nto support the jury’s conclusion that the Porsche sale was\\na sham.\\n\\n XI. Prejudicial Spillover\\n Finally, Fattah, Vederman, Nicholas, and Brand\\neach contend that their convictions on various counts\\nresulted from prejudicial spillover. We are not persuaded.\\n We exercise plenary review over a district court’s\\ndenial of a claim of prejudicial spillover, United States v.\\nLee, 612 F.3d 170, 178–79 (3d Cir. 2010), and we apply a\\ntwo-step test when reviewing such a claim. United States\\nv. Wright, 665 F.3d 560, 575 (3d Cir. 2002). First, a court\\nmust consider “whether the jury heard evidence that would\\nhave been inadmissible at a trial limited to the remaining\\nvalid count[s].” Id. (quoting United States v. Cross, 308\\nF.3d 308, 317 (3d Cir. 2002)). The second step requires\\nthat we “ask whether that evidence (the ‘spillover\\nevidence’) was prejudicial.” Id. We consider four factors:\\n“whether (1) the charges are intertwined with each other;\\n(2) the evidence for the remaining counts is sufficiently\\ndistinct to support the verdict on these counts; (3) the\\nelimination of the invalid count [will] significantly\\nchange[] the strategy of the trial; and (4) the prosecution\\nused language of the sort to arouse a jury.” Id. (quoting\\n 158\\n\\fUnited States v. Murphy, 323 F.3d 102, 118 (3d Cir.\\n2003)); see also United States v. Pelullo (Pellulo II), 14\\nF.3d 881, 898–99 (3d. Cir. 1994). These four factors are\\nconsidered in a light “somewhat favorable to the\\ndefendant.” Wright, 665 F.3d at 575 (quoting Murphy, 323\\nF.3d at 122); see also Gov’t Br. 198 (same).\\n\\n A. Fattah’s Claim of Prejudicial Spillover\\n Fattah argues that he suffered prejudicial spillover\\non the remaining counts of conviction in light of (1)\\nevidence pertinent to the alleged Vederman bribery\\nschemes that is now arguably inadmissible under\\nMcDonnell; and (2) “the government’s flawed RICO\\nconspiracy theory.” Fattah Br. 50, 64. Fattah’s argument\\nis undercut substantially because of our determination that\\nMcDonnell requires a new trial for Counts 16, 17, 22, and\\n23 and our decision to affirm the RICO conspiracy\\nconviction. The only possible spillover left to consider is\\nthe evidence pertaining to Fattah’s arranging a meeting\\nbetween Vederman and the U.S. Trade Representative,\\nRon Kirk, which in light of McDonnell is now arguably\\ninadmissible.36\\n\\n The evidence of the Kirk meeting admitted during\\nthis five-week trial was limited. Although this evidence\\n\\n36\\n Nothing in this opinion is intended to foreclose the\\npossibility that evidence of the Kirk meeting may be\\nadmissible on retrial for some purpose other than as proof\\nof an official act.\\n 159\\n\\fwas part of the Government’s proof as to both the RICO\\nand the bribery related charges, there is more than\\nsufficient—and distinct —evidence to support Fattah’s\\nconviction on all the other counts. In our view, eliminating\\nany evidence of the Kirk meeting would not have altered\\nthe strategy of the trial, nor should it significantly change\\nthe strategy for any new trial that may be held. Because\\nFattah has not pointed us to any argument by the\\nprosecution relating to this meeting that could have\\ninflamed the jury, we conclude that Fattah’s prejudicial\\nspillover claim fails. Like the District Court, we presume\\nthat the jury followed the Court’s instructions to consider\\nand weigh separately the evidence on each count as to each\\ndefendant and not to be swayed by evidence pertaining to\\nother defendants. 37\\n\\n B. Vederman’s Assertion of Prejudicial Spillover\\n Because the District Court acquitted Vederman of\\nthe RICO charge, Vederman argues that he was “severely\\nprejudiced by the presentation to the jury of a legally\\nflawed racketeering conspiracy charge,” and as a\\nconsequence his bribery and money laundering\\n\\n37\\n We likewise reject Brand’s prejudicial spillover\\narguments. See Brand Br. 6 (“Brand adopts the significant\\nissue advanced by his co-appellant pursuant to Fed. R.\\nApp. P. 28(i) that improper jury instructions and the\\nresulting spillover of related improperly admitted\\nevidence and argument unfairly prejudiced Brand.”).\\n 160\\n\\fconvictions should be overturned. Vederman Br. 46. In\\nresponse to the Government’s appeal of the District\\nCourt’s Rule 29 acquittal on Counts 19–20 involving\\nCUMA, Vederman asserts that these two counts also were\\naffected by spillover evidence because the Government’s\\ntheory tied the bribery charges to the actions taken to\\ndefraud CUMA. In that we are vacating Vederman’s\\nconvictions of Counts 16–18 and 22–23 based on\\nMcDonnell and remanding for further proceedings, we\\nneed address only Vederman’s argument of prejudicial\\nspillover as it relates to the charges involving CUMA in\\nCounts 19–20, charges that we will reinstate.\\n The District Court’s acquittal of Vederman on the\\nRICO count establishes that step one of the Wright\\nspillover test has been met. “[T]he jury heard evidence that\\nwould have been inadmissible at a trial limited” to the\\nbribery and CUMA-related counts. Wright, 665 F.3d at\\n575 (quoting Cross, 308 F.3d at 317).\\n\\n Wright’s second step requires “ask[ing] whether\\nthat evidence (the ‘spillover evidence’) was prejudicial.”\\nId. Vederman submits that the RICO, bribery, and CUMA-\\nrelated charges were intertwined “in that the acts relating\\nto the alleged bribery scheme were also charged as\\n‘predicates’ under RICO.” Vederman Br. 49. We disagree.\\n\\n To be sure, the RICO, bribery, and CUMA Counts\\nare related to one another. But in this instance, mere\\nrelatedness is not enough to demonstrate the foundation\\nnecessary for spillover. This is so because the bribery\\n 161\\n\\fcharges were a predicate to the RICO charge. In other\\nwords, the jury had to determine if Vederman was guilty\\nof bribery, and the jury then used that “predicate” to\\nconsider whether he was also guilty of the RICO\\nconspiracy. Thus, the necessarily tiered structure of the\\nquestions presented to the jury refute Vederman’s\\nargument that the counts were intertwined.\\n\\n That the bribery charges were predicates for the\\nRICO conspiracy further demonstrates that the “evidence\\nfor the different counts was sufficiently distinct to support\\nthe verdict on other separate counts.” Pelullo II, 14 F.3d at\\n898. Regardless of the evidence pertaining solely to the\\nRICO conviction, the evidence supporting both the bribery\\ncharges and the charges involving CUMA in Counts 19–\\n20 would have remained the same.\\n\\n The next factor we address is “whether the\\nelimination of the count on which the defendant was\\ninvalidly convicted would have significantly changed the\\n[defendant’s] strategy of the trial.” Id. As Vederman\\nargues, “the RICO charge interfered with Vederman’s\\ncentral defense to the bribery charge—that his gestures\\ntoward Fattah ‘were motivated purely by friendship.’ ”\\nVederman Reply Br. 28 (citing Gov’t Br. 200). In other\\nwords, the “RICO count made it dangerous to unduly\\nemphasize [Vederman’s] close friendship” with Fattah. Id.\\nFrom Vederman’s perspective, “a bribery-only trial would\\nhave reduced this danger and allowed a freer presentation\\nof the defense.” Id.\\n\\n 162\\n\\f It is quite likely that Vederman’s claim of friendship\\nwould have been less risky as a litigation strategy if he had\\nnot been facing a RICO charge. But Vederman\\nnevertheless chose to take that risk and fully presented his\\nfriendship argument to the jury. Moreover, while\\nVederman’s reliance on friendship might have helped him\\ndefend against the bribery charges, that friendship would\\nnot have altered the evidence pertaining to Counts 19–20\\ninvolving CUMA. Whether done for friendship or some\\nother reason, submitting fraudulent information to a\\nfinancial institution is unlawful.\\n\\n Finally, we “examine the charges, the language that\\nthe government used, and the evidence introduced during\\nthe trial to see whether they are ‘of the sort to arouse a\\njury.’ ” Pelullo II, 14 F.3d at 899 (quoting United States v.\\nIvic, 700 F.2d 51, 65 (2d Cir. 1983)). Vederman points out\\nthat Fattah was presented as “a backslapping, corrupt party\\nboss,” with “predictable spillover to his friend and\\nassociate, Vederman.” Vederman Br. 50 (quoting United\\nStates v. Murphy, 323 F.3d 102, 118 (3d Cir. 2003)). But\\nthis description was of Fattah, not Vederman. Vederman\\ncites other examples of prejudicial, pejorative language in\\nthe Government’s closing arguments. At one point, the\\nGovernment referred to “conspirators engaged in what can\\nonly be described as a white collar crime spree from\\nPhiladelphia all the way to Washington, D.C.” and\\npromised “to untangle the webs of lies and deception that\\nthese conspirators spun.” Vederman Br. 51 (quoting\\nJA5295, 5297). Whatever rhetorical flair these words\\n 163\\n\\fcontained, they did not obscure the evidence which\\nindependently supported the convictions for bank fraud at\\nCount 19 and for making false statements to CUMA at\\nCount 20. Accordingly, because we presume that the jury\\nfollowed the District Court’s instruction to consider and to\\nweigh separately the evidence on each count and as to each\\ndefendant, and because the evidence supporting the\\nCUMA-related charges in Counts 19–20 is sufficiently\\ndistinct from the RICO conspiracy, we conclude that\\nVederman’s spillover argument is unavailing.38\\n\\n XII. Conclusion\\n We will vacate the convictions of Chaka Fattah, Sr.\\nand Herbert Vederman as to Counts 16, 17, 18, 22, and 23.\\n\\n38\\n Nicholas adopted “pertinent portions” of the prejudicial\\nspillover arguments advanced by Vederman and Fattah.\\nNicholas Br. 65. Her spillover claim has no more merit\\nthan theirs. Nicholas’s involvement in the RICO\\nconspiracy was distinct from the bribery charges, which\\ndid not unfairly influence the other counts. As to\\nNicholas’s assertion that the NOAA charges did not\\nbelong in the indictment and should have been tried\\nseparately, we fail to see how this relates to a claim of\\nprejudicial spillover. To the extent it challenges the\\nDistrict Court’s denial of Nicholas’s motion for a\\nseverance, Nicholas has failed to provide legal support for\\nsuch a contention. See Fed. R. App. P. 28(a)(8)(A); United\\nStates v. Irizarry, 341 F.3d 273, 305 (3d Cir. 2003).\\n 164\\n\\fFattah and Vederman may be retried on these counts\\nbefore a properly instructed jury. We will also reverse the\\nDistrict Court’s judgment of acquittal on Counts 19 and\\n20. The convictions of Chaka Fattah, Sr. and Herbert\\nVederman will be reinstated, and the case will be\\nremanded for sentencing on those counts. In all other\\nrespects, the judgments of the District Court will be\\naffirmed.\\n\\n\\n\\n\\n 165\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":63,"cells":{"id":{"kind":"number","value":8443856,"string":"8,443,856"},"name":{"kind":"string","value":"United States v. Karen NICHOLAS"},"name_abbreviation":{"kind":"string","value":"United States v. Nicholas"},"decision_date":{"kind":"string","value":"2019-01-16"},"docket_number":{"kind":"string","value":"No. 16-4410"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Smith\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415283/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"SMITH"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443856/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Karen NICHOLAS\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-16\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Karen NICHOLAS\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-16\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":64,"cells":{"id":{"kind":"number","value":4582573,"string":"4,582,573"},"name":{"kind":"string","value":"UNITED STATES of America, Appellant v. Raymont WRIGHT"},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-17"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Shwartz, Nygaard\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887874/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9887875/\", \"author_raw\": \"\"}, {\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014. 1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\\n\\nNo. 17-1972, United States of America v. Raymont Wright\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent. 1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm. 2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\nthird turn, and if it did, whether the court should use that\\npower. 3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting, 4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case. 5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin 6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\n\\n\\nprosecution of law violators is part of the implementation of\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\npower of the prosecutor intersect. Drawing from factors set\\nout in State v. Abbati, 7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.” 8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction. 9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts. 10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\nnecessarily result to our Courts of justice from the nature of\\ntheir institution.” 11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority. 12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc., 13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.” 14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\ncannot be inhibited by any rule or act of Congress. As we\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,” 15 and “it is not always possible to\\ncategorize inherent power.” 16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,” 17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.” 18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’” 19 In other words, powers\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority” 20 and “the core\\nArticle III power.” 21 It is nothing less than our ability to\\ndecide a case over which we have jurisdiction, without\\ninterference by Congress or the Executive. 22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’” 23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.” 24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers. 25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers. 26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.” 27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.” 28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.” 29 At times,\\nwe too have been guilty of adding to the confusion. 30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers. 31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution. 32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.” 33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.” 34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules. 35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’” 36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision. 37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure. 38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts 39 and to\\nreview attorney-client fee arrangements. 40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation. 41 They can, for example, seal and unseal records, 42\\nreassign a case to a different judge on remand, 43 or disqualify\\nan attorney on ethical grounds. 44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.” 45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments. 46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function. 47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution. 48 It is incidental and\\nnecessary to the fair and efficient operation of the courts. 49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.” 50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother. 52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility. 53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.” 54 The Government’s authority\\nnot to prosecute a case is clear as well. 55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation. 56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.” 57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”). 58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it. 59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.” 60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.” 61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so 62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause, 63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power. 64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue. 65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power. 66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position. 67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials. 68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct. 69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.” 70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.” 71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.” 72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction. 73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial. 74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials. 75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised. 76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati, 77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n • the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n • the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n • the probability that any subsequent trial will be\\n much different from the previous ones;\\n • the relative strength of the party’s case, as\\n determined by the trial court;\\n • the conduct of counsel during the previous\\n trials. 78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice. 79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship. 80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver. 81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4359826/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"SHWARTZ"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"SHWARTZ"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":5,"string":"5"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":3,"string":"3"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582573/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Appellant v. Raymont WRIGHT\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-17\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014. 1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Appellant v. Raymont WRIGHT\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-17\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014. 1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":65,"cells":{"id":{"kind":"number","value":4582984,"string":"4,582,984"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\\n\\nNo. 17-1972, United States of America v. Raymont Wright\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent. 1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm. 2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\nthird turn, and if it did, whether the court should use that\\npower. 3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting, 4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case. 5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin 6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\n\\n\\nprosecution of law violators is part of the implementation of\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\npower of the prosecutor intersect. Drawing from factors set\\nout in State v. Abbati, 7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.” 8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction. 9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts. 10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\nnecessarily result to our Courts of justice from the nature of\\ntheir institution.” 11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority. 12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc., 13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.” 14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\ncannot be inhibited by any rule or act of Congress. As we\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,” 15 and “it is not always possible to\\ncategorize inherent power.” 16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,” 17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.” 18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’” 19 In other words, powers\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority” 20 and “the core\\nArticle III power.” 21 It is nothing less than our ability to\\ndecide a case over which we have jurisdiction, without\\ninterference by Congress or the Executive. 22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’” 23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.” 24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers. 25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers. 26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.” 27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.” 28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.” 29 At times,\\nwe too have been guilty of adding to the confusion. 30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers. 31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution. 32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.” 33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.” 34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules. 35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’” 36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision. 37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure. 38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts 39 and to\\nreview attorney-client fee arrangements. 40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation. 41 They can, for example, seal and unseal records, 42\\nreassign a case to a different judge on remand, 43 or disqualify\\nan attorney on ethical grounds. 44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.” 45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments. 46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function. 47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution. 48 It is incidental and\\nnecessary to the fair and efficient operation of the courts. 49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.” 50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother. 52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility. 53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.” 54 The Government’s authority\\nnot to prosecute a case is clear as well. 55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation. 56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.” 57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”). 58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it. 59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.” 60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.” 61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so 62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause, 63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power. 64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue. 65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power. 66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position. 67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials. 68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct. 69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.” 70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.” 71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.” 72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction. 73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial. 74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials. 75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised. 76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati, 77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n • the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n • the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n • the probability that any subsequent trial will be\\n much different from the previous ones;\\n • the relative strength of the party’s case, as\\n determined by the trial court;\\n • the conduct of counsel during the previous\\n trials. 78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice. 79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship. 80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver. 81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360237/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}, {\"author\": \"McKEE, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"McKEE, Circuit Judge, concurring in the judgment.\\n\\n As I shall explain, I am sympathetic to what the District\\nCourt was trying to do in this case and I think I understand why\\nthe court acted as it did. Moreover, I agree with Judge Nygaard\\ninsofar as he posits in dissent that a District Court can step in\\nat some point and bar a retrial without infringing on the\\nseparation of powers. Nevertheless, despite my belief that the\\nseparation of powers doctrine is not necessarily violated by a\\ntrial court barring a retrial after successive mistrials, and\\ndespite my belief that the District Court was trying to act in a\\nmanner that would assure a measure of justice for Wright, I\\nconcur in the judgment reversing the District Court. I simply\\ndo not believe that the current state of the law supports the\\nDistrict Court’s action in the absence of prosecutorial\\nmisconduct, bad faith, or more than two unsuccessful trials.\\nSince the record is clear that the District Court found neither\\nprosecutorial misconduct nor bad faith, I concur in the\\njudgment reversing the court’s order but feel compelled to\\nwrite separately to explain why.\\n I.\\n At the outset, it is important to note that I do not believe\\nthat a trial court lacks the power to, at some point, call a halt to\\nsuccessive prosecutions following deadlocked juries, and I do\\nnot read Judge Shwartz’s opinion as standing for that principle.\\nThe Government even conceded at oral argument that there\\ncould come a point where successive prosecutions become so\\nonerous and burdensome that additional trials rise to the level\\nof a Due Process violation which a trial court is clearly\\nempowered to prevent. Moreover, in Barkus v. Illinois, 1 the\\nSupreme Court noted that there “may” come a point where\\nmultiple prosecutions become so harassing that they violate the\\nDue Process Clause. 2\\n\\n Here the evidence in both trials consisted solely of\\npolice testimony. According to the officers’ testimony, some\\nresidents of the community witnessed crucial parts of Wright’s\\nencounter with the police, but they did not testify. Similarly,\\nWright did not testify on his own behalf, nor did the defense\\nput on a case. His theory was that he had no way of knowing\\n\\n1\\n 359 U.S. 121 (1959).\\n2\\n Id. at 127.\\n 1\\n\\nthat the men in plain clothes and unmarked cars who began\\npursuing him were police; he panicked, sped away, and\\ncrashed; and police subsequently planted the gun at the scene.\\nWright also asserted that the officers chose not to test the gun\\nfor DNA or fingerprints because they knew the results would\\ncontradict their story. In an effort to counter Wright’s\\nargument from the first trial that police decided not to test the\\ngun for fingerprints and DNA in order to hide their\\nmalfeasance, the Government called experts at the second trial\\n“who testified about the difficulty of retrieving DNA and\\nfingerprint evidence from firearms.” 3\\n\\n Nevertheless, the Government’s case depended entirely\\non the testimony of police officers who had worked together\\nfor many years and/or knew one another. Over the span of ten\\nmonths, the District Court twice listened to the police\\ntestimony during the trials. That testimony was at times\\ncontradictory and at other times strained credulity.\\n\\n At the first trial, Detective Fallert, who first noticed\\nWright speeding, testified that Wright was travelling at 90\\nmph, but he did not note that in his police paperwork nor did\\nhe note it at the pretrial hearing. His contemporaneously\\nprepared investigative report also did not claim that Wright\\nwas initially speeding. Detective Henson, who took over the\\nchase, testified that he saw Wright holding a handgun, but\\nconceded that he had no way of knowing whether Wright knew\\nhe was a police officer when the pursuit began. Lastly,\\nDetective Baker testified similarly to Henson, yet guessed that\\nWright had been going at a speed of 60 mph and accelerated.\\nThis is a very substantial discrepancy, especially for seasoned\\npolice officers who can be expected to have some expertise and\\nexperience in estimating the speed of an automobile.\\n\\n In the second trial, the Government called the same\\nwitnesses, with the exception of Detective Fallert. Notably,\\nthis time Detective Henson testified he actually did not see\\nWright speeding. Two different juries found themselves\\ndeadlocked—unable to convict or acquit.\\n II.\\n The majority opinion suggests that the District Court’s\\n\\n3\\n Appellant Br. at 11.\\n 2\\n\\ndecision to dismiss the indictment with prejudice\\nimpermissibly infringed upon the jury’s role. Judge Shwartz\\nstates: “[t]he District Court nonetheless applied its own\\npredictions about what another jury may do when presented\\nwith the same evidence,” and concluded that was “an improper\\nexercise of a court’s supervisory power.” 4 However, it is\\ndifficult to know whether the District Court ruled as it did\\nbased upon a belief that a third jury presented with the same\\nevidence would be unable to reach a verdict or whether it\\nsimply shared the doubts that some of the jurors obviously had\\nabout the veracity of police officers’ testimony.\\n\\n In any event, either scenario poses exactly the same\\nissue about a court overstepping its bounds and infringing on\\nthe role of a jury as well as prosecutorial discretion. As I stated\\nat the beginning, to the extent that a trial judge can intervene\\nand dismiss an indictment, I am skeptical that this record\\nsupports such an assertion of judicial authority. Nevertheless,\\nthere is more support for the judge’s actions here than our\\nreversal suggests.\\n\\n It is not a novel proposition that a trial judge must\\n“ensure that any and all . . . evidence is not only relevant, but\\nalso reliable.” 5 “The trial judge’s role is to preside over the\\ntrial; passively if possible but aggressively when indicated.” 6\\nThus, the law allows for trial courts to channel the jury’s\\njudgment in certain circumstances. Here, the court’s decision\\nwould prevent another jury from hearing the same evidence\\nthat has failed to convict Wright on two prior occasions.\\n\\n There are situations in which judges must act as\\n“gatekeepers” and ensure the reliability of evidence before a\\njury is able to consider it. Accordingly, in an admittedly very\\ndifferent context, the Supreme Court has described trial judges\\nas gatekeepers of evidence. 7 “[A] gatekeeping role for the\\n\\n4\\n Maj. Op. 13–14.\\n5\\n Kannankeril v. Terminix Int’l, Inc., 128 F.3d 802, 806 (3d\\nCir. 1997) (citing Daubert v. Merrill Dow Pharms., 509 U.S.\\n579, 589 (1993)).\\n6\\n Holdnrook v. Lykes Bros. Steamship Co., 80 F.3d 777, 788\\n(3d Cir. 1996).\\n7\\n Daubert, 509 U.S. at 597.\\n 3\\n\\njudge, no matter how flexible, inevitably on occasion will\\nprevent the jury from learning of authentic insights and\\ninnovations.” 8\\n\\n Despite the importance of the jury system, and the faith\\nwe place in juries, the law has thus traditionally recognized the\\ndanger that jurors may not be able to restrict their deliberations\\nto admissible evidence and that they may return a verdict based\\non factors other than the evidence presented at trial. For\\nexample, Federal Rule of Evidence 403 allows courts to\\nprevent jurors from learning of certain testimony (even\\nuncontradicted testimony) if the court concludes that the\\ntestimony could cause a jury to reach a verdict based more on\\nemotion or prejudice than on evidence. 9\\n\\n The best known example of how courts are empowered\\nto limit what a jury can consider may well be the body of law\\nthat has developed in the wake of the Supreme Court’s decision\\nin Daubert. In Daubert, the Court stated: “the trial judge must\\nensure that any and all scientific testimony or evidence\\nadmitted is not only relevant, but reliable.” 10 We certainly\\ncould, but do not, allow the jury to determine whether the\\nscientific evidence is reliable in the first instance based upon\\ntestimony at trial. Instead, that preliminary factual\\ndetermination rests solely with the trial court if the reliability\\nis challenged.\\n\\n The difficulty with relying on this body of law here is,\\nof course, the fact that the trial court’s dismissal of Wright’s\\nindictment was not limited to an intrusion into the jury-box.\\nMore fundamentally, and more importantly, it also trespassed\\non the separation of powers, and concomitantly, on the\\nprosecutorial discretion that is endemic in that concept.\\n\\n Despite Judge Nygaard’s thoughtful attempt to address\\nthat issue and the jury’s obvious concerns regarding the\\n\\n8\\n Id.\\n9\\n See, e.g., United States v. Bailey, 840 F.3d 99, 117, 121–23,\\n(3d Cir. 2016) (finding that the probative value of video\\nevidence of murder committed by coconspirators was\\nsubstantially outweighed by risk of unfair prejudice).\\n10\\n Daubert, 509 U.S. at 589.\\n 4\\n\\ntestimony of police officers in this case, I am not convinced\\nthat the United States Supreme Court would agree that the\\ninherent powers of a trial court are broad enough to justify what\\nhappened here.\\n\\n The Government clearly has the inherent authority to\\ndecide not to retry Wright given all of the circumstances in this\\ncase, including the seemingly improbable account of what\\nhappened, 11 the conflicting nature of the police testimony and\\nthe jurors’ apparent trouble with it, the fact that there is no\\nadditional evidence to offer at a third trial, and Wright’s\\napparent steps toward rehabilitation since the offense which\\ndisqualified him from lawfully owning a firearm, as well as any\\nother factors that the Government might appropriately\\nconsider. 12 However, I can find no authority that convinces me\\nthat the United States Supreme Court would agree that a trial\\ncourt’s inherent authority allows it to dismiss an indictment\\nwith prejudice on this record.\\n\\n III.\\n\\n\\n\\n11\\n According to the officers’ accounts, they watched (in the\\nopen and without cover) as Wright fumbled in the back of a\\ncar with tinted windows and came out holding a gun. They\\nthen continued to stand and watch from approximately 25\\nyards away—without cover and without taking any actions to\\nprotect themselves—as he attempted to rack the slide which\\nwould have placed a bullet in the chamber.\\n12\\n Appellee argues without contradiction that:\\n\\n [f]ollowing early involvement with the criminal\\n justice system, Mr. Wright began to turn his life\\n around, returning to school and earning his\\n Associates degree in Computer Management-\\n Networking Engineering Technology[,] . . . a\\n Bachelor of Science degree in Information\\n Technology and Management . . . graduating\\n cum laude[,] . . . and . . . a Master of Science\\n degree.\\n\\nAppellee Br. at 52.\\n 5\\n\\n As I noted at the outset, the Government agrees that\\nsuccessive prosecutions can rise to the level of a Due Process\\nviolation, which a court clearly could remedy by dismissing an\\nindictment. However, the Government strenuously argues\\nWright’s prosecution has not yet reached that point. The\\nGovernment’s position inherently argues that the court’s action\\nhere is also not justified by any concept of fundamental\\nfairness. In Ake v. Oklahoma, 13 the Supreme Court observed\\nthat the right to Due Process includes the “guarantee of\\nfundamental fairness.” 14 As has been discussed by Judge\\nShwartz, the District Court here relied on the decision of the\\nNew Jersey Supreme Court in State v. Abbati. 15 There, the\\nNew Jersey Supreme Court affirmed a trial court’s dismissal of\\nan indictment with prejudice after two juries deadlocked,\\nresulting in mistrials. 16 That situation is on “all fours” with the\\ncircumstances here and the District Court relied heavily on that\\ndecision to justify its action and fashion a rule that would\\nproperly allow a trial court to dismiss an indictment with\\nprejudice under certain circumstances. 17\\n\\n However, the New Jersey Supreme Court based its\\ndecision on the inherent authority of state courts under the New\\nJersey Constitution. 18 It did not purport to rest its decision on\\nthe U.S. Constitution and, with very limited exception, it cited\\nto state judicial decisions—not federal ones—in discussing\\nwhen consecutive hung juries justified dismissing an\\nindictment with prejudice. 19 The holding of the Court is\\n\\n13\\n 470 U.S. 68 (1985).\\n14\\n Id. at 76.\\n15\\n 493 A.2d 513 (N.J. 1985).\\n16\\n Id. at 522.\\n17\\n See United States v. Wright, Crim A No. 14-292, 2017 WL\\n1179006, at *3, *4 (W.D. Pa. Mar. 30, 2017).\\n18\\n Abbati, 493 A.3d at 517–18.\\n19\\n Abbati cited to Ake, for the general proposition that the\\n“requirement of fundamental fairness [is] grounded in [the]\\nfourteenth amendment’s due process guarantee.” 493 A.2d at\\n518. However, with the exception of a single District Court\\ncase, the Court cited numerous state court cases for the\\nproposition that a trial court had the inherent authority to\\ndismiss an indictment with prejudice after two juries\\ndeadlocked. Id. at 519–20. It concluded by finding “[t]hese\\n 6\\n\\nsummarized in its statement that the “judicial responsibility for\\nthe proper administration of criminal justice also gives rise to\\nthe inherent power to dismiss an indictment in appropriate\\ncircumstances.” 20\\n\\n The Abbati standard has not been discussed by this\\nCourt (aside from in the instant case), let alone adopted by it.\\nAlthough some of the factors used by the New Jersey Supreme\\nCourt are analogous to considerations federal courts have made\\nin similar federal cases, such as United States v. Ingram 21 and\\nUnited States v. Rossoff, 22 Abbati has no real corollary in\\nfederal case law. 23\\n\\nexamples of the courts’ exercise of their power to administer\\nthe criminal justice system assist in answering the further\\nargument of the State that recognition of an inherent judicial\\npower to dismiss an indictment with prejudice would overstep\\nthe separation of powers.” Id. at 520. Abbati dismissed that\\nargument based upon its belief that “[t]he separation of\\npowers is not an end in itself, but a general principle intended\\nto ensure that the system of checks and balances remains\\nvital.” Id. at 521 (citing State v. Leonardis, 375 A.2d 607, 612\\n(N.J. 1977)).\\n20\\n Id. at 520.\\n21\\n 412 F. Supp. 384 (D.D.C. 1976). The District Court of the\\nDistrict of Columbia dismissed an indictment after two trials\\nin which twenty-one of twenty-four jurors voted to acquit.\\nThe court found no prosecutorial misconduct. Id. at 386. It\\ninstead considered the issue a “matter of fair play,”\\nemphasizing that “[t]he Government has no new proof; it\\nsimply wants another chance” and “simply wishes to keep\\npressing so long as juries disagree in the hope that a\\nconviction eventually will result.” Id. at 385.\\n22\\n 806 F. Supp. 200 (C.D. Ill. 1992).\\n23\\n For example, the first prong of Abbati’s analysis concerns\\nthe number of mistrials and the outcome of the juries’\\ndeliberations. 493 A.2d at 521. Both Rossoff and Ingram took\\nthis into account in dismissing indictments. See Rossoff, 806\\nF. Supp. at 203 (naming, as “additional compelling\\ncircumstances: 1) the majority of jurors in both cases found\\nDr. Rossoff Not Guilty; 2) if not for the allegedly biased juror\\nin the second trial, Dr. Rossoff would have been acquitted on\\nall counts; 3) the two trials have taken over one solid month\\n 7\\n\\n Accordingly, as I noted at the outset, I am sympathetic\\nto the District Court’s efforts given the totality of the\\ncircumstances here. However, until Congress or the United\\nStates Supreme Court determines otherwise, I agree that we\\nhave no alternative but to enter judgment reversing the District\\nCourt. I therefore concur in the judgment reversing the District\\nCourt’s order.\\n\\n\\n\\n\\nof the Court’s time”); Ingram, 412 F. Supp. at 385 (“The\\nproof was legally sufficient to support a conviction in each\\ninstance but the juries simply did not credit the witnesses,\\nvoting 10–2 and 11–1 for acquittal.”).\\n The Abbati standard is also based on the likelihood of\\nany substantial difference in a subsequent trial, which the\\nIngram decision also considered. See Ingram, 412 F. Supp. at\\n385 (“If another trial takes place there is every reason to\\nbelieve the jury will again be divided or will acquit.”).\\n Finally, Rossoff and Ingram both made determinations\\nsimilar to Abbati’s seventh prong, the status of the individual\\nand the impact of a retrial upon the defendant in terms of\\nuntoward hardship and unfairness. 483 A.2d at 422; see\\nIngram, 412 F. Supp. at 385–86 (“Here is a man in jail now\\nmore than seven months primarily because of an offense\\nwhich the Government is unable to convince a jury he\\ncommitted. . . . To permit a retrial, after 21 of 24 jurors have\\nalready refused to convict, is to ignore the reasonable doubt\\nstandard.”); Rossoff, 806 F. Supp. at 203 (“Dr. Rossoff is 71\\nyears of age and in poor health. He has had heart surgery,\\nsuffers from severe anemia and at the time of the second trial\\nwas on experimental treatment. He has been under great\\nphysical and emotional strain as the result of these repeated\\ntrials and was even hospitalized immediately following the\\nsecond trial.”).\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360237/\", \"author_raw\": \"McKEE, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"MCKEE"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MCKEE\": \", Circuit\", \"SHWARTZ\": \", Circuit\", \"NYGAARD\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582984/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Raymont Wright\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014.1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Raymont Wright\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":66,"cells":{"id":{"kind":"number","value":4582985,"string":"4,582,985"},"name":{"kind":"string","value":"Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice"},"name_abbreviation":{"kind":"string","value":"Carlyle Bryan v. United States"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1519"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Krause, Roth, Fisher\", \"parties\": \"\", \"opinions\": [{\"author\": \"ROTH, Circuit Judge\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-1519\\n ________________\\n\\n CARLYLE BRYAN; JULIE BEBERMAN;\\n CHARLES FRANCIS,\\n\\n Appellants\\n\\n v.\\n\\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\\n ________________\\n\\n Appeal from the District Court of the Virgin Islands\\n (Division of St. Croix)\\n (D.C. Civil Action No. 1-10-cv-00066)\\n District Judge: Honorable Wilma A. Lewis\\n ________________\\n\\n Argued on May 22, 2018\\n\\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\\n\\n (Opinion filed: January 18, 2019)\\n\\n\\nDavid M. Nissman, (Argued)\\nMcChain Nissman Law Group\\n53A Company Street\\nChristiansted, VI 00820\\n\\n Counsel for Appellants\\n\\fSamantha L. Chaifetz (Argued)\\nJoycelyn Hewett\\nChad A. Readler\\nMark B. Stern\\nUnited States Department of Justice\\nAppellate Section\\nRoom 7248\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\nJeffrey E. Sandberg\\nUnited States Department of Justice\\nCivil Division\\nRoom 7214\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\nROTH, Circuit Judge\\n\\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\\nreturned to the United States. During their trip, U.S. Customs and Border Protection\\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\\nasserted tort claims against the United States government under the Federal Tort Claims\\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\\njudgment in favor of the officers and the government.\\n\\n\\n\\n1 Bivens provides for private rights of action against federal officials for certain\\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\\nNarcotics, 403 U.S. 388 (1971).\\n 2\\n\\f Because we conclude that the officers are entitled to qualified immunity and the\\nUnited States government is shielded from liability under the FTCA’s discretionary\\nfunction exception, we will affirm.\\n\\n I.\\n\\n The Cruise\\n\\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\\n\\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\\na notation in the Treasury Enforcement Communications System (TECS) database that\\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\\nhis employment, but that the examination of his bag did not uncover anything.2\\n\\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\\n\\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\\nworthy of further scrutiny. Around September 1, he compared the names on the\\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\\n\\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\\n\\n2 JA 8.\\n3 JA 9.\\n 3\\n\\fhad previously worked with Agent Hodge and credited his entry in part because he\\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\\n\\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\\nreport was authored while the Drug Enforcement Administration investigation was going\\non and characterized Francis as a “subject of current interest”; the second was authored\\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\\nreports urged personnel to alert special agents if they encountered Francis.\\n\\n According to Officer Ogg’s subsequent deposition testimony, another factor\\naroused his suspicion: CBP officers had previously made narcotics seizures on the\\nAdventure of the Seas on the same route. A number of islands along the route were\\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\\ncharacterized them as high-risk islands.\\n\\n On September 5, primarily on the strength of the TECS records concerning Bryan\\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\\nrecommends certain investigative steps when they are encountered. In the case of Bryan\\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\\ninspected before their return to San Juan on September 7. 6\\n\\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\\ntwo individuals about whom there were independent TECS entries predicated on drug-\\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\\n\\n\\n\\n\\n4 JA 9-10.\\n5 JA 10.\\n6 Id.\\n\\n\\n 4\\n\\fdetection and inspection by having her submit a single customs declaration form for the\\nthree of them, but in her name only.7\\n\\n The St. Thomas Cabin Searches (September 6, 2008)\\n\\n On the morning of September 6, 2008, after the travelers had returned to United\\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\\nBeberman’s cabin, along with Francis’s.\\n\\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\\nofficers knocked on the cabin doors before opening them. The occupants were asked to\\nget dressed without using the bathroom, and in at least partial view of the officers. They\\nwere then asked to leave their cabins and stand against a wall in the hallway. They\\nwaited in the hallway for between two and five minutes, while officers with a drug-\\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\\nThomas Officers created TECS entries to that effect.9\\n\\n II.\\n\\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\\nOgg, who had recommended, but not participated in, the cabin searches and against the\\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\\ntort claims against the United States under the FTCA for invasion of privacy, false\\nimprisonment, and intentional infliction of emotional distress.\\n\\n\\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\\na single customs declaration form without identifying every passenger. Because\\nsecondary inspections were triggered by the names included on declaration forms, Bryan\\nand Francis could have attempted to evade detection by having Beberman submit a form\\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\\nguard against that possibility.\\n8 The cabin inspections differed in two respects: The occupants found themselves in\\n\\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\\npartially clothed) and the occupants were observed to different extents while they dressed\\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\\nwhile Francis dressed in full view of the officers).\\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\\n\\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\\nvoluntarily dismissed their Bivens claims against the San Juan officers.\\n 5\\n\\f At the close of discovery, the officers and the United States moved for summary\\njudgment. The District Court granted their motion on all claims.\\n\\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\\nrights. Further, it held that the officers were entitled to qualified immunity because their\\nconduct did not violate clearly established Fourth Amendment rights.\\n\\n As for the United States, the District Court held that the FTCA claims were barred\\nby the Act’s discretionary function exception.\\n\\n We review the District Court’s grant of summary judgment de novo, applying the\\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\\n1291.\\n\\n III.\\n\\n The Fourth Amendment protects the public “against unreasonable searches and\\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\\nsurrounding the search,” including where the search took place. 12\\n\\n The search here took place at the border. The border serves a unique gate-keeping\\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\\nextend the government special latitude at the border and strike “the Fourth Amendment\\nbalance between the interests of the Government and the privacy right of the individual”\\nin the government’s favor.14\\n\\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\\n11 U.S. Const. amend. IV.\\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\\n\\nof the integrity of the border. This concern is, if anything, heightened by the veritable\\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\\n\\nCir. 1994).\\n 6\\n\\f In view of the government’s interests, we “have long held that routine searches at\\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\\nship’s first port of call in the United States. 19 Under this standard, the search here was a\\nborder search.\\n\\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\\ntravelers and two days before the cabin searches, we ruled for the first time on the\\nconstitutional propriety of border searches in the same context presented in this appeal —\\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\\nand objective basis” to suspect criminal activity).21 We held for the first time that\\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\\nreasonable suspicion.23\\n\\n IV.\\n\\n In considering whether a government official is entitled to qualified immunity, a\\ncourt can determine whether a constitutional right was violated or in the alternative,\\nwhether that right was clearly established.24 Following that precedent, we will not opine\\nas to whether there were underlying Fourth Amendment violations involved in the search\\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\\n\\n15 Bradley, 299 F.3d at 201 (citations omitted).\\n16 Montoya, 473 U.S. at 538 (footnote omitted).\\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\\n21 Whitted, 541 F.3d at 486, 489.\\n22 Id. at 489.\\n23 Id. at 490.\\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\\n\\n\\n 7\\n\\fthree travelers, i.e., examination of their cabins, was recommended and the next day\\nwhen the St. Thomas officers searched the travelers’ cabins.\\n\\n The doctrine of qualified immunity shields government officials from Bivens\\nclaims and money damages, unless a plaintiff can establish that the official violated a\\nstatutory or constitutional right, and that the right was “clearly established at the time of\\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\\nor constitutional question confronted by the official beyond debate.” 26\\n\\n Further, as the Supreme Court recently reiterated, “clearly established law should\\nnot be defined at a high level of generality” but must instead “be particularized to the\\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\\nincompetent or those who knowingly violate the law.”28\\n\\n Supreme Court discussion of searches has emphasized the threats posed at borders\\nand the government’s compelling interests in searches there. 29 Because the government’s\\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\\ncourts would not be bound by Whitted, a Third Circuit case.\\n\\n When such a ruling is made, a ruling which affects the procedures used in border\\nsearches, it is beyond belief that within two days the government could determine what\\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\\nmuch less communicate that new policy to the CBP officers. We can only conclude that\\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\\n\\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\\n800, 818 (1982)).\\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\\n\\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\\n29 See, e.g., Montoya, 473 U.S. at 539-40.\\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\\n31 Id. at 153.\\n\\n\\n 8\\n\\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\\nhe did not violate clearly established law by entering lookouts for the three passengers the\\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\\n\\n We conclude that the same situation applies to the St. Thomas officers. On\\nSeptember 6, the Whitted standard was no more clearly established than it had been the\\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\\nhave known that Whitted held that unsubstantiated information from TECS can establish\\nreasonable suspicion.32\\n\\n For these reasons, we conclude that the Whitted standard was not clearly\\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\\nto have learned of this development in our Fourth Amendment jurisprudence. At that\\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\\nimmunity, a legal principle does not become “clearly established” the day we announce a\\ndecision, or even one or two days later.\\n\\n This holding is informed by the overarching aim of the qualified immunity\\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\\nprinciple becomes “clearly established.” We leave that exercise for another day.\\n\\n Finally, the tort claims against the United States also fail because of the FTCA’s\\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\\nimmunity in certain tort actions against the United States for money damages.36 That\\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\\n\\n\\n\\n\\n32 541 F.3d at 490.\\n33 White, 137 S. Ct. at 552.\\n34 Id.\\n35 Plumhoff, 134 S. Ct. at 2023.\\n36 28 U.S.C. § 1346(b)(1).\\n\\n\\n 9\\n\\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\\n\\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\\nsearches that followed were discretionary acts under the “discretionary function”\\nexception.38 Rather, they argue that the United States is not shielded from liability\\nbecause the officers in this case, though exercising their discretion, violated “clearly\\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\\n\\n Because, for the reasons set out above, the CBP officers did not violate clearly\\nestablished constitutional rights, the FTCA claims also fail.\\n\\n V.\\n\\n For the reasons stated above, we will affirm the judgment of the District Court.\\n\\n\\n\\n\\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\\nor policy specifically prescribes a course of action for an employee to follow” and the\\ngovernment “employee has no rightful option but to adhere to the directive.” United\\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\\nStates, 486 U.S. 531, 536 (1988)).\\n38 Br. at 63-64.\\n39 Harlow, 457 U.S. at 818.\\n\\n\\n 10\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360238/\", \"author_raw\": \"ROTH, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"KRAUSE"},"judge2":{"kind":"string","value":"ROTH"},"judge3":{"kind":"string","value":"FISHER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4582985/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 17-1519\n ________________\n\n CARLYLE BRYAN; JULIE BEBERMAN;\n CHARLES FRANCIS,\n\n Appellants\n\n v.\n\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\n ________________\n\n Appeal from the District Court of the Virgin Islands\n (Division of St. Croix)\n (D.C. Civil Action No. 1-10-cv-00066)\n District Judge: Honorable Wilma A. Lewis\n ________________\n\n Argued on May 22, 2018\n\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\n\n (Opinion filed: January 18, 2019)\n\n\nDavid M. Nissman, (Argued)\nMcChain Nissman Law Group\n53A Company Street\nChristiansted, VI 00820\n\n Counsel for Appellants\n\fSamantha L. Chaifetz (Argued)\nJoycelyn Hewett\nChad A. Readler\nMark B. Stern\nUnited States Department of Justice\nAppellate Section\nRoom 7248\n950 Pennsylvania Avenue, N.W.\nWashington, DC 20530\n\nJeffrey E. Sandberg\nUnited States Department of Justice\nCivil Division\nRoom 7214\n950 Pennsylvania Avenue, N.W.\nWashington, DC 20530\n\n Counsel for Appellee\n\n\n ________________\n\n OPINION\n ________________\n\nROTH, Circuit Judge\n\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\nreturned to the United States. During their trip, U.S. Customs and Border Protection\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\nasserted tort claims against the United States government under the Federal Tort Claims\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\njudgment in favor of the officers and the government.\n\n\n\n1 Bivens provides for private rights of action against federal officials for certain\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\nNarcotics, 403 U.S. 388 (1971).\n 2\n\f Because we conclude that the officers are entitled to qualified immunity and the\nUnited States government is shielded from liability under the FTCA’s discretionary\nfunction exception, we will affirm.\n\n I.\n\n The Cruise\n\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\n\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\na notation in the Treasury Enforcement Communications System (TECS) database that\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\nhis employment, but that the examination of his bag did not uncover anything.2\n\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\n\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\nworthy of further scrutiny. Around September 1, he compared the names on the\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\n\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\n\n2 JA 8.\n3 JA 9.\n 3\n\fhad previously worked with Agent Hodge and credited his entry in part because he\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\n\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\nreport was authored while the Drug Enforcement Administration investigation was going\non and characterized Francis as a “subject of current interest”; the second was authored\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\nreports urged personnel to alert special agents if they encountered Francis.\n\n According to Officer Ogg’s subsequent deposition testimony, another factor\naroused his suspicion: CBP officers had previously made narcotics seizures on the\nAdventure of the Seas on the same route. A number of islands along the route were\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\ncharacterized them as high-risk islands.\n\n On September 5, primarily on the strength of the TECS records concerning Bryan\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\nrecommends certain investigative steps when they are encountered. In the case of Bryan\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\ninspected before their return to San Juan on September 7. 6\n\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\ntwo individuals about whom there were independent TECS entries predicated on drug-\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\n\n\n\n\n4 JA 9-10.\n5 JA 10.\n6 Id.\n\n\n 4\n\fdetection and inspection by having her submit a single customs declaration form for the\nthree of them, but in her name only.7\n\n The St. Thomas Cabin Searches (September 6, 2008)\n\n On the morning of September 6, 2008, after the travelers had returned to United\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\nBeberman’s cabin, along with Francis’s.\n\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\nofficers knocked on the cabin doors before opening them. The occupants were asked to\nget dressed without using the bathroom, and in at least partial view of the officers. They\nwere then asked to leave their cabins and stand against a wall in the hallway. They\nwaited in the hallway for between two and five minutes, while officers with a drug-\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\nThomas Officers created TECS entries to that effect.9\n\n II.\n\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\nOgg, who had recommended, but not participated in, the cabin searches and against the\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\ntort claims against the United States under the FTCA for invasion of privacy, false\nimprisonment, and intentional infliction of emotional distress.\n\n\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\na single customs declaration form without identifying every passenger. Because\nsecondary inspections were triggered by the names included on declaration forms, Bryan\nand Francis could have attempted to evade detection by having Beberman submit a form\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\nguard against that possibility.\n8 The cabin inspections differed in two respects: The occupants found themselves in\n\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\npartially clothed) and the occupants were observed to different extents while they dressed\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\nwhile Francis dressed in full view of the officers).\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\n\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\nvoluntarily dismissed their Bivens claims against the San Juan officers.\n 5\n\f At the close of discovery, the officers and the United States moved for summary\njudgment. The District Court granted their motion on all claims.\n\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\nrights. Further, it held that the officers were entitled to qualified immunity because their\nconduct did not violate clearly established Fourth Amendment rights.\n\n As for the United States, the District Court held that the FTCA claims were barred\nby the Act’s discretionary function exception.\n\n We review the District Court’s grant of summary judgment de novo, applying the\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\n1291.\n\n III.\n\n The Fourth Amendment protects the public “against unreasonable searches and\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\nsurrounding the search,” including where the search took place. 12\n\n The search here took place at the border. The border serves a unique gate-keeping\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\nextend the government special latitude at the border and strike “the Fourth Amendment\nbalance between the interests of the Government and the privacy right of the individual”\nin the government’s favor.14\n\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\n11 U.S. Const. amend. IV.\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\n\nof the integrity of the border. This concern is, if anything, heightened by the veritable\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\n\nCir. 1994).\n 6\n\f In view of the government’s interests, we “have long held that routine searches at\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\nship’s first port of call in the United States. 19 Under this standard, the search here was a\nborder search.\n\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\ntravelers and two days before the cabin searches, we ruled for the first time on the\nconstitutional propriety of border searches in the same context presented in this appeal —\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\nand objective basis” to suspect criminal activity).21 We held for the first time that\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\nreasonable suspicion.23\n\n IV.\n\n In considering whether a government official is entitled to qualified immunity, a\ncourt can determine whether a constitutional right was violated or in the alternative,\nwhether that right was clearly established.24 Following that precedent, we will not opine\nas to whether there were underlying Fourth Amendment violations involved in the search\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\n\n15 Bradley, 299 F.3d at 201 (citations omitted).\n16 Montoya, 473 U.S. at 538 (footnote omitted).\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\n21 Whitted, 541 F.3d at 486, 489.\n22 Id. at 489.\n23 Id. at 490.\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\n\n\n 7\n\fthree travelers, i.e., examination of their cabins, was recommended and the next day\nwhen the St. Thomas officers searched the travelers’ cabins.\n\n The doctrine of qualified immunity shields government officials from Bivens\nclaims and money damages, unless a plaintiff can establish that the official violated a\nstatutory or constitutional right, and that the right was “clearly established at the time of\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\nor constitutional question confronted by the official beyond debate.” 26\n\n Further, as the Supreme Court recently reiterated, “clearly established law should\nnot be defined at a high level of generality” but must instead “be particularized to the\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\nincompetent or those who knowingly violate the law.”28\n\n Supreme Court discussion of searches has emphasized the threats posed at borders\nand the government’s compelling interests in searches there. 29 Because the government’s\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\ncourts would not be bound by Whitted, a Third Circuit case.\n\n When such a ruling is made, a ruling which affects the procedures used in border\nsearches, it is beyond belief that within two days the government could determine what\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\nmuch less communicate that new policy to the CBP officers. We can only conclude that\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\n\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\n800, 818 (1982)).\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\n\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\n29 See, e.g., Montoya, 473 U.S. at 539-40.\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\n31 Id. at 153.\n\n\n 8\n\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\nhe did not violate clearly established law by entering lookouts for the three passengers the\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\n\n We conclude that the same situation applies to the St. Thomas officers. On\nSeptember 6, the Whitted standard was no more clearly established than it had been the\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\nhave known that Whitted held that unsubstantiated information from TECS can establish\nreasonable suspicion.32\n\n For these reasons, we conclude that the Whitted standard was not clearly\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\nto have learned of this development in our Fourth Amendment jurisprudence. At that\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\nimmunity, a legal principle does not become “clearly established” the day we announce a\ndecision, or even one or two days later.\n\n This holding is informed by the overarching aim of the qualified immunity\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\nprinciple becomes “clearly established.” We leave that exercise for another day.\n\n Finally, the tort claims against the United States also fail because of the FTCA’s\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\nimmunity in certain tort actions against the United States for money damages.36 That\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\n\n\n\n\n32 541 F.3d at 490.\n33 White, 137 S. Ct. at 552.\n34 Id.\n35 Plumhoff, 134 S. Ct. at 2023.\n36 28 U.S.C. § 1346(b)(1).\n\n\n 9\n\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\n\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\nsearches that followed were discretionary acts under the “discretionary function”\nexception.38 Rather, they argue that the United States is not shielded from liability\nbecause the officers in this case, though exercising their discretion, violated “clearly\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\n\n Because, for the reasons set out above, the CBP officers did not violate clearly\nestablished constitutional rights, the FTCA claims also fail.\n\n V.\n\n For the reasons stated above, we will affirm the judgment of the District Court.\n\n\n\n\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\nor policy specifically prescribes a course of action for an employee to follow” and the\ngovernment “employee has no rightful option but to adhere to the directive.” United\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\nStates, 486 U.S. 531, 536 (1988)).\n38 Br. at 63-64.\n39 Harlow, 457 U.S. at 818.\n\n\n 10\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Carlyle BRYAN ; Julie Beberman; Charles Francis, Appellants v. UNITED STATES of America; Unknown Officers of the Department of Homeland Security; Bureau of Customs & Border Protection; Customs and Border Protection Officers John Mazur; Jamie Demarais; Obed Torres; William Santiago ; Orlando Baez; Timothy Ogg; Andres Vazquez ; Joel Osorio; Juan Gracia; Gregory Defelice\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 17-1519\\n ________________\\n\\n CARLYLE BRYAN; JULIE BEBERMAN;\\n CHARLES FRANCIS,\\n\\n Appellants\\n\\n v.\\n\\nUNITED STATES OF AMERICA; UNKNOWN OFFICERS OF THE DEPARTMENT\\nOF HOMELAND SECURITY; BUREAU OF CUSTOMS & BORDER PROTECTION;\\n CUSTOMS AND BORDER PROTECTION OFFICERS JOHN MAZUR;\\n JAMIE DEMARAIS; OBED TORRES; WILLIAM SANTIAGO;\\n ORLANDO BAEZ; TIMOTHY OGG; ANDRES VAZQUEZ;\\n JOEL OSORIO; JUAN GRACIA; GREGORY DEFELICE\\n ________________\\n\\n Appeal from the District Court of the Virgin Islands\\n (Division of St. Croix)\\n (D.C. Civil Action No. 1-10-cv-00066)\\n District Judge: Honorable Wilma A. Lewis\\n ________________\\n\\n Argued on May 22, 2018\\n\\n Before: KRAUSE, ROTH and FISHER, Circuit Judges\\n\\n (Opinion filed: January 18, 2019)\\n\\n\\nDavid M. Nissman, (Argued)\\nMcChain Nissman Law Group\\n53A Company Street\\nChristiansted, VI 00820\\n\\n Counsel for Appellants\\n\\fSamantha L. Chaifetz (Argued)\\nJoycelyn Hewett\\nChad A. Readler\\nMark B. Stern\\nUnited States Department of Justice\\nAppellate Section\\nRoom 7248\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\nJeffrey E. Sandberg\\nUnited States Department of Justice\\nCivil Division\\nRoom 7214\\n950 Pennsylvania Avenue, N.W.\\nWashington, DC 20530\\n\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\nROTH, Circuit Judge\\n\\n In 2008, Carlyle Bryan, Julie Beberman, and Charles Francis (the travelers),\\nresidents of St. Croix in the U.S. Virgin Islands, embarked on a Caribbean cruise aboard\\nthe Adventure of the Seas. Their trip took them to a number of foreign ports before they\\nreturned to the United States. During their trip, U.S. Customs and Border Protection\\n(CBP) officers searched their cabins on suspicion of drug-smuggling activity. Those\\nsearches yielded no contraband and prompted the three travelers to assert Bivens claims1\\nagainst the officers for allegedly violating their Fourth Amendment rights. They also\\nasserted tort claims against the United States government under the Federal Tort Claims\\nAct (FTCA or the Act). The District Court of the Virgin Islands granted summary\\njudgment in favor of the officers and the government.\\n\\n\\n\\n1 Bivens provides for private rights of action against federal officials for certain\\nconstitutional violations. Bivens v. Six Unknown Named Agents of Federal Bureau of\\nNarcotics, 403 U.S. 388 (1971).\\n 2\\n\\f Because we conclude that the officers are entitled to qualified immunity and the\\nUnited States government is shielded from liability under the FTCA’s discretionary\\nfunction exception, we will affirm.\\n\\n I.\\n\\n The Cruise\\n\\n The cruise lasted from August 31 to September 7, 2008. Beberman had booked\\ntwo cabins for the three travelers: one for Bryan and herself, and a second for Francis.\\nThe cruise began in the United States. They sailed from San Juan, Puerto Rico, stopped\\nat several foreign ports, including Antigua, Barbados, St. Lucia, and St. Maarten,\\nproceeded to St. Thomas in the U.S. Virgin Islands, and returned to San Juan.\\n\\n The travelers had to pass through a CBP checkpoint in San Juan before boarding\\nthe ship. Bryan and Beberman went through without incident. Francis’s trip through the\\ncheckpoint was not so smooth. When a CBP officer asked Francis what his occupation\\nwas, he hesitated and then said “oil change.” (Francis worked with automobiles and\\nchanged motor oil.) CBP officers then inspected Francis’s bag. There was a very full\\ncanister of shaving powder in the bag. When a CBP officer opened the canister, the\\npowder dispersed through the room and coated the officer. Bryan laughed. They contend\\nnow that the inspection of their cabins was in retaliation for Bryan’s laughing at the CBP\\nofficer. The officers found nothing unlawful in Francis’s bags. CBP Officer Baez made\\na notation in the Treasury Enforcement Communications System (TECS) database that\\nFrancis had appeared “disoriented and nervous” and that it took him some time to state\\nhis employment, but that the examination of his bag did not uncover anything.2\\n\\n The Creation of “Lookout” Entries by Officer Timothy Ogg (September 5, 2008)\\n\\n CBP Officer Timothy Ogg, stationed in San Juan, was routinely assigned the task\\nof reviewing passenger manifests for the Adventure of the Seas to identify passengers\\nworthy of further scrutiny. Around September 1, he compared the names on the\\npassenger manifest against the names on reports logged onto TECS. Both Bryan’s and\\nFrancis’s names yielded matches; both had TECS entries related to drug smuggling.\\n\\n Officer Ogg found two entries on Bryan. The first, dated May 17, 2000, was\\nauthored by Immigration & Customs Enforcement (ICE) Agent Hillary Hodge. Referring\\nto Bryan, the entry read: “Subject is associate[d] with suspected drug smugglers within\\nthe US Virgin Islands. Subject is also suspected of smuggling narcotics within the Virgin\\nIslands. If encountered, conduct 100% exam . . ..”3 Officer Ogg later testified that he\\n\\n2 JA 8.\\n3 JA 9.\\n 3\\n\\fhad previously worked with Agent Hodge and credited his entry in part because he\\nregarded Hodge as an excellent worker. The second TECS entry, from 2004, referred to\\nthe prior entry, characterized Bryan as a “suspect in USVI drug smuggling,” and\\nencouraged agents to “document [his] co-travelers, employment and reason for travel.”4\\n\\n As for Francis, Officer Ogg uncovered two TECS reports from 2006 identifying\\nFrancis as the “Subject of [a Drug Enforcement Administration] indictment.” The first\\nreport was authored while the Drug Enforcement Administration investigation was going\\non and characterized Francis as a “subject of current interest”; the second was authored\\nafter the investigation had ended and referred to him as a “Previous Suspect.”5 Both\\nreports urged personnel to alert special agents if they encountered Francis.\\n\\n According to Officer Ogg’s subsequent deposition testimony, another factor\\naroused his suspicion: CBP officers had previously made narcotics seizures on the\\nAdventure of the Seas on the same route. A number of islands along the route were\\nknown to be sources of narcotics smuggled into the United States. Officer Ogg\\ncharacterized them as high-risk islands.\\n\\n On September 5, primarily on the strength of the TECS records concerning Bryan\\nand Francis, Officer Ogg created “lookout” entries for Bryan and Francis in the TECS\\ndatabase. A “lookout” is a TECS entry that alerts CBP officers to specific passengers and\\nrecommends certain investigative steps when they are encountered. In the case of Bryan\\nand Francis, the “lookout entries” noted their connection to “drug smuggling” and\\nrecommended, in the standard TECS shorthand (i.e., “100% exam”), that their cabins be\\ninspected before their return to San Juan on September 7. 6\\n\\n Officer Ogg also entered a separate “lookout” for Beberman. Except for the co-\\ntravelers listed, the “lookout” entry for Beberman mirrored Bryan’s. At his deposition,\\nOfficer Ogg gave two reasons for the Beberman “lookout.” First, she was traveling with\\ntwo individuals about whom there were independent TECS entries predicated on drug-\\nsmuggling concerns. Second, as a practical matter, Officer Ogg stated that he had to\\nenter a lookout for Beberman to ensure that Bryan and Francis did not use her to evade\\n\\n\\n\\n\\n4 JA 9-10.\\n5 JA 10.\\n6 Id.\\n\\n\\n 4\\n\\fdetection and inspection by having her submit a single customs declaration form for the\\nthree of them, but in her name only.7\\n\\n The St. Thomas Cabin Searches (September 6, 2008)\\n\\n On the morning of September 6, 2008, after the travelers had returned to United\\nStates waters and had docked in St. Thomas, CBP Officers DeFelice, Demarais, Mazur,\\nSantiago, and Torres (collectively, the St. Thomas Officers) inspected Bryan and\\nBeberman’s cabin, along with Francis’s.\\n\\n The cabin searches each lasted between five and ten minutes.8 The St. Thomas\\nofficers knocked on the cabin doors before opening them. The occupants were asked to\\nget dressed without using the bathroom, and in at least partial view of the officers. They\\nwere then asked to leave their cabins and stand against a wall in the hallway. They\\nwaited in the hallway for between two and five minutes, while officers with a drug-\\nsniffing dog inspected their cabins. Neither cabin search yielded any contraband; the St.\\nThomas Officers created TECS entries to that effect.9\\n\\n II.\\n\\n As a result of the searches, Beberman, Bryan, and Francis filed suit in the District\\nCourt for the Virgin Islands, asserting Fourth Amendment Bivens claims against Officer\\nOgg, who had recommended, but not participated in, the cabin searches and against the\\nSt. Thomas officers, who had executed the cabin searches. The travelers also asserted\\ntort claims against the United States under the FTCA for invasion of privacy, false\\nimprisonment, and intentional infliction of emotional distress.\\n\\n\\n7 Ogg testified at his deposition that passengers traveling together were allowed to submit\\na single customs declaration form without identifying every passenger. Because\\nsecondary inspections were triggered by the names included on declaration forms, Bryan\\nand Francis could have attempted to evade detection by having Beberman submit a form\\nin her name only. Officer Ogg explained that he had entered three separate “lookouts” to\\nguard against that possibility.\\n8 The cabin inspections differed in two respects: The occupants found themselves in\\n\\ndifferent states of undress (i.e., Francis was naked, while Bryan and Beberman were\\npartially clothed) and the occupants were observed to different extents while they dressed\\n(i.e., Bryan and Beberman dressed with their cabin door ajar and the officers outside,\\nwhile Francis dressed in full view of the officers).\\n9 On September 7, when the ship reached San Juan, a different set of CBP officers began\\n\\nto inspect the travelers’ cabins but cut short the searches when they learned of the St.\\nThomas searches. The San Juan searches are not implicated in this appeal. The travelers\\nvoluntarily dismissed their Bivens claims against the San Juan officers.\\n 5\\n\\f At the close of discovery, the officers and the United States moved for summary\\njudgment. The District Court granted their motion on all claims.\\n\\n As for the officers, the District Court reasoned that neither Officer Ogg’s entry of\\n“lookouts” nor the St. Thomas cabin searches violated the travelers’ Fourth Amendment\\nrights. Further, it held that the officers were entitled to qualified immunity because their\\nconduct did not violate clearly established Fourth Amendment rights.\\n\\n As for the United States, the District Court held that the FTCA claims were barred\\nby the Act’s discretionary function exception.\\n\\n We review the District Court’s grant of summary judgment de novo, applying the\\nsame decisional principle.10 The District Court exercised subject matter jurisdiction\\nunder 28 U.S.C. §§ 1331 and 1346(b). We have appellate jurisdiction under 28 U.S.C. §\\n1291.\\n\\n III.\\n\\n The Fourth Amendment protects the public “against unreasonable searches and\\nseizures.”11 Whether a search is reasonable turns on “all of the circumstances\\nsurrounding the search,” including where the search took place. 12\\n\\n The search here took place at the border. The border serves a unique gate-keeping\\nfunction. Our controlling Fourth Amendment precedent is attuned to that reality. The\\nSupreme Court has stressed the border’s role in protecting our territorial sovereignty,\\nalong with the need to curb the inflow of drugs at the border. 13 For those reasons, we\\nextend the government special latitude at the border and strike “the Fourth Amendment\\nbalance between the interests of the Government and the privacy right of the individual”\\nin the government’s favor.14\\n\\n10 Summary judgment should be granted when, “after drawing all reasonable inferences\\nfrom the underlying facts in the light most favorable to the nonmoving party, the court\\nconcludes that there is no genuine issue of material fact to be resolved at trial and the\\nmoving party is entitled to judgment as a matter of law.” Petruzzi’s IGA Supermarkets,\\nInc. v. Darling-Delaware Co., 998 F.2d 1224, 1230 (3d Cir. 1993).\\n11 U.S. Const. amend. IV.\\n12 United States v. Montoya de Hernandez, 473 U.S. 531, 537 (1985).\\n13 See Montoya, 473 U.S. at 538 (highlighting a “longstanding concern for the protection\\n\\nof the integrity of the border. This concern is, if anything, heightened by the veritable\\nnational crisis in law enforcement caused by smuggling of illicit narcotics . . ..”) (citation\\nomitted); see also Bradley v. United States, 299 F.3d 197, 201-02 (3d Cir. 2002).\\n14 Montoya, 473 U.S. at 539-40; see also United States v. Hyde, 37 F.3d 116, 119-20 (3d\\n\\nCir. 1994).\\n 6\\n\\f In view of the government’s interests, we “have long held that routine searches at\\nour nation’s borders are presumed to be reasonable under the Fourth Amendment.” 15\\nIndeed, “[r]outine searches of the persons and effects of entrants are not subject to any\\nrequirement of reasonable suspicion, probable cause, or warrant . . ..”16 In contrast,\\n“nonroutine searches . . . require reasonable suspicion.”17 This approach to border\\nsearches applies with equal force at “the functional equivalent” of the border,18 such as a\\nship’s first port of call in the United States. 19 Under this standard, the search here was a\\nborder search.\\n\\n On September 4, 2008, a day before Officer Ogg entered “lookouts” for the\\ntravelers and two days before the cabin searches, we ruled for the first time on the\\nconstitutional propriety of border searches in the same context presented in this appeal —\\nin remarkable coincidence, searches of cabins aboard the Adventure of the Seas. 20 In\\nUnited States v. Whitted, we acknowledged “the surprising dearth of authority” on\\nwhether a search of a cruise ship cabin at the border is a routine search requiring no\\nsuspicion, or a non-routine search requiring “reasonable suspicion” (i.e., a “particularized\\nand objective basis” to suspect criminal activity).21 We held for the first time that\\nbecause of a passenger’s “high expectation of privacy” and the “level of intrusiveness,” a\\nsearch of a cruise ship cabin at the border is non-routine and requires reasonable\\nsuspicion.22 We also held that unsubstantiated information from TECS can establish\\nreasonable suspicion.23\\n\\n IV.\\n\\n In considering whether a government official is entitled to qualified immunity, a\\ncourt can determine whether a constitutional right was violated or in the alternative,\\nwhether that right was clearly established.24 Following that precedent, we will not opine\\nas to whether there were underlying Fourth Amendment violations involved in the search\\nhere. We will instead determine whether the Whitted standard, that a search of a cabin on\\na cruise ship required reasonable suspicion, was clearly established when Officer Ogg\\nincluded in his entry of “lookouts” in the TECS System that 100 % examination of the\\n\\n15 Bradley, 299 F.3d at 201 (citations omitted).\\n16 Montoya, 473 U.S. at 538 (footnote omitted).\\n17 Bradley, 299 F.3d at 204 n.8 (citation omitted).\\n18 Almeida-Sanchez v. United States, 413 U.S. 266, 272-73 (1973).\\n19 United States v. Smith, 273 F.3d 629, 633 n.8 (5th Cir. 2001) (citation omitted).\\n20 United States v. Whitted, 541 F.3d 480 (3d Cir. 2008).\\n21 Whitted, 541 F.3d at 486, 489.\\n22 Id. at 489.\\n23 Id. at 490.\\n24 Pearson v. Callahan, 555 U.S. 223, 236 (2009).\\n\\n\\n 7\\n\\fthree travelers, i.e., examination of their cabins, was recommended and the next day\\nwhen the St. Thomas officers searched the travelers’ cabins.\\n\\n The doctrine of qualified immunity shields government officials from Bivens\\nclaims and money damages, unless a plaintiff can establish that the official violated a\\nstatutory or constitutional right, and that the right was “clearly established at the time of\\nthe challenged conduct.”25 To be clearly established, a right’s contours must be\\n“sufficiently definite that any reasonable official in the defendant’s shoes would have\\nunderstood that he was violating it” and that “existing precedent . . . placed the statutory\\nor constitutional question confronted by the official beyond debate.” 26\\n\\n Further, as the Supreme Court recently reiterated, “clearly established law should\\nnot be defined at a high level of generality” but must instead “be particularized to the\\nfacts of the case.”27 The doctrine is designed to “give[] government officials breathing\\nroom to make reasonable but mistaken judgments by protect[ing] all but the plainly\\nincompetent or those who knowingly violate the law.”28\\n\\n Supreme Court discussion of searches has emphasized the threats posed at borders\\nand the government’s compelling interests in searches there. 29 Because the government’s\\ninterest in preventing the entry of unwarranted persons and effects is at its zenith at the\\nborder,30 Congress “has granted the Executive plenary authority to conduct routine\\nsearches and seizures at the border, without probable cause or a warrant . . ..”31 Until\\nSeptember 4, 2008, there had been no ruling in the Third Circuit as to what constituted a\\n“routine search.” As for Officer Ogg, he was located in San Juan, Puerto Rico, in the\\nFirst Circuit. There had not been any such ruling in the First Circuit, and the First Circuit\\ncourts would not be bound by Whitted, a Third Circuit case.\\n\\n When such a ruling is made, a ruling which affects the procedures used in border\\nsearches, it is beyond belief that within two days the government could determine what\\nwas “reasonable suspicion” and what new policy was required to conform to the ruling,\\nmuch less communicate that new policy to the CBP officers. We can only conclude that\\nas of September 5, 2008, it was not clearly established in either the Third Circuit or the\\nFirst Circuit that a search of a cruise ship cabin at the border had to be supported by\\n\\n25 Ashcroft v. al-Kidd, 563 U.S. 731, 735 (2011) (citing Harlow v. Fitzgerald, 457 U.S.\\n800, 818 (1982)).\\n26 Plumhoff v. Rickard, 134 S. Ct. 2012, 2023 (2014) (quoting Ashcroft, 563 U.S. at 741).\\n27 White v. Pauly, 137 S. Ct. 548, 552 (2017) (per curiam) (citation omitted); see also\\n\\nL.R. v. Sch. Dist. of Phila., 836 F.3d 235, 248 (3d Cir. 2016).\\n28 City & Cty. of S.F. v. Sheehan, 135 S. Ct. 1765, 1774 (2015) (citation omitted).\\n29 See, e.g., Montoya, 473 U.S. at 539-40.\\n30 United States v. Flores-Montano, 541 U.S. 149, 152-53 (2004).\\n31 Id. at 153.\\n\\n\\n 8\\n\\freasonable suspicion. Accordingly, under the circumstances that Officer Ogg confronted,\\nhe did not violate clearly established law by entering lookouts for the three passengers the\\nday after we issued our decision in Whitted. He is entitled to qualified immunity.\\n\\n We conclude that the same situation applies to the St. Thomas officers. On\\nSeptember 6, the Whitted standard was no more clearly established than it had been the\\nday before. Moreover, if the St. Thomas officers had been aware of Whitted, they would\\nhave known that Whitted held that unsubstantiated information from TECS can establish\\nreasonable suspicion.32\\n\\n For these reasons, we conclude that the Whitted standard was not clearly\\nestablished in the Third Circuit, or the First Circuit, on September 5 or 6. Within one or\\ntwo days, neither Officer Ogg nor the St. Thomas officers could reasonably be expected\\nto have learned of this development in our Fourth Amendment jurisprudence. At that\\ntime, it would not have been beyond debate that, absent reasonable suspicion, the Fourth\\nAmendment prohibited the search of the travelers’ cabins. For purposes of qualified\\nimmunity, a legal principle does not become “clearly established” the day we announce a\\ndecision, or even one or two days later.\\n\\n This holding is informed by the overarching aim of the qualified immunity\\ndoctrine to insulate from civil liability “all but the plainly incompetent or those who\\nknowingly violate the law,”33 and the need to ensure that the relevant legal principle is\\nframed with particularity34 and settled “beyond debate.”35 We are, however, deciding\\nonly this case. For that reason, we decline to draw a bright line demarcating when a legal\\nprinciple becomes “clearly established.” We leave that exercise for another day.\\n\\n Finally, the tort claims against the United States also fail because of the FTCA’s\\ndiscretionary function exception. The FTCA provides a limited waiver of sovereign\\nimmunity in certain tort actions against the United States for money damages.36 That\\nwaiver does not extend to various types of government conduct enumerated in 28 U.S.C.\\n\\n\\n\\n\\n32 541 F.3d at 490.\\n33 White, 137 S. Ct. at 552.\\n34 Id.\\n35 Plumhoff, 134 S. Ct. at 2023.\\n36 28 U.S.C. § 1346(b)(1).\\n\\n\\n 9\\n\\f§ 2680, including “the exercise or performance or the failure to exercise or perform a\\ndiscretionary function or duty . . . whether or not the discretion involved be abused.”37\\n\\n The travelers do not dispute that Officer Ogg’s entry of “lookouts” and the\\nsearches that followed were discretionary acts under the “discretionary function”\\nexception.38 Rather, they argue that the United States is not shielded from liability\\nbecause the officers in this case, though exercising their discretion, violated “clearly\\nestablished . . . constitutional rights of which a reasonable person would have known.” 39\\n\\n Because, for the reasons set out above, the CBP officers did not violate clearly\\nestablished constitutional rights, the FTCA claims also fail.\\n\\n V.\\n\\n For the reasons stated above, we will affirm the judgment of the District Court.\\n\\n\\n\\n\\n37 28 U.S.C. § 2680(a). Discretionary acts and omissions “involv[e] an element of\\njudgment or choice.” Conduct is non-discretionary only if a “federal statute, regulation,\\nor policy specifically prescribes a course of action for an employee to follow” and the\\ngovernment “employee has no rightful option but to adhere to the directive.” United\\nStates v. Gaubert, 499 U.S. 315, 322 (1991) (quoting Berkovitz ex rel. Berkovitz v. United\\nStates, 486 U.S. 531, 536 (1988)).\\n38 Br. at 63-64.\\n39 Harlow, 457 U.S. at 818.\\n\\n\\n 10\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":67,"cells":{"id":{"kind":"number","value":4583040,"string":"4,583,040"},"name":{"kind":"string","value":"UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765"},"name_abbreviation":{"kind":"string","value":"United States v. William Hird"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4754; 14-4804; 14-4812; 15-1344; 15-1739; 15-3765"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Greenaway, Nygaard, Fisher\", \"parties\": \"\", \"opinions\": [{\"author\": \"NYGAARD, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIAM HIRD,\\n Appellant at No. 14-4754\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n THOMASINE TYNES,\\n Appellant at No. 14-4804\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n ROBERT MULGREW,\\n Appellant at No. 14-4812\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n MICHAEL LOWRY,\\n Appellant at No. 15-1344\\n\\f __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIE SINGLETARY,\\n Appellant at No. 15-1739\\n ___________\\n\\n UNITED STATES OF AMERICA\\n v.\\n HENRY P. ALFANO,\\n aka Ed, aka Eddie,\\n\\n Henry P. Alfano,\\n Appellant at No. 15-3765\\n __________\\n\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n\\n (District Court Criminal Nos. 2-13-cr-00039-007,\\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\\n 2-13-cr-00039-004, 2-13-cr-00039-008)\\n District Judge: Honorable Robert F. Kelly\\n District Judge: Honorable Lawrence F. Stengel\\n\\n Argued October 23, 2017\\n\\n BEFORE: GREENAWAY, JR., NYGAARD,\\n and FISHER, Circuit Judges\\n\\n\\n (Opinion Filed: January 18, 2019)\\n\\n\\n\\n\\n 2\\n\\fAngela Halim\\nHalim Drossner\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n\\nGregory J. Pagano\\n1315 Walnut Street, 12th Floor\\nPhiladelphia, PA 19107\\n Counsel for Appellant in No. 14-4754\\n\\nLisa A. Mathewson [Argued]\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant No. 14-4804\\n\\nPeter Goldberger [Argued]\\nPamela A. Wilk\\n50 Rittenhouse Place\\nArdmore, PA 19003\\n Counsel for Appellant in No. 14-4812\\n\\nMichael J. Engle [Argued]\\nStradley Ronon Stevens & Young\\n2005 Market Street, Suite 2600\\nPhiladelphia, PA 19103\\n\\nMeredith A. Lowry\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n Counsel for Appellant in No. 15-1344\\n\\n\\n\\n\\n 3\\n\\fWilliam J. Brennan\\n1600 Locust Street\\nPhiladelphia, PA 19103\\n Counsel for Appellant in No. 15-1739\\n\\nMark E. Cedrone [Argued]\\nCedrone & Mancano\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant in No. 15-3765\\n\\n\\nLouis D. Lappen\\nDenise S. Wolf\\nAnthony J. Wzorek\\nRobert A. Zauzmer [Argued]\\nOffice of United States Attorney\\n615 Chestnut Street, Suite 1250\\nPhiladelphia, PA 19106\\n Counsel for Appellee\\n\\n\\n\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n I.\\n\\n\\n\\n\\n 4\\n\\f In the run-up to a joint trial on a 77-count indictment\\nthat charged Appellants with operating a ticket-fixing scheme\\nin the Philadelphia Traffic Court, the District Court denied a\\nmotion, under Federal Rule of Criminal Procedure\\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\\nand William Hird (Traffic Court administrator) subsequently\\npleaded guilty to all counts against them. But now they\\nappeal the District Court’s decision on this motion,\\nquestioning whether the indictment properly alleged offenses\\nof mail fraud and wire fraud. 1\\n\\n Appellants Michael Lowry, Robert Mulgrew, and\\nThomasine Tynes (Traffic Court judges) proceeded to a joint\\ntrial and were acquitted on the fraud and conspiracy counts,\\nbut they were convicted of perjury for statements they made\\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\\nthe sufficiency of the evidence on which they were convicted\\nby arguing that the prosecutor’s questions were vague, and\\nthat their answers were literally true. Lowry and Mulgrew\\ncontend alternatively that the jury was prejudiced by evidence\\npresented at trial on the fraud and conspiracy counts.\\nMulgrew also complains that the District Court erred by\\nruling that certain evidence was inadmissible.\\n\\n At the same trial, the jury convicted Willie Singletary\\n(Traffic Court judge) of making false statements during the\\ninvestigation. He claims the District Court made errors when\\n\\n\\n1\\n Alfano and Hird preserved their right to appeal. See infra\\nsubsection I.C.\\n\\n\\n\\n\\n 5\\n\\fit sentenced him. 2 The Government concurs with\\nSingletary’s challenge to his sentence.\\n\\n We have consolidated these appeals for efficiency and\\nhave grouped the arguments—to the extent that it is\\npossible—by common issues. We agree with Singletary and\\nthe Government that he should be resentenced. We will\\nreverse the judgment and remand his cause to the District\\nCourt for this purpose. We are not persuaded by the rest of\\nAppellants’ arguments and will affirm their judgments of\\nconviction. 3\\n\\n II.\\n\\n Appellants Alfano 4 and Hird 5\\n\\n\\n\\n2\\n Singletary also attempted to join additional arguments raised\\nby other appellants, but for reasons we explain later, see infra\\nnote 33, we focus only on his challenge to his sentence.\\n3\\n The District Court had jurisdiction pursuant to 18 U.S.C. §\\n3231. We have jurisdiction to review these claims under 28\\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\\n4\\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\\n51, 52, 53, 54, 55, 56).\\n5\\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\\nMail Fraud (Counts 58, 59, 60).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n We begin with a brief look at the indictment’s\\ndescription of the Traffic Court and its operations to\\ncontextualize the arguments made by Alfano and Hird. The\\nPhiladelphia Traffic Court was part of the First Judicial\\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\\nadjudicated violations of the Pennsylvania Motor Vehicle\\nCode occurring in the City of Philadelphia, no matter whether\\nthe Philadelphia Police or the Pennsylvania State Police\\nissued the tickets. App. 187 (Indictment ¶5). When a person\\nwas cited for a violation he or she was required—within ten\\ndays—to enter a plea of guilty or not guilty. If the person\\nfailed to plead, the Traffic Court issued a notice that his or her\\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\\nperson who pleaded not guilty proceeded to a hearing with a\\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\\n\\n A guilty plea, or a determination of guilt by a Traffic\\nCourt judge after a hearing, resulted in a judgment ordering\\npayment of statutory fines and court costs. App. 188\\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\\ncollecting these fines (sending them to the City and\\n\\n\\n6\\n Philadelphia Traffic Court was abolished and its jurisdiction\\nwas transferred to the Municipal Court in 2013 by an Act of\\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\\n§1121(a)(2) (2013). The court is now known as the Traffic\\nDivision of the Municipal Court.\\n7\\n Although other penalties are prescribed by the Pennsylvania\\nMotor Vehicle Code (App. 188), this appeal is limited to the\\nmonetary fines and costs. App. 355.\\n\\n\\n\\n\\n 7\\n\\fCommonwealth) and costs (which it distributed to several\\npre-designated funds). App. 188-89 (Indictment ¶ 9).\\nFinally, it reported the disposition of each adjudication to the\\nPennsylvania Department of Transportation (PennDOT).\\nApp. 189 (Indictment ¶ 11).\\n\\n B.\\n\\n The indictment charged that, at the behest of Alfano\\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\\nadministrator and judges operated an “extra-judicial system,\\nnot sanctioned by the Pennsylvania court system” that\\nignored court procedure and gave preferential treatment\\n(“consideration”) to select individuals with connections to the\\ncourt who had been cited for motor vehicle violations. App.\\n196 (Indictment ¶ 31). The special treatment included:\\n\\n (1) dismissing tickets outright; (2)\\n finding the ticketholder not guilty\\n after a “show” hearing; (3)\\n adjudicating the ticket in a\\n manner to reduce fines and avoid\\n assignment of points to a driver’s\\n record; and (4) obtaining\\n continuances of trial dates to\\n “judge-shop,” that is find a Traffic\\n Court judge who would accede to\\n a request for preferential\\n treatment.\\n\\nApp. 195-196 (Indictment ¶ 30). All of this was “not\\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\\n32). It also alleged that Appellants cooperated with each\\n\\n\\n\\n\\n 8\\n\\fother to fulfill requests they and their staffs received. App.\\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\\nacceding to requests for ‘consideration,’ defendants were\\ndepriving the City of Philadelphia and the Commonwealth of\\nPennsylvania of money which would have been properly due\\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\\n After extending consideration to favored individuals,\\nTraffic Court judges would report the final adjudication to\\n“various authorities, including PennDOT, as if there had been\\na fair and open review of the circumstances.” App. 197\\n(Indictment ¶ 34). Appellant Hird provided a printout to\\nAppellant Alfano showing citations that had been “dismissed\\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\\nSuch “receipts” were not routinely issued in cases.\\n\\n C.\\n\\n Hird and Alfano pleaded guilty to all the charges\\nagainst them in the indictment. But, in their plea agreement\\nthey reserved the right to appeal “whether the Indictment\\n\\n\\n8\\n An example of the many allegations involving Alfano and\\nHird is: A.S. requested assistance from Appellant Alfano and\\nAppellant Hird on Citation Number P1J0PK568L4 on or\\naround February 17, 2010. The citation charged A.S. with\\ndriving a tractor-trailer from which snow and ice fell, striking\\nvehicles on Interstate 95. The violation carried a $300 fine\\nand costs of $142. Appellant Hird promised that he would\\n“stop all action” on the citation and instructed A.S. to ignore\\nthe ticket. Although A.S. did not appear at the hearing, the\\nTraffic Court judge (who is not an appellant here) ruled A.S.\\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\\n\\n\\n\\n\\n 9\\n\\fsufficiently alleged that the defendants engaged in a scheme\\nto defraud the Commonwealth of Pennsylvania and the City\\nof Philadelphia of money in costs and fees.” App. 355 (Plea\\nAgreement ¶ 9(b)(4)). So they now appeal the District\\nCourt’s order denying the motion to dismiss, asserting that\\nthe indictment failed to allege violations of mail fraud and\\nwire fraud.\\n\\n “To be sufficient, an indictment must allege that the\\ndefendant performed acts which, if proven, constitute a\\nviolation of the law that he is charged with violating.” United\\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\\nassume in our review that the allegations in the indictment are\\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\\n2004). “The question of whether the . . . indictments alleged\\nfacts that are within the ambit of the mail fraud statute is a\\nquestion of statutory interpretation subject to plenary review.”\\nId. at 590 n.10.\\n\\n To indict on mail or wire fraud, the Government must\\nallege that defendants “devised or intend[ed] to devise any\\nscheme or artifice to defraud, or for obtaining money or\\nproperty by means of false or fraudulent pretenses,\\nrepresentations, or promises” and used mail or wire to effect\\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\\nthe Government failed to allege that the scheme to commit\\nwire and mail fraud had an objective of “obtaining money or\\nproperty.” 9\\n\\n9\\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\\nthe term “money” has the same meaning. The same is true\\nfor the term “property.” Carpenter v. United States, 484 U.S.\\n19, 25 n. 6 (1987).\\n\\n\\n\\n\\n 10\\n\\f The District Court ruled that the indictment\\nsufficiently alleged that the scheme “involved defrauding the\\nCommonwealth and the City of money.” App. 20. It noted,\\namong others, allegations that:\\n\\n The conspirators used the\\n Philadelphia Traffic Court\\n (“Traffic Court”) to give\\n preferential treatment to certain\\n ticketholders, most commonly by\\n “fixing” tickets for those with\\n whom they were politically and\\n socially connected. By doing so,\\n the conspirators defrauded the\\n Commonwealth of Pennsylvania\\n and the City of Philadelphia of\\n funds to which the\\n Commonwealth and the City were\\n entitled.\\n\\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\\nreferred to the following.\\n\\n In acceding to requests for\\n “consideration,” defendants were\\n depriving the City of Philadelphia\\n and the Commonwealth of\\n Pennsylvania of money which\\n would have been properly due as\\n fines and costs.\\n\\n\\n\\n\\n 11\\n\\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\\nHighlighting the references to “funds” and “money,” and that\\nthe monetary amounts of the fines are specifically pleaded,\\nthe District Court cited to a case from the Court of Appeals\\nfor the Eighth Circuit which concluded succinctly that\\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\\nCir. 1990)). The District Court was satisfied that the\\nindictment alleged enough.\\n\\n “Money, of course, is a form of property.” Reiter v.\\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\\nHird argue that the mere mention of money in an indictment\\nis not enough. They point to a string of Supreme Court and\\nCourt of Appeals decisions analyzing Section 1341 and\\nSection 1343 which reinforce the point that crimes of mail\\nfraud and wire fraud are “limited in scope to the protection of\\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\\n(1987). 10 The Supreme Court said that “[a]ny benefit which\\nthe government derives from the [mail fraud] statute must be\\nlimited to the Government’s interests as a property holder.”\\nId. at 359 n.8 (emphasis added). Appellants are convinced\\nthat money in the form of traffic fines and costs cannot be\\nregarded as the Government’s “property” for purposes of mail\\nor wire fraud, and they identify two decisions as particularly\\nsupportive of their position: Cleveland v. United States, 531\\n\\n10\\n The District Court cited to a number of cases that came\\nafter McNally: Carpenter v. United States, 484 U.S. 19\\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\\nPasquantino v. United States, 544 U.S. 349 (2005).\\n\\n\\n\\n\\n 12\\n\\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\\nCir. 1994).\\n\\n The Court in Cleveland examined the mail fraud\\nconvictions of individuals who received a state video poker\\nlicense by submitting a license application that withheld\\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\\nnoted that the video poker licenses were part of a state\\nprogram that was “purely regulatory.” Id. at 22 (citation\\nomitted). 12 It ruled that licenses are a “paradigmatic\\nexercise[] of the States’ traditional police powers.” Id. at 23.\\nThe Court went on to say that the state’s regulatory powers\\ninvolving “intangible rights of allocation, exclusion, and\\ncontrol” (which are embodied in a license) are not interests\\nthat traditionally have been recognized as property. Id.\\nTherefore, even though appellants may have obtained the\\nlicense through deception, this was not mail fraud because the\\nlicense—at least while still in the hands of the state—was not\\n\\n\\n\\n11\\n The licenses were part of a regulatory scheme that had as\\nits purpose to increase public confidence in the honesty of\\ngaming activities that are free of criminal involvement.\\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\\n27:306(A)(1) (2000) (repealed 2012)).\\n12\\n The Court rebuffed the Government’s attempts to analogize\\nlicenses to other forms of property like patents and franchise\\nrights. As for likening licenses to franchise rights, the Court\\nobserved that the Government did not enter the video poker\\nbusiness, but rather decided to “permit, regulate, and tax\\nprivate operators of the games.” Id. at 24.\\n\\n\\n\\n\\n 13\\n\\fproperty. Id. at 26-27. It was a purely administrative tool\\nused to achieve regulatory objectives. Id. at 21.\\n\\n The state responded to the Court’s concerns by\\nagreeing that the licenses served a regulatory purpose, but it\\ndirected attention to the revenue it received from fees\\ncollected for license applications and renewals, as well as\\ndevice fees. Id. at 21-22. It argued that this revenue is a\\nproperty interest. Id. The Court was not convinced:\\n\\n Tellingly, as to the character of\\n Louisiana’s stake in its video\\n poker licenses, the Government\\n nowhere alleges that Cleveland\\n defrauded the State of any money\\n to which the State was entitled by\\n law. Indeed, there is no dispute\\n that TSG paid the State of\\n Louisiana its proper share of\\n revenue, which totaled more than\\n $1.2 million, between 1993 and\\n 1995. If Cleveland defrauded the\\n State of “property,” the nature of\\n that property cannot be economic.\\n\\nId. at 22 (emphasis added). It concluded that “[e]ven when\\ntied to an expected stream of revenue, the State’s right of\\ncontrol does not create a property interest any more than a\\nlaw licensing liquor sales in a State that levies a sales tax on\\n\\n\\n\\n\\n 14\\n\\fliquor.” Id. at 23. 13 The money collected from application\\nand processing fees was an integral part of the state\\nregulatory program and it did not create any property interest.\\nSee id.\\n\\n The purpose of the Pennsylvania Motor Vehicle Code\\nis to “promote the safety of persons and property within the\\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\\nMoreover, issuing traffic tickets is a crucial element in the\\nenforcement of the Motor Vehicle Code: it is a quintessential\\nexercise of state police power. Alfano and Hird conclude,\\nmuch like Cleveland, that no property interest could arise\\nfrom revenue generated from the state’s exercise of its police\\npower in the form of a traffic-ticket fine. They see nothing\\nbut a regulatory program here. But this ignores crucial\\naspects of the case before us that make it different.\\n\\n Simply stated, fees charged to obtain a license cannot\\nbe equated with fines and costs that result from a traffic\\nticket. The license fee was imposed, adjusted, and collected\\nsolely by the state’s exercise of its regulatory authority. In\\ncontrast, here the state’s police power is exercised when a\\ncitation is issued, but this ticket merely establishes the\\nsummary violation with which the person is charged. Once a\\nperson has been charged, it is judicial power (not the state’s\\npolice power) that is exercised to determine whether the\\n\\n\\n\\n\\n13\\n Cleveland also held that Government-issued licenses have\\nno intrinsic economic worth before they are given to\\napplicants. Id. at 23.\\n\\n\\n\\n\\n 15\\n\\fperson is guilty and, if guilty, to impose the fine and costs. 14\\nThese fines and costs, although specified by the Motor\\nVehicle Code, cannot be cabined as a product of the state’s\\nregulatory authority. They are part and parcel of the\\njudgment of the court. With this in mind, it is significant that\\nthe indictment does not focus on how the citations were\\nissued (which would implicate police power), but rather\\nalleges that the judicial process was rigged to produce only\\njudgments that imposed lower fines—or most often—no fines\\nand costs at all. 15\\n\\n But this raises a further question: can a criminal\\njudgment held by the government ever be “property?” The\\nCourt in Cleveland offered a critique in its analysis of a\\n\\n14\\n The Traffic Court was not an administrative tribunal.\\nRather, it was part of the First Judicial District of\\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\\nnote 6 and accompanying text.\\n15\\n On this point, it is noteworthy that the Supreme Court also\\nsaid the following: “We resist . . . [any invitation] to approve\\na sweeping expansion of federal criminal jurisdiction in the\\nabsence of a clear statement by Congress. . . . ‘[U]nless\\nCongress conveys its purpose clearly, it will not be deemed to\\nhave significantly changed the federal-state balance’ in the\\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\\nAs we discuss later, the legal tradition of understanding\\njudgments as property is long-established. Consequently, the\\nconcern about expanding the reach of federal fraud statutes to\\nnew classes of property that was present in the deliberation of\\nstate licenses in Cleveland is not at issue here.\\n\\n\\n\\n\\n 16\\n\\fdifferent issue (whether licenses were analogous to patents)\\nthat is apropos to answering this question.\\n\\n [W]hile a patent holder may sell\\n her patent, see 35 U.S.C. § 261 . .\\n . “patents shall have the attributes\\n of personal property” . . . the State\\n may not sell its licensing\\n authority. Instead of a patent\\n holder’s interest in an unlicensed\\n patent, the better analogy is to the\\n Federal Government’s interest in\\n an unissued patent. That interest,\\n like the State’s interest in\\n licensing video poker operations,\\n surely implicates the\\n Government’s role as sovereign,\\n not as property holder.\\n\\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\\ncriminal penalties that “implicate[] the Government’s role as\\nsovereign.” Id. at 24. Judgments ordering traffic fines and\\ncosts cannot be sold and, in the logic of Cleveland, would\\nseem then to have no intrinsic economic value. Indeed, the\\npenal (non-economic) nature of the fine is undeniable because\\nthe failure to pay a fine can result in the imposition of\\nsentences of greater consequence, including imprisonment.\\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\\nword. As we will discuss below, a Supreme Court opinion\\nissued five years later, Pasquantino v. United States, 544 U.S.\\n349 (2005), forecloses the defendants’ argument.\\n\\n\\n\\n\\n 17\\n\\f Finally, we note a dissimilarity between this case and\\nCleveland, highlighted by the District Court, on the\\nsignificance of the monetary interest that the Government\\nassociates with the fraud. The Cleveland Court regarded the\\nlicensing fees as integral to the regulatory effort and collateral\\nto the matter at hand. The indictment there centered on the\\nscheme to obtain liceneses, and did not even raise the\\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\\ncharged with the fraud paid all the appropriate fees; there was\\nno evidence that the government suffered any economic\\ndetriment. Id.\\n\\n In contrast, the indictment here explicitly states that\\nthe scheme deprived the City and the Commonwealth of\\nmoney, and it describes the object of the scheme as obviating\\njudgments of guilt that imposed the fines and costs. Unlike\\nCleveland, the fines and costs play a central role in the\\nscheme as alleged.\\n\\n Alfano and Hird next focus on our decision in Henry\\nto argue that the Government cannot claim to have a property\\nright because the Government never had a legal claim to the\\nfines and costs at any point in the scheme. In Henry, we\\nexamined convictions for wire fraud arising from a\\ncompetitive bidding process among banks to receive deposits\\nof a public agency’s bridge tolls. Henry v. United States, 29\\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\\nwere convicted of mail fraud for giving one bank confidential\\ninformation about bids from other banks. Id. at 113. We\\nidentified several problems, 16 but Alfano and Hird highlight\\n\\n16\\n The Supreme Court had already made clear that “a\\ngovernment official’s breach of his or her obligations to the\\n\\n\\n\\n\\n 18\\n\\four observation in Henry that the object of the mail and wire\\nfraud must be something to which the victim could claim a\\nright of entitlement. Id. at 115 (“a grant of a right of\\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\\nwe noted that a bank’s property right to the tolls would attach\\nonly after the funds were deposited. Id. at 114. So the banks\\nthat lost the bidding process never had a basis to claim any\\nlegally recognized entitlement to the toll deposits. 18 Id. at\\n115. A fraud claim cannot rest on the bidders being cheated\\nout of an opportunity to receive the deposits. For these\\nreasons, we concluded that the indictment did not allege a\\nscheme to obtain fraudulently someone’s “property.” Id. at\\n116.\\n\\n Here, the Government alleged that the defendants\\n“were depriving . . . Philadelphia and . . . Pennsylvania of\\nmoney which would have been properly due as fines and\\ncosts” by making it possible for certain well-connected\\nindividuals to avoid a judgment of guilt that imposed an\\nobligation to pay appropriate statutory fines. App. 197\\n\\n\\npublic or an employee’s breach of his or her obligations to an\\nemployer” did not fall within the scope of Section 1343.\\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\\n17\\n To assess whether a particular claim is a legal entitlement,\\n“we look to whether the law traditionally has recognized and\\nenforced [the entitlement] as a property right.” Henry, 29\\nF.3d at 115.\\n18\\n They were, no doubt, robbed of a fair process, but we could\\nnot identify any legal tradition that recognized this\\ndeprivation as a property right. Id. at 115.\\n\\n\\n\\n\\n 19\\n\\f(Indictment ¶ 38). But Appellants stress that, like the\\ndeposits in Henry, the indictment here alleged an entitlement\\nthat does not yet exist because a person must be adjudicated\\n(or plead) guilty before they must pay any fines or costs.\\nNone of the cases directly associated with Alfano and Hird\\nresulted in a guilty judgment. As a result, they argue, the\\nGovernment cannot claim here that it was cheated of an\\nentitlement, because they were only fines and costs that the\\npeople might have owed if they had been found guilty.\\n\\n The District Court said it well. Accepting this\\nargument “would permit the alleged conspirators” to take\\nadvantage of their “unique position” in this case “to enter into\\na scheme to commit fraud and then hide behind the argument\\nthat the success of their fraud precludes prosecution under the\\n‘money or property interest’ requirement of the mail and wire\\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\\nAppellants cannot rest on the very object of their scheme (to\\nwork on behalf of favored individuals to obviate judgments of\\nguilt and the imposition of fines and costs) as the basis to\\nclaim that there is no fraud. Indeed, the not-guilty judgments\\nthat Alfano and Hird worked to obtain through the\\nextrajudicial system were alleged in the indictment as\\nevidence of the scheme itself.\\n\\n Even if some of the cases in the extra-judicial system\\nwould have been judged not guilty in a real adjudication it is\\n(as the District Court correctly noted) the intent of the\\nscheme, not the successful execution of it, that is the basis for\\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\\n(1999) (In the criminal context, the court focuses on the\\nobjective of the scheme rather than its actual outcome; what\\noperatives intended to do, not whether they were successful in\\n\\n\\n\\n\\n 20\\n\\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\\n(“Civilly of course the [mail fraud statute]would fail without\\nproof of damage, but that has no application to criminal\\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\\ngenerally alleges not just that Appellants operated a system\\nthat operated outside the bounds of Traffic Court procedures,\\nbut that it did so for the purpose of obviating judgments of\\nguilt imposing fines and costs in those selected cases. See,\\ne.g., supra note 8. Moreover, we note that in one case not\\ndirectly involving either Alfano or Hird, the indictment\\nalleged that fines and costs were not just obviated, but were\\nactually erased by an alleged co-conspirator traffic court\\njudge who ignored the conviction, backdated a continuance,\\nand “adjudicated” the person not-guilty. App. 228-29\\n(Indictment ¶¶ 108-113). This episode serves to highlight\\nthat the entire scheme was centered on keeping (or taking)\\njudgments out of the hands of the Government to prevent the\\nimposition of fines and costs. As a result, Appellants’\\nreliance on our justice system’s presumption of innocence as\\na basis to argue against the existence of a governmental\\nproperty interest is a red herring that is properly disregarded\\nhere.\\n\\n Accordingly, we conclude that the indictment’s\\nallegation that the scheme had an objective of depriving\\n“Philadelphia and . . . Pennsylvania of money which would\\nhave been properly due as fines and costs” is not undermined\\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\\n(emphasis added)).\\n\\n Alfano and Hird next highlight that, in Henry, our\\nproperty interest analysis centered on “whether the law\\ntraditionally has recognized and enforced [the entitlement in\\n\\n\\n\\n\\n 21\\n\\fquestion] as a property right.” 29 F.3d at 115. Appellants\\nassert that traffic fines and costs typically have not been\\nconsidered economic property and are unsupported by any\\nlegal tradition sufficient to ground charges of wire and mail\\nfraud. As we have already noted we disagree with any\\nconclusion that the fines and costs at issue have no intrinsic\\neconomic value. But we turn to another decision of the\\nSupreme Court that came after Cleveland to address squarely\\nwhether jurisprudence supports our conclusion.\\n\\n In 2005 the Supreme Court reviewed convictions\\narising from a scheme to smuggle large quantities of liquor\\nfrom the United States into Canada, evading Canadian taxes.\\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\\nThe Court noted that the right to be paid has been routinely\\nrecognized as property, id. at 355–56, 19 observing that there is\\nan equivalence between “money in hand and money legally\\ndue,” id. at 356. Affirming the conviction, the Court said:\\n“Had petitioners complied with this legal obligation, they\\nwould have paid money to Canada. Petitioners’ tax evasion\\ndeprived Canada of that money, inflicting an economic injury\\nno less than had they embezzled funds from the Canadian\\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\\nscheme was to deprive Canada of money legally due, and\\ntheir scheme thereby had as its object the deprivation of\\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\\ntickets (or more precisely, judgments arising from them) are\\nconsidered an “entitlement to collect money from individuals,\\n\\n\\n19\\n The Court cited 3 W. Blackstone, Commentaries on the\\nLaws of England 153–155 (1768), which classified the right\\nto sue on a debt as personal property.\\n\\n\\n\\n\\n 22\\n\\fthe possession of which is ‘something of value.’” 544 U.S. at\\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\\na scheme to obviate judgments imposing fines, effectively\\npreventing the government from holding and collecting on\\nsuch judgments imposes an economic injury that is the\\nequivalent of unlawfully taking money from fines paid out of\\nthe Government’s accounts. See id. at 358.\\n\\n Alfano and Hird focus, finally, on the role that a\\njudge’s discretion plays in the adjudication of a case,\\nasserting that the uncertainty this creates about outcomes in\\nany given case undermines any argument that a judgment in a\\nTraffic Court case can be claimed as an entitlement to\\nproperty. To the extent that this merely rephrases the issue of\\nguilt or innocence on particular charges, we have already\\n\\n20\\n We also note that Pennsylvania law permits the government\\nto remedy the nonpayment of fines and costs as an unpaid\\ndebt through civil process, enabling the government to\\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\\n(“Nothing in this rule [concerning criminal fines] is intended\\nto abridge any rights the Commonwealth may have in a civil\\nproceeding to collect a fine or costs.”). Because of this, a\\nseparate legal tradition is implicated that recognizes the\\njudgment itself as property. See, e.g., Armada (Singapore)\\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\\n(7th Cir. 2018). This long, stable legal tradition of\\nrecognizing civil judgments for money as property supports\\nthe conclusion that the fines arising from judgments in traffic\\ncourt cannot be regarded merely as implicating the act of a\\nsovereign imposing a criminal penalty. They can be collected\\nby civil process as a debt and are, thus, a property interest.\\n\\n\\n\\n\\n 23\\n\\faddressed it above. To the degree that it refers to a judge’s\\ndiscretion in sentencing, as the District Court noted, there is\\nno such discretion here. 21 The Motor Vehicle Code imposes\\nfines and costs for each violation, eliminating any judicial\\ndiscretion in this regard.\\n\\n D.\\n\\n All of this leads us to conclude that the District Court\\ndid not err by denying the motion to dismiss. We conclude\\nthat, as alleged, this scheme had the objective of preventing\\nthe City of Philadelphia and the Commonwealth of\\nPennsylvania from possessing a lawful entitlement to collect\\nmoney in the form of fines and costs—a property interest—\\nfrom individuals who Alfano and Hird assisted. We will thus\\naffirm the convictions of Appellants Alfano and Hird.\\n\\n III.\\n\\n Appellants Tynes, Lowry, and Mulgrew\\n\\n A.\\n\\n\\n\\n\\n21\\n We question, in general, the relevance of an entity’s\\nauthority to relinquish a just entitlement or to forbear an\\nobligation that an entitlement imposes upon another, as a\\nbasis to call into doubt the legitimacy of, or the very existence\\nof the entitlement. But see United States v. Mariani, 90 F.\\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\\nand penalties “may be too speculative to constitute a valid\\nproperty interest.”) (internal citation omitted).\\n\\n\\n\\n\\n 24\\n\\f In 2011, the United States Attorney presented to the\\nGrand Jury evidence arising from the Federal Bureau of\\nInvestigation’s inquiry into the Traffic Court. Appellants\\nLowry, Mulgrew, and Tynes testified and the Government\\nbrought perjury charges against them for statements they\\nmade to the Grand Jury. After Hird and Alfano pleaded\\nguilty, the rest of the Appellants went to trial. The jury\\nacquitted Lowry, Mulgrew, and Tynes of all counts against\\nthem on wire fraud, mail fraud, and conspiracy. But it found\\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\\nchallenge their convictions by raising similar legal arguments\\nabout the sufficiency of the evidence.\\n As with all challenges to the sufficiency of the\\nevidence, we use a highly deferential standard of review. See\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\\nCir. 2013) (en banc). We examine the record in a light most\\nfavorable to the prosecution, and will not disturb the verdict if\\n“any rational trier of fact could have found the essential\\nelements of the crime beyond a reasonable doubt.” United\\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\\n(1979)). Tynes, Lowry, and Mulgrew argue that the\\nquestions asked of them at trial were fatally vague and/or that\\ntheir answers were truthful. As a result, they contend that\\nthese questions and answers are an inadequate basis for a\\nperjury conviction.\\n\\n A conviction for perjury before a grand jury requires\\nthe Government to prove that the defendant took an oath\\nbefore the grand jury and then knowingly made a “false\\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\\n(in the context of a sentencing enhancement for perjury) that\\nsometimes “confusion, mistake, or faulty memory” results in\\n\\n\\n\\n\\n 25\\n\\finaccuracies that cannot be categorized as a “willful attempt\\nto obstruct justice” under perjury statutes. United States v.\\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\\nSentencing Comm’n 2003). So we do understand that\\n“[p]recise questioning is imperative as a predicate for the\\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\\n362 (1973).\\n\\n Precision, however, is assessed in context. An\\nexaminer’s line of questioning should, at a minimum,\\nestablish the factual basis grounding an accusation that an\\nanswer to a particular question is false. Miller, 527 F.3d at\\n78. So a perjury conviction is supported by the record “when\\nthe defendant’s testimony ‘can reasonably be inferred to be\\nknowingly untruthful and intentionally misleading, even\\nthough the specific question to which the response is given\\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\\n157 F.3d 1042, 1043 (6th Cir. 1998)).\\n\\n Challenges to the clarity of a question are typically left\\nto the jury, which has the responsibility of determining\\nwhether the defendant understood the question to be\\nconfusing or subject to many interpretations. United States v.\\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\\nwith our standard of review, we will not disturb a jury’s\\ndetermination that a response under oath constitutes perjury\\nunless “it is ‘entirely unreasonable to expect that the\\ndefendant understood the question posed to him.’” Serafini,\\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\\n\\n\\n\\n\\n 26\\n\\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\\nwe review every aspect of the record pertinent to both the\\nquestion and answer to reach a conclusion about whether, in\\ncontext, the witness understood the question well enough to\\ngive an answer that he or she knew to be false. See Miller,\\n527 F.3d at 78. Our review, however, is focused on glaring\\ninstances of vagueness or double-speak by the examiner at the\\ntime of questioning (rather than artful post-hoc interpretations\\nof the questions) that—by the lights of any reasonable fact-\\nfinder—would mislead or confuse a witness into making a\\nresponse that later becomes the basis of a perjury conviction.\\nQuestions that breach this threshold are “fundamentally\\nambiguous” and cannot legitimately ground a perjury\\nconviction. Id. at 77. 23\\n\\n\\n22\\n The Court of Appeals for the Second Circuit underscored\\nthe high bar this establishes for appellants by noting that a\\nfundamentally ambiguous question is “not a phrase with a\\nmeaning about which men of ordinary intellect could agree,\\nnor one which could be used with mutual understanding by a\\nquestioner and answerer unless it were defined at the time it\\nwere sought and offered as testimony.” United States v.\\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\\n232 F.2d. 334 (D.C. Cir. 1955)).\\n23\\n The rule of fundamental ambiguity is intended to\\n“preclude convictions that are grounded on little more than\\nsurmise or conjecture, and . . . prevent witnesses . . . from\\nunfairly bearing the risks associated with the inadequacies of\\ntheir examiners.” Ryan, 828 F.2d at 1015.\\n\\n\\n\\n\\n 27\\n\\f That is the law applicable to the claims raised by\\nTynes, Lowry and Mulgrew. But, because our review is fact-\\ndependent, and because each raises some unique issues, we\\nwill address each of their claims individually. 24\\n B.\\n\\n\\n\\n\\n24\\n Adopting the arguments made by Alfano and Hird,\\nAppellants Lowry, Mulgrew and Tynes assert that the\\nGovernment improperly charged them with conspiracy, wire\\nfraud, and mail fraud. Therefore, they assert, their joint trial\\non these counts of the indictment prejudiced the jury’s\\ndeliberation on the charges of perjury. They claim such\\nevidence would have been excluded under Federal Rule of\\nEvidence. 403. They also contend that, without a charge of\\nconspiracy, the joinder of their cases would have been\\nimpermissible under Federal Rule of Criminal Evidence 8(b)\\nor, at the very least, severance of their cases would have been\\nwarranted under Federal Rule of Criminal Procedure 14(a).\\nCertainly, where there is evidence of prejudice resulting from\\n“spillover” evidence from counts that should have been\\ndismissed, reversal is warranted. See United States v. Wright,\\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\\nconcluded that the District Court did not err by denying the\\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\\ndismiss the conspiracy, wire fraud and mail fraud counts of\\nthe indictment. Thus, Appellants’ spillover argument has\\nbeen nullified. Likewise, Appellants have no basis to claim\\nthat the Court unfairly prejudiced them by not granting\\nseparate trials.\\n\\n\\n\\n\\n 28\\n\\f Appellant Tynes 25\\n\\n Appellant Tynes claims her convictions for perjury at\\nCount 71 and Count 72 lack sufficient evidence because she\\nwas responding to questions that were fundamentally\\nambiguous. The perjury charged at Count 71 arises from the\\nfollowing exchange.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n\\n\\n25\\n Tynes filed a separate motion to dismiss. App. 291-99.\\nThe record also contains Tynes’ proposed order to join\\nSullivan’s motion to dismiss. App. 290. However, Tynes’\\nmotion contains no such request. Moreover, the\\nGovernment’s response to the motions notes that Lowry and\\nMulgrew moved to join (without argument), and makes no\\nmention of Tynes. The District Court’s ruling on Tynes’\\nmotion to dismiss relates only to the arguments she made\\nseparately in her brief. As a result, we cannot consider\\nTynes’ arguments on appeal that relate to those raised in\\nSullivan’s motion. Moreover, since she failed to raise any of\\nthe arguments she made in her separate motion to dismiss,\\nthese arguments are waived. With that said, we will affirm\\nthe District Court’s ruling on the Motion raised by Sullivan\\nand joined by the five Appellants. Therefore, we need not\\naddress Tynes’ assertion that the District Court’s mishandled\\nher joinder motion because it does not prejudice the outcome\\nof her appeal.\\n\\n\\n\\n\\n 29\\n\\f favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously, and the\\n cards fall where they may.\\n\\nApp. 255, 5720. 26 Tynes contends that the Government\\npursued a novel theory here (applying federal fraud statutes to\\nallegations of ticket fixing) and used the vague term\\n“favorable treatment” to gloss over its uncertainty about what,\\nultimately, would constitute an illegal act. She points out that\\nthe term had not been used before in reference to this case\\nand that the Government offered no explanation or definition\\nof the term to alert Tynes to the intent of the question.\\n\\n Also, from Tynes’ perspective, every litigant\\nappearing before a court seeks an outcome that is favorable,\\nthus making “favorable treatment” a term that essentially\\nreferred to “how litigation works.” She claims that its use\\namounted to a fishing expedition designed to capture unfairly\\n\\n26\\n We cite to the testimony quoted in the indictment and the\\nGrand Jury that was used at trial. We note that there are some\\ntypographical inconsistencies between these sources and in\\nthose instances we have quoted the Grand Jury testimony.\\n\\n\\n\\n\\n 30\\n\\fthe entirety of her conduct in the courtroom. She warns that\\nthis is precisely the type of “open-ended construction” in\\nquestioning that we found unacceptable in Serafini. 167 F.3d\\nat 822.\\n\\n Tynes makes a related argument against her perjury\\nconviction for Count 72. That conviction is based on this\\nexchange.\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 257, 5722. She maintains that the word “request” was\\npresented to the jury as a follow-on to the question grounding\\nCount 71, requiring a person to link the term “favorable\\ntreatment” and the word “request” to make sense of it. She\\nargues that the Government took advantage of the ambiguity\\nof “favorable treatment,” forcing the jury to speculate that\\nTynes interpreted “request” as “favorable treatment.” This\\nreliance on “sequential referents” is, from her perspective,\\nexactly what we criticized in Serafini. 167 F.3d at 821. But\\nshe misconstrues our holding.\\n\\n In Serafini, the surrounding questions focused on a\\ndifferent topic. This bolstered appellant’s argument in that\\ncase that the question on which the perjury conviction rested\\nwas fundamentally ambiguous. Id. The appellant said the\\nmultiplicity of topics in surrounding questions caused the jury\\nto speculate improperly on how he understood the question at\\nissue. We said: “The meaning of individual questions and\\nanswers is not determined by ‘lifting a statement . . . out of its\\nimmediate context,’ when it is that very context which fixes\\n\\n\\n\\n\\n 31\\n\\fthe meaning of the question.” Serafini, 167 F.3d at 821\\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\\n1978)). In the case of Serafini, the context made the\\nconfusing nature of the question apparent. The various topics\\nin surrounding questions created sufficient ambiguity to\\nundermine the conviction. Id.\\n\\n Here, however, even though the terms used by the\\nexaminer changed, we conclude that the line of questioning—\\nincluding both questions that ground Count 71 and 72—have\\nan obvious, consistent focus.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously and the\\n cards fall where they\\n may. Most of the time . . .\\n the people in my Court\\n plea bargain. They know\\n that most of the time,\\n\\n\\n\\n\\n 32\\n\\fninety percent of the time,\\nsay 90 percent, I go with\\nthe police officer’s\\nrecommendation. . . .\\n\\nQ. So, in all those years\\nno one has ever asked you\\nto find somebody not\\nguilty--\\n\\nA. No.\\n\\nQ. --or to find a lesser\\nviolation; find a lesser fine;\\nanything along those lines?\\n\\nA. No. I will say to\\npeople go to court, go to\\ntrial and see what\\nhappens. . . .\\n\\nQ. Ward leaders,\\npoliticians has anyone\\ncalled you and said I\\nhave Johnny Jones coming\\nup next week and I\\nwould appreciate it if -- if\\nyou would look\\nfavorably on him when he\\ncomes through? Has\\nanything like that ever\\nhappened?\\n\\n\\n\\n\\n 33\\n\\f A. Throughout the\\n years ward leaders and\\n people have called all the\\n time and asked me\\n questions. The only thing I\\n will say to them is they\\n need to go to court. If you\\n think it’s a problem, they\\n need to hire a lawyer, or\\n make sure you bring all\\n your evidence to court. If\\n it’s something like\\n inspection, make sure you\\n bring your -- papers and\\n things like that. That’s\\n what I would tell them to\\n do. I give advice that\\n way. I don’t know if that’s\\n wrong or not, but I do.\\n\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 528-29, 530; 5720-22. This broader context would give\\nany reasonable fact-finder more than enough basis to\\nconclude that the witness knew the point of reference for both\\nthe term “favorable treatment” and “request” was ticket\\nfixing. In fact, Tynes is asking us to do precisely the thing we\\ncriticized in Serafini, to lift a phrase or statement out of its\\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\\nus that the question harbors any fatal ambiguity.\\n\\n\\n\\n\\n 34\\n\\f Tynes next contends that her responses to questions\\ngrounding Count 71 and Count 72 cannot support convictions\\nfor perjury because they were literally true. Of course,\\nperjury arises only from making knowingly false material\\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\\nanswers an ambiguous question with a non-responsive answer\\nthat the witness believes is true—even if the answer is\\nmisleading—does not commit perjury. See Bronston, 409\\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\\n1416 (3d Cir. 1994).\\n Tynes argues that, because she regarded the question\\nabout favorable treatment as vague, she interpreted it as\\nasking whether she accepted any bribes in exchange for a\\njudgment of not guilty or a reduced punishment. Her\\nresponse of “no” (grounding Count 71) is literally true—she\\nsays—because there is no evidence that she accepted any\\nbribes in return for giving preferential outcomes in the\\nadjudication of some individuals who were cited for breaking\\nthe law. Under this theory, the same argument can also\\nnegate the charges at Count 72 since she says she did not\\naccept any “requests” (bribes) in exchange for preferential\\ntreatment.\\n\\n Although the jury is permitted reasonable inferences\\ndrawn from the record about the witness’ understanding of\\nthe truth or falsity of the answer, it is not (as we noted above)\\npermitted to reach conclusions based merely on speculation\\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\\nassertion of literal truth is undermined because the trial record\\nsupports no reasonable inference that the Government was\\nasking her about matters outside of the alleged bribes, nor\\n\\n\\n\\n\\n 35\\n\\fdoes it provide any reason why Tynes would interpret the\\nquestion in this way.\\n\\n Finally, Tynes contends that the evidence was not\\nsufficient to support her conviction. However, the jury heard\\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\\nthat she received from personal assistants of other judges\\nthree to four cards per week requesting consideration. Each\\ncard had the name of a person who was appearing before\\nTynes on that day. She passed these to Tynes’ court officer,\\nwho was present during the proceedings. App. 4593-95.\\nTynes also instructed Warren to give similar cards to the staff\\nof other judges. App. 4598. Warren knew to act discreetly\\nwhen she was transferring the cards. App. 4599. The jury\\nalso heard testimony from those who actually received\\nconsideration from Tynes. For example, Timothy Blong was\\ncited for reckless driving and driving without a license. He\\nadmitted in testimony that he did not have a license when he\\nwas cited. App. 3150. He also testified that he requested\\nconsideration through a Traffic Court employee (Danielle\\nCzerniakowski, who worked as a personal assistant to a\\nTraffic Court judge) with whom he was acquainted. When he\\nappeared in court, he was simply told that his case was\\ndismissed. He did not have to say anything, App. 3159-60.\\nBlong testified he was told his case was dismissed because\\nthe police officer did not appear (App. 3160-61), but the\\ngovernment produced evidence that an officer was present.\\nApp. 3193-96. The Government also showed that Tynes was\\nthe presiding judge in Blong’s case. App. 3193. Richard\\nCarrigan—who admitted in testimony that he drove through a\\nred light—described a similar experience in which, after\\nrequesting favorable treatment through Judge Lowry’s\\npersonal assistant, Kevin O’Donnell, his case was dismissed\\n\\n\\n\\n\\n 36\\n\\fby Judge Tynes without ever having to say a word. App.\\n3178-82.\\n\\n Tynes does not challenge any of this in her appeal.\\nInstead she focuses on the weight of other evidence and\\nperceived gaps in testimony. We conclude that all of this\\nprovides more than a sufficient basis to support a reasonable\\njury’s conclusion that Tynes did “give favorable treatment on\\na case,” and did “take[] action on a request.” App. 528-30.\\n\\n For all of these reasons, we will affirm the judgment of\\nconviction on perjury as to Appellant Tynes.\\n C.\\n\\n Appellant Lowry 27\\n\\n Like Tynes, Appellant Lowry advances arguments of\\nfundamental ambiguity and literal truth. His perjury\\nconviction centered on one question and answer.\\n\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n\\n27\\n Lowry was charged with perjury in Count 69 of the\\nindictment.\\n\\n\\n\\n\\n 37\\n\\fApp. 489. Lowry attacks the Government’s use of the term\\n“special favors” as one with many potential meanings.\\nHowever, as we noted above in our reference to Serafini, we\\nreject arguments that lift individual questions or answers—or\\nindividual phrases embedded in either—from the context of\\nsurrounding questions that help fix their meaning. Serafini,\\n167 F.3d at 821. The larger context for the question asked of\\nLowry is as follows.\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. Well, I know it\\n appears that way; and it’s\\n hard for me to prove to\\n you . . .\\n\\n Q. I’m just asking,\\n your testimony is you don’t\\n give out special favors, is\\n that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n Q. You treat everybody\\n fairly?\\n\\n A. I’m a lenient judge.\\n I will admit to that.\\n\\n\\n\\n\\n 38\\n\\f Q. You treat everybody\\n fairly?\\n\\n A. Yes, I do.\\n\\n Q. And these notices\\n that you get from your\\n personal or from other\\n people, they don’t affect\\n you in any way; is that\\n right?\\n\\n A. Virtually no effect\\n at all.\\n\\n\\nApp. 489-90.\\n\\n Lowry’s assertion that the phrase “special favors” is\\nsubject to many interpretations is unconvincing. We note two\\nthings. First, the line of questioning reasonably supports a\\nconclusion that this inquiry referenced conduct associated\\nwith allegations of ticket fixing. Second, Lowry answered as\\nif his understanding of the question was consistent with this\\ninterpretation. He said that he was aware it may “appear” that\\nhe gave special favors. He also defended himself by saying\\nthat such requests did not affect his conduct in the courtroom\\nat all. If—as he says—he understood “special favors” to\\nmean fair treatment, his answer makes no sense.\\n\\n Lowry next claims that, since the question was\\nstructured to elicit a negative response, his answer cannot be\\n\\n\\n\\n\\n 39\\n\\fused as the basis of a perjury charge. Relatedly, he contends\\nthat the question was merely a summation of an answer that\\nhe gave just before this question. In essence he argues that\\nthis was a leading question. We have concluded, in the\\ncontext of a trial, that the propriety of leading questions in\\ndirect examinations is a matter left to the sound discretion of\\nthe trial judge. See United States v. Montgomery, 126 F.2d\\n151, 153 (3d Cir. 1942). We extend the same deference here\\nto the District Court’s decision to admit this portion of the\\nGrand Jury transcript. We do not regard the question as\\nfundamentally unfair or unclear, or something outside the\\nnorm of questions typically employed on direct examination.\\nFor these reasons, we conclude that the District Court did not\\nabuse its discretion here.\\n\\n Alternatively, Lowry argues that—if the term is\\nunderstood to reference fixing tickets—there is no evidence\\nto contradict his response that requests for special favors did\\nnot impact any of his adjudications. We do not agree. The\\nrecord contains the following testimony.\\n\\n Kevin O’Donnell, who was Lowry’s personal\\nassistant, testified about Lowry’s involvement with requesting\\nand giving consideration. He said that Lowry made four to\\nfive requests each month for consideration and that\\nO’Donnell transmitted them to the personal assistants of other\\nTraffic Court judges. App. 1854. Likewise, he said other\\njudges transmitted requests for consideration to Lowry\\nthrough their personal assistants. App. 1812-13. Appellant\\nHird and various politicians also made requests of Lowry for\\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\\nwould give the requests to Lowry on the day scheduled for\\nhearing on the citation. App. 1818-19. The requests were for\\n\\n\\n\\n\\n 40\\n\\fpreferential treatment in the adjudication of particular\\ncitations: typically the requests were for “removing points”\\nand obtaining a “not guilty” judgment. App. 1819.\\nO’Donnell said he sometimes had to signal Lowry in the\\ncourtroom to remind him that a particular case was supposed\\nto receive consideration. App. 1822-23. He testified from\\nhis own observation that Lowry typically honored requests\\nfor consideration. App. 1829. He also declared if Lowry\\nclaimed he never gave consideration or asked it of others, this\\nwould not be truthful. App. 1813. The same assistant\\ntestified that if Lowry testified that he ignored requests for\\nconsideration, or that he never honored requests for\\nconsideration, that testimony would not be true. App. 1855.\\nThe Government also asked: “If [Lowry] claimed that . . .\\nconsideration requests had no impact when he disposed of\\ncases, would that be true?” The assistant responded,\\n“probably not.” Id.\\n\\n Another witness, Walt Smaczylo, employed as a court\\nofficer in the Traffic Court, provided an example of how\\n“consideration” worked in the courtroom.\\n\\n When someone comes in,\\n for example, for a reckless\\n driving ticket and that\\n judge normally comes\\n down pretty hard and finds\\n that defendant guilty and\\n then the same type cases\\n come in and you see a\\n defendant walk out either\\n not guilty or a significantly\\n reduced charge.\\n\\n\\n\\n\\n 41\\n\\fApp. 1912. The Government asked Smaczylo if he saw\\nLowry preside over such instances, and he answered: “That’s\\ncorrect, yes.” Id. Smaczylo testified that requests for\\nconsideration were written on small note cards or “sticky”\\nnotes and that he saw Lowry in possession of these cards and\\nnotes. App. 1914. He also provided a generalized example\\nof consideration, based on his observation and understanding,\\nin which a reckless driving citation would be reduced to\\ncareless driving. In such instances, he indicated that a $300\\nto $400 fine would be cut in half. He said: “So, that money\\nwas not collected, obviously, by the state. If that ticket was\\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\\ndidn’t give consideration would that be a truth or would that\\nbe a lie?” He responded: “That would not be the truth.”\\nApp. 1921.\\n\\n All of this testimony provides more than a sufficient\\nbasis to support a reasonable jury’s conclusion that Lowry\\nwas not truthful when he responded to the Government’s\\nquestion about special favors. 28\\n\\n28\\n Lowry points to the cross-examination of both witnesses in\\nwhich they seem to equivocate on some of their observations\\nand responses to the Government. For instance O’Donnell\\nstated his view that giving consideration was no different\\nfrom the leniency that Lowry extended to every other person\\nwho pleaded not guilty and appeared at the hearing.\\nHowever, we do not weigh the credibility of evidence in the\\nrecord. We only judge whether there is sufficient evidence in\\nthe record to support a reasonable fact-finder’s determination\\nthat the record supported conviction of Lowry on a charge of\\n\\n\\n\\n\\n 42\\n\\f Finally, Lowry argues that the Government’s question\\nsought a dispositive response from him on the charges of\\nconspiracy and fraud. He says an affirmative answer to\\nwhether he gave “special favors” to certain individuals would\\nhave been enough to convict him of conspiracy and fraud.\\nThus, he maintains that his acquittal on charges of mail fraud,\\nwire fraud, and conspiracy is res judicata as to the perjury\\ncharges that are based on his answer. He said he did not\\ncommit fraud and the jury agreed with him. Therefore, he\\nsays, he did not perjure himself. However, even if we\\naccepted Lowry’s characterization of the question, we reject\\nthis argument.\\n\\n First, a jury’s determination that Lowry’s ticket-fixing\\nconduct did not constitute wire fraud, mail fraud, and\\nconspiracy does not preclude its determination that he lied\\nabout this conduct before the Grand Jury. Moreover, as the\\nSupreme Court has articulated, a verdict on one count that\\nseems to be at odds with another “shows that either in the\\nacquittal or the conviction the jury did not speak their real\\nconclusions, but that does not show that they were not\\nconvinced of the defendant’s guilt.” United States v. Powell,\\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\\nU.S. 390, 393 (1932)). It is impossible to know in such cases\\nwhether the verdicts were an exercise of lenity by the jury or\\noutright error.\\n\\n Nonetheless, as the Powell Court noted, any\\nassessment of the jury’s rationale for its verdicts “would be\\n\\n\\nperjury. See United States v. Richardson, 658 F.3d 333, 337\\n(3d Cir. 2011).\\n\\n\\n\\n\\n 43\\n\\fbased either on pure speculation or would require inquiries\\ninto the jury’s deliberations that courts generally will not\\nundertake.” Id. at 58. So, even if Lowry was correct that the\\nacquittal is relevant to his response to the question grounding\\nhis perjury conviction, we are not convinced that his perjury\\nconviction is unfounded. Given the substantial body of\\nevidence presented to the jury, nothing here demands that we\\nabandon the deference we traditionally give to the collective\\njudgment of the jury. For all these reasons, we will affirm the\\njury’s verdict as to Lowry.\\n\\n D.\\n\\n Appellant Mulgrew 29\\n\\n Mulgrew does not argue that the question asked at the\\nGrand Jury was ambiguous, he simply maintains that his\\nstatement was truthful. 30 The questions and answers\\ngrounding his perjury conviction are as follows.\\n\\n Q. How about your\\n personal, has your personal\\n received any calls like that\\n from other judges, other\\n ward leaders that she’s\\n conveyed to you, saying\\n\\n29\\n Mulgrew was charged with perjury in Count 70 of the\\nindictment.\\n30\\n Mulgrew’s claims are reviewed for plain error because he\\ndid not make the same argument before the District Court.\\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\\n\\n\\n\\n\\n 44\\n\\f so-and-so has called about\\n this case?\\n\\n A. If she did, she didn’t\\n convey them to me.\\n\\n\\nApp. 432-33 (emphasis added). Shortly after this, the\\nfollowing exchange occurred:\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people, whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\nApp. 438. As to the first exchange, Mulgrew claims that the\\nGovernment’s use of the word “call” referred exclusively to\\ntelephone calls. This mattered to him, he says, because others\\n\\n\\n\\n\\n 45\\n\\fhad testified that personal assistants of other Traffic Court\\njudges would give index cards to his personal assistant in his\\nchambers or robing room containing names of some\\nindividuals whose tickets were listed for hearing. Mulgrew\\nclaims that there is no evidence that he ever received any\\nphone calls asking that he act extrajudicially to give well-\\nconnected individuals preferential treatment. The implication\\nis that, had the Government asked him about receiving index\\ncards with such requests, his answer would have been\\ncompletely different.\\n As with Tynes and Lowry, our review of claims of\\nliteral truth drives us to examine the context of the question.\\n\\n Q. How about other\\n judges, have other judges\\n ever approached you or\\n called to you or get a\\n message to you either\\n themselves or through their\\n personals saying that\\n someone is going to be on\\n your list next week or next\\n Monday and can you could\\n some special way towards\\n the case?\\n\\n A. No, they haven’t.\\n\\n Q. Never?\\n\\n A. No.\\n\\n\\n\\n\\n 46\\n\\fQ. How about your\\npersonal, has your personal\\nreceived any calls like that\\nfrom other judges, other\\nward leaders that she’s\\nconveyed to you saying so\\nand so has called about this\\ncase?\\n\\nA. If she did, she didn’t\\nconvey them to me.\\n\\nQ. And your personal\\nis who?\\n\\nA. Gloria McNasby.\\n\\nQ. Have you ever seen\\non traffic court files --You\\nactually get a file when\\nsomeone’s case is called?\\n\\nA. Right.\\n\\nQ. So the case is called\\nand you get a file presented\\nto you; is that right?\\n\\nA. uh-huh.\\n\\nQ. Have you ever seen\\nany index cards or\\nnotations on the file\\n\\n\\n\\n\\n 47\\n\\f indicating that a person has\\n called or taken some\\n special interest in this\\n case?\\n\\n A. Nope.\\n\\nApp. 432-33 (emphasis added). The transcript makes it\\nobvious that Mulgrew’s singular reliance on the reference to a\\n“call” ignores the thrust of the Government’s line of\\nquestions. The questions focus on the substance of the\\ncommunications between Mulgrew’s personal assistant and\\nhimself, rather than the mode of those communications.\\n\\n Mulgrew also claims that he responded truthfully to\\nthe second question.\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n\\n\\n\\n\\n 48\\n\\f information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\n Q. Wouldn’t you want\\n to know it?\\n\\n A. No, I don’t want to\\n know. Then I never have to\\n worry about what I do in\\n the courtroom.\\n\\nApp. 437-38 (emphasis added). Apparently focusing on the\\nwords “see what she can do,” he says that he answered\\ntruthfully by responding that his personal assistant did not tell\\nhim that people were approaching her and asking her to give\\nthem preferential treatment. But, as with the first question,\\nMulgrew cherry-picks a small part of the question out of\\ncontext, distorting it. The full text and follow up question\\nshow that the thrust of the inquiry was whether Mulgrew’s\\npersonal assistant was informing him of the names of those\\nrequesting preferential treatment from him. And Mulgrew’s\\nresponse to the follow-up question —saying that he did not\\nwant to know so that he did not have to worry about what he\\ndid in the courtroom—is consistent with one who understood\\nthis. App. 438.\\n\\n We conclude that, ultimately, the evidence is sufficient\\nfor a reasonable jury to conclude Mulgrew understood that\\nboth of these questions were focused on whether his personal\\nassistant informed him of requests for him to give preferential\\ntreatment, and that he answered in the negative to both.\\n\\n\\n\\n\\n 49\\n\\f Mulgrew alternatively asserts that the District Court\\nerred by refusing to admit additional testimony from the\\nGrand Jury that he claims is relevant to his perjury\\nconviction. 31 After the Government introduced Mulgrew’s\\nGrand Jury testimony, Mulgrew sought the admission of other\\nportions of his testimony. But the District Court sustained the\\nGovernment’s hearsay objection. The portion of the\\ntranscript supporting the perjury conviction is as follows:\\n\\n Q. [W]hether you have\\n ever been asked to provide,\\n what I’ll call, favorable\\n treatment for people in\\n traffic court or however\\n you define that, whether it\\n would be special handling,\\n keep an eye out for a\\n ticket, do me a favor.\\n Have you ever been asked\\n to provide any type of\\n treatment like that for\\n people in traffic court?\\n\\n A. People have asked\\n me for consideration, but I\\n give consideration to\\n everybody that comes in\\n my courtroom[,] so it\\n\\n31\\n We review the District Court’s ruling on the admissibility\\nof evidence for abuse of discretion. United States v. Green,\\n617 F.3d 233, 239 (3d Cir. 2010).\\n\\n\\n\\n\\n 50\\n\\f doesn’t make a difference\\n to me.\\n\\n\\nApp. 422-23. The basis for the Government’s hearsay\\nobjection to this portion of the testimony was that it raised an\\nout-of-court statement not offered by a party opponent.\\n\\n Mulgrew first contends that the District Court erred by\\nruling that this was hearsay because it was not offered for the\\ntruth of the matter asserted. He says that the testimony was\\ninstead offered to show his state of mind later in his\\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\\n191-92 (3d Cir. 2008). However, we conclude that it was not\\nan abuse of discretion for the District Court to sustain the\\nGovernment’s hearsay objection. It was reasonable for the\\nDistrict Court to conclude here that his response relied on\\nout-of-court statements offered to assert his innocence since\\nhis response conveys a declaration that he treated no person\\ndifferent from another.\\n\\n Mulgrew also argues that this portion of the transcript\\nis admissible under Federal Rule of Evidence 106: “[i]f a\\nparty introduces all or part of a writing or recorded statement,\\nan adverse party may require the introduction, at that time, of\\nany other part—or any other writing or recorded statement—\\nthat in fairness ought to be considered at the same time.”\\nMulgrew maintains that this question and answer provides\\ncontext showing that he did not commit perjury. He also\\nmaintains that the “doctrine of completeness” applies here:\\nfairness demanded the admission of the statements. See\\n\\n\\n\\n\\n 51\\n\\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\\nare not convinced.\\n\\n The excerpt at issue occurs many pages before the\\ntestimony regarded as perjurious. It is unrelated in the overall\\nsequence of questions and to the answers grounding his\\nconviction. Moreover, as the intervening pages suggest, it\\nwas separated by the passage of time during questioning. We\\nalso fail to see how Mulgrew’s equivocation over the term\\n“consideration” gives helpful context to his later denial of\\nreceiving requests for consideration. For these reasons, we\\nconclude the District Court did not abuse its discretion by\\nsustaining the Government’s hearsay objection.\\n\\n IV.\\n\\n Appellant Singletary 33\\n\\n\\n32\\n “Under this doctrine of completeness, a second writing may\\nbe required to be read if it is necessary to (1) explain the\\nadmitted portion, (2) place the admitted portion in context, (3)\\navoid misleading the trier of fact, or (4) insure a fair and\\nimpartial understanding.” Soures, 736 F.2d at 91.\\n33\\n Appellant Singletary was charged with making false\\nstatements in Counts 73 and 74 of the indictment. He states\\nin his brief that he ‘joins all arguments on behalf of co-\\nappellants pursuant to Federal Rules of Appellate Procedure\\n28(i).” Singletary Br. 19. To the extent that he joins the\\nargument of prejudice resulting from the trial on the fraud and\\nconspiracy charges, we already have determined that the\\nindictment was proper and no prejudice resulted from\\n\\n\\n\\n\\n 52\\n\\f During the investigation of the Traffic Court by the\\nFederal Bureau of Investigation, Appellant Singletary was\\namong those interviewed. The jury acquitted Singletary of all\\ncounts of wire fraud, mail fraud, and conspiracy. It found\\nhim guilty of false statements made to the Federal Bureau of\\nInvestigation. At sentencing, over Singletary’s objection, the\\nDistrict Court sentenced Singletary using the Guideline on\\nobstruction.\\n\\n The Government agrees that the single count on which\\nhe was convicted does not contain all of the elements of\\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\\nGovernment agrees with Singletary that he is entitled to a\\nremand for resentencing. Accordingly, we will vacate the\\njudgment of sentence as to Singletary and remand to the\\nDistrict Court for resentencing.\\n\\n V.\\n\\n For all of these reasons, we will vacate the judgment of\\nsentence of the District Court with regard to Appellant\\nSingletary and remand for resentencing. We will affirm the\\njudgments of the District Court as to Appellants Alfano, Hird,\\nLowry, Mulgrew and Tynes.\\n\\n\\n\\nbringing these charges to trial. As for the challenges to\\nperjury in Counts 72 and 74, we note that Singletary was\\ncharged with a different crime: false statements in a federal\\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\\nchallenges to all of such charges are inherently fact-intensive.\\nAs he did not provide a factual basis for such a challenge, we\\nregard the issue to be waived.\\n\\n\\n\\n\\n 53\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360293/\", \"author_raw\": \"NYGAARD, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"GREENAWAY"},"judge2":{"kind":"string","value":"NYGAARD"},"judge3":{"kind":"string","value":"FISHER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583040/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n\n __________\n\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\n __________\n\n UNITED STATES OF AMERICA\n v.\n WILLIAM HIRD,\n Appellant at No. 14-4754\n __________\n\n UNITED STATES OF AMERICA\n v.\n THOMASINE TYNES,\n Appellant at No. 14-4804\n __________\n\n UNITED STATES OF AMERICA\n v.\n ROBERT MULGREW,\n Appellant at No. 14-4812\n __________\n\n UNITED STATES OF AMERICA\n v.\n MICHAEL LOWRY,\n Appellant at No. 15-1344\n\f __________\n\n UNITED STATES OF AMERICA\n v.\n WILLIE SINGLETARY,\n Appellant at No. 15-1739\n ___________\n\n UNITED STATES OF AMERICA\n v.\n HENRY P. ALFANO,\n aka Ed, aka Eddie,\n\n Henry P. Alfano,\n Appellant at No. 15-3765\n __________\n\n On Appeal from the United States District Court\n for the Eastern District of Pennsylvania\n\n (District Court Criminal Nos. 2-13-cr-00039-007,\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\n 2-13-cr-00039-004, 2-13-cr-00039-008)\n District Judge: Honorable Robert F. Kelly\n District Judge: Honorable Lawrence F. Stengel\n\n Argued October 23, 2017\n\n BEFORE: GREENAWAY, JR., NYGAARD,\n and FISHER, Circuit Judges\n\n\n (Opinion Filed: January 18, 2019)\n\n\n\n\n 2\n\fAngela Halim\nHalim Drossner\n1528 Walnut Street, Suite 1501\nPhiladelphia, PA 19102\n\nGregory J. Pagano\n1315 Walnut Street, 12th Floor\nPhiladelphia, PA 19107\n Counsel for Appellant in No. 14-4754\n\nLisa A. Mathewson [Argued]\n123 South Broad Street, Suite 810\nPhiladelphia, PA 19109\n Counsel for Appellant No. 14-4804\n\nPeter Goldberger [Argued]\nPamela A. Wilk\n50 Rittenhouse Place\nArdmore, PA 19003\n Counsel for Appellant in No. 14-4812\n\nMichael J. Engle [Argued]\nStradley Ronon Stevens & Young\n2005 Market Street, Suite 2600\nPhiladelphia, PA 19103\n\nMeredith A. Lowry\n1528 Walnut Street, Suite 1501\nPhiladelphia, PA 19102\n Counsel for Appellant in No. 15-1344\n\n\n\n\n 3\n\fWilliam J. Brennan\n1600 Locust Street\nPhiladelphia, PA 19103\n Counsel for Appellant in No. 15-1739\n\nMark E. Cedrone [Argued]\nCedrone & Mancano\n123 South Broad Street, Suite 810\nPhiladelphia, PA 19109\n Counsel for Appellant in No. 15-3765\n\n\nLouis D. Lappen\nDenise S. Wolf\nAnthony J. Wzorek\nRobert A. Zauzmer [Argued]\nOffice of United States Attorney\n615 Chestnut Street, Suite 1250\nPhiladelphia, PA 19106\n Counsel for Appellee\n\n\n\n\n __________\n\n OPINION OF THE COURT\n __________\n\nNYGAARD, Circuit Judge.\n\n I.\n\n\n\n\n 4\n\f In the run-up to a joint trial on a 77-count indictment\nthat charged Appellants with operating a ticket-fixing scheme\nin the Philadelphia Traffic Court, the District Court denied a\nmotion, under Federal Rule of Criminal Procedure\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\nand William Hird (Traffic Court administrator) subsequently\npleaded guilty to all counts against them. But now they\nappeal the District Court’s decision on this motion,\nquestioning whether the indictment properly alleged offenses\nof mail fraud and wire fraud. 1\n\n Appellants Michael Lowry, Robert Mulgrew, and\nThomasine Tynes (Traffic Court judges) proceeded to a joint\ntrial and were acquitted on the fraud and conspiracy counts,\nbut they were convicted of perjury for statements they made\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\nthe sufficiency of the evidence on which they were convicted\nby arguing that the prosecutor’s questions were vague, and\nthat their answers were literally true. Lowry and Mulgrew\ncontend alternatively that the jury was prejudiced by evidence\npresented at trial on the fraud and conspiracy counts.\nMulgrew also complains that the District Court erred by\nruling that certain evidence was inadmissible.\n\n At the same trial, the jury convicted Willie Singletary\n(Traffic Court judge) of making false statements during the\ninvestigation. He claims the District Court made errors when\n\n\n1\n Alfano and Hird preserved their right to appeal. See infra\nsubsection I.C.\n\n\n\n\n 5\n\fit sentenced him. 2 The Government concurs with\nSingletary’s challenge to his sentence.\n\n We have consolidated these appeals for efficiency and\nhave grouped the arguments—to the extent that it is\npossible—by common issues. We agree with Singletary and\nthe Government that he should be resentenced. We will\nreverse the judgment and remand his cause to the District\nCourt for this purpose. We are not persuaded by the rest of\nAppellants’ arguments and will affirm their judgments of\nconviction. 3\n\n II.\n\n Appellants Alfano 4 and Hird 5\n\n\n\n2\n Singletary also attempted to join additional arguments raised\nby other appellants, but for reasons we explain later, see infra\nnote 33, we focus only on his challenge to his sentence.\n3\n The District Court had jurisdiction pursuant to 18 U.S.C. §\n3231. We have jurisdiction to review these claims under 28\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\n4\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\n51, 52, 53, 54, 55, 56).\n5\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\nMail Fraud (Counts 58, 59, 60).\n\n\n\n\n 6\n\f A.\n\n We begin with a brief look at the indictment’s\ndescription of the Traffic Court and its operations to\ncontextualize the arguments made by Alfano and Hird. The\nPhiladelphia Traffic Court was part of the First Judicial\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\nadjudicated violations of the Pennsylvania Motor Vehicle\nCode occurring in the City of Philadelphia, no matter whether\nthe Philadelphia Police or the Pennsylvania State Police\nissued the tickets. App. 187 (Indictment ¶5). When a person\nwas cited for a violation he or she was required—within ten\ndays—to enter a plea of guilty or not guilty. If the person\nfailed to plead, the Traffic Court issued a notice that his or her\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\nperson who pleaded not guilty proceeded to a hearing with a\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\n\n A guilty plea, or a determination of guilt by a Traffic\nCourt judge after a hearing, resulted in a judgment ordering\npayment of statutory fines and court costs. App. 188\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\ncollecting these fines (sending them to the City and\n\n\n6\n Philadelphia Traffic Court was abolished and its jurisdiction\nwas transferred to the Municipal Court in 2013 by an Act of\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\n§1121(a)(2) (2013). The court is now known as the Traffic\nDivision of the Municipal Court.\n7\n Although other penalties are prescribed by the Pennsylvania\nMotor Vehicle Code (App. 188), this appeal is limited to the\nmonetary fines and costs. App. 355.\n\n\n\n\n 7\n\fCommonwealth) and costs (which it distributed to several\npre-designated funds). App. 188-89 (Indictment ¶ 9).\nFinally, it reported the disposition of each adjudication to the\nPennsylvania Department of Transportation (PennDOT).\nApp. 189 (Indictment ¶ 11).\n\n B.\n\n The indictment charged that, at the behest of Alfano\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\nadministrator and judges operated an “extra-judicial system,\nnot sanctioned by the Pennsylvania court system” that\nignored court procedure and gave preferential treatment\n(“consideration”) to select individuals with connections to the\ncourt who had been cited for motor vehicle violations. App.\n196 (Indictment ¶ 31). The special treatment included:\n\n (1) dismissing tickets outright; (2)\n finding the ticketholder not guilty\n after a “show” hearing; (3)\n adjudicating the ticket in a\n manner to reduce fines and avoid\n assignment of points to a driver’s\n record; and (4) obtaining\n continuances of trial dates to\n “judge-shop,” that is find a Traffic\n Court judge who would accede to\n a request for preferential\n treatment.\n\nApp. 195-196 (Indictment ¶ 30). All of this was “not\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\n32). It also alleged that Appellants cooperated with each\n\n\n\n\n 8\n\fother to fulfill requests they and their staffs received. App.\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\nacceding to requests for ‘consideration,’ defendants were\ndepriving the City of Philadelphia and the Commonwealth of\nPennsylvania of money which would have been properly due\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\n After extending consideration to favored individuals,\nTraffic Court judges would report the final adjudication to\n“various authorities, including PennDOT, as if there had been\na fair and open review of the circumstances.” App. 197\n(Indictment ¶ 34). Appellant Hird provided a printout to\nAppellant Alfano showing citations that had been “dismissed\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\nSuch “receipts” were not routinely issued in cases.\n\n C.\n\n Hird and Alfano pleaded guilty to all the charges\nagainst them in the indictment. But, in their plea agreement\nthey reserved the right to appeal “whether the Indictment\n\n\n8\n An example of the many allegations involving Alfano and\nHird is: A.S. requested assistance from Appellant Alfano and\nAppellant Hird on Citation Number P1J0PK568L4 on or\naround February 17, 2010. The citation charged A.S. with\ndriving a tractor-trailer from which snow and ice fell, striking\nvehicles on Interstate 95. The violation carried a $300 fine\nand costs of $142. Appellant Hird promised that he would\n“stop all action” on the citation and instructed A.S. to ignore\nthe ticket. Although A.S. did not appear at the hearing, the\nTraffic Court judge (who is not an appellant here) ruled A.S.\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\n\n\n\n\n 9\n\fsufficiently alleged that the defendants engaged in a scheme\nto defraud the Commonwealth of Pennsylvania and the City\nof Philadelphia of money in costs and fees.” App. 355 (Plea\nAgreement ¶ 9(b)(4)). So they now appeal the District\nCourt’s order denying the motion to dismiss, asserting that\nthe indictment failed to allege violations of mail fraud and\nwire fraud.\n\n “To be sufficient, an indictment must allege that the\ndefendant performed acts which, if proven, constitute a\nviolation of the law that he is charged with violating.” United\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\nassume in our review that the allegations in the indictment are\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\n2004). “The question of whether the . . . indictments alleged\nfacts that are within the ambit of the mail fraud statute is a\nquestion of statutory interpretation subject to plenary review.”\nId. at 590 n.10.\n\n To indict on mail or wire fraud, the Government must\nallege that defendants “devised or intend[ed] to devise any\nscheme or artifice to defraud, or for obtaining money or\nproperty by means of false or fraudulent pretenses,\nrepresentations, or promises” and used mail or wire to effect\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\nthe Government failed to allege that the scheme to commit\nwire and mail fraud had an objective of “obtaining money or\nproperty.” 9\n\n9\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\nthe term “money” has the same meaning. The same is true\nfor the term “property.” Carpenter v. United States, 484 U.S.\n19, 25 n. 6 (1987).\n\n\n\n\n 10\n\f The District Court ruled that the indictment\nsufficiently alleged that the scheme “involved defrauding the\nCommonwealth and the City of money.” App. 20. It noted,\namong others, allegations that:\n\n The conspirators used the\n Philadelphia Traffic Court\n (“Traffic Court”) to give\n preferential treatment to certain\n ticketholders, most commonly by\n “fixing” tickets for those with\n whom they were politically and\n socially connected. By doing so,\n the conspirators defrauded the\n Commonwealth of Pennsylvania\n and the City of Philadelphia of\n funds to which the\n Commonwealth and the City were\n entitled.\n\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\nreferred to the following.\n\n In acceding to requests for\n “consideration,” defendants were\n depriving the City of Philadelphia\n and the Commonwealth of\n Pennsylvania of money which\n would have been properly due as\n fines and costs.\n\n\n\n\n 11\n\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\nHighlighting the references to “funds” and “money,” and that\nthe monetary amounts of the fines are specifically pleaded,\nthe District Court cited to a case from the Court of Appeals\nfor the Eighth Circuit which concluded succinctly that\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\nCir. 1990)). The District Court was satisfied that the\nindictment alleged enough.\n\n “Money, of course, is a form of property.” Reiter v.\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\nHird argue that the mere mention of money in an indictment\nis not enough. They point to a string of Supreme Court and\nCourt of Appeals decisions analyzing Section 1341 and\nSection 1343 which reinforce the point that crimes of mail\nfraud and wire fraud are “limited in scope to the protection of\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\n(1987). 10 The Supreme Court said that “[a]ny benefit which\nthe government derives from the [mail fraud] statute must be\nlimited to the Government’s interests as a property holder.”\nId. at 359 n.8 (emphasis added). Appellants are convinced\nthat money in the form of traffic fines and costs cannot be\nregarded as the Government’s “property” for purposes of mail\nor wire fraud, and they identify two decisions as particularly\nsupportive of their position: Cleveland v. United States, 531\n\n10\n The District Court cited to a number of cases that came\nafter McNally: Carpenter v. United States, 484 U.S. 19\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\nPasquantino v. United States, 544 U.S. 349 (2005).\n\n\n\n\n 12\n\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\nCir. 1994).\n\n The Court in Cleveland examined the mail fraud\nconvictions of individuals who received a state video poker\nlicense by submitting a license application that withheld\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\nnoted that the video poker licenses were part of a state\nprogram that was “purely regulatory.” Id. at 22 (citation\nomitted). 12 It ruled that licenses are a “paradigmatic\nexercise[] of the States’ traditional police powers.” Id. at 23.\nThe Court went on to say that the state’s regulatory powers\ninvolving “intangible rights of allocation, exclusion, and\ncontrol” (which are embodied in a license) are not interests\nthat traditionally have been recognized as property. Id.\nTherefore, even though appellants may have obtained the\nlicense through deception, this was not mail fraud because the\nlicense—at least while still in the hands of the state—was not\n\n\n\n11\n The licenses were part of a regulatory scheme that had as\nits purpose to increase public confidence in the honesty of\ngaming activities that are free of criminal involvement.\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\n27:306(A)(1) (2000) (repealed 2012)).\n12\n The Court rebuffed the Government’s attempts to analogize\nlicenses to other forms of property like patents and franchise\nrights. As for likening licenses to franchise rights, the Court\nobserved that the Government did not enter the video poker\nbusiness, but rather decided to “permit, regulate, and tax\nprivate operators of the games.” Id. at 24.\n\n\n\n\n 13\n\fproperty. Id. at 26-27. It was a purely administrative tool\nused to achieve regulatory objectives. Id. at 21.\n\n The state responded to the Court’s concerns by\nagreeing that the licenses served a regulatory purpose, but it\ndirected attention to the revenue it received from fees\ncollected for license applications and renewals, as well as\ndevice fees. Id. at 21-22. It argued that this revenue is a\nproperty interest. Id. The Court was not convinced:\n\n Tellingly, as to the character of\n Louisiana’s stake in its video\n poker licenses, the Government\n nowhere alleges that Cleveland\n defrauded the State of any money\n to which the State was entitled by\n law. Indeed, there is no dispute\n that TSG paid the State of\n Louisiana its proper share of\n revenue, which totaled more than\n $1.2 million, between 1993 and\n 1995. If Cleveland defrauded the\n State of “property,” the nature of\n that property cannot be economic.\n\nId. at 22 (emphasis added). It concluded that “[e]ven when\ntied to an expected stream of revenue, the State’s right of\ncontrol does not create a property interest any more than a\nlaw licensing liquor sales in a State that levies a sales tax on\n\n\n\n\n 14\n\fliquor.” Id. at 23. 13 The money collected from application\nand processing fees was an integral part of the state\nregulatory program and it did not create any property interest.\nSee id.\n\n The purpose of the Pennsylvania Motor Vehicle Code\nis to “promote the safety of persons and property within the\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\nMoreover, issuing traffic tickets is a crucial element in the\nenforcement of the Motor Vehicle Code: it is a quintessential\nexercise of state police power. Alfano and Hird conclude,\nmuch like Cleveland, that no property interest could arise\nfrom revenue generated from the state’s exercise of its police\npower in the form of a traffic-ticket fine. They see nothing\nbut a regulatory program here. But this ignores crucial\naspects of the case before us that make it different.\n\n Simply stated, fees charged to obtain a license cannot\nbe equated with fines and costs that result from a traffic\nticket. The license fee was imposed, adjusted, and collected\nsolely by the state’s exercise of its regulatory authority. In\ncontrast, here the state’s police power is exercised when a\ncitation is issued, but this ticket merely establishes the\nsummary violation with which the person is charged. Once a\nperson has been charged, it is judicial power (not the state’s\npolice power) that is exercised to determine whether the\n\n\n\n\n13\n Cleveland also held that Government-issued licenses have\nno intrinsic economic worth before they are given to\napplicants. Id. at 23.\n\n\n\n\n 15\n\fperson is guilty and, if guilty, to impose the fine and costs. 14\nThese fines and costs, although specified by the Motor\nVehicle Code, cannot be cabined as a product of the state’s\nregulatory authority. They are part and parcel of the\njudgment of the court. With this in mind, it is significant that\nthe indictment does not focus on how the citations were\nissued (which would implicate police power), but rather\nalleges that the judicial process was rigged to produce only\njudgments that imposed lower fines—or most often—no fines\nand costs at all. 15\n\n But this raises a further question: can a criminal\njudgment held by the government ever be “property?” The\nCourt in Cleveland offered a critique in its analysis of a\n\n14\n The Traffic Court was not an administrative tribunal.\nRather, it was part of the First Judicial District of\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\nnote 6 and accompanying text.\n15\n On this point, it is noteworthy that the Supreme Court also\nsaid the following: “We resist . . . [any invitation] to approve\na sweeping expansion of federal criminal jurisdiction in the\nabsence of a clear statement by Congress. . . . ‘[U]nless\nCongress conveys its purpose clearly, it will not be deemed to\nhave significantly changed the federal-state balance’ in the\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\nAs we discuss later, the legal tradition of understanding\njudgments as property is long-established. Consequently, the\nconcern about expanding the reach of federal fraud statutes to\nnew classes of property that was present in the deliberation of\nstate licenses in Cleveland is not at issue here.\n\n\n\n\n 16\n\fdifferent issue (whether licenses were analogous to patents)\nthat is apropos to answering this question.\n\n [W]hile a patent holder may sell\n her patent, see 35 U.S.C. § 261 . .\n . “patents shall have the attributes\n of personal property” . . . the State\n may not sell its licensing\n authority. Instead of a patent\n holder’s interest in an unlicensed\n patent, the better analogy is to the\n Federal Government’s interest in\n an unissued patent. That interest,\n like the State’s interest in\n licensing video poker operations,\n surely implicates the\n Government’s role as sovereign,\n not as property holder.\n\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\ncriminal penalties that “implicate[] the Government’s role as\nsovereign.” Id. at 24. Judgments ordering traffic fines and\ncosts cannot be sold and, in the logic of Cleveland, would\nseem then to have no intrinsic economic value. Indeed, the\npenal (non-economic) nature of the fine is undeniable because\nthe failure to pay a fine can result in the imposition of\nsentences of greater consequence, including imprisonment.\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\nword. As we will discuss below, a Supreme Court opinion\nissued five years later, Pasquantino v. United States, 544 U.S.\n349 (2005), forecloses the defendants’ argument.\n\n\n\n\n 17\n\f Finally, we note a dissimilarity between this case and\nCleveland, highlighted by the District Court, on the\nsignificance of the monetary interest that the Government\nassociates with the fraud. The Cleveland Court regarded the\nlicensing fees as integral to the regulatory effort and collateral\nto the matter at hand. The indictment there centered on the\nscheme to obtain liceneses, and did not even raise the\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\ncharged with the fraud paid all the appropriate fees; there was\nno evidence that the government suffered any economic\ndetriment. Id.\n\n In contrast, the indictment here explicitly states that\nthe scheme deprived the City and the Commonwealth of\nmoney, and it describes the object of the scheme as obviating\njudgments of guilt that imposed the fines and costs. Unlike\nCleveland, the fines and costs play a central role in the\nscheme as alleged.\n\n Alfano and Hird next focus on our decision in Henry\nto argue that the Government cannot claim to have a property\nright because the Government never had a legal claim to the\nfines and costs at any point in the scheme. In Henry, we\nexamined convictions for wire fraud arising from a\ncompetitive bidding process among banks to receive deposits\nof a public agency’s bridge tolls. Henry v. United States, 29\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\nwere convicted of mail fraud for giving one bank confidential\ninformation about bids from other banks. Id. at 113. We\nidentified several problems, 16 but Alfano and Hird highlight\n\n16\n The Supreme Court had already made clear that “a\ngovernment official’s breach of his or her obligations to the\n\n\n\n\n 18\n\four observation in Henry that the object of the mail and wire\nfraud must be something to which the victim could claim a\nright of entitlement. Id. at 115 (“a grant of a right of\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\nwe noted that a bank’s property right to the tolls would attach\nonly after the funds were deposited. Id. at 114. So the banks\nthat lost the bidding process never had a basis to claim any\nlegally recognized entitlement to the toll deposits. 18 Id. at\n115. A fraud claim cannot rest on the bidders being cheated\nout of an opportunity to receive the deposits. For these\nreasons, we concluded that the indictment did not allege a\nscheme to obtain fraudulently someone’s “property.” Id. at\n116.\n\n Here, the Government alleged that the defendants\n“were depriving . . . Philadelphia and . . . Pennsylvania of\nmoney which would have been properly due as fines and\ncosts” by making it possible for certain well-connected\nindividuals to avoid a judgment of guilt that imposed an\nobligation to pay appropriate statutory fines. App. 197\n\n\npublic or an employee’s breach of his or her obligations to an\nemployer” did not fall within the scope of Section 1343.\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\n17\n To assess whether a particular claim is a legal entitlement,\n“we look to whether the law traditionally has recognized and\nenforced [the entitlement] as a property right.” Henry, 29\nF.3d at 115.\n18\n They were, no doubt, robbed of a fair process, but we could\nnot identify any legal tradition that recognized this\ndeprivation as a property right. Id. at 115.\n\n\n\n\n 19\n\f(Indictment ¶ 38). But Appellants stress that, like the\ndeposits in Henry, the indictment here alleged an entitlement\nthat does not yet exist because a person must be adjudicated\n(or plead) guilty before they must pay any fines or costs.\nNone of the cases directly associated with Alfano and Hird\nresulted in a guilty judgment. As a result, they argue, the\nGovernment cannot claim here that it was cheated of an\nentitlement, because they were only fines and costs that the\npeople might have owed if they had been found guilty.\n\n The District Court said it well. Accepting this\nargument “would permit the alleged conspirators” to take\nadvantage of their “unique position” in this case “to enter into\na scheme to commit fraud and then hide behind the argument\nthat the success of their fraud precludes prosecution under the\n‘money or property interest’ requirement of the mail and wire\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\nAppellants cannot rest on the very object of their scheme (to\nwork on behalf of favored individuals to obviate judgments of\nguilt and the imposition of fines and costs) as the basis to\nclaim that there is no fraud. Indeed, the not-guilty judgments\nthat Alfano and Hird worked to obtain through the\nextrajudicial system were alleged in the indictment as\nevidence of the scheme itself.\n\n Even if some of the cases in the extra-judicial system\nwould have been judged not guilty in a real adjudication it is\n(as the District Court correctly noted) the intent of the\nscheme, not the successful execution of it, that is the basis for\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\n(1999) (In the criminal context, the court focuses on the\nobjective of the scheme rather than its actual outcome; what\noperatives intended to do, not whether they were successful in\n\n\n\n\n 20\n\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\n(“Civilly of course the [mail fraud statute]would fail without\nproof of damage, but that has no application to criminal\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\ngenerally alleges not just that Appellants operated a system\nthat operated outside the bounds of Traffic Court procedures,\nbut that it did so for the purpose of obviating judgments of\nguilt imposing fines and costs in those selected cases. See,\ne.g., supra note 8. Moreover, we note that in one case not\ndirectly involving either Alfano or Hird, the indictment\nalleged that fines and costs were not just obviated, but were\nactually erased by an alleged co-conspirator traffic court\njudge who ignored the conviction, backdated a continuance,\nand “adjudicated” the person not-guilty. App. 228-29\n(Indictment ¶¶ 108-113). This episode serves to highlight\nthat the entire scheme was centered on keeping (or taking)\njudgments out of the hands of the Government to prevent the\nimposition of fines and costs. As a result, Appellants’\nreliance on our justice system’s presumption of innocence as\na basis to argue against the existence of a governmental\nproperty interest is a red herring that is properly disregarded\nhere.\n\n Accordingly, we conclude that the indictment’s\nallegation that the scheme had an objective of depriving\n“Philadelphia and . . . Pennsylvania of money which would\nhave been properly due as fines and costs” is not undermined\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\n(emphasis added)).\n\n Alfano and Hird next highlight that, in Henry, our\nproperty interest analysis centered on “whether the law\ntraditionally has recognized and enforced [the entitlement in\n\n\n\n\n 21\n\fquestion] as a property right.” 29 F.3d at 115. Appellants\nassert that traffic fines and costs typically have not been\nconsidered economic property and are unsupported by any\nlegal tradition sufficient to ground charges of wire and mail\nfraud. As we have already noted we disagree with any\nconclusion that the fines and costs at issue have no intrinsic\neconomic value. But we turn to another decision of the\nSupreme Court that came after Cleveland to address squarely\nwhether jurisprudence supports our conclusion.\n\n In 2005 the Supreme Court reviewed convictions\narising from a scheme to smuggle large quantities of liquor\nfrom the United States into Canada, evading Canadian taxes.\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\nThe Court noted that the right to be paid has been routinely\nrecognized as property, id. at 355–56, 19 observing that there is\nan equivalence between “money in hand and money legally\ndue,” id. at 356. Affirming the conviction, the Court said:\n“Had petitioners complied with this legal obligation, they\nwould have paid money to Canada. Petitioners’ tax evasion\ndeprived Canada of that money, inflicting an economic injury\nno less than had they embezzled funds from the Canadian\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\nscheme was to deprive Canada of money legally due, and\ntheir scheme thereby had as its object the deprivation of\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\ntickets (or more precisely, judgments arising from them) are\nconsidered an “entitlement to collect money from individuals,\n\n\n19\n The Court cited 3 W. Blackstone, Commentaries on the\nLaws of England 153–155 (1768), which classified the right\nto sue on a debt as personal property.\n\n\n\n\n 22\n\fthe possession of which is ‘something of value.’” 544 U.S. at\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\na scheme to obviate judgments imposing fines, effectively\npreventing the government from holding and collecting on\nsuch judgments imposes an economic injury that is the\nequivalent of unlawfully taking money from fines paid out of\nthe Government’s accounts. See id. at 358.\n\n Alfano and Hird focus, finally, on the role that a\njudge’s discretion plays in the adjudication of a case,\nasserting that the uncertainty this creates about outcomes in\nany given case undermines any argument that a judgment in a\nTraffic Court case can be claimed as an entitlement to\nproperty. To the extent that this merely rephrases the issue of\nguilt or innocence on particular charges, we have already\n\n20\n We also note that Pennsylvania law permits the government\nto remedy the nonpayment of fines and costs as an unpaid\ndebt through civil process, enabling the government to\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\n(“Nothing in this rule [concerning criminal fines] is intended\nto abridge any rights the Commonwealth may have in a civil\nproceeding to collect a fine or costs.”). Because of this, a\nseparate legal tradition is implicated that recognizes the\njudgment itself as property. See, e.g., Armada (Singapore)\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\n(7th Cir. 2018). This long, stable legal tradition of\nrecognizing civil judgments for money as property supports\nthe conclusion that the fines arising from judgments in traffic\ncourt cannot be regarded merely as implicating the act of a\nsovereign imposing a criminal penalty. They can be collected\nby civil process as a debt and are, thus, a property interest.\n\n\n\n\n 23\n\faddressed it above. To the degree that it refers to a judge’s\ndiscretion in sentencing, as the District Court noted, there is\nno such discretion here. 21 The Motor Vehicle Code imposes\nfines and costs for each violation, eliminating any judicial\ndiscretion in this regard.\n\n D.\n\n All of this leads us to conclude that the District Court\ndid not err by denying the motion to dismiss. We conclude\nthat, as alleged, this scheme had the objective of preventing\nthe City of Philadelphia and the Commonwealth of\nPennsylvania from possessing a lawful entitlement to collect\nmoney in the form of fines and costs—a property interest—\nfrom individuals who Alfano and Hird assisted. We will thus\naffirm the convictions of Appellants Alfano and Hird.\n\n III.\n\n Appellants Tynes, Lowry, and Mulgrew\n\n A.\n\n\n\n\n21\n We question, in general, the relevance of an entity’s\nauthority to relinquish a just entitlement or to forbear an\nobligation that an entitlement imposes upon another, as a\nbasis to call into doubt the legitimacy of, or the very existence\nof the entitlement. But see United States v. Mariani, 90 F.\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\nand penalties “may be too speculative to constitute a valid\nproperty interest.”) (internal citation omitted).\n\n\n\n\n 24\n\f In 2011, the United States Attorney presented to the\nGrand Jury evidence arising from the Federal Bureau of\nInvestigation’s inquiry into the Traffic Court. Appellants\nLowry, Mulgrew, and Tynes testified and the Government\nbrought perjury charges against them for statements they\nmade to the Grand Jury. After Hird and Alfano pleaded\nguilty, the rest of the Appellants went to trial. The jury\nacquitted Lowry, Mulgrew, and Tynes of all counts against\nthem on wire fraud, mail fraud, and conspiracy. But it found\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\nchallenge their convictions by raising similar legal arguments\nabout the sufficiency of the evidence.\n As with all challenges to the sufficiency of the\nevidence, we use a highly deferential standard of review. See\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\nCir. 2013) (en banc). We examine the record in a light most\nfavorable to the prosecution, and will not disturb the verdict if\n“any rational trier of fact could have found the essential\nelements of the crime beyond a reasonable doubt.” United\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\n(1979)). Tynes, Lowry, and Mulgrew argue that the\nquestions asked of them at trial were fatally vague and/or that\ntheir answers were truthful. As a result, they contend that\nthese questions and answers are an inadequate basis for a\nperjury conviction.\n\n A conviction for perjury before a grand jury requires\nthe Government to prove that the defendant took an oath\nbefore the grand jury and then knowingly made a “false\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\n(in the context of a sentencing enhancement for perjury) that\nsometimes “confusion, mistake, or faulty memory” results in\n\n\n\n\n 25\n\finaccuracies that cannot be categorized as a “willful attempt\nto obstruct justice” under perjury statutes. United States v.\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\nSentencing Comm’n 2003). So we do understand that\n“[p]recise questioning is imperative as a predicate for the\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\n362 (1973).\n\n Precision, however, is assessed in context. An\nexaminer’s line of questioning should, at a minimum,\nestablish the factual basis grounding an accusation that an\nanswer to a particular question is false. Miller, 527 F.3d at\n78. So a perjury conviction is supported by the record “when\nthe defendant’s testimony ‘can reasonably be inferred to be\nknowingly untruthful and intentionally misleading, even\nthough the specific question to which the response is given\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\n157 F.3d 1042, 1043 (6th Cir. 1998)).\n\n Challenges to the clarity of a question are typically left\nto the jury, which has the responsibility of determining\nwhether the defendant understood the question to be\nconfusing or subject to many interpretations. United States v.\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\nwith our standard of review, we will not disturb a jury’s\ndetermination that a response under oath constitutes perjury\nunless “it is ‘entirely unreasonable to expect that the\ndefendant understood the question posed to him.’” Serafini,\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\n\n\n\n\n 26\n\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\nwe review every aspect of the record pertinent to both the\nquestion and answer to reach a conclusion about whether, in\ncontext, the witness understood the question well enough to\ngive an answer that he or she knew to be false. See Miller,\n527 F.3d at 78. Our review, however, is focused on glaring\ninstances of vagueness or double-speak by the examiner at the\ntime of questioning (rather than artful post-hoc interpretations\nof the questions) that—by the lights of any reasonable fact-\nfinder—would mislead or confuse a witness into making a\nresponse that later becomes the basis of a perjury conviction.\nQuestions that breach this threshold are “fundamentally\nambiguous” and cannot legitimately ground a perjury\nconviction. Id. at 77. 23\n\n\n22\n The Court of Appeals for the Second Circuit underscored\nthe high bar this establishes for appellants by noting that a\nfundamentally ambiguous question is “not a phrase with a\nmeaning about which men of ordinary intellect could agree,\nnor one which could be used with mutual understanding by a\nquestioner and answerer unless it were defined at the time it\nwere sought and offered as testimony.” United States v.\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\n232 F.2d. 334 (D.C. Cir. 1955)).\n23\n The rule of fundamental ambiguity is intended to\n“preclude convictions that are grounded on little more than\nsurmise or conjecture, and . . . prevent witnesses . . . from\nunfairly bearing the risks associated with the inadequacies of\ntheir examiners.” Ryan, 828 F.2d at 1015.\n\n\n\n\n 27\n\f That is the law applicable to the claims raised by\nTynes, Lowry and Mulgrew. But, because our review is fact-\ndependent, and because each raises some unique issues, we\nwill address each of their claims individually. 24\n B.\n\n\n\n\n24\n Adopting the arguments made by Alfano and Hird,\nAppellants Lowry, Mulgrew and Tynes assert that the\nGovernment improperly charged them with conspiracy, wire\nfraud, and mail fraud. Therefore, they assert, their joint trial\non these counts of the indictment prejudiced the jury’s\ndeliberation on the charges of perjury. They claim such\nevidence would have been excluded under Federal Rule of\nEvidence. 403. They also contend that, without a charge of\nconspiracy, the joinder of their cases would have been\nimpermissible under Federal Rule of Criminal Evidence 8(b)\nor, at the very least, severance of their cases would have been\nwarranted under Federal Rule of Criminal Procedure 14(a).\nCertainly, where there is evidence of prejudice resulting from\n“spillover” evidence from counts that should have been\ndismissed, reversal is warranted. See United States v. Wright,\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\nconcluded that the District Court did not err by denying the\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\ndismiss the conspiracy, wire fraud and mail fraud counts of\nthe indictment. Thus, Appellants’ spillover argument has\nbeen nullified. Likewise, Appellants have no basis to claim\nthat the Court unfairly prejudiced them by not granting\nseparate trials.\n\n\n\n\n 28\n\f Appellant Tynes 25\n\n Appellant Tynes claims her convictions for perjury at\nCount 71 and Count 72 lack sufficient evidence because she\nwas responding to questions that were fundamentally\nambiguous. The perjury charged at Count 71 arises from the\nfollowing exchange.\n\n Q. In all the years\n you’ve been [at Traffic\n Court] have you\n ever been asked to give\n\n\n25\n Tynes filed a separate motion to dismiss. App. 291-99.\nThe record also contains Tynes’ proposed order to join\nSullivan’s motion to dismiss. App. 290. However, Tynes’\nmotion contains no such request. Moreover, the\nGovernment’s response to the motions notes that Lowry and\nMulgrew moved to join (without argument), and makes no\nmention of Tynes. The District Court’s ruling on Tynes’\nmotion to dismiss relates only to the arguments she made\nseparately in her brief. As a result, we cannot consider\nTynes’ arguments on appeal that relate to those raised in\nSullivan’s motion. Moreover, since she failed to raise any of\nthe arguments she made in her separate motion to dismiss,\nthese arguments are waived. With that said, we will affirm\nthe District Court’s ruling on the Motion raised by Sullivan\nand joined by the five Appellants. Therefore, we need not\naddress Tynes’ assertion that the District Court’s mishandled\nher joinder motion because it does not prejudice the outcome\nof her appeal.\n\n\n\n\n 29\n\f favorable treatment on\n a case to anybody?\n\n A. No, not favorable\n treatment. People basically\n know me. The lawyers\n know me. The court\n officers know me. I have\n been called a nononsense\n person because I’m just not\n that way. I take my\n position seriously, and the\n cards fall where they may.\n\nApp. 255, 5720. 26 Tynes contends that the Government\npursued a novel theory here (applying federal fraud statutes to\nallegations of ticket fixing) and used the vague term\n“favorable treatment” to gloss over its uncertainty about what,\nultimately, would constitute an illegal act. She points out that\nthe term had not been used before in reference to this case\nand that the Government offered no explanation or definition\nof the term to alert Tynes to the intent of the question.\n\n Also, from Tynes’ perspective, every litigant\nappearing before a court seeks an outcome that is favorable,\nthus making “favorable treatment” a term that essentially\nreferred to “how litigation works.” She claims that its use\namounted to a fishing expedition designed to capture unfairly\n\n26\n We cite to the testimony quoted in the indictment and the\nGrand Jury that was used at trial. We note that there are some\ntypographical inconsistencies between these sources and in\nthose instances we have quoted the Grand Jury testimony.\n\n\n\n\n 30\n\fthe entirety of her conduct in the courtroom. She warns that\nthis is precisely the type of “open-ended construction” in\nquestioning that we found unacceptable in Serafini. 167 F.3d\nat 822.\n\n Tynes makes a related argument against her perjury\nconviction for Count 72. That conviction is based on this\nexchange.\n Q. You’ve never taken\n action on a request?\n\n A. No.\n\nApp. 257, 5722. She maintains that the word “request” was\npresented to the jury as a follow-on to the question grounding\nCount 71, requiring a person to link the term “favorable\ntreatment” and the word “request” to make sense of it. She\nargues that the Government took advantage of the ambiguity\nof “favorable treatment,” forcing the jury to speculate that\nTynes interpreted “request” as “favorable treatment.” This\nreliance on “sequential referents” is, from her perspective,\nexactly what we criticized in Serafini. 167 F.3d at 821. But\nshe misconstrues our holding.\n\n In Serafini, the surrounding questions focused on a\ndifferent topic. This bolstered appellant’s argument in that\ncase that the question on which the perjury conviction rested\nwas fundamentally ambiguous. Id. The appellant said the\nmultiplicity of topics in surrounding questions caused the jury\nto speculate improperly on how he understood the question at\nissue. We said: “The meaning of individual questions and\nanswers is not determined by ‘lifting a statement . . . out of its\nimmediate context,’ when it is that very context which fixes\n\n\n\n\n 31\n\fthe meaning of the question.” Serafini, 167 F.3d at 821\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\n1978)). In the case of Serafini, the context made the\nconfusing nature of the question apparent. The various topics\nin surrounding questions created sufficient ambiguity to\nundermine the conviction. Id.\n\n Here, however, even though the terms used by the\nexaminer changed, we conclude that the line of questioning—\nincluding both questions that ground Count 71 and 72—have\nan obvious, consistent focus.\n\n Q. In all the years\n you’ve been [at Traffic\n Court] have you\n ever been asked to give\n favorable treatment on\n a case to anybody?\n\n A. No, not favorable\n treatment. People basically\n know me. The lawyers\n know me. The court\n officers know me. I have\n been called a nononsense\n person because I’m just not\n that way. I take my\n position seriously and the\n cards fall where they\n may. Most of the time . . .\n the people in my Court\n plea bargain. They know\n that most of the time,\n\n\n\n\n 32\n\fninety percent of the time,\nsay 90 percent, I go with\nthe police officer’s\nrecommendation. . . .\n\nQ. So, in all those years\nno one has ever asked you\nto find somebody not\nguilty--\n\nA. No.\n\nQ. --or to find a lesser\nviolation; find a lesser fine;\nanything along those lines?\n\nA. No. I will say to\npeople go to court, go to\ntrial and see what\nhappens. . . .\n\nQ. Ward leaders,\npoliticians has anyone\ncalled you and said I\nhave Johnny Jones coming\nup next week and I\nwould appreciate it if -- if\nyou would look\nfavorably on him when he\ncomes through? Has\nanything like that ever\nhappened?\n\n\n\n\n 33\n\f A. Throughout the\n years ward leaders and\n people have called all the\n time and asked me\n questions. The only thing I\n will say to them is they\n need to go to court. If you\n think it’s a problem, they\n need to hire a lawyer, or\n make sure you bring all\n your evidence to court. If\n it’s something like\n inspection, make sure you\n bring your -- papers and\n things like that. That’s\n what I would tell them to\n do. I give advice that\n way. I don’t know if that’s\n wrong or not, but I do.\n\n Q. You’ve never taken\n action on a request?\n\n A. No.\n\nApp. 528-29, 530; 5720-22. This broader context would give\nany reasonable fact-finder more than enough basis to\nconclude that the witness knew the point of reference for both\nthe term “favorable treatment” and “request” was ticket\nfixing. In fact, Tynes is asking us to do precisely the thing we\ncriticized in Serafini, to lift a phrase or statement out of its\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\nus that the question harbors any fatal ambiguity.\n\n\n\n\n 34\n\f Tynes next contends that her responses to questions\ngrounding Count 71 and Count 72 cannot support convictions\nfor perjury because they were literally true. Of course,\nperjury arises only from making knowingly false material\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\nanswers an ambiguous question with a non-responsive answer\nthat the witness believes is true—even if the answer is\nmisleading—does not commit perjury. See Bronston, 409\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\n1416 (3d Cir. 1994).\n Tynes argues that, because she regarded the question\nabout favorable treatment as vague, she interpreted it as\nasking whether she accepted any bribes in exchange for a\njudgment of not guilty or a reduced punishment. Her\nresponse of “no” (grounding Count 71) is literally true—she\nsays—because there is no evidence that she accepted any\nbribes in return for giving preferential outcomes in the\nadjudication of some individuals who were cited for breaking\nthe law. Under this theory, the same argument can also\nnegate the charges at Count 72 since she says she did not\naccept any “requests” (bribes) in exchange for preferential\ntreatment.\n\n Although the jury is permitted reasonable inferences\ndrawn from the record about the witness’ understanding of\nthe truth or falsity of the answer, it is not (as we noted above)\npermitted to reach conclusions based merely on speculation\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\nassertion of literal truth is undermined because the trial record\nsupports no reasonable inference that the Government was\nasking her about matters outside of the alleged bribes, nor\n\n\n\n\n 35\n\fdoes it provide any reason why Tynes would interpret the\nquestion in this way.\n\n Finally, Tynes contends that the evidence was not\nsufficient to support her conviction. However, the jury heard\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\nthat she received from personal assistants of other judges\nthree to four cards per week requesting consideration. Each\ncard had the name of a person who was appearing before\nTynes on that day. She passed these to Tynes’ court officer,\nwho was present during the proceedings. App. 4593-95.\nTynes also instructed Warren to give similar cards to the staff\nof other judges. App. 4598. Warren knew to act discreetly\nwhen she was transferring the cards. App. 4599. The jury\nalso heard testimony from those who actually received\nconsideration from Tynes. For example, Timothy Blong was\ncited for reckless driving and driving without a license. He\nadmitted in testimony that he did not have a license when he\nwas cited. App. 3150. He also testified that he requested\nconsideration through a Traffic Court employee (Danielle\nCzerniakowski, who worked as a personal assistant to a\nTraffic Court judge) with whom he was acquainted. When he\nappeared in court, he was simply told that his case was\ndismissed. He did not have to say anything, App. 3159-60.\nBlong testified he was told his case was dismissed because\nthe police officer did not appear (App. 3160-61), but the\ngovernment produced evidence that an officer was present.\nApp. 3193-96. The Government also showed that Tynes was\nthe presiding judge in Blong’s case. App. 3193. Richard\nCarrigan—who admitted in testimony that he drove through a\nred light—described a similar experience in which, after\nrequesting favorable treatment through Judge Lowry’s\npersonal assistant, Kevin O’Donnell, his case was dismissed\n\n\n\n\n 36\n\fby Judge Tynes without ever having to say a word. App.\n3178-82.\n\n Tynes does not challenge any of this in her appeal.\nInstead she focuses on the weight of other evidence and\nperceived gaps in testimony. We conclude that all of this\nprovides more than a sufficient basis to support a reasonable\njury’s conclusion that Tynes did “give favorable treatment on\na case,” and did “take[] action on a request.” App. 528-30.\n\n For all of these reasons, we will affirm the judgment of\nconviction on perjury as to Appellant Tynes.\n C.\n\n Appellant Lowry 27\n\n Like Tynes, Appellant Lowry advances arguments of\nfundamental ambiguity and literal truth. His perjury\nconviction centered on one question and answer.\n\n\n Q. So if I understand\n your testimony, you’re\n saying you don’t give out\n special favors; is that right?\n\n A. No, I treat\n everybody in that\n courtroom the same.\n\n\n27\n Lowry was charged with perjury in Count 69 of the\nindictment.\n\n\n\n\n 37\n\fApp. 489. Lowry attacks the Government’s use of the term\n“special favors” as one with many potential meanings.\nHowever, as we noted above in our reference to Serafini, we\nreject arguments that lift individual questions or answers—or\nindividual phrases embedded in either—from the context of\nsurrounding questions that help fix their meaning. Serafini,\n167 F.3d at 821. The larger context for the question asked of\nLowry is as follows.\n\n Q. So if I understand\n your testimony, you’re\n saying you don’t give out\n special favors; is that right?\n\n A. Well, I know it\n appears that way; and it’s\n hard for me to prove to\n you . . .\n\n Q. I’m just asking,\n your testimony is you don’t\n give out special favors, is\n that right?\n\n A. No, I treat\n everybody in that\n courtroom the same.\n\n Q. You treat everybody\n fairly?\n\n A. I’m a lenient judge.\n I will admit to that.\n\n\n\n\n 38\n\f Q. You treat everybody\n fairly?\n\n A. Yes, I do.\n\n Q. And these notices\n that you get from your\n personal or from other\n people, they don’t affect\n you in any way; is that\n right?\n\n A. Virtually no effect\n at all.\n\n\nApp. 489-90.\n\n Lowry’s assertion that the phrase “special favors” is\nsubject to many interpretations is unconvincing. We note two\nthings. First, the line of questioning reasonably supports a\nconclusion that this inquiry referenced conduct associated\nwith allegations of ticket fixing. Second, Lowry answered as\nif his understanding of the question was consistent with this\ninterpretation. He said that he was aware it may “appear” that\nhe gave special favors. He also defended himself by saying\nthat such requests did not affect his conduct in the courtroom\nat all. If—as he says—he understood “special favors” to\nmean fair treatment, his answer makes no sense.\n\n Lowry next claims that, since the question was\nstructured to elicit a negative response, his answer cannot be\n\n\n\n\n 39\n\fused as the basis of a perjury charge. Relatedly, he contends\nthat the question was merely a summation of an answer that\nhe gave just before this question. In essence he argues that\nthis was a leading question. We have concluded, in the\ncontext of a trial, that the propriety of leading questions in\ndirect examinations is a matter left to the sound discretion of\nthe trial judge. See United States v. Montgomery, 126 F.2d\n151, 153 (3d Cir. 1942). We extend the same deference here\nto the District Court’s decision to admit this portion of the\nGrand Jury transcript. We do not regard the question as\nfundamentally unfair or unclear, or something outside the\nnorm of questions typically employed on direct examination.\nFor these reasons, we conclude that the District Court did not\nabuse its discretion here.\n\n Alternatively, Lowry argues that—if the term is\nunderstood to reference fixing tickets—there is no evidence\nto contradict his response that requests for special favors did\nnot impact any of his adjudications. We do not agree. The\nrecord contains the following testimony.\n\n Kevin O’Donnell, who was Lowry’s personal\nassistant, testified about Lowry’s involvement with requesting\nand giving consideration. He said that Lowry made four to\nfive requests each month for consideration and that\nO’Donnell transmitted them to the personal assistants of other\nTraffic Court judges. App. 1854. Likewise, he said other\njudges transmitted requests for consideration to Lowry\nthrough their personal assistants. App. 1812-13. Appellant\nHird and various politicians also made requests of Lowry for\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\nwould give the requests to Lowry on the day scheduled for\nhearing on the citation. App. 1818-19. The requests were for\n\n\n\n\n 40\n\fpreferential treatment in the adjudication of particular\ncitations: typically the requests were for “removing points”\nand obtaining a “not guilty” judgment. App. 1819.\nO’Donnell said he sometimes had to signal Lowry in the\ncourtroom to remind him that a particular case was supposed\nto receive consideration. App. 1822-23. He testified from\nhis own observation that Lowry typically honored requests\nfor consideration. App. 1829. He also declared if Lowry\nclaimed he never gave consideration or asked it of others, this\nwould not be truthful. App. 1813. The same assistant\ntestified that if Lowry testified that he ignored requests for\nconsideration, or that he never honored requests for\nconsideration, that testimony would not be true. App. 1855.\nThe Government also asked: “If [Lowry] claimed that . . .\nconsideration requests had no impact when he disposed of\ncases, would that be true?” The assistant responded,\n“probably not.” Id.\n\n Another witness, Walt Smaczylo, employed as a court\nofficer in the Traffic Court, provided an example of how\n“consideration” worked in the courtroom.\n\n When someone comes in,\n for example, for a reckless\n driving ticket and that\n judge normally comes\n down pretty hard and finds\n that defendant guilty and\n then the same type cases\n come in and you see a\n defendant walk out either\n not guilty or a significantly\n reduced charge.\n\n\n\n\n 41\n\fApp. 1912. The Government asked Smaczylo if he saw\nLowry preside over such instances, and he answered: “That’s\ncorrect, yes.” Id. Smaczylo testified that requests for\nconsideration were written on small note cards or “sticky”\nnotes and that he saw Lowry in possession of these cards and\nnotes. App. 1914. He also provided a generalized example\nof consideration, based on his observation and understanding,\nin which a reckless driving citation would be reduced to\ncareless driving. In such instances, he indicated that a $300\nto $400 fine would be cut in half. He said: “So, that money\nwas not collected, obviously, by the state. If that ticket was\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\ndidn’t give consideration would that be a truth or would that\nbe a lie?” He responded: “That would not be the truth.”\nApp. 1921.\n\n All of this testimony provides more than a sufficient\nbasis to support a reasonable jury’s conclusion that Lowry\nwas not truthful when he responded to the Government’s\nquestion about special favors. 28\n\n28\n Lowry points to the cross-examination of both witnesses in\nwhich they seem to equivocate on some of their observations\nand responses to the Government. For instance O’Donnell\nstated his view that giving consideration was no different\nfrom the leniency that Lowry extended to every other person\nwho pleaded not guilty and appeared at the hearing.\nHowever, we do not weigh the credibility of evidence in the\nrecord. We only judge whether there is sufficient evidence in\nthe record to support a reasonable fact-finder’s determination\nthat the record supported conviction of Lowry on a charge of\n\n\n\n\n 42\n\f Finally, Lowry argues that the Government’s question\nsought a dispositive response from him on the charges of\nconspiracy and fraud. He says an affirmative answer to\nwhether he gave “special favors” to certain individuals would\nhave been enough to convict him of conspiracy and fraud.\nThus, he maintains that his acquittal on charges of mail fraud,\nwire fraud, and conspiracy is res judicata as to the perjury\ncharges that are based on his answer. He said he did not\ncommit fraud and the jury agreed with him. Therefore, he\nsays, he did not perjure himself. However, even if we\naccepted Lowry’s characterization of the question, we reject\nthis argument.\n\n First, a jury’s determination that Lowry’s ticket-fixing\nconduct did not constitute wire fraud, mail fraud, and\nconspiracy does not preclude its determination that he lied\nabout this conduct before the Grand Jury. Moreover, as the\nSupreme Court has articulated, a verdict on one count that\nseems to be at odds with another “shows that either in the\nacquittal or the conviction the jury did not speak their real\nconclusions, but that does not show that they were not\nconvinced of the defendant’s guilt.” United States v. Powell,\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\nU.S. 390, 393 (1932)). It is impossible to know in such cases\nwhether the verdicts were an exercise of lenity by the jury or\noutright error.\n\n Nonetheless, as the Powell Court noted, any\nassessment of the jury’s rationale for its verdicts “would be\n\n\nperjury. See United States v. Richardson, 658 F.3d 333, 337\n(3d Cir. 2011).\n\n\n\n\n 43\n\fbased either on pure speculation or would require inquiries\ninto the jury’s deliberations that courts generally will not\nundertake.” Id. at 58. So, even if Lowry was correct that the\nacquittal is relevant to his response to the question grounding\nhis perjury conviction, we are not convinced that his perjury\nconviction is unfounded. Given the substantial body of\nevidence presented to the jury, nothing here demands that we\nabandon the deference we traditionally give to the collective\njudgment of the jury. For all these reasons, we will affirm the\njury’s verdict as to Lowry.\n\n D.\n\n Appellant Mulgrew 29\n\n Mulgrew does not argue that the question asked at the\nGrand Jury was ambiguous, he simply maintains that his\nstatement was truthful. 30 The questions and answers\ngrounding his perjury conviction are as follows.\n\n Q. How about your\n personal, has your personal\n received any calls like that\n from other judges, other\n ward leaders that she’s\n conveyed to you, saying\n\n29\n Mulgrew was charged with perjury in Count 70 of the\nindictment.\n30\n Mulgrew’s claims are reviewed for plain error because he\ndid not make the same argument before the District Court.\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\n\n\n\n\n 44\n\f so-and-so has called about\n this case?\n\n A. If she did, she didn’t\n convey them to me.\n\n\nApp. 432-33 (emphasis added). Shortly after this, the\nfollowing exchange occurred:\n\n Q. Let me make sure as\n well that if I got your\n testimony correct [sic].\n You’re saying that if other\n people, whether they be\n political leaders, friends\n and family, anybody is\n approaching your personal\n and asking her specifically\n to look out for a case, see\n what she can do in a case,\n give preferential treatment,\n however you want to\n phrase it, that she is not\n relaying any of that\n information on to you; is\n that correct?\n\n A. No, she isn’t.\n\nApp. 438. As to the first exchange, Mulgrew claims that the\nGovernment’s use of the word “call” referred exclusively to\ntelephone calls. This mattered to him, he says, because others\n\n\n\n\n 45\n\fhad testified that personal assistants of other Traffic Court\njudges would give index cards to his personal assistant in his\nchambers or robing room containing names of some\nindividuals whose tickets were listed for hearing. Mulgrew\nclaims that there is no evidence that he ever received any\nphone calls asking that he act extrajudicially to give well-\nconnected individuals preferential treatment. The implication\nis that, had the Government asked him about receiving index\ncards with such requests, his answer would have been\ncompletely different.\n As with Tynes and Lowry, our review of claims of\nliteral truth drives us to examine the context of the question.\n\n Q. How about other\n judges, have other judges\n ever approached you or\n called to you or get a\n message to you either\n themselves or through their\n personals saying that\n someone is going to be on\n your list next week or next\n Monday and can you could\n some special way towards\n the case?\n\n A. No, they haven’t.\n\n Q. Never?\n\n A. No.\n\n\n\n\n 46\n\fQ. How about your\npersonal, has your personal\nreceived any calls like that\nfrom other judges, other\nward leaders that she’s\nconveyed to you saying so\nand so has called about this\ncase?\n\nA. If she did, she didn’t\nconvey them to me.\n\nQ. And your personal\nis who?\n\nA. Gloria McNasby.\n\nQ. Have you ever seen\non traffic court files --You\nactually get a file when\nsomeone’s case is called?\n\nA. Right.\n\nQ. So the case is called\nand you get a file presented\nto you; is that right?\n\nA. uh-huh.\n\nQ. Have you ever seen\nany index cards or\nnotations on the file\n\n\n\n\n 47\n\f indicating that a person has\n called or taken some\n special interest in this\n case?\n\n A. Nope.\n\nApp. 432-33 (emphasis added). The transcript makes it\nobvious that Mulgrew’s singular reliance on the reference to a\n“call” ignores the thrust of the Government’s line of\nquestions. The questions focus on the substance of the\ncommunications between Mulgrew’s personal assistant and\nhimself, rather than the mode of those communications.\n\n Mulgrew also claims that he responded truthfully to\nthe second question.\n\n Q. Let me make sure as\n well that if I got your\n testimony correct [sic].\n You’re saying that if other\n people whether they be\n political leaders, friends\n and family, anybody is\n approaching your personal\n and asking her specifically\n to look out for a case, see\n what she can do in a case,\n give preferential treatment,\n however you want to\n phrase it, that she is not\n relaying any of that\n\n\n\n\n 48\n\f information on to you; is\n that correct?\n\n A. No, she isn’t.\n\n Q. Wouldn’t you want\n to know it?\n\n A. No, I don’t want to\n know. Then I never have to\n worry about what I do in\n the courtroom.\n\nApp. 437-38 (emphasis added). Apparently focusing on the\nwords “see what she can do,” he says that he answered\ntruthfully by responding that his personal assistant did not tell\nhim that people were approaching her and asking her to give\nthem preferential treatment. But, as with the first question,\nMulgrew cherry-picks a small part of the question out of\ncontext, distorting it. The full text and follow up question\nshow that the thrust of the inquiry was whether Mulgrew’s\npersonal assistant was informing him of the names of those\nrequesting preferential treatment from him. And Mulgrew’s\nresponse to the follow-up question —saying that he did not\nwant to know so that he did not have to worry about what he\ndid in the courtroom—is consistent with one who understood\nthis. App. 438.\n\n We conclude that, ultimately, the evidence is sufficient\nfor a reasonable jury to conclude Mulgrew understood that\nboth of these questions were focused on whether his personal\nassistant informed him of requests for him to give preferential\ntreatment, and that he answered in the negative to both.\n\n\n\n\n 49\n\f Mulgrew alternatively asserts that the District Court\nerred by refusing to admit additional testimony from the\nGrand Jury that he claims is relevant to his perjury\nconviction. 31 After the Government introduced Mulgrew’s\nGrand Jury testimony, Mulgrew sought the admission of other\nportions of his testimony. But the District Court sustained the\nGovernment’s hearsay objection. The portion of the\ntranscript supporting the perjury conviction is as follows:\n\n Q. [W]hether you have\n ever been asked to provide,\n what I’ll call, favorable\n treatment for people in\n traffic court or however\n you define that, whether it\n would be special handling,\n keep an eye out for a\n ticket, do me a favor.\n Have you ever been asked\n to provide any type of\n treatment like that for\n people in traffic court?\n\n A. People have asked\n me for consideration, but I\n give consideration to\n everybody that comes in\n my courtroom[,] so it\n\n31\n We review the District Court’s ruling on the admissibility\nof evidence for abuse of discretion. United States v. Green,\n617 F.3d 233, 239 (3d Cir. 2010).\n\n\n\n\n 50\n\f doesn’t make a difference\n to me.\n\n\nApp. 422-23. The basis for the Government’s hearsay\nobjection to this portion of the testimony was that it raised an\nout-of-court statement not offered by a party opponent.\n\n Mulgrew first contends that the District Court erred by\nruling that this was hearsay because it was not offered for the\ntruth of the matter asserted. He says that the testimony was\ninstead offered to show his state of mind later in his\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\n191-92 (3d Cir. 2008). However, we conclude that it was not\nan abuse of discretion for the District Court to sustain the\nGovernment’s hearsay objection. It was reasonable for the\nDistrict Court to conclude here that his response relied on\nout-of-court statements offered to assert his innocence since\nhis response conveys a declaration that he treated no person\ndifferent from another.\n\n Mulgrew also argues that this portion of the transcript\nis admissible under Federal Rule of Evidence 106: “[i]f a\nparty introduces all or part of a writing or recorded statement,\nan adverse party may require the introduction, at that time, of\nany other part—or any other writing or recorded statement—\nthat in fairness ought to be considered at the same time.”\nMulgrew maintains that this question and answer provides\ncontext showing that he did not commit perjury. He also\nmaintains that the “doctrine of completeness” applies here:\nfairness demanded the admission of the statements. See\n\n\n\n\n 51\n\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\nare not convinced.\n\n The excerpt at issue occurs many pages before the\ntestimony regarded as perjurious. It is unrelated in the overall\nsequence of questions and to the answers grounding his\nconviction. Moreover, as the intervening pages suggest, it\nwas separated by the passage of time during questioning. We\nalso fail to see how Mulgrew’s equivocation over the term\n“consideration” gives helpful context to his later denial of\nreceiving requests for consideration. For these reasons, we\nconclude the District Court did not abuse its discretion by\nsustaining the Government’s hearsay objection.\n\n IV.\n\n Appellant Singletary 33\n\n\n32\n “Under this doctrine of completeness, a second writing may\nbe required to be read if it is necessary to (1) explain the\nadmitted portion, (2) place the admitted portion in context, (3)\navoid misleading the trier of fact, or (4) insure a fair and\nimpartial understanding.” Soures, 736 F.2d at 91.\n33\n Appellant Singletary was charged with making false\nstatements in Counts 73 and 74 of the indictment. He states\nin his brief that he ‘joins all arguments on behalf of co-\nappellants pursuant to Federal Rules of Appellate Procedure\n28(i).” Singletary Br. 19. To the extent that he joins the\nargument of prejudice resulting from the trial on the fraud and\nconspiracy charges, we already have determined that the\nindictment was proper and no prejudice resulted from\n\n\n\n\n 52\n\f During the investigation of the Traffic Court by the\nFederal Bureau of Investigation, Appellant Singletary was\namong those interviewed. The jury acquitted Singletary of all\ncounts of wire fraud, mail fraud, and conspiracy. It found\nhim guilty of false statements made to the Federal Bureau of\nInvestigation. At sentencing, over Singletary’s objection, the\nDistrict Court sentenced Singletary using the Guideline on\nobstruction.\n\n The Government agrees that the single count on which\nhe was convicted does not contain all of the elements of\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\nGovernment agrees with Singletary that he is entitled to a\nremand for resentencing. Accordingly, we will vacate the\njudgment of sentence as to Singletary and remand to the\nDistrict Court for resentencing.\n\n V.\n\n For all of these reasons, we will vacate the judgment of\nsentence of the District Court with regard to Appellant\nSingletary and remand for resentencing. We will affirm the\njudgments of the District Court as to Appellants Alfano, Hird,\nLowry, Mulgrew and Tynes.\n\n\n\nbringing these charges to trial. As for the challenges to\nperjury in Counts 72 and 74, we note that Singletary was\ncharged with a different crime: false statements in a federal\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\nchallenges to all of such charges are inherently fact-intensive.\nAs he did not provide a factual basis for such a challenge, we\nregard the issue to be waived.\n\n\n\n\n 53\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. William HIRD, Appellant at No. 14-4754 United States of America v. Thomasine Tynes, Appellant at No. 14-4804 United States of America v. Robert Mulgrew, Appellant at No. 14-4812 United States of America v. Michael Lowry, Appellant at No. 15-1344 United States of America v. Willie Singletary, Appellant at No. 15-1739 United States of America v. Henry P. Alfano, AKA Ed, AKA Eddie, Henry P. Alfano, Appellant at No. 15-3765\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n\\n __________\\n\\nNos. 14-4754, 14-4804, 14-4812, 15-1344, 15-1739, 15-3765\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIAM HIRD,\\n Appellant at No. 14-4754\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n THOMASINE TYNES,\\n Appellant at No. 14-4804\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n ROBERT MULGREW,\\n Appellant at No. 14-4812\\n __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n MICHAEL LOWRY,\\n Appellant at No. 15-1344\\n\\f __________\\n\\n UNITED STATES OF AMERICA\\n v.\\n WILLIE SINGLETARY,\\n Appellant at No. 15-1739\\n ___________\\n\\n UNITED STATES OF AMERICA\\n v.\\n HENRY P. ALFANO,\\n aka Ed, aka Eddie,\\n\\n Henry P. Alfano,\\n Appellant at No. 15-3765\\n __________\\n\\n On Appeal from the United States District Court\\n for the Eastern District of Pennsylvania\\n\\n (District Court Criminal Nos. 2-13-cr-00039-007,\\n2-13-cr-00039-005, 2-13-cr-00039-003, 2-13-cr-00039-002,\\n 2-13-cr-00039-004, 2-13-cr-00039-008)\\n District Judge: Honorable Robert F. Kelly\\n District Judge: Honorable Lawrence F. Stengel\\n\\n Argued October 23, 2017\\n\\n BEFORE: GREENAWAY, JR., NYGAARD,\\n and FISHER, Circuit Judges\\n\\n\\n (Opinion Filed: January 18, 2019)\\n\\n\\n\\n\\n 2\\n\\fAngela Halim\\nHalim Drossner\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n\\nGregory J. Pagano\\n1315 Walnut Street, 12th Floor\\nPhiladelphia, PA 19107\\n Counsel for Appellant in No. 14-4754\\n\\nLisa A. Mathewson [Argued]\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant No. 14-4804\\n\\nPeter Goldberger [Argued]\\nPamela A. Wilk\\n50 Rittenhouse Place\\nArdmore, PA 19003\\n Counsel for Appellant in No. 14-4812\\n\\nMichael J. Engle [Argued]\\nStradley Ronon Stevens & Young\\n2005 Market Street, Suite 2600\\nPhiladelphia, PA 19103\\n\\nMeredith A. Lowry\\n1528 Walnut Street, Suite 1501\\nPhiladelphia, PA 19102\\n Counsel for Appellant in No. 15-1344\\n\\n\\n\\n\\n 3\\n\\fWilliam J. Brennan\\n1600 Locust Street\\nPhiladelphia, PA 19103\\n Counsel for Appellant in No. 15-1739\\n\\nMark E. Cedrone [Argued]\\nCedrone & Mancano\\n123 South Broad Street, Suite 810\\nPhiladelphia, PA 19109\\n Counsel for Appellant in No. 15-3765\\n\\n\\nLouis D. Lappen\\nDenise S. Wolf\\nAnthony J. Wzorek\\nRobert A. Zauzmer [Argued]\\nOffice of United States Attorney\\n615 Chestnut Street, Suite 1250\\nPhiladelphia, PA 19106\\n Counsel for Appellee\\n\\n\\n\\n\\n __________\\n\\n OPINION OF THE COURT\\n __________\\n\\nNYGAARD, Circuit Judge.\\n\\n I.\\n\\n\\n\\n\\n 4\\n\\f In the run-up to a joint trial on a 77-count indictment\\nthat charged Appellants with operating a ticket-fixing scheme\\nin the Philadelphia Traffic Court, the District Court denied a\\nmotion, under Federal Rule of Criminal Procedure\\n12(b)(3)(B)(v), to dismiss charges of conspiracy (18 U.S.C. §\\n1349), mail fraud (18 U.S.C. § 1341), and wire fraud (18\\nU.S.C. § 1343). Appellants Henry Alfano (private citizen)\\nand William Hird (Traffic Court administrator) subsequently\\npleaded guilty to all counts against them. But now they\\nappeal the District Court’s decision on this motion,\\nquestioning whether the indictment properly alleged offenses\\nof mail fraud and wire fraud. 1\\n\\n Appellants Michael Lowry, Robert Mulgrew, and\\nThomasine Tynes (Traffic Court judges) proceeded to a joint\\ntrial and were acquitted on the fraud and conspiracy counts,\\nbut they were convicted of perjury for statements they made\\nbefore the Grand Jury. Lowry, Mulgrew, and Tynes dispute\\nthe sufficiency of the evidence on which they were convicted\\nby arguing that the prosecutor’s questions were vague, and\\nthat their answers were literally true. Lowry and Mulgrew\\ncontend alternatively that the jury was prejudiced by evidence\\npresented at trial on the fraud and conspiracy counts.\\nMulgrew also complains that the District Court erred by\\nruling that certain evidence was inadmissible.\\n\\n At the same trial, the jury convicted Willie Singletary\\n(Traffic Court judge) of making false statements during the\\ninvestigation. He claims the District Court made errors when\\n\\n\\n1\\n Alfano and Hird preserved their right to appeal. See infra\\nsubsection I.C.\\n\\n\\n\\n\\n 5\\n\\fit sentenced him. 2 The Government concurs with\\nSingletary’s challenge to his sentence.\\n\\n We have consolidated these appeals for efficiency and\\nhave grouped the arguments—to the extent that it is\\npossible—by common issues. We agree with Singletary and\\nthe Government that he should be resentenced. We will\\nreverse the judgment and remand his cause to the District\\nCourt for this purpose. We are not persuaded by the rest of\\nAppellants’ arguments and will affirm their judgments of\\nconviction. 3\\n\\n II.\\n\\n Appellants Alfano 4 and Hird 5\\n\\n\\n\\n2\\n Singletary also attempted to join additional arguments raised\\nby other appellants, but for reasons we explain later, see infra\\nnote 33, we focus only on his challenge to his sentence.\\n3\\n The District Court had jurisdiction pursuant to 18 U.S.C. §\\n3231. We have jurisdiction to review these claims under 28\\nU.S.C.§ 1291 and 18 U.S.C. § 3742(a).\\n4\\n Appellant Alfano pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 2, 3, 4, 5, 6, 7) and Mail Fraud (Counts\\n51, 52, 53, 54, 55, 56).\\n5\\n Appellant Hird pleaded guilty to Conspiracy (Count 1),\\nWire Fraud (Counts 3, 4, 5, 6, 16, 17, 18, 19, 20, 22, 23) and\\nMail Fraud (Counts 58, 59, 60).\\n\\n\\n\\n\\n 6\\n\\f A.\\n\\n We begin with a brief look at the indictment’s\\ndescription of the Traffic Court and its operations to\\ncontextualize the arguments made by Alfano and Hird. The\\nPhiladelphia Traffic Court was part of the First Judicial\\nDistrict of Pennsylvania. App. 186 (Indictment ¶ 2). 6 It\\nadjudicated violations of the Pennsylvania Motor Vehicle\\nCode occurring in the City of Philadelphia, no matter whether\\nthe Philadelphia Police or the Pennsylvania State Police\\nissued the tickets. App. 187 (Indictment ¶5). When a person\\nwas cited for a violation he or she was required—within ten\\ndays—to enter a plea of guilty or not guilty. If the person\\nfailed to plead, the Traffic Court issued a notice that his or her\\nlicense was being suspended. App. 189 (Indictment ¶ 12). A\\nperson who pleaded not guilty proceeded to a hearing with a\\nTraffic Court judge presiding. App. 187 (Indictment ¶ 6).\\n\\n A guilty plea, or a determination of guilt by a Traffic\\nCourt judge after a hearing, resulted in a judgment ordering\\npayment of statutory fines and court costs. App. 188\\n(Indictment ¶ 8). 7 The Traffic Court was responsible for\\ncollecting these fines (sending them to the City and\\n\\n\\n6\\n Philadelphia Traffic Court was abolished and its jurisdiction\\nwas transferred to the Municipal Court in 2013 by an Act of\\nthe Pennsylvania General Assembly. 42 Pa.Con.Stat.\\n§1121(a)(2) (2013). The court is now known as the Traffic\\nDivision of the Municipal Court.\\n7\\n Although other penalties are prescribed by the Pennsylvania\\nMotor Vehicle Code (App. 188), this appeal is limited to the\\nmonetary fines and costs. App. 355.\\n\\n\\n\\n\\n 7\\n\\fCommonwealth) and costs (which it distributed to several\\npre-designated funds). App. 188-89 (Indictment ¶ 9).\\nFinally, it reported the disposition of each adjudication to the\\nPennsylvania Department of Transportation (PennDOT).\\nApp. 189 (Indictment ¶ 11).\\n\\n B.\\n\\n The indictment charged that, at the behest of Alfano\\n(App. 193 (Indictment ¶ 25)) and others, the Traffic Court\\nadministrator and judges operated an “extra-judicial system,\\nnot sanctioned by the Pennsylvania court system” that\\nignored court procedure and gave preferential treatment\\n(“consideration”) to select individuals with connections to the\\ncourt who had been cited for motor vehicle violations. App.\\n196 (Indictment ¶ 31). The special treatment included:\\n\\n (1) dismissing tickets outright; (2)\\n finding the ticketholder not guilty\\n after a “show” hearing; (3)\\n adjudicating the ticket in a\\n manner to reduce fines and avoid\\n assignment of points to a driver’s\\n record; and (4) obtaining\\n continuances of trial dates to\\n “judge-shop,” that is find a Traffic\\n Court judge who would accede to\\n a request for preferential\\n treatment.\\n\\nApp. 195-196 (Indictment ¶ 30). All of this was “not\\navailable to the rest of the citizenry.” App. 196 (Indictment ¶\\n32). It also alleged that Appellants cooperated with each\\n\\n\\n\\n\\n 8\\n\\fother to fulfill requests they and their staffs received. App.\\n194-95 (Indictment ¶ 27). Finally, it charged that “[i]n\\nacceding to requests for ‘consideration,’ defendants were\\ndepriving the City of Philadelphia and the Commonwealth of\\nPennsylvania of money which would have been properly due\\nas fines and costs.” App. 197 (Indictment ¶ 38). 8\\n After extending consideration to favored individuals,\\nTraffic Court judges would report the final adjudication to\\n“various authorities, including PennDOT, as if there had been\\na fair and open review of the circumstances.” App. 197\\n(Indictment ¶ 34). Appellant Hird provided a printout to\\nAppellant Alfano showing citations that had been “dismissed\\nor otherwise disposed of.” App. 198-99 (Indictment ¶ 42).\\nSuch “receipts” were not routinely issued in cases.\\n\\n C.\\n\\n Hird and Alfano pleaded guilty to all the charges\\nagainst them in the indictment. But, in their plea agreement\\nthey reserved the right to appeal “whether the Indictment\\n\\n\\n8\\n An example of the many allegations involving Alfano and\\nHird is: A.S. requested assistance from Appellant Alfano and\\nAppellant Hird on Citation Number P1J0PK568L4 on or\\naround February 17, 2010. The citation charged A.S. with\\ndriving a tractor-trailer from which snow and ice fell, striking\\nvehicles on Interstate 95. The violation carried a $300 fine\\nand costs of $142. Appellant Hird promised that he would\\n“stop all action” on the citation and instructed A.S. to ignore\\nthe ticket. Although A.S. did not appear at the hearing, the\\nTraffic Court judge (who is not an appellant here) ruled A.S.\\nnot guilty. App. 210-12 (Indictment ¶¶ 25-34).\\n\\n\\n\\n\\n 9\\n\\fsufficiently alleged that the defendants engaged in a scheme\\nto defraud the Commonwealth of Pennsylvania and the City\\nof Philadelphia of money in costs and fees.” App. 355 (Plea\\nAgreement ¶ 9(b)(4)). So they now appeal the District\\nCourt’s order denying the motion to dismiss, asserting that\\nthe indictment failed to allege violations of mail fraud and\\nwire fraud.\\n\\n “To be sufficient, an indictment must allege that the\\ndefendant performed acts which, if proven, constitute a\\nviolation of the law that he is charged with violating.” United\\nStates v. Small, 793 F.3d 350, 352 (3d Cir. 2015). We\\nassume in our review that the allegations in the indictment are\\ntrue. United States v. Hedaithy, 392 F.3d 580, 583 (3d Cir.\\n2004). “The question of whether the . . . indictments alleged\\nfacts that are within the ambit of the mail fraud statute is a\\nquestion of statutory interpretation subject to plenary review.”\\nId. at 590 n.10.\\n\\n To indict on mail or wire fraud, the Government must\\nallege that defendants “devised or intend[ed] to devise any\\nscheme or artifice to defraud, or for obtaining money or\\nproperty by means of false or fraudulent pretenses,\\nrepresentations, or promises” and used mail or wire to effect\\nthe scheme. 18 U.S.C. §§ 1341, 1343. Alfano and Hird claim\\nthe Government failed to allege that the scheme to commit\\nwire and mail fraud had an objective of “obtaining money or\\nproperty.” 9\\n\\n9\\n In the context of mail fraud (§ 1341) and wire fraud (§1343)\\nthe term “money” has the same meaning. The same is true\\nfor the term “property.” Carpenter v. United States, 484 U.S.\\n19, 25 n. 6 (1987).\\n\\n\\n\\n\\n 10\\n\\f The District Court ruled that the indictment\\nsufficiently alleged that the scheme “involved defrauding the\\nCommonwealth and the City of money.” App. 20. It noted,\\namong others, allegations that:\\n\\n The conspirators used the\\n Philadelphia Traffic Court\\n (“Traffic Court”) to give\\n preferential treatment to certain\\n ticketholders, most commonly by\\n “fixing” tickets for those with\\n whom they were politically and\\n socially connected. By doing so,\\n the conspirators defrauded the\\n Commonwealth of Pennsylvania\\n and the City of Philadelphia of\\n funds to which the\\n Commonwealth and the City were\\n entitled.\\n\\nId. at 18; see also id. at 185 (Indictment ¶ 1). Similarly, it\\nreferred to the following.\\n\\n In acceding to requests for\\n “consideration,” defendants were\\n depriving the City of Philadelphia\\n and the Commonwealth of\\n Pennsylvania of money which\\n would have been properly due as\\n fines and costs.\\n\\n\\n\\n\\n 11\\n\\fId. at 9; see also id. at 197 (quoting Indictment ¶ 38).\\nHighlighting the references to “funds” and “money,” and that\\nthe monetary amounts of the fines are specifically pleaded,\\nthe District Court cited to a case from the Court of Appeals\\nfor the Eighth Circuit which concluded succinctly that\\n“[m]oney is money.” United States v. Sullivan, No. 2:13-cr-\\n00039, 2013 WL 3305217, at *7 (E.D. Pa. July 1, 2013)\\n(quoting United States v. Granberry, 908 F.2d 278, 280 (8th\\nCir. 1990)). The District Court was satisfied that the\\nindictment alleged enough.\\n\\n “Money, of course, is a form of property.” Reiter v.\\nSonotone Corp., 442 U.S. 330, 338 (1979). But Alfano and\\nHird argue that the mere mention of money in an indictment\\nis not enough. They point to a string of Supreme Court and\\nCourt of Appeals decisions analyzing Section 1341 and\\nSection 1343 which reinforce the point that crimes of mail\\nfraud and wire fraud are “limited in scope to the protection of\\nproperty rights.” McNally v. United States, 483 U.S. 350, 360\\n(1987). 10 The Supreme Court said that “[a]ny benefit which\\nthe government derives from the [mail fraud] statute must be\\nlimited to the Government’s interests as a property holder.”\\nId. at 359 n.8 (emphasis added). Appellants are convinced\\nthat money in the form of traffic fines and costs cannot be\\nregarded as the Government’s “property” for purposes of mail\\nor wire fraud, and they identify two decisions as particularly\\nsupportive of their position: Cleveland v. United States, 531\\n\\n10\\n The District Court cited to a number of cases that came\\nafter McNally: Carpenter v. United States, 484 U.S. 19\\n(1987); Cleveland v. United States, 531 U.S. 12 (2000);\\nPasquantino v. United States, 544 U.S. 349 (2005).\\n\\n\\n\\n\\n 12\\n\\fU.S. 12 (2000); and United States v. Henry¸ 29 F.3d 112 (3d\\nCir. 1994).\\n\\n The Court in Cleveland examined the mail fraud\\nconvictions of individuals who received a state video poker\\nlicense by submitting a license application that withheld\\nimportant information. Cleveland, 531 U.S. 12. 11 The Court\\nnoted that the video poker licenses were part of a state\\nprogram that was “purely regulatory.” Id. at 22 (citation\\nomitted). 12 It ruled that licenses are a “paradigmatic\\nexercise[] of the States’ traditional police powers.” Id. at 23.\\nThe Court went on to say that the state’s regulatory powers\\ninvolving “intangible rights of allocation, exclusion, and\\ncontrol” (which are embodied in a license) are not interests\\nthat traditionally have been recognized as property. Id.\\nTherefore, even though appellants may have obtained the\\nlicense through deception, this was not mail fraud because the\\nlicense—at least while still in the hands of the state—was not\\n\\n\\n\\n11\\n The licenses were part of a regulatory scheme that had as\\nits purpose to increase public confidence in the honesty of\\ngaming activities that are free of criminal involvement.\\nCleveland, 531 U.S. at 20–21 (quoting La. Rev. Stat. Ann. §\\n27:306(A)(1) (2000) (repealed 2012)).\\n12\\n The Court rebuffed the Government’s attempts to analogize\\nlicenses to other forms of property like patents and franchise\\nrights. As for likening licenses to franchise rights, the Court\\nobserved that the Government did not enter the video poker\\nbusiness, but rather decided to “permit, regulate, and tax\\nprivate operators of the games.” Id. at 24.\\n\\n\\n\\n\\n 13\\n\\fproperty. Id. at 26-27. It was a purely administrative tool\\nused to achieve regulatory objectives. Id. at 21.\\n\\n The state responded to the Court’s concerns by\\nagreeing that the licenses served a regulatory purpose, but it\\ndirected attention to the revenue it received from fees\\ncollected for license applications and renewals, as well as\\ndevice fees. Id. at 21-22. It argued that this revenue is a\\nproperty interest. Id. The Court was not convinced:\\n\\n Tellingly, as to the character of\\n Louisiana’s stake in its video\\n poker licenses, the Government\\n nowhere alleges that Cleveland\\n defrauded the State of any money\\n to which the State was entitled by\\n law. Indeed, there is no dispute\\n that TSG paid the State of\\n Louisiana its proper share of\\n revenue, which totaled more than\\n $1.2 million, between 1993 and\\n 1995. If Cleveland defrauded the\\n State of “property,” the nature of\\n that property cannot be economic.\\n\\nId. at 22 (emphasis added). It concluded that “[e]ven when\\ntied to an expected stream of revenue, the State’s right of\\ncontrol does not create a property interest any more than a\\nlaw licensing liquor sales in a State that levies a sales tax on\\n\\n\\n\\n\\n 14\\n\\fliquor.” Id. at 23. 13 The money collected from application\\nand processing fees was an integral part of the state\\nregulatory program and it did not create any property interest.\\nSee id.\\n\\n The purpose of the Pennsylvania Motor Vehicle Code\\nis to “promote the safety of persons and property within the\\nstate.” Mauer v. Boardman, 7 A.2d 466, 472 (Pa. 1939).\\nMoreover, issuing traffic tickets is a crucial element in the\\nenforcement of the Motor Vehicle Code: it is a quintessential\\nexercise of state police power. Alfano and Hird conclude,\\nmuch like Cleveland, that no property interest could arise\\nfrom revenue generated from the state’s exercise of its police\\npower in the form of a traffic-ticket fine. They see nothing\\nbut a regulatory program here. But this ignores crucial\\naspects of the case before us that make it different.\\n\\n Simply stated, fees charged to obtain a license cannot\\nbe equated with fines and costs that result from a traffic\\nticket. The license fee was imposed, adjusted, and collected\\nsolely by the state’s exercise of its regulatory authority. In\\ncontrast, here the state’s police power is exercised when a\\ncitation is issued, but this ticket merely establishes the\\nsummary violation with which the person is charged. Once a\\nperson has been charged, it is judicial power (not the state’s\\npolice power) that is exercised to determine whether the\\n\\n\\n\\n\\n13\\n Cleveland also held that Government-issued licenses have\\nno intrinsic economic worth before they are given to\\napplicants. Id. at 23.\\n\\n\\n\\n\\n 15\\n\\fperson is guilty and, if guilty, to impose the fine and costs. 14\\nThese fines and costs, although specified by the Motor\\nVehicle Code, cannot be cabined as a product of the state’s\\nregulatory authority. They are part and parcel of the\\njudgment of the court. With this in mind, it is significant that\\nthe indictment does not focus on how the citations were\\nissued (which would implicate police power), but rather\\nalleges that the judicial process was rigged to produce only\\njudgments that imposed lower fines—or most often—no fines\\nand costs at all. 15\\n\\n But this raises a further question: can a criminal\\njudgment held by the government ever be “property?” The\\nCourt in Cleveland offered a critique in its analysis of a\\n\\n14\\n The Traffic Court was not an administrative tribunal.\\nRather, it was part of the First Judicial District of\\nPennsylvania. App. 186 (Indictment ¶ 2). See also supra\\nnote 6 and accompanying text.\\n15\\n On this point, it is noteworthy that the Supreme Court also\\nsaid the following: “We resist . . . [any invitation] to approve\\na sweeping expansion of federal criminal jurisdiction in the\\nabsence of a clear statement by Congress. . . . ‘[U]nless\\nCongress conveys its purpose clearly, it will not be deemed to\\nhave significantly changed the federal-state balance’ in the\\nprosecution of crimes.” Cleveland, 531 U.S. at 24-25\\n(quoting Jones v. United States, 529 U.S. 848, 858 (2000)).\\nAs we discuss later, the legal tradition of understanding\\njudgments as property is long-established. Consequently, the\\nconcern about expanding the reach of federal fraud statutes to\\nnew classes of property that was present in the deliberation of\\nstate licenses in Cleveland is not at issue here.\\n\\n\\n\\n\\n 16\\n\\fdifferent issue (whether licenses were analogous to patents)\\nthat is apropos to answering this question.\\n\\n [W]hile a patent holder may sell\\n her patent, see 35 U.S.C. § 261 . .\\n . “patents shall have the attributes\\n of personal property” . . . the State\\n may not sell its licensing\\n authority. Instead of a patent\\n holder’s interest in an unlicensed\\n patent, the better analogy is to the\\n Federal Government’s interest in\\n an unissued patent. That interest,\\n like the State’s interest in\\n licensing video poker operations,\\n surely implicates the\\n Government’s role as sovereign,\\n not as property holder.\\n\\nCleveland, 531 U.S. at 23–24. Fines imposed by judges are\\ncriminal penalties that “implicate[] the Government’s role as\\nsovereign.” Id. at 24. Judgments ordering traffic fines and\\ncosts cannot be sold and, in the logic of Cleveland, would\\nseem then to have no intrinsic economic value. Indeed, the\\npenal (non-economic) nature of the fine is undeniable because\\nthe failure to pay a fine can result in the imposition of\\nsentences of greater consequence, including imprisonment.\\nSee Pa. R. Crim. P. 706 cmt. But Cleveland is not the last\\nword. As we will discuss below, a Supreme Court opinion\\nissued five years later, Pasquantino v. United States, 544 U.S.\\n349 (2005), forecloses the defendants’ argument.\\n\\n\\n\\n\\n 17\\n\\f Finally, we note a dissimilarity between this case and\\nCleveland, highlighted by the District Court, on the\\nsignificance of the monetary interest that the Government\\nassociates with the fraud. The Cleveland Court regarded the\\nlicensing fees as integral to the regulatory effort and collateral\\nto the matter at hand. The indictment there centered on the\\nscheme to obtain liceneses, and did not even raise the\\nlicensing fees. See Cleveland, 531 U.S. at 22. Indeed, those\\ncharged with the fraud paid all the appropriate fees; there was\\nno evidence that the government suffered any economic\\ndetriment. Id.\\n\\n In contrast, the indictment here explicitly states that\\nthe scheme deprived the City and the Commonwealth of\\nmoney, and it describes the object of the scheme as obviating\\njudgments of guilt that imposed the fines and costs. Unlike\\nCleveland, the fines and costs play a central role in the\\nscheme as alleged.\\n\\n Alfano and Hird next focus on our decision in Henry\\nto argue that the Government cannot claim to have a property\\nright because the Government never had a legal claim to the\\nfines and costs at any point in the scheme. In Henry, we\\nexamined convictions for wire fraud arising from a\\ncompetitive bidding process among banks to receive deposits\\nof a public agency’s bridge tolls. Henry v. United States, 29\\nF.3d 112 (3d Cir. 1994). Appellants—public employees—\\nwere convicted of mail fraud for giving one bank confidential\\ninformation about bids from other banks. Id. at 113. We\\nidentified several problems, 16 but Alfano and Hird highlight\\n\\n16\\n The Supreme Court had already made clear that “a\\ngovernment official’s breach of his or her obligations to the\\n\\n\\n\\n\\n 18\\n\\four observation in Henry that the object of the mail and wire\\nfraud must be something to which the victim could claim a\\nright of entitlement. Id. at 115 (“a grant of a right of\\nexclusion”) (citing Carpenter, 484 U.S. at 26-27)). 17 Indeed,\\nwe noted that a bank’s property right to the tolls would attach\\nonly after the funds were deposited. Id. at 114. So the banks\\nthat lost the bidding process never had a basis to claim any\\nlegally recognized entitlement to the toll deposits. 18 Id. at\\n115. A fraud claim cannot rest on the bidders being cheated\\nout of an opportunity to receive the deposits. For these\\nreasons, we concluded that the indictment did not allege a\\nscheme to obtain fraudulently someone’s “property.” Id. at\\n116.\\n\\n Here, the Government alleged that the defendants\\n“were depriving . . . Philadelphia and . . . Pennsylvania of\\nmoney which would have been properly due as fines and\\ncosts” by making it possible for certain well-connected\\nindividuals to avoid a judgment of guilt that imposed an\\nobligation to pay appropriate statutory fines. App. 197\\n\\n\\npublic or an employee’s breach of his or her obligations to an\\nemployer” did not fall within the scope of Section 1343.\\nHenry, 29 F.3d at 114 (citing Carpenter, 484 U.S. at 25).\\n17\\n To assess whether a particular claim is a legal entitlement,\\n“we look to whether the law traditionally has recognized and\\nenforced [the entitlement] as a property right.” Henry, 29\\nF.3d at 115.\\n18\\n They were, no doubt, robbed of a fair process, but we could\\nnot identify any legal tradition that recognized this\\ndeprivation as a property right. Id. at 115.\\n\\n\\n\\n\\n 19\\n\\f(Indictment ¶ 38). But Appellants stress that, like the\\ndeposits in Henry, the indictment here alleged an entitlement\\nthat does not yet exist because a person must be adjudicated\\n(or plead) guilty before they must pay any fines or costs.\\nNone of the cases directly associated with Alfano and Hird\\nresulted in a guilty judgment. As a result, they argue, the\\nGovernment cannot claim here that it was cheated of an\\nentitlement, because they were only fines and costs that the\\npeople might have owed if they had been found guilty.\\n\\n The District Court said it well. Accepting this\\nargument “would permit the alleged conspirators” to take\\nadvantage of their “unique position” in this case “to enter into\\na scheme to commit fraud and then hide behind the argument\\nthat the success of their fraud precludes prosecution under the\\n‘money or property interest’ requirement of the mail and wire\\nfraud statutes.” Sullivan, 2013 WL 3305217, at *7.\\nAppellants cannot rest on the very object of their scheme (to\\nwork on behalf of favored individuals to obviate judgments of\\nguilt and the imposition of fines and costs) as the basis to\\nclaim that there is no fraud. Indeed, the not-guilty judgments\\nthat Alfano and Hird worked to obtain through the\\nextrajudicial system were alleged in the indictment as\\nevidence of the scheme itself.\\n\\n Even if some of the cases in the extra-judicial system\\nwould have been judged not guilty in a real adjudication it is\\n(as the District Court correctly noted) the intent of the\\nscheme, not the successful execution of it, that is the basis for\\ncriminal liability. See Neder v. United States, 527 U.S. 1, 25\\n(1999) (In the criminal context, the court focuses on the\\nobjective of the scheme rather than its actual outcome; what\\noperatives intended to do, not whether they were successful in\\n\\n\\n\\n\\n 20\\n\\fdoing it.); United States v. Rowe, 56 F.2d 747, 749 (2d Cir.)\\n(“Civilly of course the [mail fraud statute]would fail without\\nproof of damage, but that has no application to criminal\\nliability.”), cert. denied 286 U.S. 554 (1932). The indictment\\ngenerally alleges not just that Appellants operated a system\\nthat operated outside the bounds of Traffic Court procedures,\\nbut that it did so for the purpose of obviating judgments of\\nguilt imposing fines and costs in those selected cases. See,\\ne.g., supra note 8. Moreover, we note that in one case not\\ndirectly involving either Alfano or Hird, the indictment\\nalleged that fines and costs were not just obviated, but were\\nactually erased by an alleged co-conspirator traffic court\\njudge who ignored the conviction, backdated a continuance,\\nand “adjudicated” the person not-guilty. App. 228-29\\n(Indictment ¶¶ 108-113). This episode serves to highlight\\nthat the entire scheme was centered on keeping (or taking)\\njudgments out of the hands of the Government to prevent the\\nimposition of fines and costs. As a result, Appellants’\\nreliance on our justice system’s presumption of innocence as\\na basis to argue against the existence of a governmental\\nproperty interest is a red herring that is properly disregarded\\nhere.\\n\\n Accordingly, we conclude that the indictment’s\\nallegation that the scheme had an objective of depriving\\n“Philadelphia and . . . Pennsylvania of money which would\\nhave been properly due as fines and costs” is not undermined\\nby the lack of guilty verdicts. App. 197 (Indictment ¶38\\n(emphasis added)).\\n\\n Alfano and Hird next highlight that, in Henry, our\\nproperty interest analysis centered on “whether the law\\ntraditionally has recognized and enforced [the entitlement in\\n\\n\\n\\n\\n 21\\n\\fquestion] as a property right.” 29 F.3d at 115. Appellants\\nassert that traffic fines and costs typically have not been\\nconsidered economic property and are unsupported by any\\nlegal tradition sufficient to ground charges of wire and mail\\nfraud. As we have already noted we disagree with any\\nconclusion that the fines and costs at issue have no intrinsic\\neconomic value. But we turn to another decision of the\\nSupreme Court that came after Cleveland to address squarely\\nwhether jurisprudence supports our conclusion.\\n\\n In 2005 the Supreme Court reviewed convictions\\narising from a scheme to smuggle large quantities of liquor\\nfrom the United States into Canada, evading Canadian taxes.\\nSee Pasquantino v. United States, 544 U.S. 349, 353 (2005).\\nThe Court noted that the right to be paid has been routinely\\nrecognized as property, id. at 355–56, 19 observing that there is\\nan equivalence between “money in hand and money legally\\ndue,” id. at 356. Affirming the conviction, the Court said:\\n“Had petitioners complied with this legal obligation, they\\nwould have paid money to Canada. Petitioners’ tax evasion\\ndeprived Canada of that money, inflicting an economic injury\\nno less than had they embezzled funds from the Canadian\\ntreasury.” Id. It concluded that: “[t]he object of petitioners’\\nscheme was to deprive Canada of money legally due, and\\ntheir scheme thereby had as its object the deprivation of\\nCanada’s ‘property.’” Id. Under Pasquantino, then, traffic\\ntickets (or more precisely, judgments arising from them) are\\nconsidered an “entitlement to collect money from individuals,\\n\\n\\n19\\n The Court cited 3 W. Blackstone, Commentaries on the\\nLaws of England 153–155 (1768), which classified the right\\nto sue on a debt as personal property.\\n\\n\\n\\n\\n 22\\n\\fthe possession of which is ‘something of value.’” 544 U.S. at\\n355 (quoting McNally, 483 U.S. at 358). 20 We conclude that\\na scheme to obviate judgments imposing fines, effectively\\npreventing the government from holding and collecting on\\nsuch judgments imposes an economic injury that is the\\nequivalent of unlawfully taking money from fines paid out of\\nthe Government’s accounts. See id. at 358.\\n\\n Alfano and Hird focus, finally, on the role that a\\njudge’s discretion plays in the adjudication of a case,\\nasserting that the uncertainty this creates about outcomes in\\nany given case undermines any argument that a judgment in a\\nTraffic Court case can be claimed as an entitlement to\\nproperty. To the extent that this merely rephrases the issue of\\nguilt or innocence on particular charges, we have already\\n\\n20\\n We also note that Pennsylvania law permits the government\\nto remedy the nonpayment of fines and costs as an unpaid\\ndebt through civil process, enabling the government to\\nbecome a judgment creditor. Pa. R. Crim. P. 706 cmt.\\n(“Nothing in this rule [concerning criminal fines] is intended\\nto abridge any rights the Commonwealth may have in a civil\\nproceeding to collect a fine or costs.”). Because of this, a\\nseparate legal tradition is implicated that recognizes the\\njudgment itself as property. See, e.g., Armada (Singapore)\\nPTE Ltd. v. Amcol International Corp., 885 F.3d 1090, 1094\\n(7th Cir. 2018). This long, stable legal tradition of\\nrecognizing civil judgments for money as property supports\\nthe conclusion that the fines arising from judgments in traffic\\ncourt cannot be regarded merely as implicating the act of a\\nsovereign imposing a criminal penalty. They can be collected\\nby civil process as a debt and are, thus, a property interest.\\n\\n\\n\\n\\n 23\\n\\faddressed it above. To the degree that it refers to a judge’s\\ndiscretion in sentencing, as the District Court noted, there is\\nno such discretion here. 21 The Motor Vehicle Code imposes\\nfines and costs for each violation, eliminating any judicial\\ndiscretion in this regard.\\n\\n D.\\n\\n All of this leads us to conclude that the District Court\\ndid not err by denying the motion to dismiss. We conclude\\nthat, as alleged, this scheme had the objective of preventing\\nthe City of Philadelphia and the Commonwealth of\\nPennsylvania from possessing a lawful entitlement to collect\\nmoney in the form of fines and costs—a property interest—\\nfrom individuals who Alfano and Hird assisted. We will thus\\naffirm the convictions of Appellants Alfano and Hird.\\n\\n III.\\n\\n Appellants Tynes, Lowry, and Mulgrew\\n\\n A.\\n\\n\\n\\n\\n21\\n We question, in general, the relevance of an entity’s\\nauthority to relinquish a just entitlement or to forbear an\\nobligation that an entitlement imposes upon another, as a\\nbasis to call into doubt the legitimacy of, or the very existence\\nof the entitlement. But see United States v. Mariani, 90 F.\\nSupp. 2d 574, 583 (M.D. Pa. 2000) (Discretionary civil fines\\nand penalties “may be too speculative to constitute a valid\\nproperty interest.”) (internal citation omitted).\\n\\n\\n\\n\\n 24\\n\\f In 2011, the United States Attorney presented to the\\nGrand Jury evidence arising from the Federal Bureau of\\nInvestigation’s inquiry into the Traffic Court. Appellants\\nLowry, Mulgrew, and Tynes testified and the Government\\nbrought perjury charges against them for statements they\\nmade to the Grand Jury. After Hird and Alfano pleaded\\nguilty, the rest of the Appellants went to trial. The jury\\nacquitted Lowry, Mulgrew, and Tynes of all counts against\\nthem on wire fraud, mail fraud, and conspiracy. But it found\\nthem guilty of perjury. Tynes, Lowry, and Mulgrew\\nchallenge their convictions by raising similar legal arguments\\nabout the sufficiency of the evidence.\\n As with all challenges to the sufficiency of the\\nevidence, we use a highly deferential standard of review. See\\nUnited States v. Caraballo-Rodriguez, 726 F.3d 418, 430 (3d\\nCir. 2013) (en banc). We examine the record in a light most\\nfavorable to the prosecution, and will not disturb the verdict if\\n“any rational trier of fact could have found the essential\\nelements of the crime beyond a reasonable doubt.” United\\nStates v. McGee, 763 F.3d 304, 316 (3d Cir. 2014) (emphasis\\nin original) (quoting Jackson v. Virginia, 443 U.S. 307, 319\\n(1979)). Tynes, Lowry, and Mulgrew argue that the\\nquestions asked of them at trial were fatally vague and/or that\\ntheir answers were truthful. As a result, they contend that\\nthese questions and answers are an inadequate basis for a\\nperjury conviction.\\n\\n A conviction for perjury before a grand jury requires\\nthe Government to prove that the defendant took an oath\\nbefore the grand jury and then knowingly made a “false\\nmaterial declaration.” 18 U.S.C. § 1623. But we recognized\\n(in the context of a sentencing enhancement for perjury) that\\nsometimes “confusion, mistake, or faulty memory” results in\\n\\n\\n\\n\\n 25\\n\\finaccuracies that cannot be categorized as a “willful attempt\\nto obstruct justice” under perjury statutes. United States v.\\nMiller, 527 F.3d 54, 75 (3d Cir. 2008) (quoting U.S.\\nSentencing Guidelines Manual § 3C1.1 cmt. n.2 (U.S.\\nSentencing Comm’n 2003). So we do understand that\\n“[p]recise questioning is imperative as a predicate for the\\noffense of perjury.” Bronston v. United States, 409 U.S. 352,\\n362 (1973).\\n\\n Precision, however, is assessed in context. An\\nexaminer’s line of questioning should, at a minimum,\\nestablish the factual basis grounding an accusation that an\\nanswer to a particular question is false. Miller, 527 F.3d at\\n78. So a perjury conviction is supported by the record “when\\nthe defendant’s testimony ‘can reasonably be inferred to be\\nknowingly untruthful and intentionally misleading, even\\nthough the specific question to which the response is given\\nmay itself be imprecise.’” United States v. Serafini, 167 F.3d\\n812, 823 (3d Cir. 1999) (quoting United States v. DeZarn,\\n157 F.3d 1042, 1043 (6th Cir. 1998)).\\n\\n Challenges to the clarity of a question are typically left\\nto the jury, which has the responsibility of determining\\nwhether the defendant understood the question to be\\nconfusing or subject to many interpretations. United States v.\\nSlawik, 548 F.2d 75, 86 (3d Cir. 1977). Moreover, consistent\\nwith our standard of review, we will not disturb a jury’s\\ndetermination that a response under oath constitutes perjury\\nunless “it is ‘entirely unreasonable to expect that the\\ndefendant understood the question posed to him.’” Serafini,\\n167 F.3d at 820 (quoting United States v. Ryan, 828 F.2d\\n1010, 1015 (3d Cir. 1987), abrogated on other grounds by\\n\\n\\n\\n\\n 26\\n\\fUnited States v. Wells, 519 U.S. 482 (1997)). 22 On appeal,\\nwe review every aspect of the record pertinent to both the\\nquestion and answer to reach a conclusion about whether, in\\ncontext, the witness understood the question well enough to\\ngive an answer that he or she knew to be false. See Miller,\\n527 F.3d at 78. Our review, however, is focused on glaring\\ninstances of vagueness or double-speak by the examiner at the\\ntime of questioning (rather than artful post-hoc interpretations\\nof the questions) that—by the lights of any reasonable fact-\\nfinder—would mislead or confuse a witness into making a\\nresponse that later becomes the basis of a perjury conviction.\\nQuestions that breach this threshold are “fundamentally\\nambiguous” and cannot legitimately ground a perjury\\nconviction. Id. at 77. 23\\n\\n\\n22\\n The Court of Appeals for the Second Circuit underscored\\nthe high bar this establishes for appellants by noting that a\\nfundamentally ambiguous question is “not a phrase with a\\nmeaning about which men of ordinary intellect could agree,\\nnor one which could be used with mutual understanding by a\\nquestioner and answerer unless it were defined at the time it\\nwere sought and offered as testimony.” United States v.\\nLighte, 782 F.2d 367, 375 (2d Cir. 1986) (quoting United\\nStates v. Lattimore, 127 F. Supp. 405, 410 (D. D.C.), aff’d,\\n232 F.2d. 334 (D.C. Cir. 1955)).\\n23\\n The rule of fundamental ambiguity is intended to\\n“preclude convictions that are grounded on little more than\\nsurmise or conjecture, and . . . prevent witnesses . . . from\\nunfairly bearing the risks associated with the inadequacies of\\ntheir examiners.” Ryan, 828 F.2d at 1015.\\n\\n\\n\\n\\n 27\\n\\f That is the law applicable to the claims raised by\\nTynes, Lowry and Mulgrew. But, because our review is fact-\\ndependent, and because each raises some unique issues, we\\nwill address each of their claims individually. 24\\n B.\\n\\n\\n\\n\\n24\\n Adopting the arguments made by Alfano and Hird,\\nAppellants Lowry, Mulgrew and Tynes assert that the\\nGovernment improperly charged them with conspiracy, wire\\nfraud, and mail fraud. Therefore, they assert, their joint trial\\non these counts of the indictment prejudiced the jury’s\\ndeliberation on the charges of perjury. They claim such\\nevidence would have been excluded under Federal Rule of\\nEvidence. 403. They also contend that, without a charge of\\nconspiracy, the joinder of their cases would have been\\nimpermissible under Federal Rule of Criminal Evidence 8(b)\\nor, at the very least, severance of their cases would have been\\nwarranted under Federal Rule of Criminal Procedure 14(a).\\nCertainly, where there is evidence of prejudice resulting from\\n“spillover” evidence from counts that should have been\\ndismissed, reversal is warranted. See United States v. Wright,\\n665 F.3d 560, 575-577 (3d Cir. 2012). But we have\\nconcluded that the District Court did not err by denying the\\nmotion, under Federal Rule of Civil Procedure 12(b)(3), to\\ndismiss the conspiracy, wire fraud and mail fraud counts of\\nthe indictment. Thus, Appellants’ spillover argument has\\nbeen nullified. Likewise, Appellants have no basis to claim\\nthat the Court unfairly prejudiced them by not granting\\nseparate trials.\\n\\n\\n\\n\\n 28\\n\\f Appellant Tynes 25\\n\\n Appellant Tynes claims her convictions for perjury at\\nCount 71 and Count 72 lack sufficient evidence because she\\nwas responding to questions that were fundamentally\\nambiguous. The perjury charged at Count 71 arises from the\\nfollowing exchange.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n\\n\\n25\\n Tynes filed a separate motion to dismiss. App. 291-99.\\nThe record also contains Tynes’ proposed order to join\\nSullivan’s motion to dismiss. App. 290. However, Tynes’\\nmotion contains no such request. Moreover, the\\nGovernment’s response to the motions notes that Lowry and\\nMulgrew moved to join (without argument), and makes no\\nmention of Tynes. The District Court’s ruling on Tynes’\\nmotion to dismiss relates only to the arguments she made\\nseparately in her brief. As a result, we cannot consider\\nTynes’ arguments on appeal that relate to those raised in\\nSullivan’s motion. Moreover, since she failed to raise any of\\nthe arguments she made in her separate motion to dismiss,\\nthese arguments are waived. With that said, we will affirm\\nthe District Court’s ruling on the Motion raised by Sullivan\\nand joined by the five Appellants. Therefore, we need not\\naddress Tynes’ assertion that the District Court’s mishandled\\nher joinder motion because it does not prejudice the outcome\\nof her appeal.\\n\\n\\n\\n\\n 29\\n\\f favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously, and the\\n cards fall where they may.\\n\\nApp. 255, 5720. 26 Tynes contends that the Government\\npursued a novel theory here (applying federal fraud statutes to\\nallegations of ticket fixing) and used the vague term\\n“favorable treatment” to gloss over its uncertainty about what,\\nultimately, would constitute an illegal act. She points out that\\nthe term had not been used before in reference to this case\\nand that the Government offered no explanation or definition\\nof the term to alert Tynes to the intent of the question.\\n\\n Also, from Tynes’ perspective, every litigant\\nappearing before a court seeks an outcome that is favorable,\\nthus making “favorable treatment” a term that essentially\\nreferred to “how litigation works.” She claims that its use\\namounted to a fishing expedition designed to capture unfairly\\n\\n26\\n We cite to the testimony quoted in the indictment and the\\nGrand Jury that was used at trial. We note that there are some\\ntypographical inconsistencies between these sources and in\\nthose instances we have quoted the Grand Jury testimony.\\n\\n\\n\\n\\n 30\\n\\fthe entirety of her conduct in the courtroom. She warns that\\nthis is precisely the type of “open-ended construction” in\\nquestioning that we found unacceptable in Serafini. 167 F.3d\\nat 822.\\n\\n Tynes makes a related argument against her perjury\\nconviction for Count 72. That conviction is based on this\\nexchange.\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 257, 5722. She maintains that the word “request” was\\npresented to the jury as a follow-on to the question grounding\\nCount 71, requiring a person to link the term “favorable\\ntreatment” and the word “request” to make sense of it. She\\nargues that the Government took advantage of the ambiguity\\nof “favorable treatment,” forcing the jury to speculate that\\nTynes interpreted “request” as “favorable treatment.” This\\nreliance on “sequential referents” is, from her perspective,\\nexactly what we criticized in Serafini. 167 F.3d at 821. But\\nshe misconstrues our holding.\\n\\n In Serafini, the surrounding questions focused on a\\ndifferent topic. This bolstered appellant’s argument in that\\ncase that the question on which the perjury conviction rested\\nwas fundamentally ambiguous. Id. The appellant said the\\nmultiplicity of topics in surrounding questions caused the jury\\nto speculate improperly on how he understood the question at\\nissue. We said: “The meaning of individual questions and\\nanswers is not determined by ‘lifting a statement . . . out of its\\nimmediate context,’ when it is that very context which fixes\\n\\n\\n\\n\\n 31\\n\\fthe meaning of the question.” Serafini, 167 F.3d at 821\\n(quoting United States v. Tonelli, 577 F.3d 194, 198 (3d Cir.\\n1978)). In the case of Serafini, the context made the\\nconfusing nature of the question apparent. The various topics\\nin surrounding questions created sufficient ambiguity to\\nundermine the conviction. Id.\\n\\n Here, however, even though the terms used by the\\nexaminer changed, we conclude that the line of questioning—\\nincluding both questions that ground Count 71 and 72—have\\nan obvious, consistent focus.\\n\\n Q. In all the years\\n you’ve been [at Traffic\\n Court] have you\\n ever been asked to give\\n favorable treatment on\\n a case to anybody?\\n\\n A. No, not favorable\\n treatment. People basically\\n know me. The lawyers\\n know me. The court\\n officers know me. I have\\n been called a nononsense\\n person because I’m just not\\n that way. I take my\\n position seriously and the\\n cards fall where they\\n may. Most of the time . . .\\n the people in my Court\\n plea bargain. They know\\n that most of the time,\\n\\n\\n\\n\\n 32\\n\\fninety percent of the time,\\nsay 90 percent, I go with\\nthe police officer’s\\nrecommendation. . . .\\n\\nQ. So, in all those years\\nno one has ever asked you\\nto find somebody not\\nguilty--\\n\\nA. No.\\n\\nQ. --or to find a lesser\\nviolation; find a lesser fine;\\nanything along those lines?\\n\\nA. No. I will say to\\npeople go to court, go to\\ntrial and see what\\nhappens. . . .\\n\\nQ. Ward leaders,\\npoliticians has anyone\\ncalled you and said I\\nhave Johnny Jones coming\\nup next week and I\\nwould appreciate it if -- if\\nyou would look\\nfavorably on him when he\\ncomes through? Has\\nanything like that ever\\nhappened?\\n\\n\\n\\n\\n 33\\n\\f A. Throughout the\\n years ward leaders and\\n people have called all the\\n time and asked me\\n questions. The only thing I\\n will say to them is they\\n need to go to court. If you\\n think it’s a problem, they\\n need to hire a lawyer, or\\n make sure you bring all\\n your evidence to court. If\\n it’s something like\\n inspection, make sure you\\n bring your -- papers and\\n things like that. That’s\\n what I would tell them to\\n do. I give advice that\\n way. I don’t know if that’s\\n wrong or not, but I do.\\n\\n Q. You’ve never taken\\n action on a request?\\n\\n A. No.\\n\\nApp. 528-29, 530; 5720-22. This broader context would give\\nany reasonable fact-finder more than enough basis to\\nconclude that the witness knew the point of reference for both\\nthe term “favorable treatment” and “request” was ticket\\nfixing. In fact, Tynes is asking us to do precisely the thing we\\ncriticized in Serafini, to lift a phrase or statement out of its\\ncontext. Serafini, 167 F.3d at 821. Tynes has not persuaded\\nus that the question harbors any fatal ambiguity.\\n\\n\\n\\n\\n 34\\n\\f Tynes next contends that her responses to questions\\ngrounding Count 71 and Count 72 cannot support convictions\\nfor perjury because they were literally true. Of course,\\nperjury arises only from making knowingly false material\\ndeclarations. 18 U.S.C. § 1623. Therefore, a witness who\\nanswers an ambiguous question with a non-responsive answer\\nthat the witness believes is true—even if the answer is\\nmisleading—does not commit perjury. See Bronston, 409\\nU.S. at 361-62; see also United States v. Reilly, 33 F.3d 1396,\\n1416 (3d Cir. 1994).\\n Tynes argues that, because she regarded the question\\nabout favorable treatment as vague, she interpreted it as\\nasking whether she accepted any bribes in exchange for a\\njudgment of not guilty or a reduced punishment. Her\\nresponse of “no” (grounding Count 71) is literally true—she\\nsays—because there is no evidence that she accepted any\\nbribes in return for giving preferential outcomes in the\\nadjudication of some individuals who were cited for breaking\\nthe law. Under this theory, the same argument can also\\nnegate the charges at Count 72 since she says she did not\\naccept any “requests” (bribes) in exchange for preferential\\ntreatment.\\n\\n Although the jury is permitted reasonable inferences\\ndrawn from the record about the witness’ understanding of\\nthe truth or falsity of the answer, it is not (as we noted above)\\npermitted to reach conclusions based merely on speculation\\nor conjecture. See Bronston, 409 U.S. at 359. Tynes’\\nassertion of literal truth is undermined because the trial record\\nsupports no reasonable inference that the Government was\\nasking her about matters outside of the alleged bribes, nor\\n\\n\\n\\n\\n 35\\n\\fdoes it provide any reason why Tynes would interpret the\\nquestion in this way.\\n\\n Finally, Tynes contends that the evidence was not\\nsufficient to support her conviction. However, the jury heard\\nTynes’ personal assistant, Medaglia “Dolly” Warren, testify\\nthat she received from personal assistants of other judges\\nthree to four cards per week requesting consideration. Each\\ncard had the name of a person who was appearing before\\nTynes on that day. She passed these to Tynes’ court officer,\\nwho was present during the proceedings. App. 4593-95.\\nTynes also instructed Warren to give similar cards to the staff\\nof other judges. App. 4598. Warren knew to act discreetly\\nwhen she was transferring the cards. App. 4599. The jury\\nalso heard testimony from those who actually received\\nconsideration from Tynes. For example, Timothy Blong was\\ncited for reckless driving and driving without a license. He\\nadmitted in testimony that he did not have a license when he\\nwas cited. App. 3150. He also testified that he requested\\nconsideration through a Traffic Court employee (Danielle\\nCzerniakowski, who worked as a personal assistant to a\\nTraffic Court judge) with whom he was acquainted. When he\\nappeared in court, he was simply told that his case was\\ndismissed. He did not have to say anything, App. 3159-60.\\nBlong testified he was told his case was dismissed because\\nthe police officer did not appear (App. 3160-61), but the\\ngovernment produced evidence that an officer was present.\\nApp. 3193-96. The Government also showed that Tynes was\\nthe presiding judge in Blong’s case. App. 3193. Richard\\nCarrigan—who admitted in testimony that he drove through a\\nred light—described a similar experience in which, after\\nrequesting favorable treatment through Judge Lowry’s\\npersonal assistant, Kevin O’Donnell, his case was dismissed\\n\\n\\n\\n\\n 36\\n\\fby Judge Tynes without ever having to say a word. App.\\n3178-82.\\n\\n Tynes does not challenge any of this in her appeal.\\nInstead she focuses on the weight of other evidence and\\nperceived gaps in testimony. We conclude that all of this\\nprovides more than a sufficient basis to support a reasonable\\njury’s conclusion that Tynes did “give favorable treatment on\\na case,” and did “take[] action on a request.” App. 528-30.\\n\\n For all of these reasons, we will affirm the judgment of\\nconviction on perjury as to Appellant Tynes.\\n C.\\n\\n Appellant Lowry 27\\n\\n Like Tynes, Appellant Lowry advances arguments of\\nfundamental ambiguity and literal truth. His perjury\\nconviction centered on one question and answer.\\n\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n\\n27\\n Lowry was charged with perjury in Count 69 of the\\nindictment.\\n\\n\\n\\n\\n 37\\n\\fApp. 489. Lowry attacks the Government’s use of the term\\n“special favors” as one with many potential meanings.\\nHowever, as we noted above in our reference to Serafini, we\\nreject arguments that lift individual questions or answers—or\\nindividual phrases embedded in either—from the context of\\nsurrounding questions that help fix their meaning. Serafini,\\n167 F.3d at 821. The larger context for the question asked of\\nLowry is as follows.\\n\\n Q. So if I understand\\n your testimony, you’re\\n saying you don’t give out\\n special favors; is that right?\\n\\n A. Well, I know it\\n appears that way; and it’s\\n hard for me to prove to\\n you . . .\\n\\n Q. I’m just asking,\\n your testimony is you don’t\\n give out special favors, is\\n that right?\\n\\n A. No, I treat\\n everybody in that\\n courtroom the same.\\n\\n Q. You treat everybody\\n fairly?\\n\\n A. I’m a lenient judge.\\n I will admit to that.\\n\\n\\n\\n\\n 38\\n\\f Q. You treat everybody\\n fairly?\\n\\n A. Yes, I do.\\n\\n Q. And these notices\\n that you get from your\\n personal or from other\\n people, they don’t affect\\n you in any way; is that\\n right?\\n\\n A. Virtually no effect\\n at all.\\n\\n\\nApp. 489-90.\\n\\n Lowry’s assertion that the phrase “special favors” is\\nsubject to many interpretations is unconvincing. We note two\\nthings. First, the line of questioning reasonably supports a\\nconclusion that this inquiry referenced conduct associated\\nwith allegations of ticket fixing. Second, Lowry answered as\\nif his understanding of the question was consistent with this\\ninterpretation. He said that he was aware it may “appear” that\\nhe gave special favors. He also defended himself by saying\\nthat such requests did not affect his conduct in the courtroom\\nat all. If—as he says—he understood “special favors” to\\nmean fair treatment, his answer makes no sense.\\n\\n Lowry next claims that, since the question was\\nstructured to elicit a negative response, his answer cannot be\\n\\n\\n\\n\\n 39\\n\\fused as the basis of a perjury charge. Relatedly, he contends\\nthat the question was merely a summation of an answer that\\nhe gave just before this question. In essence he argues that\\nthis was a leading question. We have concluded, in the\\ncontext of a trial, that the propriety of leading questions in\\ndirect examinations is a matter left to the sound discretion of\\nthe trial judge. See United States v. Montgomery, 126 F.2d\\n151, 153 (3d Cir. 1942). We extend the same deference here\\nto the District Court’s decision to admit this portion of the\\nGrand Jury transcript. We do not regard the question as\\nfundamentally unfair or unclear, or something outside the\\nnorm of questions typically employed on direct examination.\\nFor these reasons, we conclude that the District Court did not\\nabuse its discretion here.\\n\\n Alternatively, Lowry argues that—if the term is\\nunderstood to reference fixing tickets—there is no evidence\\nto contradict his response that requests for special favors did\\nnot impact any of his adjudications. We do not agree. The\\nrecord contains the following testimony.\\n\\n Kevin O’Donnell, who was Lowry’s personal\\nassistant, testified about Lowry’s involvement with requesting\\nand giving consideration. He said that Lowry made four to\\nfive requests each month for consideration and that\\nO’Donnell transmitted them to the personal assistants of other\\nTraffic Court judges. App. 1854. Likewise, he said other\\njudges transmitted requests for consideration to Lowry\\nthrough their personal assistants. App. 1812-13. Appellant\\nHird and various politicians also made requests of Lowry for\\nconsideration. App. 1827-28, 1832-33. O’Donnell said he\\nwould give the requests to Lowry on the day scheduled for\\nhearing on the citation. App. 1818-19. The requests were for\\n\\n\\n\\n\\n 40\\n\\fpreferential treatment in the adjudication of particular\\ncitations: typically the requests were for “removing points”\\nand obtaining a “not guilty” judgment. App. 1819.\\nO’Donnell said he sometimes had to signal Lowry in the\\ncourtroom to remind him that a particular case was supposed\\nto receive consideration. App. 1822-23. He testified from\\nhis own observation that Lowry typically honored requests\\nfor consideration. App. 1829. He also declared if Lowry\\nclaimed he never gave consideration or asked it of others, this\\nwould not be truthful. App. 1813. The same assistant\\ntestified that if Lowry testified that he ignored requests for\\nconsideration, or that he never honored requests for\\nconsideration, that testimony would not be true. App. 1855.\\nThe Government also asked: “If [Lowry] claimed that . . .\\nconsideration requests had no impact when he disposed of\\ncases, would that be true?” The assistant responded,\\n“probably not.” Id.\\n\\n Another witness, Walt Smaczylo, employed as a court\\nofficer in the Traffic Court, provided an example of how\\n“consideration” worked in the courtroom.\\n\\n When someone comes in,\\n for example, for a reckless\\n driving ticket and that\\n judge normally comes\\n down pretty hard and finds\\n that defendant guilty and\\n then the same type cases\\n come in and you see a\\n defendant walk out either\\n not guilty or a significantly\\n reduced charge.\\n\\n\\n\\n\\n 41\\n\\fApp. 1912. The Government asked Smaczylo if he saw\\nLowry preside over such instances, and he answered: “That’s\\ncorrect, yes.” Id. Smaczylo testified that requests for\\nconsideration were written on small note cards or “sticky”\\nnotes and that he saw Lowry in possession of these cards and\\nnotes. App. 1914. He also provided a generalized example\\nof consideration, based on his observation and understanding,\\nin which a reckless driving citation would be reduced to\\ncareless driving. In such instances, he indicated that a $300\\nto $400 fine would be cut in half. He said: “So, that money\\nwas not collected, obviously, by the state. If that ticket was\\nfixed then I saw it as stealing.” App. 1919. Smaczylo was\\nasked: “[I]f Judge Lowry testified at the [G]rand [J]ury he\\ndidn’t give consideration would that be a truth or would that\\nbe a lie?” He responded: “That would not be the truth.”\\nApp. 1921.\\n\\n All of this testimony provides more than a sufficient\\nbasis to support a reasonable jury’s conclusion that Lowry\\nwas not truthful when he responded to the Government’s\\nquestion about special favors. 28\\n\\n28\\n Lowry points to the cross-examination of both witnesses in\\nwhich they seem to equivocate on some of their observations\\nand responses to the Government. For instance O’Donnell\\nstated his view that giving consideration was no different\\nfrom the leniency that Lowry extended to every other person\\nwho pleaded not guilty and appeared at the hearing.\\nHowever, we do not weigh the credibility of evidence in the\\nrecord. We only judge whether there is sufficient evidence in\\nthe record to support a reasonable fact-finder’s determination\\nthat the record supported conviction of Lowry on a charge of\\n\\n\\n\\n\\n 42\\n\\f Finally, Lowry argues that the Government’s question\\nsought a dispositive response from him on the charges of\\nconspiracy and fraud. He says an affirmative answer to\\nwhether he gave “special favors” to certain individuals would\\nhave been enough to convict him of conspiracy and fraud.\\nThus, he maintains that his acquittal on charges of mail fraud,\\nwire fraud, and conspiracy is res judicata as to the perjury\\ncharges that are based on his answer. He said he did not\\ncommit fraud and the jury agreed with him. Therefore, he\\nsays, he did not perjure himself. However, even if we\\naccepted Lowry’s characterization of the question, we reject\\nthis argument.\\n\\n First, a jury’s determination that Lowry’s ticket-fixing\\nconduct did not constitute wire fraud, mail fraud, and\\nconspiracy does not preclude its determination that he lied\\nabout this conduct before the Grand Jury. Moreover, as the\\nSupreme Court has articulated, a verdict on one count that\\nseems to be at odds with another “shows that either in the\\nacquittal or the conviction the jury did not speak their real\\nconclusions, but that does not show that they were not\\nconvinced of the defendant’s guilt.” United States v. Powell,\\n469 U.S. 57, 63 (1984) (quoting Dunn v. United States, 284\\nU.S. 390, 393 (1932)). It is impossible to know in such cases\\nwhether the verdicts were an exercise of lenity by the jury or\\noutright error.\\n\\n Nonetheless, as the Powell Court noted, any\\nassessment of the jury’s rationale for its verdicts “would be\\n\\n\\nperjury. See United States v. Richardson, 658 F.3d 333, 337\\n(3d Cir. 2011).\\n\\n\\n\\n\\n 43\\n\\fbased either on pure speculation or would require inquiries\\ninto the jury’s deliberations that courts generally will not\\nundertake.” Id. at 58. So, even if Lowry was correct that the\\nacquittal is relevant to his response to the question grounding\\nhis perjury conviction, we are not convinced that his perjury\\nconviction is unfounded. Given the substantial body of\\nevidence presented to the jury, nothing here demands that we\\nabandon the deference we traditionally give to the collective\\njudgment of the jury. For all these reasons, we will affirm the\\njury’s verdict as to Lowry.\\n\\n D.\\n\\n Appellant Mulgrew 29\\n\\n Mulgrew does not argue that the question asked at the\\nGrand Jury was ambiguous, he simply maintains that his\\nstatement was truthful. 30 The questions and answers\\ngrounding his perjury conviction are as follows.\\n\\n Q. How about your\\n personal, has your personal\\n received any calls like that\\n from other judges, other\\n ward leaders that she’s\\n conveyed to you, saying\\n\\n29\\n Mulgrew was charged with perjury in Count 70 of the\\nindictment.\\n30\\n Mulgrew’s claims are reviewed for plain error because he\\ndid not make the same argument before the District Court.\\nUnited States v. Syme, 276 F.3d 131, 148 (3d Cir. 2002).\\n\\n\\n\\n\\n 44\\n\\f so-and-so has called about\\n this case?\\n\\n A. If she did, she didn’t\\n convey them to me.\\n\\n\\nApp. 432-33 (emphasis added). Shortly after this, the\\nfollowing exchange occurred:\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people, whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\nApp. 438. As to the first exchange, Mulgrew claims that the\\nGovernment’s use of the word “call” referred exclusively to\\ntelephone calls. This mattered to him, he says, because others\\n\\n\\n\\n\\n 45\\n\\fhad testified that personal assistants of other Traffic Court\\njudges would give index cards to his personal assistant in his\\nchambers or robing room containing names of some\\nindividuals whose tickets were listed for hearing. Mulgrew\\nclaims that there is no evidence that he ever received any\\nphone calls asking that he act extrajudicially to give well-\\nconnected individuals preferential treatment. The implication\\nis that, had the Government asked him about receiving index\\ncards with such requests, his answer would have been\\ncompletely different.\\n As with Tynes and Lowry, our review of claims of\\nliteral truth drives us to examine the context of the question.\\n\\n Q. How about other\\n judges, have other judges\\n ever approached you or\\n called to you or get a\\n message to you either\\n themselves or through their\\n personals saying that\\n someone is going to be on\\n your list next week or next\\n Monday and can you could\\n some special way towards\\n the case?\\n\\n A. No, they haven’t.\\n\\n Q. Never?\\n\\n A. No.\\n\\n\\n\\n\\n 46\\n\\fQ. How about your\\npersonal, has your personal\\nreceived any calls like that\\nfrom other judges, other\\nward leaders that she’s\\nconveyed to you saying so\\nand so has called about this\\ncase?\\n\\nA. If she did, she didn’t\\nconvey them to me.\\n\\nQ. And your personal\\nis who?\\n\\nA. Gloria McNasby.\\n\\nQ. Have you ever seen\\non traffic court files --You\\nactually get a file when\\nsomeone’s case is called?\\n\\nA. Right.\\n\\nQ. So the case is called\\nand you get a file presented\\nto you; is that right?\\n\\nA. uh-huh.\\n\\nQ. Have you ever seen\\nany index cards or\\nnotations on the file\\n\\n\\n\\n\\n 47\\n\\f indicating that a person has\\n called or taken some\\n special interest in this\\n case?\\n\\n A. Nope.\\n\\nApp. 432-33 (emphasis added). The transcript makes it\\nobvious that Mulgrew’s singular reliance on the reference to a\\n“call” ignores the thrust of the Government’s line of\\nquestions. The questions focus on the substance of the\\ncommunications between Mulgrew’s personal assistant and\\nhimself, rather than the mode of those communications.\\n\\n Mulgrew also claims that he responded truthfully to\\nthe second question.\\n\\n Q. Let me make sure as\\n well that if I got your\\n testimony correct [sic].\\n You’re saying that if other\\n people whether they be\\n political leaders, friends\\n and family, anybody is\\n approaching your personal\\n and asking her specifically\\n to look out for a case, see\\n what she can do in a case,\\n give preferential treatment,\\n however you want to\\n phrase it, that she is not\\n relaying any of that\\n\\n\\n\\n\\n 48\\n\\f information on to you; is\\n that correct?\\n\\n A. No, she isn’t.\\n\\n Q. Wouldn’t you want\\n to know it?\\n\\n A. No, I don’t want to\\n know. Then I never have to\\n worry about what I do in\\n the courtroom.\\n\\nApp. 437-38 (emphasis added). Apparently focusing on the\\nwords “see what she can do,” he says that he answered\\ntruthfully by responding that his personal assistant did not tell\\nhim that people were approaching her and asking her to give\\nthem preferential treatment. But, as with the first question,\\nMulgrew cherry-picks a small part of the question out of\\ncontext, distorting it. The full text and follow up question\\nshow that the thrust of the inquiry was whether Mulgrew’s\\npersonal assistant was informing him of the names of those\\nrequesting preferential treatment from him. And Mulgrew’s\\nresponse to the follow-up question —saying that he did not\\nwant to know so that he did not have to worry about what he\\ndid in the courtroom—is consistent with one who understood\\nthis. App. 438.\\n\\n We conclude that, ultimately, the evidence is sufficient\\nfor a reasonable jury to conclude Mulgrew understood that\\nboth of these questions were focused on whether his personal\\nassistant informed him of requests for him to give preferential\\ntreatment, and that he answered in the negative to both.\\n\\n\\n\\n\\n 49\\n\\f Mulgrew alternatively asserts that the District Court\\nerred by refusing to admit additional testimony from the\\nGrand Jury that he claims is relevant to his perjury\\nconviction. 31 After the Government introduced Mulgrew’s\\nGrand Jury testimony, Mulgrew sought the admission of other\\nportions of his testimony. But the District Court sustained the\\nGovernment’s hearsay objection. The portion of the\\ntranscript supporting the perjury conviction is as follows:\\n\\n Q. [W]hether you have\\n ever been asked to provide,\\n what I’ll call, favorable\\n treatment for people in\\n traffic court or however\\n you define that, whether it\\n would be special handling,\\n keep an eye out for a\\n ticket, do me a favor.\\n Have you ever been asked\\n to provide any type of\\n treatment like that for\\n people in traffic court?\\n\\n A. People have asked\\n me for consideration, but I\\n give consideration to\\n everybody that comes in\\n my courtroom[,] so it\\n\\n31\\n We review the District Court’s ruling on the admissibility\\nof evidence for abuse of discretion. United States v. Green,\\n617 F.3d 233, 239 (3d Cir. 2010).\\n\\n\\n\\n\\n 50\\n\\f doesn’t make a difference\\n to me.\\n\\n\\nApp. 422-23. The basis for the Government’s hearsay\\nobjection to this portion of the testimony was that it raised an\\nout-of-court statement not offered by a party opponent.\\n\\n Mulgrew first contends that the District Court erred by\\nruling that this was hearsay because it was not offered for the\\ntruth of the matter asserted. He says that the testimony was\\ninstead offered to show his state of mind later in his\\ntestimony. See United States v. Hoffecker, 530 F.3d 137,\\n191-92 (3d Cir. 2008). However, we conclude that it was not\\nan abuse of discretion for the District Court to sustain the\\nGovernment’s hearsay objection. It was reasonable for the\\nDistrict Court to conclude here that his response relied on\\nout-of-court statements offered to assert his innocence since\\nhis response conveys a declaration that he treated no person\\ndifferent from another.\\n\\n Mulgrew also argues that this portion of the transcript\\nis admissible under Federal Rule of Evidence 106: “[i]f a\\nparty introduces all or part of a writing or recorded statement,\\nan adverse party may require the introduction, at that time, of\\nany other part—or any other writing or recorded statement—\\nthat in fairness ought to be considered at the same time.”\\nMulgrew maintains that this question and answer provides\\ncontext showing that he did not commit perjury. He also\\nmaintains that the “doctrine of completeness” applies here:\\nfairness demanded the admission of the statements. See\\n\\n\\n\\n\\n 51\\n\\fUnited States v. Soures, 736 F.2d 87, 91 (3d Cir. 1984). 32 We\\nare not convinced.\\n\\n The excerpt at issue occurs many pages before the\\ntestimony regarded as perjurious. It is unrelated in the overall\\nsequence of questions and to the answers grounding his\\nconviction. Moreover, as the intervening pages suggest, it\\nwas separated by the passage of time during questioning. We\\nalso fail to see how Mulgrew’s equivocation over the term\\n“consideration” gives helpful context to his later denial of\\nreceiving requests for consideration. For these reasons, we\\nconclude the District Court did not abuse its discretion by\\nsustaining the Government’s hearsay objection.\\n\\n IV.\\n\\n Appellant Singletary 33\\n\\n\\n32\\n “Under this doctrine of completeness, a second writing may\\nbe required to be read if it is necessary to (1) explain the\\nadmitted portion, (2) place the admitted portion in context, (3)\\navoid misleading the trier of fact, or (4) insure a fair and\\nimpartial understanding.” Soures, 736 F.2d at 91.\\n33\\n Appellant Singletary was charged with making false\\nstatements in Counts 73 and 74 of the indictment. He states\\nin his brief that he ‘joins all arguments on behalf of co-\\nappellants pursuant to Federal Rules of Appellate Procedure\\n28(i).” Singletary Br. 19. To the extent that he joins the\\nargument of prejudice resulting from the trial on the fraud and\\nconspiracy charges, we already have determined that the\\nindictment was proper and no prejudice resulted from\\n\\n\\n\\n\\n 52\\n\\f During the investigation of the Traffic Court by the\\nFederal Bureau of Investigation, Appellant Singletary was\\namong those interviewed. The jury acquitted Singletary of all\\ncounts of wire fraud, mail fraud, and conspiracy. It found\\nhim guilty of false statements made to the Federal Bureau of\\nInvestigation. At sentencing, over Singletary’s objection, the\\nDistrict Court sentenced Singletary using the Guideline on\\nobstruction.\\n\\n The Government agrees that the single count on which\\nhe was convicted does not contain all of the elements of\\nobstruction. U.S.S.G. § 2J1.2. For this reason, the\\nGovernment agrees with Singletary that he is entitled to a\\nremand for resentencing. Accordingly, we will vacate the\\njudgment of sentence as to Singletary and remand to the\\nDistrict Court for resentencing.\\n\\n V.\\n\\n For all of these reasons, we will vacate the judgment of\\nsentence of the District Court with regard to Appellant\\nSingletary and remand for resentencing. We will affirm the\\njudgments of the District Court as to Appellants Alfano, Hird,\\nLowry, Mulgrew and Tynes.\\n\\n\\n\\nbringing these charges to trial. As for the challenges to\\nperjury in Counts 72 and 74, we note that Singletary was\\ncharged with a different crime: false statements in a federal\\ninvestigation pursuant to 18 U.S.C. § 1001. In addition, the\\nchallenges to all of such charges are inherently fact-intensive.\\nAs he did not provide a factual basis for such a challenge, we\\nregard the issue to be waived.\\n\\n\\n\\n\\n 53\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":68,"cells":{"id":{"kind":"number","value":4583111,"string":"4,583,111"},"name":{"kind":"string","value":"UNITED STATES of America v. Thomasine TYNES, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Thomasine Tynes"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4804"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc\", \"parties\": \"\", \"opinions\": [{\"author\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4804\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n THOMASINE TYNES,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\\n\\nthe above-entitled case having been submitted to the judges who participated in the\\n\\ndecision of this Court and to all the other available circuit judges of the circuit in regular\\n\\nactive service, and no judge who concurred in the decision having asked for rehearing,\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fand a majority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\\n\\nclaim that there was insufficient evidence to support Tynes’ conviction.\\n\\n After consideration of Appellant’s argument, the panel has agreed to amend the\\n\\nopinion, which will be filed simultaneously with this order in all of the consolidated\\n\\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\\n\\neffect.\\n\\n BY THE COURT,\\n\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360364/\", \"author_raw\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"MCKEE"},"judge3":{"kind":"string","value":"AMBRO"},"exactly_three_caps":{"kind":"number","value":2,"string":"2"},"extra_judges":{"kind":"string","value":"CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER"},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583111/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Thomasine TYNES, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n\n\n No. 14-4804\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n THOMASINE TYNES,\n Appellant\n\n\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\n\n\n\n\n SUR PETITION FOR REHEARING\n\n\n\n\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\n\n\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\n\nthe above-entitled case having been submitted to the judges who participated in the\n\ndecision of this Court and to all the other available circuit judges of the circuit in regular\n\nactive service, and no judge who concurred in the decision having asked for rehearing,\n\n\n\n*\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\nMichael Fisher’s votes are limited to panel rehearing.\n\fand a majority of the circuit judges of the circuit in regular service not having voted for\n\nrehearing, the petition for rehearing en banc is DENIED.\n\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\n\nclaim that there was insufficient evidence to support Tynes’ conviction.\n\n After consideration of Appellant’s argument, the panel has agreed to amend the\n\nopinion, which will be filed simultaneously with this order in all of the consolidated\n\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\n\neffect.\n\n BY THE COURT,\n\n\n s/ Richard L. Nygaard\n Circuit Judge\n\nDated: January 18, 2019\nPDB/CLW/cc: All Counsel of Record\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Thomasine TYNES, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4804\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n THOMASINE TYNES,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-005)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Thomasine Tynes in\\n\\nthe above-entitled case having been submitted to the judges who participated in the\\n\\ndecision of this Court and to all the other available circuit judges of the circuit in regular\\n\\nactive service, and no judge who concurred in the decision having asked for rehearing,\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fand a majority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to the\\n\\nclaim that there was insufficient evidence to support Tynes’ conviction.\\n\\n After consideration of Appellant’s argument, the panel has agreed to amend the\\n\\nopinion, which will be filed simultaneously with this order in all of the consolidated\\n\\ncases. Each of the judgments entered August 21, 2018, shall remain in full force and\\n\\neffect.\\n\\n BY THE COURT,\\n\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":69,"cells":{"id":{"kind":"number","value":4583112,"string":"4,583,112"},"name":{"kind":"string","value":"UNITED STATES of America v. Robert MULGREW, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Robert Mulgrew"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"14-4812"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN, HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE, RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges The petition for rehearing en banc\", \"parties\": \"\", \"opinions\": [{\"author\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4812\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n ROBERT MULGREW,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\\n\\nabove-entitled case having been submitted to the judges who participated in the decision\\n\\nof this Court and to all the other available circuit judges of the circuit in regular active\\n\\nservice, and no judge who concurred in the decision having asked for rehearing, and a\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fmajority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\\n\\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\\n\\nof perjury based upon an accurate understanding of his argument relating to his response\\n\\nto a particular question.\\n\\n Q. Let me make sure as well that if I got your\\n testimony correct [sic]. You’re saying that if\\n other people whether they be political leaders,\\n friends and family, anybody is approaching\\n your personal and asking her specifically to\\n look out for a case, see what she can do in a\\n case, give preferential treatment, however you\\n want to phrase it, that she is not relaying any of\\n that information on to you; is that correct?\\n\\n A. No, she isn’t.\\n\\n\\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\\n\\namend the opinion, which will be filed simultaneously with this order in all of the\\n\\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\\n\\nforce and effect.\\n\\n\\n BY THE COURT,\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360365/\", \"author_raw\": \"Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN\"}]}"},"judge1":{"kind":"string","value":"SMITH"},"judge2":{"kind":"string","value":"MCKEE"},"judge3":{"kind":"string","value":"AMBRO"},"exactly_three_caps":{"kind":"number","value":2,"string":"2"},"extra_judges":{"kind":"string","value":"CHAGARES; JORDAN; HARDIMAN; GREENAWAY JR; SHWARTZ; KRAUSE; RESTREPO; BIBAS; PORTER; NYGAARD; FISHER"},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583112/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Robert MULGREW, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\n\n\n\n No. 14-4812\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n ROBERT MULGREW,\n Appellant\n\n\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\n\n\n\n\n SUR PETITION FOR REHEARING\n\n\n\n\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\n\n\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\n\nabove-entitled case having been submitted to the judges who participated in the decision\n\nof this Court and to all the other available circuit judges of the circuit in regular active\n\nservice, and no judge who concurred in the decision having asked for rehearing, and a\n\n\n\n*\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\nMichael Fisher’s votes are limited to panel rehearing.\n\fmajority of the circuit judges of the circuit in regular service not having voted for\n\nrehearing, the petition for rehearing en banc is DENIED.\n\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\n\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\n\nof perjury based upon an accurate understanding of his argument relating to his response\n\nto a particular question.\n\n Q. Let me make sure as well that if I got your\n testimony correct [sic]. You’re saying that if\n other people whether they be political leaders,\n friends and family, anybody is approaching\n your personal and asking her specifically to\n look out for a case, see what she can do in a\n case, give preferential treatment, however you\n want to phrase it, that she is not relaying any of\n that information on to you; is that correct?\n\n A. No, she isn’t.\n\n\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\n\namend the opinion, which will be filed simultaneously with this order in all of the\n\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\n\nforce and effect.\n\n\n BY THE COURT,\n\n s/ Richard L. Nygaard\n Circuit Judge\n\nDated: January 18, 2019\nPDB/CLW/cc: All Counsel of Record\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Robert MULGREW, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n\\n\\n No. 14-4812\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n ROBERT MULGREW,\\n Appellant\\n\\n\\n (E. D. Pa. Criminal No. 2-13-cr-00039-003)\\n\\n\\n\\n\\n SUR PETITION FOR REHEARING\\n\\n\\n\\n\\n Present: SMITH, Chief Judge, McKEE, AMBRO, CHAGARES, JORDAN,\\n HARDIMAN, GREENAWAY, JR., SHWARTZ, KRAUSE,\\n RESTREPO, BIBAS, PORTER, NYGAARD, and FISHER * Circuit Judges\\n\\n\\n The petition for rehearing en banc filed by appellant Robert Mulgrew in the\\n\\nabove-entitled case having been submitted to the judges who participated in the decision\\n\\nof this Court and to all the other available circuit judges of the circuit in regular active\\n\\nservice, and no judge who concurred in the decision having asked for rehearing, and a\\n\\n\\n\\n*\\n Pursuant to Third Circuit I.O.P. 9.5.3, Judge Richard L. Nygaard’s and Judge D.\\nMichael Fisher’s votes are limited to panel rehearing.\\n\\fmajority of the circuit judges of the circuit in regular service not having voted for\\n\\nrehearing, the petition for rehearing en banc is DENIED.\\n\\n The petition for rehearing by the panel is GRANTED IN PART, solely as to\\n\\nAppellant’s claim that he is entitled to a consideration of the sufficiency of the evidence\\n\\nof perjury based upon an accurate understanding of his argument relating to his response\\n\\nto a particular question.\\n\\n Q. Let me make sure as well that if I got your\\n testimony correct [sic]. You’re saying that if\\n other people whether they be political leaders,\\n friends and family, anybody is approaching\\n your personal and asking her specifically to\\n look out for a case, see what she can do in a\\n case, give preferential treatment, however you\\n want to phrase it, that she is not relaying any of\\n that information on to you; is that correct?\\n\\n A. No, she isn’t.\\n\\n\\nApp. 437-38. After consideration of Appellant’s argument, the panel has agreed to\\n\\namend the opinion, which will be filed simultaneously with this order in all of the\\n\\nconsolidated cases. Each of the judgments entered August 21, 2018, shall remain in full\\n\\nforce and effect.\\n\\n\\n BY THE COURT,\\n\\n s/ Richard L. Nygaard\\n Circuit Judge\\n\\nDated: January 18, 2019\\nPDB/CLW/cc: All Counsel of Record\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":70,"cells":{"id":{"kind":"number","value":4583113,"string":"4,583,113"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Raymont Wright"},"decision_date":{"kind":"string","value":"2019-01-18"},"docket_number":{"kind":"string","value":"17-1972"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: MCKEE, SHWARTZ, and NYGAARD, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\", \"author\": \"SHWARTZ, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague says that our approach\\ndeprives the court from taking action “when warranted to\\nprotect the institutional integrity of the judiciary.” Dissent at\\n3. We disagree. This approach recognizes a court’s role in our\\ntripartite system of government and ensures that a court\\nintercedes when proceeding would violate the Constitution.\\nFurthermore, our approach does not preclude a court from\\nending a case where the evidence is insufficient or the conduct\\nof the prosecution is improper.\\n\\n\\n\\n\\n 22\"}, {\"author\": \"McKEE, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"McKEE, Circuit Judge, concurring in the judgment.\\n\\n As I shall explain, I am sympathetic to what the District\\nCourt was trying to do in this case and I think I understand why\\nthe court acted as it did. Moreover, I agree with Judge Nygaard\\ninsofar as he posits in dissent that a District Court can step in\\nat some point and bar a retrial without infringing on the\\nseparation of powers. Nevertheless, despite my belief that the\\nseparation of powers doctrine is not necessarily violated by a\\ntrial court barring a retrial after successive mistrials, and\\ndespite my belief that the District Court was trying to act in a\\nmanner that would assure a measure of justice for Wright, I\\nconcur in the judgment reversing the District Court. I simply\\ndo not believe that the current state of the law supports the\\nDistrict Court’s action in the absence of prosecutorial\\nmisconduct, bad faith, or more than two unsuccessful trials.\\nSince the record is clear that the District Court found neither\\nprosecutorial misconduct nor bad faith, I concur in the\\njudgment reversing the court’s order but feel compelled to\\nwrite separately to explain why.\\n I.\\n At the outset, it is important to note that I do not believe\\nthat a trial court lacks the power to, at some point, call a halt to\\nsuccessive prosecutions following deadlocked juries, and I do\\nnot read Judge Shwartz’s opinion as standing for that principle.\\nThe Government even conceded at oral argument that there\\ncould come a point where successive prosecutions become so\\nonerous and burdensome that additional trials rise to the level\\nof a Due Process violation which a trial court is clearly\\nempowered to prevent. Moreover, in Barkus v. Illinois, 1 the\\nSupreme Court noted that there “may” come a point where\\nmultiple prosecutions become so harassing that they violate the\\nDue Process Clause. 2\\n\\n Here the evidence in both trials consisted solely of\\npolice testimony. According to the officers’ testimony, some\\nresidents of the community witnessed crucial parts of Wright’s\\nencounter with the police, but they did not testify. Similarly,\\nWright did not testify on his own behalf, nor did the defense\\nput on a case. His theory was that he had no way of knowing\\n\\n1\\n 359 U.S. 121 (1959).\\n2\\n Id. at 127.\\n 1\\n\\nthat the men in plain clothes and unmarked cars who began\\npursuing him were police; he panicked, sped away, and\\ncrashed; and police subsequently planted the gun at the scene.\\nWright also asserted that the officers chose not to test the gun\\nfor DNA or fingerprints because they knew the results would\\ncontradict their story. In an effort to counter Wright’s\\nargument from the first trial that police decided not to test the\\ngun for fingerprints and DNA in order to hide their\\nmalfeasance, the Government called experts at the second trial\\n“who testified about the difficulty of retrieving DNA and\\nfingerprint evidence from firearms.” 3\\n\\n Nevertheless, the Government’s case depended entirely\\non the testimony of police officers who had worked together\\nfor many years and/or knew one another. Over the span of ten\\nmonths, the District Court twice listened to the police\\ntestimony during the trials. That testimony was at times\\ncontradictory and at other times strained credulity.\\n\\n At the first trial, Detective Fallert, who first noticed\\nWright speeding, testified that Wright was travelling at 90\\nmph, but he did not note that in his police paperwork nor did\\nhe note it at the pretrial hearing. His contemporaneously\\nprepared investigative report also did not claim that Wright\\nwas initially speeding. Detective Henson, who took over the\\nchase, testified that he saw Wright holding a handgun, but\\nconceded that he had no way of knowing whether Wright knew\\nhe was a police officer when the pursuit began. Lastly,\\nDetective Baker testified similarly to Henson, yet guessed that\\nWright had been going at a speed of 60 mph and accelerated.\\nThis is a very substantial discrepancy, especially for seasoned\\npolice officers who can be expected to have some expertise and\\nexperience in estimating the speed of an automobile.\\n\\n In the second trial, the Government called the same\\nwitnesses, with the exception of Detective Fallert. Notably,\\nthis time Detective Henson testified he actually did not see\\nWright speeding. Two different juries found themselves\\ndeadlocked—unable to convict or acquit.\\n II.\\n The majority opinion suggests that the District Court’s\\n\\n3\\n Appellant Br. at 11.\\n 2\\n\\ndecision to dismiss the indictment with prejudice\\nimpermissibly infringed upon the jury’s role. Judge Shwartz\\nstates: “[t]he District Court nonetheless applied its own\\npredictions about what another jury may do when presented\\nwith the same evidence,” and concluded that was “an improper\\nexercise of a court’s supervisory power.” 4 However, it is\\ndifficult to know whether the District Court ruled as it did\\nbased upon a belief that a third jury presented with the same\\nevidence would be unable to reach a verdict or whether it\\nsimply shared the doubts that some of the jurors obviously had\\nabout the veracity of police officers’ testimony.\\n\\n In any event, either scenario poses exactly the same\\nissue about a court overstepping its bounds and infringing on\\nthe role of a jury as well as prosecutorial discretion. As I stated\\nat the beginning, to the extent that a trial judge can intervene\\nand dismiss an indictment, I am skeptical that this record\\nsupports such an assertion of judicial authority. Nevertheless,\\nthere is more support for the judge’s actions here than our\\nreversal suggests.\\n\\n It is not a novel proposition that a trial judge must\\n“ensure that any and all . . . evidence is not only relevant, but\\nalso reliable.” 5 “The trial judge’s role is to preside over the\\ntrial; passively if possible but aggressively when indicated.” 6\\nThus, the law allows for trial courts to channel the jury’s\\njudgment in certain circumstances. Here, the court’s decision\\nwould prevent another jury from hearing the same evidence\\nthat has failed to convict Wright on two prior occasions.\\n\\n There are situations in which judges must act as\\n“gatekeepers” and ensure the reliability of evidence before a\\njury is able to consider it. Accordingly, in an admittedly very\\ndifferent context, the Supreme Court has described trial judges\\nas gatekeepers of evidence. 7 “[A] gatekeeping role for the\\n\\n4\\n Maj. Op. 13–14.\\n5\\n Kannankeril v. Terminix Int’l, Inc., 128 F.3d 802, 806 (3d\\nCir. 1997) (citing Daubert v. Merrill Dow Pharms., 509 U.S.\\n579, 589 (1993)).\\n6\\n Holdnrook v. Lykes Bros. Steamship Co., 80 F.3d 777, 788\\n(3d Cir. 1996).\\n7\\n Daubert, 509 U.S. at 597.\\n 3\\n\\njudge, no matter how flexible, inevitably on occasion will\\nprevent the jury from learning of authentic insights and\\ninnovations.” 8\\n\\n Despite the importance of the jury system, and the faith\\nwe place in juries, the law has thus traditionally recognized the\\ndanger that jurors may not be able to restrict their deliberations\\nto admissible evidence and that they may return a verdict based\\non factors other than the evidence presented at trial. For\\nexample, Federal Rule of Evidence 403 allows courts to\\nprevent jurors from learning of certain testimony (even\\nuncontradicted testimony) if the court concludes that the\\ntestimony could cause a jury to reach a verdict based more on\\nemotion or prejudice than on evidence. 9\\n\\n The best known example of how courts are empowered\\nto limit what a jury can consider may well be the body of law\\nthat has developed in the wake of the Supreme Court’s decision\\nin Daubert. In Daubert, the Court stated: “the trial judge must\\nensure that any and all scientific testimony or evidence\\nadmitted is not only relevant, but reliable.” 10 We certainly\\ncould, but do not, allow the jury to determine whether the\\nscientific evidence is reliable in the first instance based upon\\ntestimony at trial. Instead, that preliminary factual\\ndetermination rests solely with the trial court if the reliability\\nis challenged.\\n\\n The difficulty with relying on this body of law here is,\\nof course, the fact that the trial court’s dismissal of Wright’s\\nindictment was not limited to an intrusion into the jury-box.\\nMore fundamentally, and more importantly, it also trespassed\\non the separation of powers, and concomitantly, on the\\nprosecutorial discretion that is endemic in that concept.\\n\\n Despite Judge Nygaard’s thoughtful attempt to address\\nthat issue and the jury’s obvious concerns regarding the\\n\\n8\\n Id.\\n9\\n See, e.g., United States v. Bailey, 840 F.3d 99, 117, 121–23,\\n(3d Cir. 2016) (finding that the probative value of video\\nevidence of murder committed by coconspirators was\\nsubstantially outweighed by risk of unfair prejudice).\\n10\\n Daubert, 509 U.S. at 589.\\n 4\\n\\ntestimony of police officers in this case, I am not convinced\\nthat the United States Supreme Court would agree that the\\ninherent powers of a trial court are broad enough to justify what\\nhappened here.\\n\\n The Government clearly has the inherent authority to\\ndecide not to retry Wright given all of the circumstances in this\\ncase, including the seemingly improbable account of what\\nhappened, 11 the conflicting nature of the police testimony and\\nthe jurors’ apparent trouble with it, the fact that there is no\\nadditional evidence to offer at a third trial, and Wright’s\\napparent steps toward rehabilitation since the offense which\\ndisqualified him from lawfully owning a firearm, as well as any\\nother factors that the Government might appropriately\\nconsider. 12 However, I can find no authority that convinces me\\nthat the United States Supreme Court would agree that a trial\\ncourt’s inherent authority allows it to dismiss an indictment\\nwith prejudice on this record.\\n\\n III.\\n\\n\\n\\n11\\n According to the officers’ accounts, they watched (in the\\nopen and without cover) as Wright fumbled in the back of a\\ncar with tinted windows and came out holding a gun. They\\nthen continued to stand and watch from approximately 25\\nyards away—without cover and without taking any actions to\\nprotect themselves—as he attempted to rack the slide which\\nwould have placed a bullet in the chamber.\\n12\\n Appellee argues without contradiction that:\\n\\n [f]ollowing early involvement with the criminal\\n justice system, Mr. Wright began to turn his life\\n around, returning to school and earning his\\n Associates degree in Computer Management-\\n Networking Engineering Technology[,] . . . a\\n Bachelor of Science degree in Information\\n Technology and Management . . . graduating\\n cum laude[,] . . . and . . . a Master of Science\\n degree.\\n\\nAppellee Br. at 52.\\n 5\\n\\n As I noted at the outset, the Government agrees that\\nsuccessive prosecutions can rise to the level of a Due Process\\nviolation, which a court clearly could remedy by dismissing an\\nindictment. However, the Government strenuously argues\\nWright’s prosecution has not yet reached that point. The\\nGovernment’s position inherently argues that the court’s action\\nhere is also not justified by any concept of fundamental\\nfairness. In Ake v. Oklahoma, 13 the Supreme Court observed\\nthat the right to Due Process includes the “guarantee of\\nfundamental fairness.” 14 As has been discussed by Judge\\nShwartz, the District Court here relied on the decision of the\\nNew Jersey Supreme Court in State v. Abbati. 15 There, the\\nNew Jersey Supreme Court affirmed a trial court’s dismissal of\\nan indictment with prejudice after two juries deadlocked,\\nresulting in mistrials. 16 That situation is on “all fours” with the\\ncircumstances here and the District Court relied heavily on that\\ndecision to justify its action and fashion a rule that would\\nproperly allow a trial court to dismiss an indictment with\\nprejudice under certain circumstances. 17\\n\\n However, the New Jersey Supreme Court based its\\ndecision on the inherent authority of state courts under the New\\nJersey Constitution. 18 It did not purport to rest its decision on\\nthe U.S. Constitution and, with very limited exception, it cited\\nto state judicial decisions—not federal ones—in discussing\\nwhen consecutive hung juries justified dismissing an\\nindictment with prejudice. 19 The holding of the Court is\\n\\n13\\n 470 U.S. 68 (1985).\\n14\\n Id. at 76.\\n15\\n 493 A.2d 513 (N.J. 1985).\\n16\\n Id. at 522.\\n17\\n See United States v. Wright, Crim A No. 14-292, 2017 WL\\n1179006, at *3, *4 (W.D. Pa. Mar. 30, 2017).\\n18\\n Abbati, 493 A.3d at 517–18.\\n19\\n Abbati cited to Ake, for the general proposition that the\\n“requirement of fundamental fairness [is] grounded in [the]\\nfourteenth amendment’s due process guarantee.” 493 A.2d at\\n518. However, with the exception of a single District Court\\ncase, the Court cited numerous state court cases for the\\nproposition that a trial court had the inherent authority to\\ndismiss an indictment with prejudice after two juries\\ndeadlocked. Id. at 519–20. It concluded by finding “[t]hese\\n 6\\n\\nsummarized in its statement that the “judicial responsibility for\\nthe proper administration of criminal justice also gives rise to\\nthe inherent power to dismiss an indictment in appropriate\\ncircumstances.” 20\\n\\n The Abbati standard has not been discussed by this\\nCourt (aside from in the instant case), let alone adopted by it.\\nAlthough some of the factors used by the New Jersey Supreme\\nCourt are analogous to considerations federal courts have made\\nin similar federal cases, such as United States v. Ingram 21 and\\nUnited States v. Rossoff, 22 Abbati has no real corollary in\\nfederal case law. 23\\n\\nexamples of the courts’ exercise of their power to administer\\nthe criminal justice system assist in answering the further\\nargument of the State that recognition of an inherent judicial\\npower to dismiss an indictment with prejudice would overstep\\nthe separation of powers.” Id. at 520. Abbati dismissed that\\nargument based upon its belief that “[t]he separation of\\npowers is not an end in itself, but a general principle intended\\nto ensure that the system of checks and balances remains\\nvital.” Id. at 521 (citing State v. Leonardis, 375 A.2d 607, 612\\n(N.J. 1977)).\\n20\\n Id. at 520.\\n21\\n 412 F. Supp. 384 (D.D.C. 1976). The District Court of the\\nDistrict of Columbia dismissed an indictment after two trials\\nin which twenty-one of twenty-four jurors voted to acquit.\\nThe court found no prosecutorial misconduct. Id. at 386. It\\ninstead considered the issue a “matter of fair play,”\\nemphasizing that “[t]he Government has no new proof; it\\nsimply wants another chance” and “simply wishes to keep\\npressing so long as juries disagree in the hope that a\\nconviction eventually will result.” Id. at 385.\\n22\\n 806 F. Supp. 200 (C.D. Ill. 1992).\\n23\\n For example, the first prong of Abbati’s analysis concerns\\nthe number of mistrials and the outcome of the juries’\\ndeliberations. 493 A.2d at 521. Both Rossoff and Ingram took\\nthis into account in dismissing indictments. See Rossoff, 806\\nF. Supp. at 203 (naming, as “additional compelling\\ncircumstances: 1) the majority of jurors in both cases found\\nDr. Rossoff Not Guilty; 2) if not for the allegedly biased juror\\nin the second trial, Dr. Rossoff would have been acquitted on\\nall counts; 3) the two trials have taken over one solid month\\n 7\\n\\n Accordingly, as I noted at the outset, I am sympathetic\\nto the District Court’s efforts given the totality of the\\ncircumstances here. However, until Congress or the United\\nStates Supreme Court determines otherwise, I agree that we\\nhave no alternative but to enter judgment reversing the District\\nCourt. I therefore concur in the judgment reversing the District\\nCourt’s order.\\n\\n\\n\\n\\nof the Court’s time”); Ingram, 412 F. Supp. at 385 (“The\\nproof was legally sufficient to support a conviction in each\\ninstance but the juries simply did not credit the witnesses,\\nvoting 10–2 and 11–1 for acquittal.”).\\n The Abbati standard is also based on the likelihood of\\nany substantial difference in a subsequent trial, which the\\nIngram decision also considered. See Ingram, 412 F. Supp. at\\n385 (“If another trial takes place there is every reason to\\nbelieve the jury will again be divided or will acquit.”).\\n Finally, Rossoff and Ingram both made determinations\\nsimilar to Abbati’s seventh prong, the status of the individual\\nand the impact of a retrial upon the defendant in terms of\\nuntoward hardship and unfairness. 483 A.2d at 422; see\\nIngram, 412 F. Supp. at 385–86 (“Here is a man in jail now\\nmore than seven months primarily because of an offense\\nwhich the Government is unable to convince a jury he\\ncommitted. . . . To permit a retrial, after 21 of 24 jurors have\\nalready refused to convict, is to ignore the reasonable doubt\\nstandard.”); Rossoff, 806 F. Supp. at 203 (“Dr. Rossoff is 71\\nyears of age and in poor health. He has had heart surgery,\\nsuffers from severe anemia and at the time of the second trial\\nwas on experimental treatment. He has been under great\\nphysical and emotional strain as the result of these repeated\\ntrials and was even hospitalized immediately following the\\nsecond trial.”).\\n\\n 8\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360366/\", \"author_raw\": \"McKEE, Circuit Judge, concurring\"}, {\"author\": \"NYGAARD, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"NYGAARD, Circuit Judge, dissenting\\n\\n This appeal presents us with two issues: First, does a\\ndistrict court possess the inherent power to dismiss an\\nindictment after serial hung juries, and second, did the\\nDistrict Court here abuse its discretion by dismissing this\\nindictment after two of them. I answer yes to the first and no\\nto the second. Because I view this to be a matter of\\nsubstantial importance, I must respectfully dissent.1\\n\\n As the majority notes, twice now, the Government has\\ntried Raymont Wright for a violation of federal law: being a\\nfelon in possession of a firearm.2 Twice now, the\\nGovernment has done so on the basis of essentially the same\\nevidence at trials presided over by the same District Court.\\nAnd twice now, two different juries could not reach a verdict.\\nThus, when the Government announced its intention to put\\nWright on trial for the third time, the District Court was\\nskeptical. It asked for briefing on whether it possessed the\\ninherent power to prohibit the Government from taking a\\nthird turn, and if it did, whether the court should use that\\n\\n\\n\\n\\n1\\n Whether the District Court had the inherent power to\\ndismiss the indictment is a legal question. We employ a\\nplenary standard of review to that issue. See United States v.\\nSchiff, 602 F.3d 152, 161 (3d Cir. 2010) (citing United States\\nv. Scott, 223 F.3d 208, 210 (3d Cir. 2000)). Whether the\\nDistrict Court appropriately exercised this power is reviewed\\nfor an abuse of discretion. Link v. Wabash R.R. Co., 370 U.S.\\n626, 633 (1962).\\n2\\n See 18 U.S.C. § 922(g).\\n\\n\\n\\n\\n 1\\n\\npower.3 After hearing from both sides, the District Court\\nconcluded that its inherent power applied to this\\ncircumstance. It then exercised its discretion to dismiss the\\nindictment.\\n\\n Neither the Government nor the majority disputes that\\ndistrict courts have the inherent authority to dismiss\\nindictments under at least some circumstances. Citing to\\nUnited States v. Hasting,4 however, the majority cabins that\\nauthority to those instances in which there is evidence of\\nprosecutorial misconduct. In my view, in so doing, the\\nmajority conflates and confuses the various powers of the\\ncourt. And it also hobbles the court’s discretion to probe the\\nimpact on the fair administration of justice of those\\nprosecutorial decisions that sit outside the definition of bad\\nconduct but still pose—or threaten to pose—real institutional\\nharm.\\n\\n The executive office inheres prosecutors with the\\npower to bring a case to trial. The judicial office, on the other\\nhand, inheres the court with the power to end a case.5 Both\\n\\n3\\n The District Court ordered the parties to “file cross briefs\\nstating their position regarding whether the Court, through an\\nexercise of its inherent authority, should prohibit or permit a\\nsecond re-trial in this case.” United States v. Wright, No. 14-\\ncr-292, 2017 WL 1179006, at *1 (W.D. Pa. 2017).\\n4\\n 461 U.S. 499, 505 (1983).\\n5\\n See Young v. U.S. ex rel. Vuitton et Fils S.A., 481 U.S. 787,\\n816 (1987)(Scalia, J. concurring)(“The judicial power is the\\npower to decide, in accordance with law, who should prevail\\nin a case or controversy. See Art. III, § 2. . . . [S]ince the\\nprosecution of law violators is part of the implementation of\\n\\n\\n\\n\\n 2\\n\\noffices share a responsibility to safeguard the overall integrity\\nof the judicial process. But when a prosecutor decides to\\nproceed with another trial in the aftermath of multiple\\nmistrials, who but the court is empowered to question the\\nimpact of the prosecutor’s discretion on the fair\\nadministration of justice, particularly when the court has\\nconcerns that the proceedings—and the institution—will be\\ntainted by the abuse of jury shopping? It could be argued that\\ntwo mistrials may not in some instances be enough to inflict\\nserious institutional damage. But, the majority’s combined\\nreliance on Dietz v. Bouldin6 and Fed. R. Crim. P. 31(b)(3) to\\nallow the prosecutor to bring an unlimited number of retrials,\\nso long as she or he does not stray into the realm of “illegal\\nconduct,” provides the prosecutor with an unchecked power.\\nThis poses a threat to the integrity of the judiciary and\\ncontradicts the inherent responsibility and authority vested in\\nthe judiciary by the framers of the Constitution. Thus, it is\\nthe majority’s decision—and not the District Court’s exercise\\nof its inherent authority—that violates the separation of\\npower principles on which the majority relies. We must\\naffirm that our trial court judges have the discretion,\\noriginating in the court’s inherent power, to take proper\\naction when warranted to protect the institutional integrity of\\nthe judiciary.\\n\\n Here, the District Court mindfully struck the balance\\nthat is necessary anytime the power of the court and the\\npower of the prosecutor intersect. Drawing from factors set\\n\\n\\nthe laws, it is—at least to the extent that it is publicly\\nexercised—executive power, vested by the Constitution in the\\nPresident.”) (footnote omitted)).\\n6\\n 136 S. Ct. 1885, 1892 (2016).\\n\\n\\n\\n\\n 3\\n\\nout in State v. Abbati,7 the District Court identified and\\ninvestigated a circumstance that it identified as harmful to the\\ninstitution and to the defendant: jury shopping. It also took\\nnote of the impact of serial retrials on the defendant. It then\\nproperly dismissed the indictment. Its use of the court’s\\ninherent discretion did not violate the separation of powers\\ndoctrine. To the contrary, it gave definition and substance to\\nit.\\n\\n I.\\n\\n Some review is appropriate to illuminate how and\\npossibly why I believe the majority confuses the court’s\\nvarious powers.\\n\\n A.\\n\\n Federal courts operate within a constitutional system\\nthat enumerates the powers of each branch of government, as\\nset forth in the founding document. Article I restrains\\ncongressional power to those “legislative Powers granted\\nherein.”8 By comparison, Article II vests the President with\\n“the executive Power” without further description, limitation,\\nor restriction.9 Analogous to Article II, Article III conveys\\nwithout restriction or limitation the “judicial Power” to\\nfederal courts.10 Accordingly, the Supreme Court has—since\\nat least 1812—recognized that “[c]ertain implied powers must\\nnecessarily result to our Courts of justice from the nature of\\n\\n7\\n 493 A.2d 513, 521-22 (N.J. 1985).\\n8\\n U.S. Const. art. I, § 1.\\n9\\n U.S. Const. art. II, § 1.\\n10\\n U.S. Const. art. III, § 1.\\n\\n\\n\\n\\n 4\\n\\ntheir institution.”11 “The moment the courts of the United\\nStates were called into existence and invested with\\njurisdiction over any subject, they became possessed of”\\ninherent authority.12\\n\\n Moreover, two bedrock purposes of the Constitution—\\nchecking the actions of the states and ensuring that Congress\\nand the Executive do not overstep their boundaries—require a\\nfederal judiciary that exercises its own independent judicial\\npower. That is, it would be impossible for federal courts to\\ndischarge these vital duties if they lacked some inherent\\npower beyond the reach of the Executive or the legislature. I\\nthink of it this way: the elaborate measures set out in the\\nConstitution to protect the independence of the judiciary (life\\ntenure, removal from office only through impeachment, no\\ndecrease in salary during a judge’s tenure, for example)\\nwould be meaningless if there were not some inherent,\\nunimpeachable power vested solely in the federal courts.\\n\\n In Eash v. Riggins Trucking Inc.,13 we defined inherent\\npower as vesting in federal courts upon their creation and as\\nnot deriving from any statute. In this sense, the “judicial\\npower” given to the federal courts by Article III of the\\nConstitution is the “power to decide, in accordance with law,\\nwho should prevail in a case or controversy.”14 No matter the\\ndescription, this power is intrinsic to the judicial office and\\ncannot be inhibited by any rule or act of Congress. As we\\n\\n11\\n United States v. Hudson, 11 U.S. (7 Cranch) 32, 34 (1812).\\n12\\n Ex parte Robinson, 86 U.S. 505, 510 (1873) (speaking of\\nthe inherent contempt power).\\n13\\n 757 F.2d 557, 561 (3d Cir. 1985) (en banc).\\n14\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n\\n\\n\\n\\n 5\\n\\nhave recognized, the boundaries of this power are often\\n“nebulous” and “shadowy,”15 and “it is not always possible to\\ncategorize inherent power.”16 Yet, we have an outline.\\n\\n In Eash, we identified three main classes or categories\\nof inherent power: 1) inherent powers based in Article III,\\nthat is, the power of a lower federal court to decide a case\\nover which it has jurisdiction; 2) those powers “necessary to\\nthe exercise of all others,”17 and 3) powers that include those\\nreasonably useful to achieve justice, which are “necessary\\nonly in the practical sense of being useful.”18 Focusing on the\\nfirst category, the inherent power to decide a case is “so\\nfundamental to the essence of a court as a constitutional\\ntribunal that to divest the court of absolute command within\\nthis sphere is really to render practically meaningless the\\nterms ‘court’ and ‘judicial power.’”19 In other words, powers\\n\\n\\n15\\n Eash, 757 F.2d at 561 (citation omitted).\\n16\\n Id. at 562.\\n17\\n Id. (quoting Roadway Express, Inc., v. Piper, 447 U.S. 752,\\n764 (1980)).\\n18\\n Id. at 563; see also Am. Civil Liberties Union v. Holder,\\n673 F.3d 245, 255-56 (4th Cir. 2011) (applying Eash factors);\\nIn re Stone, 986 F.2d 898, 901-02 (5th Cir. 1993) (per\\ncuriam) (adopting Eash factors). In Chambers v. NASCO\\nInc., the Supreme Court was urged to adopt our approach to\\ninherent powers. But the Court held that it “ha[d] never so\\nclassified the inherent powers and . . . ha[d] no need to do so\\nnow.” 501 U.S. 32, 47 n.12 (1991).\\n19\\n Eash, 757 F.2d at 562. The third aspect of a court’s\\ninherent power is its authority to employ persons or\\ninstruments not connected with the court, such as experts and\\n\\n\\n\\n\\n 6\\n\\nin this category make a court a court; they are encoded into\\nthe judiciary’s DNA. Courts have referred to this power as a\\ncourt’s “irreducible inherent authority”20 and “the core Article\\nIII power.”21 It is nothing less than our ability to decide a\\ncase over which we have jurisdiction, without interference by\\nCongress or the Executive.22\\n\\n Drawing from this, when I refer to a district court’s\\ninherent power, I mean a ‘“[c]ertain implied power[] [that]\\nmust necessarily result to our Courts of justice from the\\nnature of their institution,’ [a] power[] ‘which cannot be\\ndispensed with in a Court, because they are necessary to the\\nexercise of all others.’”23 It is “grounded in the separation of\\npowers concept,” since to deny it and yet maintain an\\nindependent judiciary “is a self-contradiction.”24\\n\\n However, that is not to say that the court operates\\nsolely outside the realm of legislatively granted judicial\\n\\n\\nauditors, to assist in its decision-making function. This facet\\nof inherent power is not in play here.\\n20\\n Id.\\n21\\n Am. Civil Liberties Union v. Holder, 673 F.3d at 256.\\n22\\n United States v. Klein, 80 U.S. (13 Wall.) 128, 147 (1871),\\nEash, 757 F.2d at 562 (noting that courts may exercise this\\ntype of inherent power despite legislation to the contrary); see\\nalso Michaelson v. United States ex rel. Chicago, St. P., M. &\\nO. Ry. Co., 266 U.S. 42, 64 (1924) (acknowledging that the\\nConstitution vests courts with some powers unalterable by\\nlegislation).\\n23\\n Chambers, 501 U.S. at 43 (quoting Hudson, 11 U.S. (7\\nCranch) at 34.).\\n24\\n Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 7\\n\\npowers.25 In fact, the categorization scheme in Eash was\\nintended largely as a means of explaining the relationship\\nbetween inherent judicial powers and legislatively granted\\njudicial powers.26 It is here that I believe the majority’s\\nanalysis strays.\\n\\n B.\\n\\n The majority, the briefs, and the discussion at oral\\nargument reveal what has become a commonplace but\\nimprecise conflation of the terms “inherent power” and\\n“supervisory power.”27 The Government, while referencing\\nthe District Court’s “inherent power,” also referred to the\\ncourt’s “supervisory power,” and its “inherent supervisory\\njudicial authority.”28 The Appellee covers the entire panoply,\\nciting the District Court’s “supervisory authority,” its\\n\\n\\n25\\n See Hudson, 11 U.S. (7 Cranch) at 33.\\n26\\n See In re Tutu Wells Contamination Litig., 120 F.3d 368,\\n384 n.14 (3d Cir. 1997), overruled on other grounds by\\nCunningham v. Hamilton County, Ohio, 527 U.S. 198 (1999).\\n27\\n In Eash, we noted that “[t]he conceptual and definitional\\nproblems regarding inherent power . . . have bedeviled\\ncommentators for years,” 757 F.2d at 561, and that “those\\ncases that have employed inherent power appear to use that\\ngeneric term to describe several distinguishable court\\npowers,” id. at 562. We also noted that “this lack of\\nspecificity [has been compounded by courts] rel[ying] . . . on\\nprecedents involving one form of power to support the court’s\\nuse of another.” Id.\\n28\\n E.g., Appellant’s Br. at 13, 16; Appellant’s Reply Br. at 2,\\n14.\\n\\n\\n\\n\\n 8\\n\\n“supervisory power,” and its “inherent power.”29 At times,\\nwe too have been guilty of adding to the confusion.30 The\\nerroneous interchangeability of these terms clouds an\\nimportant distinction that is crucial to this appeal: the\\ndifference between inherent judicial powers and legislatively\\ngranted judicial powers.31 As noted supra, inherent “judicial\\npower” is given to the federal courts by Article III of the\\nConstitution.32 Through this grant, federal courts receive the\\n“power to decide, in accordance with law, who should prevail\\nin a case or controversy.”33 The merging of the terms\\n“inherent” and “supervisory” likely has its genesis in the fact\\nthat some inherent powers are supervisory in function, such\\nas a federal court’s inherent power “to supervise the\\nadministration of criminal justice.”34\\n\\n29\\n E.g., Appellee’s Br. at 22, 26.\\n30\\n See, e.g., United States v. Accetturo, 783 F.2d 382, 396 (3d\\nCir. 1986) (Sloviter, J., dissenting) (speaking of our “inherent\\nsupervisory power”); see also United States v. Watkins, 339\\nF.3d 167, 180 (3d Cir. 2003) (Nygaard, J., concurring)\\n(referring to both a court’s supervisory power and inherent\\npower to dismiss a case under Fed. R. Crim. P. 48(b)).\\n31\\n In re Tutu Wells Litig., 120 F.3d at 384 n. 14.\\n32\\n See U.S. Const. art. III, § 1.\\n33\\n Young, 481 U.S. at 816 (Scalia, J., concurring).\\n34\\n United States v. Payner, 447 U.S. 727, 735 n.7 (1980)\\n(quotation marks omitted); see also Sara Sun Beale,\\nReconsidering Supervisory Power in Criminal Cases;\\nConstitutional and Statutory Limits of the Federal Courts, 84\\nColum. L. Rev. 1433, 1433-34, 1465, 1470 (1984)\\n(identification of Article III “judicial power,” not\\ncongressional acts, as the source of the Supreme Court’s\\nsupervisory authority).\\n\\n\\n\\n\\n 9\\n\\n However, unlike inherent powers, a court’s\\nsupervisory authority may come from, and can be limited by,\\nacts of Congress or a court’s own rules.35 Supervisory power\\noften speaks to the power “to mandate ‘procedures deemed\\ndesirable from the viewpoint of sound judicial practice.’”36 A\\ncourt’s use of supervisory power can usually be classified in\\none of three ways. First, supervisory power can refer to an\\nappellate court’s supervision of a district court, through the\\nimposition of procedures in addition to those already imposed\\nby federal statute or constitutional provision.37 We have, for\\nexample, relied on our supervisory power over district courts\\nto review the application of local rules of practice and\\nprocedure.38 We have also used our supervisory power to\\n\\n\\n\\n\\n35\\n See, e.g., McNabb v. United States, 318 U.S. 332, 340-41\\n(1943); Hasting, 461 U.S. at 505.\\n36\\n United States v. Moreno, 809 F.3d 766, 780 (3d Cir. 2016)\\n(quoting Thomas v. Arn, 474 U.S. 140, 146-47 (1985)).\\n37\\n See, e.g., Castro v. United States, 540 U.S. 375, 384 (2003)\\n(instructing district courts to notify pro se litigants about\\nconsequences of re-characterizing motions as ones seeking\\nrelief under 28 U.S.C. § 2255); Thiel v. S. Pac. Co., 328 U.S.\\n217, 225 (1946) (announcing a new rule for the composition\\nof federal juries); Dunbar v. Triangle Lumber & Supply Co.,\\n816 F.2d 126, 129 (3d Cir. 1987) (prescribing procedures for\\nmotions to dismiss based on the conduct of a litigant’s\\ncounsel); United States v. Bazzano, 570 F.2d 1120, 1137-38\\n(3d Cir. 1977) (requiring district courts to state reasons for a\\ncriminal sentence).\\n38\\n See United States v. Wecht, 484 F.3d 194, 204-05 (3d Cir.\\n2007).\\n\\n\\n\\n\\n 10\\n\\nprohibit certain jury instructions in the district courts39 and to\\nreview attorney-client fee arrangements.40 Second, Courts—\\nboth trial and appellate—also refer to their “supervisory\\npower” when meaning their power to supervise pending\\nlitigation.41 They can, for example, seal and unseal records,42\\nreassign a case to a different judge on remand,43 or disqualify\\nan attorney on ethical grounds.44 Lastly, the power of a\\nfederal court to supervise law enforcement officials can also\\nbe what a court intends when it speaks of its “supervisory\\n\\n\\n\\n\\n39\\n See United States v. E. Med. Billing Inc., 230 F.3d 600,\\n607-12 (3d Cir. 2000).\\n40\\n See Ryan v. Butera, Beausang, Cohen & Brennan, 193 F.3d\\n210, 214 (3d Cir. 1999).\\n41\\n See, e.g., Carlisle v. United States, 517 U.S. 416, 425-26\\n(1996) (acknowledging “supervisory power” of district courts\\nover litigation before them).\\n42\\n See, e.g., Hagestad v. Tragesser, 49 F.3d 1430, 1434 (9th\\nCir. 1995).\\n43\\n See Gov’t of the Virgin Islands v. Walker, 261 F.3d 370,\\n376 (3d Cir. 2001) (noting that, “[a]lthough it is the standard\\npractice in the district courts and in this circuit that a case on\\nremand is assigned to the judge who originally heard it, we\\ncan, in the exercise of our supervisory power, reassign this\\ncase to a different judge upon remand.”) (quotation marks\\nomitted).\\n44\\n In re Grand Jury Investigation, 447 F. Supp. 2d 453, 456-\\n57 (E.D. Pa. 2006) (collecting cases); see also United States\\nv. Moreno, 809 F.3d at 780 (summarizing supervisory\\nauthority).\\n\\n\\n\\n\\n 11\\n\\npower.”45 These powers broadly ensure that pending cases\\nare managed uniformly and efficiently.\\n\\n I concede that the boundary between supervisory\\nauthority that is inherent to the court and that which is granted\\nby the legislature can, at times, be difficult to identify.\\nHowever, these difficulties are irrelevant to this case because\\nI conclude that the District Court here acted pursuant to its\\ninherent power and not to any authority conferred by any\\nstatute or rule. The District Court’s action was not\\nundertaken in supervision of pending litigation—two trials\\nwere already concluded and a potential third trial had not yet\\nbegun. Nor was it exercised according to a rule of procedure\\nor practice newly announced by an appellate tribunal.\\nMoreover, its action was not a response to any prosecutorial\\nmisconduct or request from Wright to dismiss the indictment.\\nThere is simply no basis to conclude that the inherent power\\nthat the District Court exercised in this case derived from any\\nlegislative grant.\\n\\n To the contrary, the specific power under review here\\nis the power to dismiss an indictment after two mistrials\\nbecause of deadlocked juries in each instance. This power\\nfalls within Eash’s first category of power because it is an\\ninherent power to resolve a case. A court, by its nature, must\\nbe able to dismiss with prejudice actions brought before it,\\njust as it must have the power to decide cases and enter\\n\\n45\\n See, e.g., United States v. Thompson, 772 F.3d 752, 763 (3d\\nCir. 2014). For a comprehensive discussion of the origins\\nand uses of supervisory power, see Amy Coney Barrett, The\\nSupervisory Power of the Supreme Court, 106 Colum. L. Rev.\\n324, 330 (2006).\\n\\n\\n\\n\\n 12\\n\\njudgments.46 Such exercises of power are fundamental to the\\nessence of a court. Were they not, the judicial system simply\\ncould not function.47\\n\\n The inherent power to dismiss is “of ancient origin,\\nhaving its roots in judgments of nonsuit and non prosequitur\\nentered at common law,” and so is a power that is part of the\\nvery nature of the judicial institution.48 It is incidental and\\nnecessary to the fair and efficient operation of the courts.49\\nIndeed, “the power to dismiss exists in many situations. For\\nexample, a district court has the inherent power to dismiss sua\\nsponte for lack of jurisdiction, or under the doctrine of forum\\nnon conveniens.”50 Because the power to resolve a case by\\ndismissing an indictment (in a criminal action) or a complaint\\n(in a civil action) is fundamental to the essence of a court of\\njustice, it cannot be interfered with. Indeed, as two\\ncommentators have explained, “McNabb, other Supreme\\n\\n46\\n We have also noted that our power to remand is a subset of\\nthe inherent power to dismiss a case. See Bradgate Assocs.,\\nInc. v. Fellows, Read & Assocs., Inc., 999 F.2d. 745, 750 n.4\\n(3d Cir. 1993).\\n47\\n See, e.g., Fitzgerald v. First E. Seventh St. Tenants Corp.,\\n221 F.3d 362, 363-364 (2d Cir. 2000) (holding a district court\\nhas the inherent power to dismiss a case, sua sponte, if it\\ndetermines that the action is frivolous or the court lacks\\njurisdiction over the matter).\\n48\\n Link, 370 U.S. at 630.\\n49\\n See, e.g., Bowers v. Nat’l Collegiate Athletic Ass’n, 564 F.\\nSupp. 2d 322, 333 (D.N.J. 2008) (citing Derzack v. County of\\nAllegheny, 173 F.R.D. 400, 411 (W.D. Pa. 1996), aff’d\\nwithout op., 118 F.3d 1575 (3d Cir. 1997)).\\n50\\n In re Prevot, 59 F.3d 556, 565-66 (6th Cir. 1995).\\n\\n\\n\\n\\n 13\\n\\nCourt cases, and an analysis of several lower court opinions\\naddressing this precise issue should sufficiently dispel any\\nnotion that the federal courts lack the power to bar repeated\\nattempts to obtain a conviction” following serial mistrials.51\\nThus, the District Court’s action here was well within the\\nboundaries of its inherent power.\\n\\n Therefore, the majority’s conclusion that “inherent\\nauthority,” “supervisory power,” and “supervisory authority”\\nall refer to the same thing (while understandable given the\\nrampant muddled references that persist) ultimately misses\\nthe point. The power at issue here is the inherent power of\\nthe court to decide a case: a power that is limited by the\\nboundaries of reason and discretion and is subject to appellate\\nreview for abuse. It is not subject to the power of Congress\\nor the Executive.\\n\\n II.\\n\\n There is no dispute that district courts have the\\ninherent power to dismiss indictments in at least some\\ncircumstance. The majority nevertheless concludes that the\\nDistrict Court lacked the power to do so in this case. The\\nmajority reaches that conclusion for three principal reasons,\\nbut none withstands scrutiny.\\n\\n A.\\n\\n51\\n Michael A. Berch & Rebecca White Berch, The Power of\\nthe Judiciary to Dismiss Criminal Charges After Several\\nHung Juries: A Proposed Rule to Control Judicial Discretion,\\n30 Loy. L.A. L. Rev. 535, 543 & nn. 42-43 (1997) (collecting\\ncases).\\n\\n\\n\\n\\n 14\\n\\n First, the majority agrees with the Government’s\\nargument that the District Court’s dismissal violated the\\nSeparation of Powers Doctrine. I agree that the District\\nCourt’s dismissal implicates the separation of powers. But its\\nactions were in furtherance—not in violation—of the\\ndoctrine. The separation of powers doctrine refers to the\\nbalance among the branches of Government which prevents\\none branch from disrupting the constitutional functions of\\nanother.52\\n\\n Here, the majority concludes that, in dismissing the\\nindictment after two hung juries, the District Court\\nencroached on the independence of the Executive because it\\nprohibited the prosecution from exercising its constitutional\\nduty to enforce the laws of the United States. Certainly, the\\nUnited States Attorney, as a member of the Executive Branch,\\nhas such a responsibility.53 And, just as certainly, the\\ndecision to prosecute “is soundly within the discretion of the\\nprosecutor, not the courts.”54 The Government’s authority\\nnot to prosecute a case is clear as well.55 But we see no sign\\nthat the District Court did anything to prevent the\\nGovernment from fulfilling its duty. To the contrary, the\\nGovernment was twice given a full and fair opportunity to\\n\\n52\\n See, e.g., Clinton v. Jones, 520 U.S. 681, 699-700 (1997);\\nMorrison v. Olson, 487 U.S. 654, 696 (1988); Nixon v. Adm’r\\nof Gen. Servs., 433 U.S. 425, 442-43 (1977); Baraka v.\\nMcGreevey, 481 F.3d 187, 201 (3d Cir. 2007).\\n53\\n See, e.g., In re Grand Jury, 286 F.3d 153, 163 (3d Cir.\\n2002).\\n54\\n United States v. Talley, 164 F.3d 989, 997 (6th Cir. 1999).\\n55\\n See, e.g., United States v. Quinn, 728 F.3d 243, 255-56 (3d\\nCir. 2013).\\n\\n\\n\\n\\n 15\\n\\npresent its case and makes no claim that the District Court\\never prevented it from doing so. Having had those\\nopportunities, the Government had no absolute right as a\\nmatter of separation of powers or otherwise to try again. As\\ntwo commentators have explained, a district court’s use of its\\ninherent power to dismiss an indictment after serial mistrials\\ndoes not raise “significant separation of powers concerns”\\nbecause the nature of that inherent power means that federal\\ncourts “need not automatically defer to a prosecutor’s\\ndecision to retry a defendant” in this situation.56\\n\\n The majority nevertheless concludes that prosecutors\\nhave the unimpeded right to try persons for violating federal\\nlaw based on an indictment as many times as they wish and\\nthat the separation of powers doctrine prohibits a federal court\\nfrom interfering. This position is untenable because it is not a\\ntrue reflection of the separation of powers. It is axiomatic\\nthat no one branch of government is completely divorced\\nfrom the other two. In reality, “our constitutional system\\nimposes on the Branches a degree of overlapping\\nresponsibility, a duty of interdependence as well as\\nindependence.”57 This overlap becomes problematic, of\\ncourse, when it results in an encroachment (when an action of\\none branch might undermine the independence of another\\nbranch) or an aggrandizement (where one branch seeks\\n“powers more appropriately diffused among separate\\nBranches”).58\\n\\n\\n56\\n Berch & Berch, supra note 51, at 544.\\n57\\n Mistretta v. United States, 488 U.S. 361, 381 (1989).\\n58\\n Id. at 381; see also In re Tribune Media Co., 799 F.3d 272,\\n285 (3d Cir. 2015) (Ambro, J., concurring).\\n\\n\\n\\n\\n 16\\n\\n But recognizing a district court’s right to prohibit a\\nretrial following serial mistrials does not implicate these\\nconcerns. To the contrary, and putting the shoe on the other\\nfoot, the Government’s position that nothing limits its\\nopportunity to try and retry a defendant as many times as it\\nchooses violates the judicial branch’s constitutional mandate\\nto exercise its judicial power. Just as the filing of an\\nindictment is an exercise of executive power, the dismissal of\\none is an exercise of judicial power. The unlimited serial\\nprosecutions that the Government advocates for, and that the\\nmajority permits, would limit a court’s authority to dismiss an\\nindictment to only those instances in which the prosecutor\\nsteps outside the bounds of professional conduct. But our\\nindependence as an institution of government must include an\\nability to adjudicate, and thus dismiss with prejudice,\\nindividual cases when a district court, in its discretion, has\\nconcerns about the impact of serial retrials on the institution\\nand the defendant. We view the prosecution of a defendant\\nafter deadlocked juries as a tipping point in balancing the\\nseparation of powers. As the repeated prosecutions increase,\\nso too does the judiciary’s power to limit them. As we stated\\nin Eash, and as we said supra, a court’s exercise of its\\ninherent power to dismiss an indictment after retrials does not\\nviolate the separation of powers but is grounded in it.59\\n\\n B.\\n\\n Second, and relatedly, the majority concludes that the\\nDistrict Court’s dismissal was in violation of Fed. R. Crim. P.\\n31(b)(3), which the majority claims confers on prosecutors\\nthe unlimited discretion to retry defendants following serial\\n\\n59\\n See Eash, 757 F.2d at 562.\\n\\n\\n\\n\\n 17\\n\\nmistrials. Rule 31 does nothing of the kind. Rule 31 provides\\nin relevant part that “if a jury cannot agree on a verdict on one\\nor more counts, the court may declare a mistrial on those\\ncounts. The government may retry any defendant on any\\ncounts on which the jury could not agree.”60 The Supreme\\nCourt adopted this rule in its original form in 1944 as a\\n“restatement of existing law.”61 The Supreme Court itself\\nappears never to have cited Rule 31(b)(3), and neither the few\\nCourts of Appeals to have done so62 nor its Advisory\\nCommittee Notes have discussed its history or purpose in any\\ndetail. Arguably, the rule’s reference to the prosecutor’s\\ngeneral ability to retry a defendant following a mistrial may\\nbe nothing more than a recognition of the longstanding\\nprinciple that retrials following mistrials are not prohibited by\\nthe Double Jeopardy Clause,63 which is not at issue here.\\n\\n In any event, this rule does not by its terms prohibit\\ndistrict courts from dismissing indictments following serial\\nmistrials. District courts have the inherent power to do so as\\nexplained above. A district court’s exercise of that power\\ncould be contrary to Rule 31(b)(3) only if the rule contained\\nan “express grant of or limitation on” that power.64 It does\\nnot. The rule does not mandate a retrial after a mistrial. Nor\\n\\n60\\n Fed. R. Crim. P. 31(b)(3).\\n61\\n Id. advisory committee’s note to 1944 adoption.\\n62\\n See United States v. Melendez, 775 F.3d 50, 57 (1st Cir.\\n2014); United States v. Warren, 593 F.3d 540, 546 (7th Cir.\\n2010); United States v. Fort, 472 F.3d 1106, 1111 n.3 (9th\\nCir. 2007); United States v. Gotti, 451 F.3d 133, 137 (2d Cir.\\n2006).\\n63\\n See United States v. Perez, 22 U.S. 579, 580 (1824).\\n64\\n Dietz, 136 S. Ct. at 1892.\\n\\n\\n\\n\\n 18\\n\\ndoes it contain any other limitation on the district court’s\\npower to prohibit one. In fact, the rule does not even mention\\nthat issue.65 Thus, as the Supreme Court has noted in\\naddressing other rules of court, “[i]t would require a much\\nclearer expression of purpose than [this rule] provides for us\\nto assume that it was intended to abrogate” the district courts’\\ninherent power.66 Put simply, when there have been multiple\\nmistrials and the prosecutor seeks to try the case again, Rule\\n31(b)(3) does not purport to reduce the role of the district\\ncourts to that of a rubber stamp.\\n\\n C.\\n\\n Finally, the majority claims that a district court can\\nexercise its inherent power to dismiss an indictment only if\\nthere is evidence of willful bad faith or prosecutorial\\nmisconduct on the part of the government and resultant\\nprejudice to the defendant. It cites to numerous decisions that\\nit says supports this position.67 But none of these cases deals\\n\\n65\\n The majority claims that Rule 31(b)(3)’s silence on this\\nissue supports the proposition that district courts lack the\\nauthority to dismiss an indictment following serial mistrials.\\nBut because district courts have the inherent power to do so\\nas explained above, the question is not whether Rule 31(b)(3)\\npermits district courts to dismiss an indictment in that\\ncircumstance. The question instead is whether Rule 31(b)(3)\\nprohibits them from doing so. It does not.\\n66\\n Link, 370 U.S. at 631-32.\\n67\\n See Bank of Nova Scotia v. United States, 487 U.S. 250,\\n254-56, 263 (1988); United States v. Chapman, 524 F.3d\\n1073, 1087 (9th Cir. 2008); United States v. Goodson, 204\\nF.3d 508, 514 (4th Cir. 2000); United States v. Derrick, 163\\n\\n\\n\\n\\n 19\\n\\nwith the particular circumstance we face here: the decision to\\nretry a defendant after serial mistrials.68 In fact, many are\\ndismissals due to prosecutorial misconduct. The majority’s\\nreliance on such decisions is misplaced because it ignores the\\nfact that the dismissal in this case was not punitive in nature;\\nit was not a sanction for misconduct.69 As two commentators\\nhave explained, “[a]lthough the inherent power principle has\\nusually involved cases of misconduct by the parties or a\\nvindication of statutory principles, the doctrine is not so\\nlimited.”70 To the contrary, courts may use their inherent\\nauthority to dismiss indictments whenever necessary to\\nvindicate “principles of fairness to the defendant and the\\ninterests of the public in the effective administration of\\njustice.”71\\n\\n That is just what the District Court did here. The\\nGovernment asked the District Court to dismiss without\\nprejudice “[e]ven if this court were inclined to dismiss the\\ncase.”72 Yet the Government proffered no additional\\n\\n\\nF.3d 799, 808 (4th Cir. 1998); United States v. Tucker, 8 F.3d\\n673, 674 (9th Cir. 1993) (en banc); United States v. Van\\nEngel, 15 F.3d 623, 631-32 (7th Cir. 1993); United States v.\\nSantana, 6 F.3d 1, 11 (1st Cir. 1993); United States v. Isgro,\\n974 F.2d 1091, 1094 (9th Cir. 1992).\\n68\\n Derrick does deal with a dismissal of the indictment after\\nan initial grant of a retrial, but the circumstance differs from\\nthis case because the mistrials were not due to deadlocked\\nverdicts. See 163 F.3d at 803\\n69\\n Cf., e.g., Isgro, 974 F.2d at 1097.\\n70\\n Berch & Berch, supra note 51, at 548.\\n71\\n Id.\\n72\\n Wright, 2017 WL 1179006, at *7.\\n\\n\\n\\n\\n 20\\n\\nevidence it would present if Wright was re-indicted. It asked\\nto try the same case again before a third jury, merely hoping\\nfor a different result. The District Court’s dismissal of the\\nindictment with prejudice was based on the merits, or lack\\nthereof, of the Government’s request, no more and no less.\\n\\n Moreover, the dismissal was not, as the majority\\ncontends, a general declaration of unfairness simply because\\nthe government failed to obtain a conviction.73 Nor was it\\nmerely an attempt to shield the defendant from the anxiety of\\na retrial.74 Reference to Miller and Shepherd misconstrues\\nnot only the circumstance of this case, but also the gravity of\\nthe District Court’s concern. As I discuss next, the District\\nCourt weighed many factors, mindful of the importance of\\neach, before making its decision. From all of this—even\\ntaking into account the separation of powers and Rule\\n31(b)(3)—it is evident to me that the District Court correctly\\nconcluded it had the inherent authority to act upon the\\nprosecutor’s decision to retry this case in the wake of two\\nmistrials.75\\n\\n73\\n See United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\n74\\n See United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975); see also Arizona v. Washington, 434 U.S. 497, 503-04\\n(1978).\\n75\\n Although we conclude that the District Court appropriately\\nexercised its inherent power as a court of law to dismiss an\\nindictment, thus placing its actions within Eash’s first\\ncategory, the District Court appeared at one point to tether its\\ndismissal to its “inherent authority to effectuate . . . the\\nspeedy and orderly administration of justice and to ensure\\nfundamental fairness.” Wright, 2017 WL 1179006, at *2.\\nThese actions are typically associated with the second\\n\\n\\n\\n\\n 21\\n\\n III.\\n\\n Before moving to the actual merits of the District\\nCourt’s decision, a word of caution is in order. Just because a\\ncourt has inherent power to dismiss an indictment after a\\nretrial does not mean it should always be exercised.76 My\\ndissenting opinion today should not be interpreted as an\\nendorsement of unchecked and ungrounded judicial power.\\nNor should it be interpreted as permitting district courts in\\nthis Circuit to dismiss indictments without a significant basis\\nfor doing so. Moreover, nothing in this opinion should be\\nread as limiting reprosecution to two trials. Cases no doubt\\nexist where a third or fourth trial on the same indictment may\\nbe appropriate where the evidence so indicates. It is simply\\nmy conclusion that, in some cases, and in the proper exercise\\nof its discretion, a district court has the inherent power to\\nprohibit continued re-prosecution by dismissing an\\nindictment.\\n\\n IV.\\n\\n This is such a case. The District Court here rightly\\nproceeded with the Government’s request for another trial\\nwith deliberate caution. Recognizing the lack of guidance\\n\\n\\nclassification of Eash’s powers. See Eash, 757 F.2d at 562-\\n563. Nonetheless, it invoked the inherent power of the court\\nand dismissed the case and it is on this basis that I conclude\\nthe District Court did not reach the boundaries of its power.\\n76\\n See Lopez v. United States 373 U.S. 427, 440 (1963); see\\nalso Chambers, 501 U.S. at 44 (“Because of their very\\npotency and discretion, inherent powers must be exercised\\nwith restraint and discretion.”).\\n\\n\\n\\n\\n 22\\n\\nfrom this Court, the District Court turned to a decision of the\\nSupreme Court of New Jersey. In State v. Abbati,77 that court\\nlisted several factors a trial court should consider before\\ndismissing an indictment after several hung juries. These\\nfactors are valid inquiries and include\\n\\n the number of previous mistrials and the\\n outcome of the juries’ deliberations, as far as\\n can be determined;\\n the character or nature of the previous trials,\\n considering their length, complexity of issues,\\n and similarities in evidence;\\n the probability that any subsequent trial will be\\n much different from the previous ones;\\n the relative strength of the party’s case, as\\n determined by the trial court;\\n the conduct of counsel during the previous\\n trials.78\\n\\nIn considering these factors, a district court must also accord\\nappropriate weight to the Government’s decision to continue\\nprosecution, giving deliberate consideration to the reasons for\\nthat choice.79\\n\\n Other considerations might include the seriousness of\\nthe crimes charged, the public’s interest in the effective\\nresolution of criminal charges, and the criminal defendant’s\\ncircumstances, including the impact that continued\\nprosecution might have on him or her and the potential for\\n\\n77\\n 493 A.2d 513.\\n78\\n Id. at 521-22.\\n79\\n See id.\\n\\n\\n\\n\\n 23\\n\\nunfairness or unnecessary hardship.80 The factors just\\noutlined are not an exhaustive list and district courts could\\nconsider other things that are reasonably useful in answering\\nwhether further prosecutions after deadlocked juries should\\nbe permitted. Moreover, all of these elements of inquiry\\nenable the court to assess the impact that a serial retrial has on\\nthe integrity of the judiciary as an institution.\\n\\n These avenues of inquiry make sense to me. Take\\ndifferences in evidence, for example. If the evidence would\\nbe different at a retrial, then there seems little chance that\\ncontinued prosecution should be curtailed. If, on the other\\nhand, there would be no substantial difference in evidence,\\nconcern about re-prosecution is appropriate. So too the\\nnumber of deadlocked juries is an important consideration.\\nContinued prosecution after two, three, or even four\\ndeadlocked juries could unbalance the scale. By inquiring\\ninto the seriousness of the charges, a district court could\\ncompare the crime being prosecuted to other cases when a\\ncourt dismissed an indictment after deadlocked juries. In\\nother words, a district court must make sufficient findings and\\nestablish a sufficient record supporting its decision, thus\\nenabling a court of appeals to accurately assess whether the\\ndistrict court abused its discretion or not. That is what the\\nDistrict Court did here.\\n\\n I see no abuse of discretion in the District Court’s\\nexercise of its inherent powers. The District Court’s ruling\\nwas not arbitrary and instead was based on a thorough,\\ncareful, and balanced consideration of the above factors. The\\nDistrict Court first acknowledged the weight of its actions\\n\\n80\\n See id.\\n\\n\\n\\n\\n 24\\n\\nwithin our constitutional scheme. It then found that the\\nevidence suggested that the deadlock was not the result of a\\nlone holdout. As to the character of the preceding trials, the\\nDistrict Court noted the Government’s position that this was a\\n“simple” case. It also stated that both previous trials were\\n“virtual duplicates” and that counsel on both sides was the\\nsame for both prosecutions. The District Court further\\nobserved the lack of any allegation of jury nullification or\\nbias. Instead, it found that “there is every indication that the\\ntwo juries engaged in deliberations in good faith, and, despite\\ntheir best efforts, were unable to reach a verdict.”\\n\\n The District Court also considered the strength of the\\nparties’ respective cases and determined that its opinion on\\nthis factor was irrelevant, given that two separate juries had\\nconcluded that the Government failed to meet its burden of\\nproof. It commended the professionalism and hence the\\neffectiveness of counsel on all sides, which it weighted as\\nfavoring disallowing any further prosecution. The District\\nCourt specifically considered the seriousness of the crime\\ncharged, and it noted that other courts had dismissed\\nindictments when the charges were far graver.81 Lastly, the\\nDistrict Court thoroughly balanced the Government’s\\nauthority to prosecute against the effect of continued\\nprosecution on Wright. Recognizing that Wright has been on\\nbond since July of 2014, and on home detention for nearly\\ntwo years, the District Court concluded that this inquiry\\ntipped in his favor.\\n\\n81\\n Wright, 2017 WL 1179006, at *6 (citing United States v.\\nIngram, 412 F. Supp. 384, 385 (D.D.C. 1976); State v.\\nMoriwake, 647 P.2d 705, 708 (Haw. 1982); Abbati, 493 A.2d\\nat 517; and State v. Witt, 572 S.W.2d 913, 914 (Tenn. 1978)).\\n\\n\\n\\n\\n 25\\n\\n V.\\n\\n In conclusion, I see no abuse of discretion in the\\nDistrict Court’s careful and thorough balancing of relevant\\nfactors, a balancing which led it to invoke its inherent power\\nand to dismiss the Government’s indictment of Wright. For\\nall of these reasons, I respectfully dissent from my esteemed\\ncolleagues in the majority. I would affirm.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360366/\", \"author_raw\": \"NYGAARD, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"MCKEE"},"judge2":{"kind":"string","value":"SHWARTZ"},"judge3":{"kind":"string","value":"NYGAARD"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MCKEE\": \", Circuit\", \"SHWARTZ\": \", Circuit\", \"NYGAARD\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":2,"string":"2"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583113/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Raymont Wright\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-18\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n _____________\n\n No. 17-1972\n _____________\n\n UNITED STATES OF AMERICA,\n\n Appellant\n\n v.\n\n RAYMONT WRIGHT\n\n ______________\n\n ON APPEAL FROM THE\n UNITED STATES DISTRICT COURT\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\n (D.C. No. 2-14-cr-00292-001)\n District Judge: Hon. Cathy Bissoon\n ______________\n\n Argued May 24, 2018\n ______________\n\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\n Judges.\n\n (Opinion Filed: January 17, 2019)\n\n ______________\n\n OPINION OF THE COURT\n ________________\n\nDonovan J. Cocas, Esq. [ARGUED]\nJane M. Datttilo, Esq.\nLaura S. Irwin, Esq.\nOffice of the United States Attorney\n700 Grant Street\nSuite 4000\nPittsburgh, PA 15219\n\n Attorney for Appellant\n\nRenee Pietropaolo, Esq. [ARGUED]\nLisa B. Freeland, Esq.\nAkin Adepoju, Esq.\nOffice of the Federal Public Defender\n1001 Liberty Avenue\n1500 Liberty Center\nPittsburgh, PA 15222\n\n Attorneys for Appellee Raymont Wright\n\nLawrence S. Lustberg, Esq. [ARGUED]\nGibbons, P.C.\nOne Gateway Center\nNewark, NJ 07102\n\n Attorney for Amicus Appellee National Association of\n Criminal Defense Lawyers\n\n\n\n\n 2\n\nSHWARTZ, Circuit Judge.\n\n The District Court barred a retrial of and dismissed the\nindictment against Defendant Raymont Wright with prejudice\nafter two juries failed to reach a verdict. The Court did so\nrelying on its inherent authority, but without finding that any\nmisconduct had occurred or that Wright would suffer any\nprejudice beyond the general anxiety and inconvenience of\nfacing a retrial. Under such circumstances, the Court lacked\nthe inherent authority to bar the retrial and dismiss the\nindictment. Therefore, we will reverse the order dismissing the\nindictment and remand for further proceedings.\n\n I\n\n In December 2014, Wright was charged with being a\nfelon in possession of a firearm, in violation of 18 U.S.C.\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\nMay 2016. The jury was unable to reach a verdict. A second\ntrial was held in March 2017, and that jury was also unable to\nreach a verdict.\n\n During both trials, the jury heard evidence from police\nofficers about Wright’s actions on July 24, 2014.1 That\nevening, five Pittsburgh Police detectives were patrolling in\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\nwere in the lead car, and Detectives Fallert and Goob were in\nthe second car. Around 8:30 p.m. (when it was still daylight),\nFallert and Goob saw a man, later identified as Wright, driving\n\n 1\n The following facts are drawn largely from the\nevidence presented at the first trial.\n\n\n\n\n 3\n\na car in the opposite direction well above the 25-mile-per-hour\nspeed limit. The detectives turned around to follow Wright,\nand Wright sped up and turned onto a loop-shaped road. The\ndetectives pursued Wright, who fled at a high speed and ran at\nleast four stop signs. The lead car lost sight of Wright shortly\nthereafter and discontinued pursuit.\n\n Officers in the lead car then noticed skid marks\nsuggesting that a car had intended but failed to make a left turn\nat the end of a street. Officers thereafter came upon Wright’s\ncar in a parking lot below. The car had gone through a fence,\nover a hillside, and into the lot. The car hit two unoccupied\nparked cars, its tires blew out, and its windows were down.\n\n Detectives Baker and Henson exited the vehicle at the\ntop of the hill and remained where Wright’s car broke through\nthe fence, and Detective Kennedy drove his car down to the\nparking lot’s entrance. Baker and Henson testified that they\nsaw Wright search around the rear passenger seat of the car,\nback out of the vehicle with a black semi-automatic handgun\nin his right hand, and try to “rack the slide,” which can insert\nor remove a round from the chamber. App. 118-19. They had\ntheir weapons drawn and told Wright to drop the gun. At first,\nWright merely stepped back, but he eventually tossed the gun\nto the side, backed away, and lied on the ground. Pittsburgh\npolice officer Elliott and his partner, who heard of the crash on\nthe radio, were the first to reach Wright, and saw him lying on\nthe ground with a handgun next to him. Henson stated that\nwhen he made it down to the parking lot, he heard Wright say\nto him, “Hey, big guy. You won this time or you won this\nround, something of that nature. He [Wright] said: You feel\nme? You won this time,” which Henson understood to mean\nthat he had just avoided a shootout or that he caught Wright\n\n\n\n\n 4\n\nafter the pursuit. App. 125. Henson subsequently took custody\nof the gun and noticed the slide lever was bent, and when he\nstraightened it, saw the gun was loaded with eight rounds, and\none in the chamber. 2\n\n At the close of the Government’s case, Wright moved\nfor a directed verdict, arguing that no reasonable juror could\nfind beyond a reasonable doubt that Wright possessed the\nfirearm. The District Court denied the motion because “the\nevidence does thus far demonstrate that a reasonable juror\ncould most certainly find the Defendant guilty of the charge in\nthis case.” App. 171. Wright did not present a case.\n\n The jury deliberated for approximately five hours and\nthen reported to the Court that it was deadlocked. After polling\nthe jurors to confirm they were deadlocked and further\ndeliberations would not bring them closer to a unanimous\nverdict, the District Court declared a mistrial.\n\n At Wright’s March 2017 retrial, the Government\npresented substantially the same evidence. The Government\nalso called Detective Kennedy and Lieutenant Palermo, who\nwere at the scene after Wright was arrested, as well as experts\nwho testified regarding the collection of DNA and fingerprint\nevidence from firearms to respond to Wright’s argument at the\nfirst trial that investigators chose not to test the gun for forensic\nevidence in an effort to cover up that they had planted the gun\nat the scene.\n\n\n 2\n The parties stipulated Wright had been convicted of a\nqualifying felony, and an ATF Special Agent testified about\nthe gun’s interstate nexus.\n\n\n\n\n 5\n\n At the close of the Government’s case, Wright again\nmoved for a judgment of acquittal, which the Court denied\nbecause “there is sufficient evidence in the record to establish\nbeyond a reasonable doubt that Mr. Wright possessed the\nfirearm in the case,” App. 650. Wright did not put on a case.\n\n The second jury deliberated for approximately three\nhours and then reported that it was hopelessly deadlocked. The\nCourt polled the jury to confirm the deadlock and then\ndismissed the jury. 3\n\n After the Government notified the Court that it intended\nto retry the case, the Court required the parties to brief\n“whether the Court, through an exercise of its inherent\nauthority, should prohibit or permit a second re-trial in this\ncase.” App. 26. After considering the parties’ arguments, the\nDistrict Court dismissed the indictment with prejudice, holding\nthat it “ha[d] the inherent authority, under some circumstances,\nto dismiss an indictment following multiple mistrials.” United\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\nunderlying the Double Jeopardy Clause also applied to a\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\n(2) other courts had dismissed indictments in similar\n\n 3\n Wright asserted that in the first trial, jurors voted 8-4\nfor acquittal, and in the second trial, the jury was evenly split.\nThe Government asserted that in the first trial, jurors voted 7-\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\nnot explain how he obtained these numbers, the Government\nsaid it obtained them by speaking with the jurors.\n\n\n\n\n 6\n\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\nexpressly allows the Government to retry a case after a mistrial,\nnothing in the rule “limits a court’s inherent supervisory\nauthority to dismiss an indictment in the interests of\nfundamental fairness,” id. at *4; and (4) if the Court were to\nadopt the Government’s position that there are no limit to the\nnumber of times the Government can retry a defendant, it\nwould be tantamount to a “type of jury shopping” that a court\nshould not permit, id. at *4. The District Court also considered\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\nconcluded that most factors supported dismissal. 4\n\n 4\n The Abbati factors are\n\n (1) the number of prior mistrials and the\n outcome of the juries’ deliberations, so far as is\n known; (2) the character of prior trials in terms\n of length, complexity, and similarity of evidence\n presented; (3) the likelihood of any substantial\n difference in a subsequent trial, if allowed;\n (4) the trial court’s own evaluation of the relative\n strength of each party’s case; and (5) the\n professional conduct and diligence of respective\n counsel, particularly of the prosecuting attorney.\n The court must also give due weight to the\n prosecutor’s decision to reprosecute, assessing\n the reasons for that decision, such as the gravity\n\n\n\n\n 7\n\n The Government appeals.\n\n II 5\n\n We review the District Court’s order dismissing the\nindictment based on the Court’s inherent power for abuse of\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\n\n of the criminal charges and the public’s concern\n in the effective and definitive conclusion of\n criminal prosecutions. Conversely, the court\n should accord careful consideration to the status\n of the individual defendant and the impact of a\n retrial upon the defendant in terms of untoward\n hardship and unfairness.\n\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\nat 521-22). For the reasons set forth herein, we would not\nadopt Abbati, but even if we were to consider the Abbati\nfactors, we would conclude that they do not support dismissal\nin this case.\n 5\n The District Court had jurisdiction pursuant to 18\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\n§ 3731.\n 6\n The phrases “inherent power,” “inherent authority,”\n“supervisory power,” and “supervisory authority” are all used\nto describe the basis for a court action seeking to maintain the\nintegrity of the proceedings that is not directly tethered to a\nspecific rule, statute, or constitutional provision. See, e.g.,\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\n43 (1991) (inherent power); Bank of Nova Scotia v. United\n\n\n\n\n 8\n\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\nindictment for abuse of discretion); cf. Chambers v. NASCO,\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\nsanctions under its inherent power for abuse of discretion);\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\n2005) (“A trial court’s remedy for a discovery violation under\nits supervisory powers is reviewed for abuse of discretion.”).\nA district court abuses its discretion when it makes an errant\nconclusion of law, an improper application of law to fact, or a\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\n\n A\n\n Federal Rule of Criminal Procedure 31 allows the\nGovernment to retry a case if the court declares a mistrial after\na jury announces it is unable to reach a verdict. Specifically,\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\non one or more counts, the court may declare a mistrial on\nthose counts. The government may retry any defendant on any\ncount on which the jury could not agree.” Fed. R. Crim. P.\n31(b)(3). The word “may” means that the Government has the\n\n\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\n(supervisory power); United States v. Payner, 447 U.S. 727,\n733-36 (1980) (supervisory power); United States v. Nobles,\n422 U.S. 225, 231 (1975) (inherent power).\n Even if we accepted the distinctions our dissenting\ncolleague has drawn between inherent judicial powers,\nlegislatively granted judicial powers, and supervisory powers,\neach category must operate within the constitutional\nframework, including the separation of powers.\n\n\n\n\n 9\n\ndiscretion to retry a case, and nothing in the rule or its\ncommentary provides or even suggests a limit on the number\nof retrials it may conduct. See United States v. Wqas Khan,\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\n\n 7\n While Rule 31 does not limit the Government’s\nauthority to retry a case, a handful of district courts have\ndismissed indictments following a second hung jury, but those\ndecisions are not persuasive. In Ingram, the district court\ndismissed the indictment sua sponte (without any initial\nobjection by the Government) after two mistrials—in which\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\njailed during the pendency of the trials, and “[t]he Government\nha[d] no new proof; it simply want[ed] another chance.” 412\nF. Supp. at 385. The court concluded that to permit a retrial\nwould be “to ignore the reasonable doubt standard,” and so\n“[t]he Court’s intervention [was] required in the interest of\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\n(McGowan, J., dissenting)). The Ingram court, however, relied\nin part on the dissent in De Diego. Cases since Ingram have\napplied the De Diego majority’s view concerning a court’s\nlimited authority to dismiss an indictment. See, e.g., United\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\nDe Diego and reversing the district court’s dismissal of the\nindictment where the district court found it would be\n“unconscionable” to retry to the defendant); United States v.\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\nDiego and its dissent and holding a district court does not have\nauthority to sua sponte dismiss an indictment based on the\n\n\n\n\n 10\n\ndefendant’s poor health); United States v. Mussehl, 453 F.\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\nto dismiss the indictment based on alleged errors at trial, and\nciting De Diego for the proposition that “[t]he duty [to\nadminister justice] encompasses the concept of review of the\nquestion whether the United States Attorney, in making his\ndecision to prosecute, complied with the law, but does not\nallow the Court to question a United States Attorney’s\njudgment decision to prosecute, when lawfully made”).\n The District Court also relied on Rossoff, where the\ncourt denied the Government’s motion to dismiss the\nindictment under Federal Rule of Criminal Procedure 48(a),\nbut still dismissed the indictment with prejudice. 806 F. Supp.\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\nbeen two trials, and the Government sought to dismiss the\nindictment and refile the charges in a different judicial district.\nId. The court determined it had authority to dismiss an\nindictment with prejudice if a retrial was “against the concept\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\nSupp. 384), and did so because, among other reasons, the\ndefendant was in poor health, was under significant strain, and\na majority of jurors at both trials found him not guilty, id. at\n203. Rossoff, however, is distinguishable from Wright’s case\nbecause in Rossoff, the Government sought to dismiss the\nindictment so that it could refile charges in a different judicial\ndistrict, which caused the court to question the Government’s\ngood faith. In Wright’s case, the District Court made no\nfinding that the Government’s desire to retry Wright was for\nan improper purpose.\n In addition, and significantly, neither Ingram nor\nRossoff addressed the doctrine of separation of powers.\nRather, each essentially relied on a general concept of fairness\n\n\n\n\n 11\n\nthe text that empowers a court to prohibit the Government from\nretrying a case. 8\n B\n\n Apparently aware that Rule 31 did not provide it with a\nbasis to preclude a retrial in these circumstances, the District\nCourt concluded that it had the inherent authority to forbid the\nretrial and dismiss the indictment. The District Court erred.\n\n The exercise of inherent authority must satisfy two\nrequirements: (1) it “must be a reasonable response to the\n\n\nto the defendant in deciding to dismiss an indictment. See\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\nIn this Circuit, however, “[t]he judiciary may not impose its\npersonal and private notions of ‘fairness’ on law enforcement\nofficials, but does have a limited authority to affect\nprosecutorial actions when those actions are taken in violation\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\n596 (3d Cir. 1992) (citations omitted).\n 8\n Rule 31 differs from other Federal Rules of Criminal\nProcedure because it makes no mention of the court’s\nauthority. For instance, Rule 48(b) states that a court has\nauthority to dismiss an indictment “if unnecessary delay occurs\nin: (1) presenting a charge to the grand jury; (2) filing an\ninformation against a defendant; or (3) bringing a defendant to\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\ngrounds on which a district court could also dismiss an\nindictment, but each would be triggered by a motion, such as a\nmotion to dismiss for failure to comply with Rule 16’s\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\n16(d)(2)(D), or a motion asserting a defect in the indictment,\nFed. R. Crim. P. 12(b)(3)(B).\n\n\n\n\n 12\n\nproblems and needs confronting the court’s fair administration\nof justice,” and (2) it “cannot be contrary to any express grant\nof or limitation on the district court’s power contained in a rule\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\n(citations and internal quotation marks omitted). We will\nexamine each of these requirements in turn.\n\n 1\n\n As to the first Dietz requirement, “[g]uided by\nconsiderations of justice, and in the exercise of supervisory\npowers, federal courts may, within limits, formulate procedural\nrules not specifically required by the Constitution or the\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\n(internal quotation marks and citation omitted). Such rules\nmust be imposed (1) “to implement a remedy for violation of\nrecognized rights,” (2) “to preserve judicial integrity by\nensuring that a conviction rests on appropriate considerations\nvalidly before the jury,” and (3) “as a remedy designed to deter\nillegal conduct.” Id. (citations omitted). Thus, a court may\nexercise its inherent authority only when it is necessary to\naddress improper conduct and ensure respect for the\nproceedings.\n\n Under these principles, a court may dismiss an\nindictment based upon its inherent authority only if the\nGovernment engaged in misconduct, the defendant was\nprejudiced, and no less severe remedy was available to address\nthe prejudice. See Bank of Nova Scotia v. United States, 487\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\n(stating that “[a] court may dismiss an indictment under its\nsupervisory powers only when the defendant suffers\nsubstantial prejudice and where no lesser remedial action is\n\n\n\n\n 13\n\navailable” (citations and internal quotation marks omitted));\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\n(observing that “a district court may not, in the management of\nits docket, exercise its discretion to dismiss an indictment with\nprejudice, either under Rule 48(b) or under its supervisory\npower, unless the violation caused prejudice to the defendant\nor posed a substantial threat thereof” (emphasis omitted));\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\n(holding that an indictment may not be dismissed for\nprosecutorial misconduct absent a showing that the misconduct\nprejudiced the defendants, and stating that “virtually every\nother circuit to consider the issue post-Hasting and Nova Scotia\nhas also held that an indictment may not be dismissed based on\nprosecutorial misconduct, absent a showing of prejudice to the\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\n(7th Cir. 1993) (“A federal judge is not authorized to punish\nthe misconduct of a prosecutor by letting the defendant walk,\nunless the misconduct not only violated the defendant’s rights\nbut also prejudiced his defense . . . .”); United States v. Tucker,\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\nexercise its supervisory authority to reverse a conviction or\ndismiss an indictment absent prejudice to the defendant.”);\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\nHasting, and Bank of Nova Scotia form a trilogy admonishing\nfederal courts to refrain from using the supervisory power to\nconform executive conduct to judicially preferred norms by\ndismissing charges, absent cognizable prejudice to a particular\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\nCir. 1992) (“Before it may invoke this [supervisory] power [to\ndismiss an indictment], a court must first find that the\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\n1480 (9th Cir. 1994).\n\n\n\n\n 14\n\n In this case, there has been no misconduct. Indeed, the\nDistrict Court noted that the Government performed diligently\nand professionally in both trials, Wright, 2017 WL 1179006,\nat *4, and found that the evidence was sufficient to prove\nbeyond a reasonable doubt that Wright possessed the gun. The\nDistrict Court nonetheless applied its own predictions about\nwhat another jury may do when presented with the same\nevidence, emphasized the need for finality, and opined that the\neffect of prosecution on the defendant precluded a proper\nprosecution from proceeding. See id. at *5-6. Invoking its own\nnotions about the unfairness of requiring a defendant to face a\nretrial where the Government did not obtain a majority of the\njurors’ votes is an improper exercise of a court’s supervisory\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\nMoreover, there is no prejudice to a defendant simply because\nhe faces the anxiety and the normal stress of undergoing a trial.\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\n1975) (“[A]nxiety is present to some degree in virtually every\ncase. Something more than the normal anxiety that\naccompanies a trial is necessary to show a degree of\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\nonly real harm alleged is the general unfairness to these\ndefendants in having to go forward yet again with a lengthy\ntrial, in their being ‘ground down’ by the several months’ drain\non their mental, emotional, and financial resources. A lack of\nsuch fairness, however, does not alone violate due process.”).\nRather, prejudice sufficient for the District Court to intervene\nin a proper prosecution based upon its inherent authority occurs\nonly where the Government engages in actions that place a\ndefendant at a disadvantage in addressing the charges. That\nsort of prejudice is absent in this case.\n\n\n\n\n 15\n\n Unless there is some constitutional basis, such as a due\nprocess violation, it makes sense to limit a court’s authority to\nbar retrial to instances of prosecutorial misconduct and\nprejudice. First, it ensures that a judge’s personal preferences\nabout a case do not influence whether the case proceeds. See\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\n(“The judiciary may not impose its personal and private\nnotions of ‘fairness’ on law enforcement officials, but does\nhave a limited authority to affect prosecutorial actions when\nthose actions are taken in violation of the Constitution.”).\nSecond, as more fully discussed below, it guarantees that a\ncourt limits the Executive’s decision to prosecute only where\nthere is a constitutionally sound reason to do so. 9 This brings\nus to the second Dietz requirement.\n\n\n 9\n For these reasons, we find unpersuasive our dissenting\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\nobservation that a court has the inherent power to resolve a\ncase, as authority for allowing a court dismiss an indictment\nafter successive hung juries. As a general matter, there is no\ndoubt that a court has the authority to dismiss a case, but it may\nnot simply end a case because it decides that it should not be\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\ntheir progeny make clear, the court must point to evidentiary\ndeficiency, prejudicial misconduct, or a constitutional basis,\nsuch as double jeopardy or due process, to justify precluding a\nprosecution. If a court believed that the evidence was deficient,\nthe prosecutor engaged in prejudicial misconduct, or a retrial\nwould violate the constitution, then it has a basis to preclude a\nretrial. Requiring such reasons for barring a retrial ensures that\n\n\n\n\n 16\n\n 2\n\n The second Dietz requirement reminds a court that the\nexercise of its powers must be in accordance with the\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\nwith the Constitution, a court must be mindful of its role in our\ntripartite form of government and the doctrine of separation of\npowers. Separation-of-powers principles limit a court’s\ninherent authority. “Regardless of whether the supervisory\npower stems from the federal courts’ inherent power to check\nintrusions by other branches of government or whether it is a\nform of specialized federal common law, the separation-of-\npowers principle imposes significant limits on it,” and\n“[p]roper regard for judicial integrity does not justify a\n‘chancellor’s foot veto’ over activities of coequal branches of\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\nCir. 1985) (internal quotation marks omitted) (quoting United\nStates v. Russell, 411 U.S. 423, 435 (1973)).\n\n In the criminal context, the Executive Branch has\n“broad discretion as to whom to prosecute,” and this discretion\n“rests largely on the recognition that the decision to prosecute\nis particularly ill-suited to judicial review.” Wayte v. United\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\nquotation marks omitted). A court is not equipped to evaluate\n\n [s]uch factors as . . . the prosecution’s general\n deterrence value, the Government’s enforcement\n priorities, and the case’s relationship to the\n\n\nthe ruling is not based on a court’s own personal sense of\nwhether a case is worthy of prosecution.\n\n\n\n\n 17\n\n Government’s overall enforcement plan . . . .\n Judicial supervision in this area, moreover,\n entails systemic costs of particular concern.\n Examining the basis of a prosecution delays the\n criminal proceeding, threatens to chill law\n enforcement by subjecting the prosecutor’s\n motives and decisionmaking to outside inquiry,\n and may undermine prosecutorial effectiveness\n by revealing the Government’s enforcement\n policy. All of these are substantial concerns that\n make the courts properly hesitant to examine the\n decision whether to prosecute.\n\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\n(echoing similar sentiments with respect to Rule 48(a)\ndismissals). Thus, absent constitutional concerns, the decision\nto try or retry a case is at the discretion of the prosecutor.\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\nas superprosecutors, second-guessing the legitimate exercise of\ncore elements of prosecutorial discretion, but rather as neutral\narbiters of the law” (citation and internal quotation marks\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\n1994) (“[T]he choice to forego permanently a prosecution is\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\n676 (“In maintaining order in our own house, we should not\nneedlessly trample on the interest of the prosecutor and of the\npublic in securing proper, lasting convictions.”); Isgro, 974\nF.2d at 1097 (stating that the doctrine of separation of powers\n“mandates judicial respect for the independence of the\nprosecutor,” and “[d]ismissal of an indictment with prejudice\n\n\n\n\n 18\n\nis the most severe sanction possible”). 10 Accordingly,\nseparation-of-powers principles preclude a court from\nterminating a prosecution absent misconduct and prejudice to\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\n974 F.2d at 1094.\n\n In short, a court’s power to preclude a prosecution is\nlimited by the separation of powers and, specifically, the\nExecutive’s law-enforcement and prosecutorial prerogative.\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\nhere to dismiss an indictment in the absence of misconduct and\nprejudice and based only on the fact that two juries could not\nreach a verdict intrudes on the Executive’s domain and thereby\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\nat 138; Isgro, 974 F.2d 1091.\n\n 10\n Several state courts have also refused to recognize\nany inherent authority to dismiss an indictment to prevent a\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\n(Fla. Dist. Ct. App. 1980). Other states, however, have\nrecognized a court’s authority to dismiss an indictment sua\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\n712; Witt, 572 S.W.2d at 917. These latter cases are\nunpersuasive because they give too little weight to the\nseparation of powers, a crucial constitutional principle in the\nfederal system.\n\n\n\n\n 19\n\n Finally, there is no statute or procedural rule that\npermits a court to bar a retrial in the absence of misconduct and\nprejudice. First, a court may not dismiss an indictment as a\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\n505. Second, a court’s inherent power does not “include the\npower to develop rules that circumvent or conflict with the\nFederal Rules of Criminal Procedure.” Carlisle v. United\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\nexercise of inherent authority circumvents the absence of\npower of the district court to dismiss an indictment in Rule\n31(b). As stated above, courts have inherent authority to\ndismiss indictments, including, for instance, for prosecutorial\nmisconduct if the defendant was prejudiced, Bank of Nova\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\nnor our Court has extended a court’s inherent authority to allow\n\n 11\n In Chambers, for example, the Supreme Court\nrecognized a court’s authority to impose silence, respect, and\ndecorum based on its authority to manage its own affairs. 501\nU.S. at 43. This authority has been exercised by controlling\nadmission to the bar and disciplining its members; punishing\nfor contempt, which penalizes disruption to proceedings and\ndisobedience to court orders; disallowing fraud on the courts;\nensuring the proceedings move forward; and curtailing\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\ncivil case for failure to prosecute to prevent delays and court\ncongestion as part of a court’s inherent power to manage its\nown affairs). Chambers and Link address how a court may\nmanage its own proceedings, but they do not address how the\ncourt must also account for issues of separation of powers in\nthe context of a criminal case.\n\n\n\n\n 20\n\nthe sua sponte dismissal of an indictment solely to preclude\nmultiple mistrials following hung juries, see Chambers, 501\nU.S. at 47; HSBC, 863 F.3d at 136. 12\n\n 12\n Most cases concerning a court’s inherent authority\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\n(noting a court’s inherent powers to rescind a jury discharge\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\n(recognizing a court’s authority to vacate a judgment upon\nproof that a fraud was perpetrated on the court, and, in\nparticular, to assess as a sanction the entire amount of the\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\n(authority to dismiss a civil case sua sponte for failure to\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\n(1947) (dismissing an action based on the doctrine of forum\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\n(citing cases involving the scope of a district court’s inherent\npower); Eash, 757 F.2d at 561-64 (same).\n There are other circumstances in which district courts\nlack the inherent authority to act, and most of those situations\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\n433 (holding that a court does not have authority to grant a\npost-verdict motion for judgment of acquittal, filed one day\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\n45-50, 55 (holding that a district court does not have inherent\nauthority to dismiss an indictment because the Government\nfailed to disclose to the grand jury substantial exculpatory\nevidence; “[b]ecause the grand jury is an institution separate\nfrom the courts, over whose functioning the courts do not\npreside, we think it clear that, as a general matter at least, no\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\nat 129, 135-37 (holding that the district court violated\nseparation-of-powers principles by sua sponte invoking its\n\n\n\n\n 21\n\n Thus, the District Court abused its discretion in barring\na retrial and dismissing the indictment. 13\n\n III\n\n For the foregoing reasons, we will reverse and remand\nfor further proceedings.\n\n\n\n\nsupervisory power to oversee the government’s entry into and\nimplementation of a deferred prosecution agreement).\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Raymont Wright\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-18\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n _____________\\n\\n No. 17-1972\\n _____________\\n\\n UNITED STATES OF AMERICA,\\n\\n Appellant\\n\\n v.\\n\\n RAYMONT WRIGHT\\n\\n ______________\\n\\n ON APPEAL FROM THE\\n UNITED STATES DISTRICT COURT\\nFOR THE WESTERN DISTRICT OF PENNSYLVANIA\\n (D.C. No. 2-14-cr-00292-001)\\n District Judge: Hon. Cathy Bissoon\\n ______________\\n\\n Argued May 24, 2018\\n ______________\\n\\nBefore: MCKEE, SHWARTZ, and NYGAARD, Circuit\\n Judges.\\n\\n (Opinion Filed: January 17, 2019)\\n\\n ______________\\n\\n OPINION OF THE COURT\\n ________________\\n\\nDonovan J. Cocas, Esq. [ARGUED]\\nJane M. Datttilo, Esq.\\nLaura S. Irwin, Esq.\\nOffice of the United States Attorney\\n700 Grant Street\\nSuite 4000\\nPittsburgh, PA 15219\\n\\n Attorney for Appellant\\n\\nRenee Pietropaolo, Esq. [ARGUED]\\nLisa B. Freeland, Esq.\\nAkin Adepoju, Esq.\\nOffice of the Federal Public Defender\\n1001 Liberty Avenue\\n1500 Liberty Center\\nPittsburgh, PA 15222\\n\\n Attorneys for Appellee Raymont Wright\\n\\nLawrence S. Lustberg, Esq. [ARGUED]\\nGibbons, P.C.\\nOne Gateway Center\\nNewark, NJ 07102\\n\\n Attorney for Amicus Appellee National Association of\\n Criminal Defense Lawyers\\n\\n\\n\\n\\n 2\\n\\nSHWARTZ, Circuit Judge.\\n\\n The District Court barred a retrial of and dismissed the\\nindictment against Defendant Raymont Wright with prejudice\\nafter two juries failed to reach a verdict. The Court did so\\nrelying on its inherent authority, but without finding that any\\nmisconduct had occurred or that Wright would suffer any\\nprejudice beyond the general anxiety and inconvenience of\\nfacing a retrial. Under such circumstances, the Court lacked\\nthe inherent authority to bar the retrial and dismiss the\\nindictment. Therefore, we will reverse the order dismissing the\\nindictment and remand for further proceedings.\\n\\n I\\n\\n In December 2014, Wright was charged with being a\\nfelon in possession of a firearm, in violation of 18 U.S.C.\\n§ 922(g)(1). He pleaded not guilty and proceeded to trial in\\nMay 2016. The jury was unable to reach a verdict. A second\\ntrial was held in March 2017, and that jury was also unable to\\nreach a verdict.\\n\\n During both trials, the jury heard evidence from police\\nofficers about Wright’s actions on July 24, 2014.1 That\\nevening, five Pittsburgh Police detectives were patrolling in\\ntwo unmarked cars. Detectives Kennedy, Henson, and Baker\\nwere in the lead car, and Detectives Fallert and Goob were in\\nthe second car. Around 8:30 p.m. (when it was still daylight),\\nFallert and Goob saw a man, later identified as Wright, driving\\n\\n 1\\n The following facts are drawn largely from the\\nevidence presented at the first trial.\\n\\n\\n\\n\\n 3\\n\\na car in the opposite direction well above the 25-mile-per-hour\\nspeed limit. The detectives turned around to follow Wright,\\nand Wright sped up and turned onto a loop-shaped road. The\\ndetectives pursued Wright, who fled at a high speed and ran at\\nleast four stop signs. The lead car lost sight of Wright shortly\\nthereafter and discontinued pursuit.\\n\\n Officers in the lead car then noticed skid marks\\nsuggesting that a car had intended but failed to make a left turn\\nat the end of a street. Officers thereafter came upon Wright’s\\ncar in a parking lot below. The car had gone through a fence,\\nover a hillside, and into the lot. The car hit two unoccupied\\nparked cars, its tires blew out, and its windows were down.\\n\\n Detectives Baker and Henson exited the vehicle at the\\ntop of the hill and remained where Wright’s car broke through\\nthe fence, and Detective Kennedy drove his car down to the\\nparking lot’s entrance. Baker and Henson testified that they\\nsaw Wright search around the rear passenger seat of the car,\\nback out of the vehicle with a black semi-automatic handgun\\nin his right hand, and try to “rack the slide,” which can insert\\nor remove a round from the chamber. App. 118-19. They had\\ntheir weapons drawn and told Wright to drop the gun. At first,\\nWright merely stepped back, but he eventually tossed the gun\\nto the side, backed away, and lied on the ground. Pittsburgh\\npolice officer Elliott and his partner, who heard of the crash on\\nthe radio, were the first to reach Wright, and saw him lying on\\nthe ground with a handgun next to him. Henson stated that\\nwhen he made it down to the parking lot, he heard Wright say\\nto him, “Hey, big guy. You won this time or you won this\\nround, something of that nature. He [Wright] said: You feel\\nme? You won this time,” which Henson understood to mean\\nthat he had just avoided a shootout or that he caught Wright\\n\\n\\n\\n\\n 4\\n\\nafter the pursuit. App. 125. Henson subsequently took custody\\nof the gun and noticed the slide lever was bent, and when he\\nstraightened it, saw the gun was loaded with eight rounds, and\\none in the chamber. 2\\n\\n At the close of the Government’s case, Wright moved\\nfor a directed verdict, arguing that no reasonable juror could\\nfind beyond a reasonable doubt that Wright possessed the\\nfirearm. The District Court denied the motion because “the\\nevidence does thus far demonstrate that a reasonable juror\\ncould most certainly find the Defendant guilty of the charge in\\nthis case.” App. 171. Wright did not present a case.\\n\\n The jury deliberated for approximately five hours and\\nthen reported to the Court that it was deadlocked. After polling\\nthe jurors to confirm they were deadlocked and further\\ndeliberations would not bring them closer to a unanimous\\nverdict, the District Court declared a mistrial.\\n\\n At Wright’s March 2017 retrial, the Government\\npresented substantially the same evidence. The Government\\nalso called Detective Kennedy and Lieutenant Palermo, who\\nwere at the scene after Wright was arrested, as well as experts\\nwho testified regarding the collection of DNA and fingerprint\\nevidence from firearms to respond to Wright’s argument at the\\nfirst trial that investigators chose not to test the gun for forensic\\nevidence in an effort to cover up that they had planted the gun\\nat the scene.\\n\\n\\n 2\\n The parties stipulated Wright had been convicted of a\\nqualifying felony, and an ATF Special Agent testified about\\nthe gun’s interstate nexus.\\n\\n\\n\\n\\n 5\\n\\n At the close of the Government’s case, Wright again\\nmoved for a judgment of acquittal, which the Court denied\\nbecause “there is sufficient evidence in the record to establish\\nbeyond a reasonable doubt that Mr. Wright possessed the\\nfirearm in the case,” App. 650. Wright did not put on a case.\\n\\n The second jury deliberated for approximately three\\nhours and then reported that it was hopelessly deadlocked. The\\nCourt polled the jury to confirm the deadlock and then\\ndismissed the jury. 3\\n\\n After the Government notified the Court that it intended\\nto retry the case, the Court required the parties to brief\\n“whether the Court, through an exercise of its inherent\\nauthority, should prohibit or permit a second re-trial in this\\ncase.” App. 26. After considering the parties’ arguments, the\\nDistrict Court dismissed the indictment with prejudice, holding\\nthat it “ha[d] the inherent authority, under some circumstances,\\nto dismiss an indictment following multiple mistrials.” United\\nStates v. Wright, Crim. A. No. 14-292, 2017 WL 1179006, at\\n*4 (W.D. Pa. Mar. 30, 2017). It reasoned that: (1) principles\\nunderlying the Double Jeopardy Clause also applied to a\\ndefendant facing a retrial after multiple mistrials, id. at *1-2;\\n(2) other courts had dismissed indictments in similar\\n\\n 3\\n Wright asserted that in the first trial, jurors voted 8-4\\nfor acquittal, and in the second trial, the jury was evenly split.\\nThe Government asserted that in the first trial, jurors voted 7-\\n5 for acquittal, and in the second trial, voted 8-4 for conviction.\\nSee United States v. Wright, Crim. A. No. 14-292, 2017 WL\\n1179006, at *5 (W.D. Pa. Mar. 30, 2017). While Wright does\\nnot explain how he obtained these numbers, the Government\\nsaid it obtained them by speaking with the jurors.\\n\\n\\n\\n\\n 6\\n\\ncircumstances, id. at *2-3 (citing United States v. Rossoff, 806\\nF. Supp. 200, 202-03 (C.D. Ill. 1992); United States v. Ingram,\\n412 F. Supp. 384, 385 (D.D.C. 1976); Sivels v. State, 741\\nN.E.2d 1197, 1201 (Ind. 2001); State v. Abbati, 493 A.2d 513,\\n517 (N.J. 1985); State v. Moriwake, 647 P.2d 705, 712-13\\n(Haw. 1982); State v. Witt, 572 S.W.2d 913, 917 (Tenn.\\n1978)); (3) while Federal Rule of Criminal Procedure 31(b)(3)\\nexpressly allows the Government to retry a case after a mistrial,\\nnothing in the rule “limits a court’s inherent supervisory\\nauthority to dismiss an indictment in the interests of\\nfundamental fairness,” id. at *4; and (4) if the Court were to\\nadopt the Government’s position that there are no limit to the\\nnumber of times the Government can retry a defendant, it\\nwould be tantamount to a “type of jury shopping” that a court\\nshould not permit, id. at *4. The District Court also considered\\nthe factors set forth in Abbati, 493 A.2d at 521-22, and\\nconcluded that most factors supported dismissal. 4\\n\\n 4\\n The Abbati factors are\\n\\n (1) the number of prior mistrials and the\\n outcome of the juries’ deliberations, so far as is\\n known; (2) the character of prior trials in terms\\n of length, complexity, and similarity of evidence\\n presented; (3) the likelihood of any substantial\\n difference in a subsequent trial, if allowed;\\n (4) the trial court’s own evaluation of the relative\\n strength of each party’s case; and (5) the\\n professional conduct and diligence of respective\\n counsel, particularly of the prosecuting attorney.\\n The court must also give due weight to the\\n prosecutor’s decision to reprosecute, assessing\\n the reasons for that decision, such as the gravity\\n\\n\\n\\n\\n 7\\n\\n The Government appeals.\\n\\n II 5\\n\\n We review the District Court’s order dismissing the\\nindictment based on the Court’s inherent power for abuse of\\ndiscretion. 6 See United States v. Chapman, 524 F.3d 1073,\\n\\n of the criminal charges and the public’s concern\\n in the effective and definitive conclusion of\\n criminal prosecutions. Conversely, the court\\n should accord careful consideration to the status\\n of the individual defendant and the impact of a\\n retrial upon the defendant in terms of untoward\\n hardship and unfairness.\\n\\nWright, 2017 WL 1179006, at *4 (quoting Abbati, 493 A.2d\\nat 521-22). For the reasons set forth herein, we would not\\nadopt Abbati, but even if we were to consider the Abbati\\nfactors, we would conclude that they do not support dismissal\\nin this case.\\n 5\\n The District Court had jurisdiction pursuant to 18\\nU.S.C. § 3231. We have jurisdiction pursuant to 18 U.S.C.\\n§ 3731.\\n 6\\n The phrases “inherent power,” “inherent authority,”\\n“supervisory power,” and “supervisory authority” are all used\\nto describe the basis for a court action seeking to maintain the\\nintegrity of the proceedings that is not directly tethered to a\\nspecific rule, statute, or constitutional provision. See, e.g.,\\nCarlisle v. United States, 517 U.S. 416, 426 (1996) (inherent\\npower); United States v. Williams, 504 U.S. 36, 46 (1992)\\n(supervisory power); Chambers v. NASCO, Inc., 501 U.S. 32,\\n43 (1991) (inherent power); Bank of Nova Scotia v. United\\n\\n\\n\\n\\n 8\\n\\n1084-88, 1090 (9th Cir. 2008) (reviewing dismissal of\\nindictment for abuse of discretion); cf. Chambers v. NASCO,\\nInc., 501 U.S. 32, 55 (1991) (reviewing a court’s imposition of\\nsanctions under its inherent power for abuse of discretion);\\nGov’t of the Virgin Islands v. Fahie, 419 F.3d 249, 258 (3d Cir.\\n2005) (“A trial court’s remedy for a discovery violation under\\nits supervisory powers is reviewed for abuse of discretion.”).\\nA district court abuses its discretion when it makes an errant\\nconclusion of law, an improper application of law to fact, or a\\nclearly erroneous finding of fact. McDowell v. Phila. Hous.\\nAuth., 423 F.3d 233, 238 (3d Cir. 2005).\\n\\n A\\n\\n Federal Rule of Criminal Procedure 31 allows the\\nGovernment to retry a case if the court declares a mistrial after\\na jury announces it is unable to reach a verdict. Specifically,\\nRule 31(b)(3) provides: “[i]f the jury cannot agree on a verdict\\non one or more counts, the court may declare a mistrial on\\nthose counts. The government may retry any defendant on any\\ncount on which the jury could not agree.” Fed. R. Crim. P.\\n31(b)(3). The word “may” means that the Government has the\\n\\n\\nStates, 487 U.S. 250, 254-56, 263 (1988) (supervisory\\nauthority); United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(supervisory power); United States v. Payner, 447 U.S. 727,\\n733-36 (1980) (supervisory power); United States v. Nobles,\\n422 U.S. 225, 231 (1975) (inherent power).\\n Even if we accepted the distinctions our dissenting\\ncolleague has drawn between inherent judicial powers,\\nlegislatively granted judicial powers, and supervisory powers,\\neach category must operate within the constitutional\\nframework, including the separation of powers.\\n\\n\\n\\n\\n 9\\n\\ndiscretion to retry a case, and nothing in the rule or its\\ncommentary provides or even suggests a limit on the number\\nof retrials it may conduct. See United States v. Wqas Khan,\\nNo. 2:10-CR-0175 KJM, 2014 WL 1330681, at *2 (E.D. Cal.\\nApr. 1, 2014) (“Nothing suggests that multiple mistrials take a\\ncase out of the Rule’s operation.”), appeal dismissed, No. 14-\\n10218 (9th Cir. July 9, 2014). 7 Moreover, there is nothing in\\n\\n 7\\n While Rule 31 does not limit the Government’s\\nauthority to retry a case, a handful of district courts have\\ndismissed indictments following a second hung jury, but those\\ndecisions are not persuasive. In Ingram, the district court\\ndismissed the indictment sua sponte (without any initial\\nobjection by the Government) after two mistrials—in which\\njurors had voted 10-2 and 11-1 for acquittal, the defendant was\\njailed during the pendency of the trials, and “[t]he Government\\nha[d] no new proof; it simply want[ed] another chance.” 412\\nF. Supp. at 385. The court concluded that to permit a retrial\\nwould be “to ignore the reasonable doubt standard,” and so\\n“[t]he Court’s intervention [was] required in the interest of\\njustice.” Id. at 386 (citing United States v. De Diego, 511 F.2d\\n818, 824 n.8 (D.C. Cir. 1975); De Diego, 511 F.2d at 833 n.6\\n(McGowan, J., dissenting)). The Ingram court, however, relied\\nin part on the dissent in De Diego. Cases since Ingram have\\napplied the De Diego majority’s view concerning a court’s\\nlimited authority to dismiss an indictment. See, e.g., United\\nStates v. Hall, 559 F.2d 1160, 1164-65 (9th Cir. 1977) (citing\\nDe Diego and reversing the district court’s dismissal of the\\nindictment where the district court found it would be\\n“unconscionable” to retry to the defendant); United States v.\\nHudson, 545 F.2d 724, 724-26 (10th Cir. 1976) (discussing De\\nDiego and its dissent and holding a district court does not have\\nauthority to sua sponte dismiss an indictment based on the\\n\\n\\n\\n\\n 10\\n\\ndefendant’s poor health); United States v. Mussehl, 453 F.\\nSupp. 1235, 1236 (D.N.D. 1978) (denying defendants’ motion\\nto dismiss the indictment based on alleged errors at trial, and\\nciting De Diego for the proposition that “[t]he duty [to\\nadminister justice] encompasses the concept of review of the\\nquestion whether the United States Attorney, in making his\\ndecision to prosecute, complied with the law, but does not\\nallow the Court to question a United States Attorney’s\\njudgment decision to prosecute, when lawfully made”).\\n The District Court also relied on Rossoff, where the\\ncourt denied the Government’s motion to dismiss the\\nindictment under Federal Rule of Criminal Procedure 48(a),\\nbut still dismissed the indictment with prejudice. 806 F. Supp.\\nat 202-03 (citing Ingram, 412 F. Supp. at 385-86). There had\\nbeen two trials, and the Government sought to dismiss the\\nindictment and refile the charges in a different judicial district.\\nId. The court determined it had authority to dismiss an\\nindictment with prejudice if a retrial was “against the concept\\nof fundamental fairness,” id. at 202 (citing Ingram, 412 F.\\nSupp. 384), and did so because, among other reasons, the\\ndefendant was in poor health, was under significant strain, and\\na majority of jurors at both trials found him not guilty, id. at\\n203. Rossoff, however, is distinguishable from Wright’s case\\nbecause in Rossoff, the Government sought to dismiss the\\nindictment so that it could refile charges in a different judicial\\ndistrict, which caused the court to question the Government’s\\ngood faith. In Wright’s case, the District Court made no\\nfinding that the Government’s desire to retry Wright was for\\nan improper purpose.\\n In addition, and significantly, neither Ingram nor\\nRossoff addressed the doctrine of separation of powers.\\nRather, each essentially relied on a general concept of fairness\\n\\n\\n\\n\\n 11\\n\\nthe text that empowers a court to prohibit the Government from\\nretrying a case. 8\\n B\\n\\n Apparently aware that Rule 31 did not provide it with a\\nbasis to preclude a retrial in these circumstances, the District\\nCourt concluded that it had the inherent authority to forbid the\\nretrial and dismiss the indictment. The District Court erred.\\n\\n The exercise of inherent authority must satisfy two\\nrequirements: (1) it “must be a reasonable response to the\\n\\n\\nto the defendant in deciding to dismiss an indictment. See\\nRossoff, 806 F. Supp. at 202; Ingram, 412 F. Supp. at 385-86.\\nIn this Circuit, however, “[t]he judiciary may not impose its\\npersonal and private notions of ‘fairness’ on law enforcement\\nofficials, but does have a limited authority to affect\\nprosecutorial actions when those actions are taken in violation\\nof the Constitution.” United States v. Santtini, 963 F.2d 585,\\n596 (3d Cir. 1992) (citations omitted).\\n 8\\n Rule 31 differs from other Federal Rules of Criminal\\nProcedure because it makes no mention of the court’s\\nauthority. For instance, Rule 48(b) states that a court has\\nauthority to dismiss an indictment “if unnecessary delay occurs\\nin: (1) presenting a charge to the grand jury; (2) filing an\\ninformation against a defendant; or (3) bringing a defendant to\\ntrial.” Fed. R. Crim. P. 48(b). There are other Rule-based\\ngrounds on which a district court could also dismiss an\\nindictment, but each would be triggered by a motion, such as a\\nmotion to dismiss for failure to comply with Rule 16’s\\ndiscovery obligations if justice so requires, Fed. R. Crim. P.\\n16(d)(2)(D), or a motion asserting a defect in the indictment,\\nFed. R. Crim. P. 12(b)(3)(B).\\n\\n\\n\\n\\n 12\\n\\nproblems and needs confronting the court’s fair administration\\nof justice,” and (2) it “cannot be contrary to any express grant\\nof or limitation on the district court’s power contained in a rule\\nor statute.” Dietz v. Bouldin, 136 S. Ct. 1885, 1892 (2016)\\n(citations and internal quotation marks omitted). We will\\nexamine each of these requirements in turn.\\n\\n 1\\n\\n As to the first Dietz requirement, “[g]uided by\\nconsiderations of justice, and in the exercise of supervisory\\npowers, federal courts may, within limits, formulate procedural\\nrules not specifically required by the Constitution or the\\nCongress.” United States v. Hasting, 461 U.S. 499, 505 (1983)\\n(internal quotation marks and citation omitted). Such rules\\nmust be imposed (1) “to implement a remedy for violation of\\nrecognized rights,” (2) “to preserve judicial integrity by\\nensuring that a conviction rests on appropriate considerations\\nvalidly before the jury,” and (3) “as a remedy designed to deter\\nillegal conduct.” Id. (citations omitted). Thus, a court may\\nexercise its inherent authority only when it is necessary to\\naddress improper conduct and ensure respect for the\\nproceedings.\\n\\n Under these principles, a court may dismiss an\\nindictment based upon its inherent authority only if the\\nGovernment engaged in misconduct, the defendant was\\nprejudiced, and no less severe remedy was available to address\\nthe prejudice. See Bank of Nova Scotia v. United States, 487\\nU.S. 250, 254-56, 263 (1988); Chapman, 524 F.3d at 1087\\n(stating that “[a] court may dismiss an indictment under its\\nsupervisory powers only when the defendant suffers\\nsubstantial prejudice and where no lesser remedial action is\\n\\n\\n\\n\\n 13\\n\\navailable” (citations and internal quotation marks omitted));\\nUnited States v. Goodson, 204 F.3d 508, 514 (4th Cir. 2000)\\n(observing that “a district court may not, in the management of\\nits docket, exercise its discretion to dismiss an indictment with\\nprejudice, either under Rule 48(b) or under its supervisory\\npower, unless the violation caused prejudice to the defendant\\nor posed a substantial threat thereof” (emphasis omitted));\\nUnited States v. Derrick, 163 F.3d 799, 808 (4th Cir. 1998)\\n(holding that an indictment may not be dismissed for\\nprosecutorial misconduct absent a showing that the misconduct\\nprejudiced the defendants, and stating that “virtually every\\nother circuit to consider the issue post-Hasting and Nova Scotia\\nhas also held that an indictment may not be dismissed based on\\nprosecutorial misconduct, absent a showing of prejudice to the\\ndefendant”); United States v. Van Engel, 15 F.3d 623, 631-32\\n(7th Cir. 1993) (“A federal judge is not authorized to punish\\nthe misconduct of a prosecutor by letting the defendant walk,\\nunless the misconduct not only violated the defendant’s rights\\nbut also prejudiced his defense . . . .”); United States v. Tucker,\\n8 F.3d 673, 674 (9th Cir. 1993) (“[A] federal court may not\\nexercise its supervisory authority to reverse a conviction or\\ndismiss an indictment absent prejudice to the defendant.”);\\nUnited States v. Santana, 6 F.3d 1, 11 (1st Cir. 1993) (“[T]aken\\ntogether, [United States v. ]Payner, [447 U.S. 727, 735 (1980),]\\nHasting, and Bank of Nova Scotia form a trilogy admonishing\\nfederal courts to refrain from using the supervisory power to\\nconform executive conduct to judicially preferred norms by\\ndismissing charges, absent cognizable prejudice to a particular\\ndefendant.”); United States v. Isgro, 974 F.2d 1091, 1094 (9th\\nCir. 1992) (“Before it may invoke this [supervisory] power [to\\ndismiss an indictment], a court must first find that the\\ndefendant is actually prejudiced . . . .”), amended by 43 F.3d\\n1480 (9th Cir. 1994).\\n\\n\\n\\n\\n 14\\n\\n In this case, there has been no misconduct. Indeed, the\\nDistrict Court noted that the Government performed diligently\\nand professionally in both trials, Wright, 2017 WL 1179006,\\nat *4, and found that the evidence was sufficient to prove\\nbeyond a reasonable doubt that Wright possessed the gun. The\\nDistrict Court nonetheless applied its own predictions about\\nwhat another jury may do when presented with the same\\nevidence, emphasized the need for finality, and opined that the\\neffect of prosecution on the defendant precluded a proper\\nprosecution from proceeding. See id. at *5-6. Invoking its own\\nnotions about the unfairness of requiring a defendant to face a\\nretrial where the Government did not obtain a majority of the\\njurors’ votes is an improper exercise of a court’s supervisory\\npower. United States v. Miller, 4 F.3d 792, 795 (9th Cir. 1993).\\nMoreover, there is no prejudice to a defendant simply because\\nhe faces the anxiety and the normal stress of undergoing a trial.\\nSee United States v. Shepherd, 511 F.2d 119, 123 (5th Cir.\\n1975) (“[A]nxiety is present to some degree in virtually every\\ncase. Something more than the normal anxiety that\\naccompanies a trial is necessary to show a degree of\\nprejudice.”); United States v. Clyburn, Crim. No. 89-0154\\n(JHG), 1991 WL 45749, at *2 (D.D.C. Mar. 22, 1991) (“The\\nonly real harm alleged is the general unfairness to these\\ndefendants in having to go forward yet again with a lengthy\\ntrial, in their being ‘ground down’ by the several months’ drain\\non their mental, emotional, and financial resources. A lack of\\nsuch fairness, however, does not alone violate due process.”).\\nRather, prejudice sufficient for the District Court to intervene\\nin a proper prosecution based upon its inherent authority occurs\\nonly where the Government engages in actions that place a\\ndefendant at a disadvantage in addressing the charges. That\\nsort of prejudice is absent in this case.\\n\\n\\n\\n\\n 15\\n\\n Unless there is some constitutional basis, such as a due\\nprocess violation, it makes sense to limit a court’s authority to\\nbar retrial to instances of prosecutorial misconduct and\\nprejudice. First, it ensures that a judge’s personal preferences\\nabout a case do not influence whether the case proceeds. See\\nUnited States v. Santtini, 963 F.2d 585, 596 (3d Cir. 1992)\\n(“The judiciary may not impose its personal and private\\nnotions of ‘fairness’ on law enforcement officials, but does\\nhave a limited authority to affect prosecutorial actions when\\nthose actions are taken in violation of the Constitution.”).\\nSecond, as more fully discussed below, it guarantees that a\\ncourt limits the Executive’s decision to prosecute only where\\nthere is a constitutionally sound reason to do so. 9 This brings\\nus to the second Dietz requirement.\\n\\n\\n 9\\n For these reasons, we find unpersuasive our dissenting\\ncolleague’s reliance on Eash v. Riggins Trucking Inc., 757\\nF.2d 557, 562 (3d Cir. 1985) (en banc), and particularly its\\nobservation that a court has the inherent power to resolve a\\ncase, as authority for allowing a court dismiss an indictment\\nafter successive hung juries. As a general matter, there is no\\ndoubt that a court has the authority to dismiss a case, but it may\\nnot simply end a case because it decides that it should not be\\ntried again. Rather, as Bank of Nova Scotia, Chapman, and\\ntheir progeny make clear, the court must point to evidentiary\\ndeficiency, prejudicial misconduct, or a constitutional basis,\\nsuch as double jeopardy or due process, to justify precluding a\\nprosecution. If a court believed that the evidence was deficient,\\nthe prosecutor engaged in prejudicial misconduct, or a retrial\\nwould violate the constitution, then it has a basis to preclude a\\nretrial. Requiring such reasons for barring a retrial ensures that\\n\\n\\n\\n\\n 16\\n\\n 2\\n\\n The second Dietz requirement reminds a court that the\\nexercise of its powers must be in accordance with the\\nConstitution, statutes, and rules. 136 S. Ct. at 1892. Beginning\\nwith the Constitution, a court must be mindful of its role in our\\ntripartite form of government and the doctrine of separation of\\npowers. Separation-of-powers principles limit a court’s\\ninherent authority. “Regardless of whether the supervisory\\npower stems from the federal courts’ inherent power to check\\nintrusions by other branches of government or whether it is a\\nform of specialized federal common law, the separation-of-\\npowers principle imposes significant limits on it,” and\\n“[p]roper regard for judicial integrity does not justify a\\n‘chancellor’s foot veto’ over activities of coequal branches of\\ngovernment.” United States v. Gatto, 763 F.2d 1040, 1046 (9th\\nCir. 1985) (internal quotation marks omitted) (quoting United\\nStates v. Russell, 411 U.S. 423, 435 (1973)).\\n\\n In the criminal context, the Executive Branch has\\n“broad discretion as to whom to prosecute,” and this discretion\\n“rests largely on the recognition that the decision to prosecute\\nis particularly ill-suited to judicial review.” Wayte v. United\\nStates, 470 U.S. 598, 607-08 (1985) (citation and internal\\nquotation marks omitted). A court is not equipped to evaluate\\n\\n [s]uch factors as . . . the prosecution’s general\\n deterrence value, the Government’s enforcement\\n priorities, and the case’s relationship to the\\n\\n\\nthe ruling is not based on a court’s own personal sense of\\nwhether a case is worthy of prosecution.\\n\\n\\n\\n\\n 17\\n\\n Government’s overall enforcement plan . . . .\\n Judicial supervision in this area, moreover,\\n entails systemic costs of particular concern.\\n Examining the basis of a prosecution delays the\\n criminal proceeding, threatens to chill law\\n enforcement by subjecting the prosecutor’s\\n motives and decisionmaking to outside inquiry,\\n and may undermine prosecutorial effectiveness\\n by revealing the Government’s enforcement\\n policy. All of these are substantial concerns that\\n make the courts properly hesitant to examine the\\n decision whether to prosecute.\\n\\nId.; see also In re Richards, 213 F.3d 773, 786 (3d Cir. 2000)\\n(echoing similar sentiments with respect to Rule 48(a)\\ndismissals). Thus, absent constitutional concerns, the decision\\nto try or retry a case is at the discretion of the prosecutor.\\nUnited States v. HSBC Bank USA, N.A., 863 F.3d 125, 129,\\n137-38 (2d Cir. 2017) (stating that the court’s “role is not to act\\nas superprosecutors, second-guessing the legitimate exercise of\\ncore elements of prosecutorial discretion, but rather as neutral\\narbiters of the law” (citation and internal quotation marks\\nomitted)); United States v. Raineri, 42 F.3d 36, 43 (1st Cir.\\n1994) (“[T]he choice to forego permanently a prosecution is\\nordinarily made by the executive branch.”); Tucker, 8 F.3d at\\n676 (“In maintaining order in our own house, we should not\\nneedlessly trample on the interest of the prosecutor and of the\\npublic in securing proper, lasting convictions.”); Isgro, 974\\nF.2d at 1097 (stating that the doctrine of separation of powers\\n“mandates judicial respect for the independence of the\\nprosecutor,” and “[d]ismissal of an indictment with prejudice\\n\\n\\n\\n\\n 18\\n\\nis the most severe sanction possible”). 10 Accordingly,\\nseparation-of-powers principles preclude a court from\\nterminating a prosecution absent misconduct and prejudice to\\nthe defendant. See Bank of Nova Scotia, 487 U.S. at 254-56,\\n263; Goodson, 204 F.3d at 514; Tucker, 8 F.3d at 674; Isgro,\\n974 F.2d at 1094.\\n\\n In short, a court’s power to preclude a prosecution is\\nlimited by the separation of powers and, specifically, the\\nExecutive’s law-enforcement and prosecutorial prerogative.\\nSee Wayte, 470 U.S. at 607-08; HSBC, 863 F.3d at 137; In re\\nRichards, 213 F.3d at 786; Raineri, 42 F.3d at 43; Tucker, 8\\nF.3d at 676; Isgro, 974 F.2d at 1095-97; Santtini, 963 F.2d at\\n596; Gatto, 763 F.2d at 1046. Exercising inherent authority\\nhere to dismiss an indictment in the absence of misconduct and\\nprejudice and based only on the fact that two juries could not\\nreach a verdict intrudes on the Executive’s domain and thereby\\nviolates the separation of powers. See, e.g., HSBC, 863 F.3d\\nat 138; Isgro, 974 F.2d 1091.\\n\\n 10\\n Several state courts have also refused to recognize\\nany inherent authority to dismiss an indictment to prevent a\\nretrial. See People v. Sierb, 581 N.W.2d 219, 225 (Mich.\\n1998); State v. Johnson, 821 S.W.2d 609, 613 (Tex. Crim.\\nApp. 1991) (en banc); State v. Sherrod, 383 So.2d 752, 753\\n(Fla. Dist. Ct. App. 1980). Other states, however, have\\nrecognized a court’s authority to dismiss an indictment sua\\nsponte. See State v. Sauve, 666 A.2d 1164, 1167-68, 1167 n.1\\n(Vt. 1995); Abbati, 493 A.2d at 521; Moriwake, 647 P.2d at\\n712; Witt, 572 S.W.2d at 917. These latter cases are\\nunpersuasive because they give too little weight to the\\nseparation of powers, a crucial constitutional principle in the\\nfederal system.\\n\\n\\n\\n\\n 19\\n\\n Finally, there is no statute or procedural rule that\\npermits a court to bar a retrial in the absence of misconduct and\\nprejudice. First, a court may not dismiss an indictment as a\\nmethod to manage its own affairs. 11 See Hasting, 461 U.S. at\\n505. Second, a court’s inherent power does not “include the\\npower to develop rules that circumvent or conflict with the\\nFederal Rules of Criminal Procedure.” Carlisle v. United\\nStates, 517 U.S. 416, 426 (1996). Barring a retrial through the\\nexercise of inherent authority circumvents the absence of\\npower of the district court to dismiss an indictment in Rule\\n31(b). As stated above, courts have inherent authority to\\ndismiss indictments, including, for instance, for prosecutorial\\nmisconduct if the defendant was prejudiced, Bank of Nova\\nScotia, 487 U.S. at 254-56, 263, but neither the Supreme Court\\nnor our Court has extended a court’s inherent authority to allow\\n\\n 11\\n In Chambers, for example, the Supreme Court\\nrecognized a court’s authority to impose silence, respect, and\\ndecorum based on its authority to manage its own affairs. 501\\nU.S. at 43. This authority has been exercised by controlling\\nadmission to the bar and disciplining its members; punishing\\nfor contempt, which penalizes disruption to proceedings and\\ndisobedience to court orders; disallowing fraud on the courts;\\nensuring the proceedings move forward; and curtailing\\nlitigation abuses. Id. at 43-45; see also Link v. Wabash R.R.\\nCo., 370 U.S. 626, 629-31 (1962) (noting a court can dismiss a\\ncivil case for failure to prosecute to prevent delays and court\\ncongestion as part of a court’s inherent power to manage its\\nown affairs). Chambers and Link address how a court may\\nmanage its own proceedings, but they do not address how the\\ncourt must also account for issues of separation of powers in\\nthe context of a criminal case.\\n\\n\\n\\n\\n 20\\n\\nthe sua sponte dismissal of an indictment solely to preclude\\nmultiple mistrials following hung juries, see Chambers, 501\\nU.S. at 47; HSBC, 863 F.3d at 136. 12\\n\\n 12\\n Most cases concerning a court’s inherent authority\\nhave arisen in the civil context. See Dietz, 136 S. Ct. at 1893\\n(noting a court’s inherent powers to rescind a jury discharge\\norder and recall a jury); Chambers, 501 U.S. at 44, 55-58\\n(recognizing a court’s authority to vacate a judgment upon\\nproof that a fraud was perpetrated on the court, and, in\\nparticular, to assess as a sanction the entire amount of the\\nopposing party’s attorney’s fees); Link, 370 U.S. at 629-31\\n(authority to dismiss a civil case sua sponte for failure to\\nprosecute); Gulf Oil Corp. v. Gilbert, 330 U.S. 501, 507-08\\n(1947) (dismissing an action based on the doctrine of forum\\nnon conveniens). See generally Dietz, 136 S. Ct. at 1892-93\\n(citing cases involving the scope of a district court’s inherent\\npower); Eash, 757 F.2d at 561-64 (same).\\n There are other circumstances in which district courts\\nlack the inherent authority to act, and most of those situations\\narise in the criminal context. See, e.g., Carlisle, 517 U.S. at\\n433 (holding that a court does not have authority to grant a\\npost-verdict motion for judgment of acquittal, filed one day\\noutside the time limit under Rule 29(e)); Williams, 504 U.S. at\\n45-50, 55 (holding that a district court does not have inherent\\nauthority to dismiss an indictment because the Government\\nfailed to disclose to the grand jury substantial exculpatory\\nevidence; “[b]ecause the grand jury is an institution separate\\nfrom the courts, over whose functioning the courts do not\\npreside, we think it clear that, as a general matter at least, no\\nsuch ‘supervisory’ judicial authority exists”); HSBC, 863 F.3d\\nat 129, 135-37 (holding that the district court violated\\nseparation-of-powers principles by sua sponte invoking its\\n\\n\\n\\n\\n 21\\n\\n Thus, the District Court abused its discretion in barring\\na retrial and dismissing the indictment. 13\\n\\n III\\n\\n For the foregoing reasons, we will reverse and remand\\nfor further proceedings.\\n\\n\\n\\n\\nsupervisory power to oversee the government’s entry into and\\nimplementation of a deferred prosecution agreement).\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":71,"cells":{"id":{"kind":"number","value":4583425,"string":"4,583,425"},"name":{"kind":"string","value":"UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant"},"name_abbreviation":{"kind":"string","value":"United States v. Jay Goldstein"},"decision_date":{"kind":"string","value":"2019-01-22"},"docket_number":{"kind":"string","value":"15-4094"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Chagares, Restrepo, Roth\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"010combined\", \"text\": \"PRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 15-4094\\n ________________\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n JAY GOLDSTEIN a/k/a Yaakov\\n\\n JAY GOLDSTEIN,\\n\\nAppellant\\n ________________\\n\\n On Appeal from the United States District Court\\n for the District of New Jersey\\n (D. C. No. 3-14-cr-00287-003)\\n District Judge: Honorable Freda L. Wolfson\\n ________________\\n\\n Argued on January 25, 2017\\n Panel Rehearing Granted on August 30, 2018\\n\\n Before: CHAGARES, RESTREPO and ROTH, Circuit\\n Judges\\n\\f (Opinion filed: January 22, 2019)\\n\\n\\nAidan P. O’Connor [Argued]\\nPashman Stein Walder Hayden\\n21 Main Street\\nCourt Plaza South, Suite 200\\nHackensack, NJ 07601\\n Counsel for Appellant\\n\\nMark E. Coyne\\nOffice of United States Attorney\\n970 Broad Street, Room 700\\nNewark, NJ 07102\\n\\nNorman Gross [Argued]\\nGlenn J. Moramarco [Argued]\\nOffice of United States Attorney\\nCamden Federal Building & Courthouse\\n401 Market Street\\nCamden, NJ 08101\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nROTH, Circuit Judge\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n We granted Appellant Jay Goldstein’s petition for\\nrehearing to address the effect of the Supreme Court’s recent\\ndecision in Carpenter v. United States1 on our prior panel\\ndecision, United States v. Stimler.2 In Stimler, we held that\\nthe District Court properly denied Goldstein’s motion to\\nsuppress his cell site location information (CSLI) because\\nGoldstein had no reasonable expectation of privacy in his\\nCSLI, and, therefore, the government did not need probable\\ncause to collect this data.3 Carpenter sets forth a new rule\\nthat defendants do in fact have a privacy interest in their\\nCSLI, and the government must generally obtain a search\\nwarrant supported by probable cause to obtain this\\ninformation.4 However, we still affirm the District Court’s\\ndecision under the good faith exception to the exclusionary\\nrule because the government had an objectively reasonable\\ngood faith belief that its conduct was legal when it acquired\\nGoldstein’s CSLI.\\n\\n II.\\n\\n We recited a comprehensive factual background in our\\nprevious decision.5 The facts relevant to this decision follow.\\n\\n1\\n 138 S. Ct. 2206 (2018).\\n2\\n 864 F.3d 253 (3d Cir. 2017).\\n3\\n Id. at 263. Carpenter does not affect our other holdings in\\nStimler. Those remain as written and are not addressed in or\\nchanged by this decision.\\n4\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n5\\n Stimler, 864 F.3d at 259-61.\\n\\n\\n\\n\\n 3\\n\\fGoldstein was arrested for his involvement in a kidnapping\\nscheme. Hoping to find evidence placing Goldstein at the\\nscene of the kidnapping, the prosecutors obtained a court\\norder under the Stored Communications Act (SCA)—\\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\\ncell phone carrier to turn over 57 days’ worth of his CSLI.\\nCSLI is a type of metadata that is generated every time a\\nuser’s cell phone connects to the nearest antenna. The user’s\\ncell phone service provider retains a time-stamped record\\nidentifying the particular antenna to which the phone\\nconnected. Because most people constantly carry and\\nfrequently use their cell phones, CSLI can provide a detailed\\nlog of an individual’s movements over a period of time.\\n\\n The legal question in this case centers on whether\\nSection 2703(d), the statutory provision under which the\\ngovernment obtained Goldstein’s CSLI, complies with the\\nFourth Amendment. The Fourth Amendment protects against\\nunreasonable searches. In order for the acquisition of CSLI to\\nbe a “search” under the Fourth Amendment, an individual\\nmust have a reasonable expectation of privacy in his CSLI.6\\nIn order for a search to be “reasonable,” it generally must be\\nconducted pursuant to a search warrant supported by probable\\ncause, unless an exception to the warrant requirement\\napplies.7 Consequently, if there is no reasonable expectation\\nof privacy as to CSLI, then its acquisition does not require a\\nsearch warrant; if there is, then a warrant is generally\\nrequired. Section 2703(d) does not require a showing of\\n\\n6\\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\\n(explaining what constitutes a reasonable expectation of\\nprivacy).\\n7\\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\\n\\n\\n\\n\\n 4\\n\\fprobable cause to obtain CSLI. Rather, it calls for a more\\nlenient standard, requiring “specific and articulable facts\\nshowing that there are reasonable grounds to believe” that the\\nCSLI is relevant and material.8\\n\\n Before trial, Goldstein moved to suppress the CSLI,\\narguing that this provision violates the Fourth Amendment\\nbecause it authorizes disclosure of CSLI without a warrant\\nsupported by probable cause. The District Court rejected this\\nargument and denied the motion. Through the testimony of\\nan FBI agent, the government introduced the CSLI at trial,\\nwhich placed him in the vicinity of the kidnapping site.\\nGoldstein was convicted and sentenced to 96 months in\\nprison.\\n\\n In our previous decision, we affirmed the District\\nCourt’s denial of Goldstein’s motion to suppress, holding that\\nSection 2703(d) complied with the Fourth Amendment\\nbecause cell phone users have no reasonable expectation of\\nprivacy in their CSLI.9 We relied on our decision in In re\\nApplication of the United States for an Order Directing a\\nProvider of Electronic Communication Service to Disclose\\nRecords to the Government (In re Application),10 which also\\nfound no reasonable expectation of privacy in CSLI,11 and we\\n\\n\\n\\n\\n8\\n 18 U.S.C. § 2703(d).\\n9\\n Stimler, 864 F.3d at 263.\\n10\\n 620 F.3d 304 (3d Cir. 2010).\\n11\\n Id. at 312-13 (holding that CSLI is obtainable without “the\\ntraditional probable cause determination” because\\nindividuals’ privacy interests do not extend to CSLI).\\n\\n\\n\\n\\n 5\\n\\freasoned that there were no intervening changes in law\\nundermining In re Application.12\\n\\n Goldstein petitioned for rehearing, and we held the\\npetition curia advisari vult pending the Supreme Court’s\\ndecision in Carpenter, which was set to address essentially\\nthe same question we answered in Stimler: whether obtaining\\nCSLI without a warrant supported by probable cause under\\nSection 2703(d) violates the Fourth Amendment’s protection\\nagainst unreasonable searches. The Supreme Court decided\\nCarpenter, and we granted Goldstein’s petition for panel\\nrehearing.13 Carpenter came to the opposite conclusion that\\nwe came to in In re Application and Stimler and held that “an\\nindividual maintains a legitimate expectation of privacy in the\\nrecord of his physical movements as captured though CSLI”\\nand that the government’s collection of CSLI requires a\\nshowing of probable cause under the Fourth Amendment.14\\nConsequently, Section 2703(d) may not be used to access\\nCSLI because it requires less than probable cause.\\n\\n Applying Carpenter to Goldstein’s case, we find that\\nthe government did violate Goldstein’s Fourth Amendment\\nrights when it acquired his CSLI under Section 2703(d) of the\\nSCA. However, we will still affirm the District Court’s\\nadmission of Goldstein’s CSLI because the government was\\nacting under an objectively reasonable good faith belief that\\n\\n\\n12\\n Stimler, 864 F.3d at 264-67.\\n13\\n Appellants Stimler and Epstein also petitioned for\\nrehearing, but we denied those petitions because the\\ngovernment did not collect their CSLI.\\n14\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n\\n\\n\\n\\n 6\\n\\fobtaining CSLI under Section 2703(d) was constitutional at\\nthe time.\\n\\n\\n 15\\n III.\\n\\n It is clear that under Carpenter, acquiring Goldstein’s\\nCSLI was an unconstitutional search under the Fourth\\nAmendment because the government did not obtain a warrant\\nsupported by probable cause.16 However, evidence obtained\\nin violation of a defendant’s Fourth Amendment rights is not\\nautomatically suppressed. Evidence will be suppressed under\\nthe exclusionary rule when suppression would further the\\nexclusionary rule’s primary objective: to deter Fourth\\nAmendment violations.17 One instance where suppressing\\nevidence will not encourage deterrence is where the\\ngovernment acted “upon an objectively reasonable good faith\\nbelief in the legality of [its] conduct” when conducting a\\n\\n\\n15\\n The District Court had jurisdiction under 18 U.S.C. § 3231.\\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\\nreviewing a motion to suppress, ‘we review a district court’s\\nfactual findings for clear error, and we exercise de novo\\nreview over its application of the law to those factual\\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\\nF.3d 651, 660 (3d Cir. 2012)).\\n16\\n A warrantless search is still reasonable under the Fourth\\nAmendment if an exception to the warrant requirement\\napplies, but the parties do not argue, and we do not find, that\\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\\n17\\n Katzin, 769 F.3d at 170-71.\\n\\n\\n\\n\\n 7\\n\\fsearch.18 Indeed, “applying the exclusionary rule would not\\n‘yield appreciable deterrence’” when government actors have\\na reasonable belief that their conduct conforms with the law.19\\nThis is known as the good faith exception, and where it\\napplies, the illegally-obtained evidence will not be suppressed\\nunder the exclusionary rule.\\n\\n The Supreme Court has applied this exception across a\\nnumber of cases where suppressing evidence would not have\\nany deterrent value—three of which are relevant here. In\\nIllinois v. Krull,20 the Court held that the good faith exception\\napplies when a search is executed pursuant to a statute that\\nwas valid at the time of the search but later declared\\nunconstitutional.21 Except in instances where a statute is\\nobviously unconstitutional, suppressing evidence obtained by\\na law enforcement officer “acting in objectively reasonable\\nreliance on a statute would have . . . little deterrent effect on\\nthe [government’s] actions.”22 Under Davis v. United\\nStates,23 this exception also applies when a search is\\nconducted based upon reasonable reliance on then-binding\\nappellate precedent because exclusion in this context would\\nnot deter improper government conduct.24 And under United\\n\\n\\n18\\n Id. at 182.\\n19\\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\\n(2011)).\\n20\\n 480 U.S. 340 (1987).\\n21\\n Id. at 349-50.\\n22\\n Id.\\n23\\n 564 U.S. 229 (2011).\\n24\\n Id. at 241.\\n\\n\\n\\n\\n 8\\n\\fStates v. Leon,25 the exclusionary rule will not apply when\\nlaw enforcement conducts a search pursuant to a judicial\\norder later found invalid.26\\n\\n The good faith exception applies to the government’s\\nsearch in this case because the government acted upon an\\nobjectively reasonable, good faith belief that obtaining\\nGoldstein’s CSLI under Section 2703(d) was legal. At the\\ntime the search was executed, it was authorized under Section\\n2703(d). The government complied with all requirements of\\nSection 2703(d) and obtained a valid judicial order to collect\\nGoldstein’s CSLI. Moreover, the government had no reason\\nto question the constitutionality of obtaining CSLI through\\nSection 2703(d) because that question had been answered by\\nthis Court in In re Application—which was binding appellate\\nprecedent.27 Thus, because the government relied on a\\nproperly-obtained valid judicial order, a then-valid statute,\\nand then-binding appellate authority, it had an objectively\\nreasonable, good faith belief that its conduct was legal.\\nIndeed, the conduct was legal at the time. Excluding\\nevidence obtained through methods that complied with the\\nlaw at the time of the search cannot serve any deterrent\\npurpose. Under Krull, Davis, and Leon, the good faith\\nexception applies, and the District Court’s denial of the\\nmotion to suppress is affirmed. Our holding puts us in good\\ncompany, as many of our sister circuits have also found that\\n\\n25\\n 468 U.S. 897 (1984).\\n26\\n Id. at 922.\\n27\\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\\nfrom cell phone calls is obtainable under a § 2703(d) order\\nand that such an order does not require the traditional\\nprobable cause determination.”).\\n\\n\\n\\n\\n 9\\n\\fthe good faith exception applies when the government\\nobtained CLSI data without a warrant prior to Carpenter.28\\n Goldstein contends that the good faith exception does\\nnot apply because the government’s reliance on Section\\n2703(d) was unreasonable for two reasons, both of which fail.\\nFirst, he argues that, at the time of the search, the Eleventh\\nCircuit had held that collecting CSLI without a warrant\\nsupported by probable cause violated the Fourth\\n\\n28\\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\\n(11th Cir. 2018) (“Here, the Government complied with the\\nrequirements of the SCA in obtaining the orders to compel\\ncell site records, and when they did so in June 2015, that\\nwarrantless procedure was, under this Court’s precedent,\\nwithin the bounds of the Fourth Amendment.”);\\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\\n(Carpenter does not affect cases where investigators acted\\npursuant to court orders and the SCA); United States v.\\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\\ntherefore, that even though it is now established that the\\nFourth Amendment requires a warrant for the type of cell-\\nphone data present here, exclusion of that information was\\nnot required because it was collected in good faith.”); United\\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\\nafter Jones, but before Carpenter, it was objectively\\nreasonable for authorities to think that if they complied with\\nthe SCA, no warrant based on probable cause was\\nconstitutionally required to obtain cell-site information from a\\nthird party.”). Judge Restrepo’s concurrence in Stimler also\\nconcluded that the good faith exception applied here in light\\nof In re Application. See Stimler, 864 F.3d at 279-80\\n(Restrepo, J., concurring).\\n\\n\\n\\n\\n 10\\n\\fAmendment.29 But, under Davis, only binding appellate\\nprecedent is relevant to the good faith exception, and In re\\nApplication was binding in this Circuit at the time. Second,\\nhe contends the government could not have reasonably relied\\non In re Application because it had been undermined by two\\nsubsequent Supreme Court cases—United States v. Jones30\\nand Riley v. California.31 As discussed in Stimler, neither\\ncase undercuts In re Application because neither addresses\\nthe long-term collection of metadata from cell phones.32\\nJones addressed long-term collection of GPS location data\\nfrom a car—not a cell phone.33 Riley involved the contents of\\na cell phone, not the metadata transmitted from a cell phone\\nto a third party.34 Indeed, Carpenter itself recognizes that the\\ncollection of CSLI does “not fit neatly under existing\\n\\n\\n29\\n See Appellant’s Supplemental Letter at 3-4. The case that\\nGoldstein refers to was reversed on rehearing and upheld the\\nconstitutionality of CSLI obtained on less than probable\\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\\nCir. 2015).\\n30\\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\\na defendant’s car for 28 days without a warrant violated the\\nFourth Amendment).\\n31\\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\\nthe contents of a cell phone violated Fourth Amendment).\\n32\\n Stimler, 864 F.3d at 264-67.\\n33\\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\\ncannot be analogized to cell phones in this context because\\ncell phones can provide law enforcement with more\\ninformation than a car about an individual’s movements.\\nCarpenter, 138 S. Ct. at 2218.\\n34\\n Riley, 134 S. Ct. at 2494-95.\\n\\n\\n\\n\\n 11\\n\\fprecedents.”35 The government could not have predicted the\\noutcome of Carpenter and the overruling of In re Application\\nfrom two Supreme Court cases that the Supreme Court itself\\nsaid are not directly applicable.\\n\\n Goldstein also argues that the good faith exception\\napplies only to police officers and other investigators, not the\\ngovernment attorneys who obtained the Section 2703(d) order\\nhere. Goldstein cites nothing in support of his proposed\\nlimitation on the good faith exception, and we see no reason\\nto limit its applicability in this case. The relevant inquiry\\nhere is not who the state actor is, but rather, whether the state\\nactor had a reasonable, good faith belief that his actions were\\nlegal. The prosecutors relied on a then-valid statute whose\\nconstitutionality had been confirmed by this Circuit. The\\ngood faith exception applies.\\n\\n IV.\\n\\n For the foregoing reasons, we affirm the District Court’s\\ndenial of Goldstein’s motion to suppress.\\n\\n\\n\\n\\n35\\n Carpenter, 138 S. Ct. at 2214-16.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360678/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"CHAGARES"},"judge2":{"kind":"string","value":"RESTREPO"},"judge3":{"kind":"string","value":"ROTH"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583425/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: \nHas concurring opinion: \nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant\nCourt: U.S. Court of Appeals for the Third Circuit\nDate decided: 2019-01-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPRECEDENTIAL\n\n UNITED STATES COURT OF APPEALS\n FOR THE THIRD CIRCUIT\n ________________\n\n No. 15-4094\n ________________\n\n\n UNITED STATES OF AMERICA\n\n v.\n\n JAY GOLDSTEIN a/k/a Yaakov\n\n JAY GOLDSTEIN,\n\nAppellant\n ________________\n\n On Appeal from the United States District Court\n for the District of New Jersey\n (D. C. No. 3-14-cr-00287-003)\n District Judge: Honorable Freda L. Wolfson\n ________________\n\n Argued on January 25, 2017\n Panel Rehearing Granted on August 30, 2018\n\n Before: CHAGARES, RESTREPO and ROTH, Circuit\n Judges\n\f (Opinion filed: January 22, 2019)\n\n\nAidan P. O’Connor [Argued]\nPashman Stein Walder Hayden\n21 Main Street\nCourt Plaza South, Suite 200\nHackensack, NJ 07601\n Counsel for Appellant\n\nMark E. Coyne\nOffice of United States Attorney\n970 Broad Street, Room 700\nNewark, NJ 07102\n\nNorman Gross [Argued]\nGlenn J. Moramarco [Argued]\nOffice of United States Attorney\nCamden Federal Building & Courthouse\n401 Market Street\nCamden, NJ 08101\n Counsel for Appellee\n\n\n ________________\n\n OPINION\n ________________\n\n\nROTH, Circuit Judge\n\n\n\n\n 2\n\f I.\n\n We granted Appellant Jay Goldstein’s petition for\nrehearing to address the effect of the Supreme Court’s recent\ndecision in Carpenter v. United States1 on our prior panel\ndecision, United States v. Stimler.2 In Stimler, we held that\nthe District Court properly denied Goldstein’s motion to\nsuppress his cell site location information (CSLI) because\nGoldstein had no reasonable expectation of privacy in his\nCSLI, and, therefore, the government did not need probable\ncause to collect this data.3 Carpenter sets forth a new rule\nthat defendants do in fact have a privacy interest in their\nCSLI, and the government must generally obtain a search\nwarrant supported by probable cause to obtain this\ninformation.4 However, we still affirm the District Court’s\ndecision under the good faith exception to the exclusionary\nrule because the government had an objectively reasonable\ngood faith belief that its conduct was legal when it acquired\nGoldstein’s CSLI.\n\n II.\n\n We recited a comprehensive factual background in our\nprevious decision.5 The facts relevant to this decision follow.\n\n1\n 138 S. Ct. 2206 (2018).\n2\n 864 F.3d 253 (3d Cir. 2017).\n3\n Id. at 263. Carpenter does not affect our other holdings in\nStimler. Those remain as written and are not addressed in or\nchanged by this decision.\n4\n Carpenter, 138 S. Ct. at 2217, 2222.\n5\n Stimler, 864 F.3d at 259-61.\n\n\n\n\n 3\n\fGoldstein was arrested for his involvement in a kidnapping\nscheme. Hoping to find evidence placing Goldstein at the\nscene of the kidnapping, the prosecutors obtained a court\norder under the Stored Communications Act (SCA)—\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\ncell phone carrier to turn over 57 days’ worth of his CSLI.\nCSLI is a type of metadata that is generated every time a\nuser’s cell phone connects to the nearest antenna. The user’s\ncell phone service provider retains a time-stamped record\nidentifying the particular antenna to which the phone\nconnected. Because most people constantly carry and\nfrequently use their cell phones, CSLI can provide a detailed\nlog of an individual’s movements over a period of time.\n\n The legal question in this case centers on whether\nSection 2703(d), the statutory provision under which the\ngovernment obtained Goldstein’s CSLI, complies with the\nFourth Amendment. The Fourth Amendment protects against\nunreasonable searches. In order for the acquisition of CSLI to\nbe a “search” under the Fourth Amendment, an individual\nmust have a reasonable expectation of privacy in his CSLI.6\nIn order for a search to be “reasonable,” it generally must be\nconducted pursuant to a search warrant supported by probable\ncause, unless an exception to the warrant requirement\napplies.7 Consequently, if there is no reasonable expectation\nof privacy as to CSLI, then its acquisition does not require a\nsearch warrant; if there is, then a warrant is generally\nrequired. Section 2703(d) does not require a showing of\n\n6\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\n(explaining what constitutes a reasonable expectation of\nprivacy).\n7\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\n\n\n\n\n 4\n\fprobable cause to obtain CSLI. Rather, it calls for a more\nlenient standard, requiring “specific and articulable facts\nshowing that there are reasonable grounds to believe” that the\nCSLI is relevant and material.8\n\n Before trial, Goldstein moved to suppress the CSLI,\narguing that this provision violates the Fourth Amendment\nbecause it authorizes disclosure of CSLI without a warrant\nsupported by probable cause. The District Court rejected this\nargument and denied the motion. Through the testimony of\nan FBI agent, the government introduced the CSLI at trial,\nwhich placed him in the vicinity of the kidnapping site.\nGoldstein was convicted and sentenced to 96 months in\nprison.\n\n In our previous decision, we affirmed the District\nCourt’s denial of Goldstein’s motion to suppress, holding that\nSection 2703(d) complied with the Fourth Amendment\nbecause cell phone users have no reasonable expectation of\nprivacy in their CSLI.9 We relied on our decision in In re\nApplication of the United States for an Order Directing a\nProvider of Electronic Communication Service to Disclose\nRecords to the Government (In re Application),10 which also\nfound no reasonable expectation of privacy in CSLI,11 and we\n\n\n\n\n8\n 18 U.S.C. § 2703(d).\n9\n Stimler, 864 F.3d at 263.\n10\n 620 F.3d 304 (3d Cir. 2010).\n11\n Id. at 312-13 (holding that CSLI is obtainable without “the\ntraditional probable cause determination” because\nindividuals’ privacy interests do not extend to CSLI).\n\n\n\n\n 5\n\freasoned that there were no intervening changes in law\nundermining In re Application.12\n\n Goldstein petitioned for rehearing, and we held the\npetition curia advisari vult pending the Supreme Court’s\ndecision in Carpenter, which was set to address essentially\nthe same question we answered in Stimler: whether obtaining\nCSLI without a warrant supported by probable cause under\nSection 2703(d) violates the Fourth Amendment’s protection\nagainst unreasonable searches. The Supreme Court decided\nCarpenter, and we granted Goldstein’s petition for panel\nrehearing.13 Carpenter came to the opposite conclusion that\nwe came to in In re Application and Stimler and held that “an\nindividual maintains a legitimate expectation of privacy in the\nrecord of his physical movements as captured though CSLI”\nand that the government’s collection of CSLI requires a\nshowing of probable cause under the Fourth Amendment.14\nConsequently, Section 2703(d) may not be used to access\nCSLI because it requires less than probable cause.\n\n Applying Carpenter to Goldstein’s case, we find that\nthe government did violate Goldstein’s Fourth Amendment\nrights when it acquired his CSLI under Section 2703(d) of the\nSCA. However, we will still affirm the District Court’s\nadmission of Goldstein’s CSLI because the government was\nacting under an objectively reasonable good faith belief that\n\n\n12\n Stimler, 864 F.3d at 264-67.\n13\n Appellants Stimler and Epstein also petitioned for\nrehearing, but we denied those petitions because the\ngovernment did not collect their CSLI.\n14\n Carpenter, 138 S. Ct. at 2217, 2222.\n\n\n\n\n 6\n\fobtaining CSLI under Section 2703(d) was constitutional at\nthe time.\n\n\n 15\n III.\n\n It is clear that under Carpenter, acquiring Goldstein’s\nCSLI was an unconstitutional search under the Fourth\nAmendment because the government did not obtain a warrant\nsupported by probable cause.16 However, evidence obtained\nin violation of a defendant’s Fourth Amendment rights is not\nautomatically suppressed. Evidence will be suppressed under\nthe exclusionary rule when suppression would further the\nexclusionary rule’s primary objective: to deter Fourth\nAmendment violations.17 One instance where suppressing\nevidence will not encourage deterrence is where the\ngovernment acted “upon an objectively reasonable good faith\nbelief in the legality of [its] conduct” when conducting a\n\n\n15\n The District Court had jurisdiction under 18 U.S.C. § 3231.\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\nreviewing a motion to suppress, ‘we review a district court’s\nfactual findings for clear error, and we exercise de novo\nreview over its application of the law to those factual\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\nF.3d 651, 660 (3d Cir. 2012)).\n16\n A warrantless search is still reasonable under the Fourth\nAmendment if an exception to the warrant requirement\napplies, but the parties do not argue, and we do not find, that\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\n17\n Katzin, 769 F.3d at 170-71.\n\n\n\n\n 7\n\fsearch.18 Indeed, “applying the exclusionary rule would not\n‘yield appreciable deterrence’” when government actors have\na reasonable belief that their conduct conforms with the law.19\nThis is known as the good faith exception, and where it\napplies, the illegally-obtained evidence will not be suppressed\nunder the exclusionary rule.\n\n The Supreme Court has applied this exception across a\nnumber of cases where suppressing evidence would not have\nany deterrent value—three of which are relevant here. In\nIllinois v. Krull,20 the Court held that the good faith exception\napplies when a search is executed pursuant to a statute that\nwas valid at the time of the search but later declared\nunconstitutional.21 Except in instances where a statute is\nobviously unconstitutional, suppressing evidence obtained by\na law enforcement officer “acting in objectively reasonable\nreliance on a statute would have . . . little deterrent effect on\nthe [government’s] actions.”22 Under Davis v. United\nStates,23 this exception also applies when a search is\nconducted based upon reasonable reliance on then-binding\nappellate precedent because exclusion in this context would\nnot deter improper government conduct.24 And under United\n\n\n18\n Id. at 182.\n19\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\n(2011)).\n20\n 480 U.S. 340 (1987).\n21\n Id. at 349-50.\n22\n Id.\n23\n 564 U.S. 229 (2011).\n24\n Id. at 241.\n\n\n\n\n 8\n\fStates v. Leon,25 the exclusionary rule will not apply when\nlaw enforcement conducts a search pursuant to a judicial\norder later found invalid.26\n\n The good faith exception applies to the government’s\nsearch in this case because the government acted upon an\nobjectively reasonable, good faith belief that obtaining\nGoldstein’s CSLI under Section 2703(d) was legal. At the\ntime the search was executed, it was authorized under Section\n2703(d). The government complied with all requirements of\nSection 2703(d) and obtained a valid judicial order to collect\nGoldstein’s CSLI. Moreover, the government had no reason\nto question the constitutionality of obtaining CSLI through\nSection 2703(d) because that question had been answered by\nthis Court in In re Application—which was binding appellate\nprecedent.27 Thus, because the government relied on a\nproperly-obtained valid judicial order, a then-valid statute,\nand then-binding appellate authority, it had an objectively\nreasonable, good faith belief that its conduct was legal.\nIndeed, the conduct was legal at the time. Excluding\nevidence obtained through methods that complied with the\nlaw at the time of the search cannot serve any deterrent\npurpose. Under Krull, Davis, and Leon, the good faith\nexception applies, and the District Court’s denial of the\nmotion to suppress is affirmed. Our holding puts us in good\ncompany, as many of our sister circuits have also found that\n\n25\n 468 U.S. 897 (1984).\n26\n Id. at 922.\n27\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\nfrom cell phone calls is obtainable under a § 2703(d) order\nand that such an order does not require the traditional\nprobable cause determination.”).\n\n\n\n\n 9\n\fthe good faith exception applies when the government\nobtained CLSI data without a warrant prior to Carpenter.28\n Goldstein contends that the good faith exception does\nnot apply because the government’s reliance on Section\n2703(d) was unreasonable for two reasons, both of which fail.\nFirst, he argues that, at the time of the search, the Eleventh\nCircuit had held that collecting CSLI without a warrant\nsupported by probable cause violated the Fourth\n\n28\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\n(11th Cir. 2018) (“Here, the Government complied with the\nrequirements of the SCA in obtaining the orders to compel\ncell site records, and when they did so in June 2015, that\nwarrantless procedure was, under this Court’s precedent,\nwithin the bounds of the Fourth Amendment.”);\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\n(Carpenter does not affect cases where investigators acted\npursuant to court orders and the SCA); United States v.\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\ntherefore, that even though it is now established that the\nFourth Amendment requires a warrant for the type of cell-\nphone data present here, exclusion of that information was\nnot required because it was collected in good faith.”); United\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\nafter Jones, but before Carpenter, it was objectively\nreasonable for authorities to think that if they complied with\nthe SCA, no warrant based on probable cause was\nconstitutionally required to obtain cell-site information from a\nthird party.”). Judge Restrepo’s concurrence in Stimler also\nconcluded that the good faith exception applied here in light\nof In re Application. See Stimler, 864 F.3d at 279-80\n(Restrepo, J., concurring).\n\n\n\n\n 10\n\fAmendment.29 But, under Davis, only binding appellate\nprecedent is relevant to the good faith exception, and In re\nApplication was binding in this Circuit at the time. Second,\nhe contends the government could not have reasonably relied\non In re Application because it had been undermined by two\nsubsequent Supreme Court cases—United States v. Jones30\nand Riley v. California.31 As discussed in Stimler, neither\ncase undercuts In re Application because neither addresses\nthe long-term collection of metadata from cell phones.32\nJones addressed long-term collection of GPS location data\nfrom a car—not a cell phone.33 Riley involved the contents of\na cell phone, not the metadata transmitted from a cell phone\nto a third party.34 Indeed, Carpenter itself recognizes that the\ncollection of CSLI does “not fit neatly under existing\n\n\n29\n See Appellant’s Supplemental Letter at 3-4. The case that\nGoldstein refers to was reversed on rehearing and upheld the\nconstitutionality of CSLI obtained on less than probable\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\nCir. 2015).\n30\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\na defendant’s car for 28 days without a warrant violated the\nFourth Amendment).\n31\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\nthe contents of a cell phone violated Fourth Amendment).\n32\n Stimler, 864 F.3d at 264-67.\n33\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\ncannot be analogized to cell phones in this context because\ncell phones can provide law enforcement with more\ninformation than a car about an individual’s movements.\nCarpenter, 138 S. Ct. at 2218.\n34\n Riley, 134 S. Ct. at 2494-95.\n\n\n\n\n 11\n\fprecedents.”35 The government could not have predicted the\noutcome of Carpenter and the overruling of In re Application\nfrom two Supreme Court cases that the Supreme Court itself\nsaid are not directly applicable.\n\n Goldstein also argues that the good faith exception\napplies only to police officers and other investigators, not the\ngovernment attorneys who obtained the Section 2703(d) order\nhere. Goldstein cites nothing in support of his proposed\nlimitation on the good faith exception, and we see no reason\nto limit its applicability in this case. The relevant inquiry\nhere is not who the state actor is, but rather, whether the state\nactor had a reasonable, good faith belief that his actions were\nlegal. The prosecutors relied on a then-valid statute whose\nconstitutionality had been confirmed by this Circuit. The\ngood faith exception applies.\n\n IV.\n\n For the foregoing reasons, we affirm the District Court’s\ndenial of Goldstein’s motion to suppress.\n\n\n\n\n35\n Carpenter, 138 S. Ct. at 2214-16.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: \\nCourt: \\nDate decided: \\nOpinion type: \\nHas dissenting opinion: \\nHas concurring opinion: \\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Jay GOLDSTEIN A/K/A Yaakov Jay Goldstein, Appellant\\nCourt: U.S. Court of Appeals for the Third Circuit\\nDate decided: 2019-01-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPRECEDENTIAL\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE THIRD CIRCUIT\\n ________________\\n\\n No. 15-4094\\n ________________\\n\\n\\n UNITED STATES OF AMERICA\\n\\n v.\\n\\n JAY GOLDSTEIN a/k/a Yaakov\\n\\n JAY GOLDSTEIN,\\n\\nAppellant\\n ________________\\n\\n On Appeal from the United States District Court\\n for the District of New Jersey\\n (D. C. No. 3-14-cr-00287-003)\\n District Judge: Honorable Freda L. Wolfson\\n ________________\\n\\n Argued on January 25, 2017\\n Panel Rehearing Granted on August 30, 2018\\n\\n Before: CHAGARES, RESTREPO and ROTH, Circuit\\n Judges\\n\\f (Opinion filed: January 22, 2019)\\n\\n\\nAidan P. O’Connor [Argued]\\nPashman Stein Walder Hayden\\n21 Main Street\\nCourt Plaza South, Suite 200\\nHackensack, NJ 07601\\n Counsel for Appellant\\n\\nMark E. Coyne\\nOffice of United States Attorney\\n970 Broad Street, Room 700\\nNewark, NJ 07102\\n\\nNorman Gross [Argued]\\nGlenn J. Moramarco [Argued]\\nOffice of United States Attorney\\nCamden Federal Building & Courthouse\\n401 Market Street\\nCamden, NJ 08101\\n Counsel for Appellee\\n\\n\\n ________________\\n\\n OPINION\\n ________________\\n\\n\\nROTH, Circuit Judge\\n\\n\\n\\n\\n 2\\n\\f I.\\n\\n We granted Appellant Jay Goldstein’s petition for\\nrehearing to address the effect of the Supreme Court’s recent\\ndecision in Carpenter v. United States1 on our prior panel\\ndecision, United States v. Stimler.2 In Stimler, we held that\\nthe District Court properly denied Goldstein’s motion to\\nsuppress his cell site location information (CSLI) because\\nGoldstein had no reasonable expectation of privacy in his\\nCSLI, and, therefore, the government did not need probable\\ncause to collect this data.3 Carpenter sets forth a new rule\\nthat defendants do in fact have a privacy interest in their\\nCSLI, and the government must generally obtain a search\\nwarrant supported by probable cause to obtain this\\ninformation.4 However, we still affirm the District Court’s\\ndecision under the good faith exception to the exclusionary\\nrule because the government had an objectively reasonable\\ngood faith belief that its conduct was legal when it acquired\\nGoldstein’s CSLI.\\n\\n II.\\n\\n We recited a comprehensive factual background in our\\nprevious decision.5 The facts relevant to this decision follow.\\n\\n1\\n 138 S. Ct. 2206 (2018).\\n2\\n 864 F.3d 253 (3d Cir. 2017).\\n3\\n Id. at 263. Carpenter does not affect our other holdings in\\nStimler. Those remain as written and are not addressed in or\\nchanged by this decision.\\n4\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n5\\n Stimler, 864 F.3d at 259-61.\\n\\n\\n\\n\\n 3\\n\\fGoldstein was arrested for his involvement in a kidnapping\\nscheme. Hoping to find evidence placing Goldstein at the\\nscene of the kidnapping, the prosecutors obtained a court\\norder under the Stored Communications Act (SCA)—\\nspecifically 18 U.S.C. § 2703(d)—compelling Goldstein’s\\ncell phone carrier to turn over 57 days’ worth of his CSLI.\\nCSLI is a type of metadata that is generated every time a\\nuser’s cell phone connects to the nearest antenna. The user’s\\ncell phone service provider retains a time-stamped record\\nidentifying the particular antenna to which the phone\\nconnected. Because most people constantly carry and\\nfrequently use their cell phones, CSLI can provide a detailed\\nlog of an individual’s movements over a period of time.\\n\\n The legal question in this case centers on whether\\nSection 2703(d), the statutory provision under which the\\ngovernment obtained Goldstein’s CSLI, complies with the\\nFourth Amendment. The Fourth Amendment protects against\\nunreasonable searches. In order for the acquisition of CSLI to\\nbe a “search” under the Fourth Amendment, an individual\\nmust have a reasonable expectation of privacy in his CSLI.6\\nIn order for a search to be “reasonable,” it generally must be\\nconducted pursuant to a search warrant supported by probable\\ncause, unless an exception to the warrant requirement\\napplies.7 Consequently, if there is no reasonable expectation\\nof privacy as to CSLI, then its acquisition does not require a\\nsearch warrant; if there is, then a warrant is generally\\nrequired. Section 2703(d) does not require a showing of\\n\\n6\\n See United States v. Knotts, 460 U.S. 276, 281 (1983)\\n(explaining what constitutes a reasonable expectation of\\nprivacy).\\n7\\n See Riley v. California, 134 S. Ct. 2473, 2482 (2014).\\n\\n\\n\\n\\n 4\\n\\fprobable cause to obtain CSLI. Rather, it calls for a more\\nlenient standard, requiring “specific and articulable facts\\nshowing that there are reasonable grounds to believe” that the\\nCSLI is relevant and material.8\\n\\n Before trial, Goldstein moved to suppress the CSLI,\\narguing that this provision violates the Fourth Amendment\\nbecause it authorizes disclosure of CSLI without a warrant\\nsupported by probable cause. The District Court rejected this\\nargument and denied the motion. Through the testimony of\\nan FBI agent, the government introduced the CSLI at trial,\\nwhich placed him in the vicinity of the kidnapping site.\\nGoldstein was convicted and sentenced to 96 months in\\nprison.\\n\\n In our previous decision, we affirmed the District\\nCourt’s denial of Goldstein’s motion to suppress, holding that\\nSection 2703(d) complied with the Fourth Amendment\\nbecause cell phone users have no reasonable expectation of\\nprivacy in their CSLI.9 We relied on our decision in In re\\nApplication of the United States for an Order Directing a\\nProvider of Electronic Communication Service to Disclose\\nRecords to the Government (In re Application),10 which also\\nfound no reasonable expectation of privacy in CSLI,11 and we\\n\\n\\n\\n\\n8\\n 18 U.S.C. § 2703(d).\\n9\\n Stimler, 864 F.3d at 263.\\n10\\n 620 F.3d 304 (3d Cir. 2010).\\n11\\n Id. at 312-13 (holding that CSLI is obtainable without “the\\ntraditional probable cause determination” because\\nindividuals’ privacy interests do not extend to CSLI).\\n\\n\\n\\n\\n 5\\n\\freasoned that there were no intervening changes in law\\nundermining In re Application.12\\n\\n Goldstein petitioned for rehearing, and we held the\\npetition curia advisari vult pending the Supreme Court’s\\ndecision in Carpenter, which was set to address essentially\\nthe same question we answered in Stimler: whether obtaining\\nCSLI without a warrant supported by probable cause under\\nSection 2703(d) violates the Fourth Amendment’s protection\\nagainst unreasonable searches. The Supreme Court decided\\nCarpenter, and we granted Goldstein’s petition for panel\\nrehearing.13 Carpenter came to the opposite conclusion that\\nwe came to in In re Application and Stimler and held that “an\\nindividual maintains a legitimate expectation of privacy in the\\nrecord of his physical movements as captured though CSLI”\\nand that the government’s collection of CSLI requires a\\nshowing of probable cause under the Fourth Amendment.14\\nConsequently, Section 2703(d) may not be used to access\\nCSLI because it requires less than probable cause.\\n\\n Applying Carpenter to Goldstein’s case, we find that\\nthe government did violate Goldstein’s Fourth Amendment\\nrights when it acquired his CSLI under Section 2703(d) of the\\nSCA. However, we will still affirm the District Court’s\\nadmission of Goldstein’s CSLI because the government was\\nacting under an objectively reasonable good faith belief that\\n\\n\\n12\\n Stimler, 864 F.3d at 264-67.\\n13\\n Appellants Stimler and Epstein also petitioned for\\nrehearing, but we denied those petitions because the\\ngovernment did not collect their CSLI.\\n14\\n Carpenter, 138 S. Ct. at 2217, 2222.\\n\\n\\n\\n\\n 6\\n\\fobtaining CSLI under Section 2703(d) was constitutional at\\nthe time.\\n\\n\\n 15\\n III.\\n\\n It is clear that under Carpenter, acquiring Goldstein’s\\nCSLI was an unconstitutional search under the Fourth\\nAmendment because the government did not obtain a warrant\\nsupported by probable cause.16 However, evidence obtained\\nin violation of a defendant’s Fourth Amendment rights is not\\nautomatically suppressed. Evidence will be suppressed under\\nthe exclusionary rule when suppression would further the\\nexclusionary rule’s primary objective: to deter Fourth\\nAmendment violations.17 One instance where suppressing\\nevidence will not encourage deterrence is where the\\ngovernment acted “upon an objectively reasonable good faith\\nbelief in the legality of [its] conduct” when conducting a\\n\\n\\n15\\n The District Court had jurisdiction under 18 U.S.C. § 3231.\\nWe have jurisdiction pursuant to 28 U.S.C. § 1291. “In\\nreviewing a motion to suppress, ‘we review a district court’s\\nfactual findings for clear error, and we exercise de novo\\nreview over its application of the law to those factual\\nfindings.’” United States v. Katzin, 769 F.3d 163, 169 n.4 (3d\\nCir. 2014) (en banc) (quoting United States v. Pavulak, 700\\nF.3d 651, 660 (3d Cir. 2012)).\\n16\\n A warrantless search is still reasonable under the Fourth\\nAmendment if an exception to the warrant requirement\\napplies, but the parties do not argue, and we do not find, that\\nany exception applies here. Carpenter, 138 S. Ct. at 2222-23.\\n17\\n Katzin, 769 F.3d at 170-71.\\n\\n\\n\\n\\n 7\\n\\fsearch.18 Indeed, “applying the exclusionary rule would not\\n‘yield appreciable deterrence’” when government actors have\\na reasonable belief that their conduct conforms with the law.19\\nThis is known as the good faith exception, and where it\\napplies, the illegally-obtained evidence will not be suppressed\\nunder the exclusionary rule.\\n\\n The Supreme Court has applied this exception across a\\nnumber of cases where suppressing evidence would not have\\nany deterrent value—three of which are relevant here. In\\nIllinois v. Krull,20 the Court held that the good faith exception\\napplies when a search is executed pursuant to a statute that\\nwas valid at the time of the search but later declared\\nunconstitutional.21 Except in instances where a statute is\\nobviously unconstitutional, suppressing evidence obtained by\\na law enforcement officer “acting in objectively reasonable\\nreliance on a statute would have . . . little deterrent effect on\\nthe [government’s] actions.”22 Under Davis v. United\\nStates,23 this exception also applies when a search is\\nconducted based upon reasonable reliance on then-binding\\nappellate precedent because exclusion in this context would\\nnot deter improper government conduct.24 And under United\\n\\n\\n18\\n Id. at 182.\\n19\\n United States v. Vasquez-Algarin, 821 F.3d 467, 482-83 (3d\\nCir. 2016) (quoting Davis v. United States, 564 U.S. 229, 237\\n(2011)).\\n20\\n 480 U.S. 340 (1987).\\n21\\n Id. at 349-50.\\n22\\n Id.\\n23\\n 564 U.S. 229 (2011).\\n24\\n Id. at 241.\\n\\n\\n\\n\\n 8\\n\\fStates v. Leon,25 the exclusionary rule will not apply when\\nlaw enforcement conducts a search pursuant to a judicial\\norder later found invalid.26\\n\\n The good faith exception applies to the government’s\\nsearch in this case because the government acted upon an\\nobjectively reasonable, good faith belief that obtaining\\nGoldstein’s CSLI under Section 2703(d) was legal. At the\\ntime the search was executed, it was authorized under Section\\n2703(d). The government complied with all requirements of\\nSection 2703(d) and obtained a valid judicial order to collect\\nGoldstein’s CSLI. Moreover, the government had no reason\\nto question the constitutionality of obtaining CSLI through\\nSection 2703(d) because that question had been answered by\\nthis Court in In re Application—which was binding appellate\\nprecedent.27 Thus, because the government relied on a\\nproperly-obtained valid judicial order, a then-valid statute,\\nand then-binding appellate authority, it had an objectively\\nreasonable, good faith belief that its conduct was legal.\\nIndeed, the conduct was legal at the time. Excluding\\nevidence obtained through methods that complied with the\\nlaw at the time of the search cannot serve any deterrent\\npurpose. Under Krull, Davis, and Leon, the good faith\\nexception applies, and the District Court’s denial of the\\nmotion to suppress is affirmed. Our holding puts us in good\\ncompany, as many of our sister circuits have also found that\\n\\n25\\n 468 U.S. 897 (1984).\\n26\\n Id. at 922.\\n27\\n In re Application, 620 F.3d at 313 (“[W]e hold that CSLI\\nfrom cell phone calls is obtainable under a § 2703(d) order\\nand that such an order does not require the traditional\\nprobable cause determination.”).\\n\\n\\n\\n\\n 9\\n\\fthe good faith exception applies when the government\\nobtained CLSI data without a warrant prior to Carpenter.28\\n Goldstein contends that the good faith exception does\\nnot apply because the government’s reliance on Section\\n2703(d) was unreasonable for two reasons, both of which fail.\\nFirst, he argues that, at the time of the search, the Eleventh\\nCircuit had held that collecting CSLI without a warrant\\nsupported by probable cause violated the Fourth\\n\\n28\\n See, e.g., United States v. Joyner, 899 F.3d 1199, 1204-05\\n(11th Cir. 2018) (“Here, the Government complied with the\\nrequirements of the SCA in obtaining the orders to compel\\ncell site records, and when they did so in June 2015, that\\nwarrantless procedure was, under this Court’s precedent,\\nwithin the bounds of the Fourth Amendment.”);\\nUnited States v. Chavez, 894 F.3d 593, 608 (4th Cir. 2018)\\n(Carpenter does not affect cases where investigators acted\\npursuant to court orders and the SCA); United States v.\\nCurtis, 901 F.3d 846, 849 (7th Cir. 2018) (“We conclude,\\ntherefore, that even though it is now established that the\\nFourth Amendment requires a warrant for the type of cell-\\nphone data present here, exclusion of that information was\\nnot required because it was collected in good faith.”); United\\nStates v. Chambers, No. 16-163-CR, 2018 WL 4523607, at\\n*3 (2d Cir. Sept. 21, 2018) (“Thus, we conclude that even\\nafter Jones, but before Carpenter, it was objectively\\nreasonable for authorities to think that if they complied with\\nthe SCA, no warrant based on probable cause was\\nconstitutionally required to obtain cell-site information from a\\nthird party.”). Judge Restrepo’s concurrence in Stimler also\\nconcluded that the good faith exception applied here in light\\nof In re Application. See Stimler, 864 F.3d at 279-80\\n(Restrepo, J., concurring).\\n\\n\\n\\n\\n 10\\n\\fAmendment.29 But, under Davis, only binding appellate\\nprecedent is relevant to the good faith exception, and In re\\nApplication was binding in this Circuit at the time. Second,\\nhe contends the government could not have reasonably relied\\non In re Application because it had been undermined by two\\nsubsequent Supreme Court cases—United States v. Jones30\\nand Riley v. California.31 As discussed in Stimler, neither\\ncase undercuts In re Application because neither addresses\\nthe long-term collection of metadata from cell phones.32\\nJones addressed long-term collection of GPS location data\\nfrom a car—not a cell phone.33 Riley involved the contents of\\na cell phone, not the metadata transmitted from a cell phone\\nto a third party.34 Indeed, Carpenter itself recognizes that the\\ncollection of CSLI does “not fit neatly under existing\\n\\n\\n29\\n See Appellant’s Supplemental Letter at 3-4. The case that\\nGoldstein refers to was reversed on rehearing and upheld the\\nconstitutionality of CSLI obtained on less than probable\\ncause. See United States v. Davis, 785 F.3d 498, 513 (11th\\nCir. 2015).\\n30\\n 565 U.S. 400 (2012) (holding that placing a GPS tracker on\\na defendant’s car for 28 days without a warrant violated the\\nFourth Amendment).\\n31\\n 134 S. Ct. 2473 (2014) (holding that a warrantless search of\\nthe contents of a cell phone violated Fourth Amendment).\\n32\\n Stimler, 864 F.3d at 264-67.\\n33\\n Jones, 565 U.S. at 412-13. Carpenter explains that cars\\ncannot be analogized to cell phones in this context because\\ncell phones can provide law enforcement with more\\ninformation than a car about an individual’s movements.\\nCarpenter, 138 S. Ct. at 2218.\\n34\\n Riley, 134 S. Ct. at 2494-95.\\n\\n\\n\\n\\n 11\\n\\fprecedents.”35 The government could not have predicted the\\noutcome of Carpenter and the overruling of In re Application\\nfrom two Supreme Court cases that the Supreme Court itself\\nsaid are not directly applicable.\\n\\n Goldstein also argues that the good faith exception\\napplies only to police officers and other investigators, not the\\ngovernment attorneys who obtained the Section 2703(d) order\\nhere. Goldstein cites nothing in support of his proposed\\nlimitation on the good faith exception, and we see no reason\\nto limit its applicability in this case. The relevant inquiry\\nhere is not who the state actor is, but rather, whether the state\\nactor had a reasonable, good faith belief that his actions were\\nlegal. The prosecutors relied on a then-valid statute whose\\nconstitutionality had been confirmed by this Circuit. The\\ngood faith exception applies.\\n\\n IV.\\n\\n For the foregoing reasons, we affirm the District Court’s\\ndenial of Goldstein’s motion to suppress.\\n\\n\\n\\n\\n35\\n Carpenter, 138 S. Ct. at 2214-16.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]"}}},{"rowIdx":72,"cells":{"id":{"kind":"number","value":4583426,"string":"4,583,426"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"G.S. v. Rose Tree Media School Distric"},"decision_date":{"kind":"string","value":"2019-01-22"},"docket_number":{"kind":"string","value":"17-2886"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Third Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Present: AMBRO and JORDAN, Circuit Judges Motion by Amici to Convert a Not Precedential Opinion to Precedential.\", \"parties\": \"\", \"opinions\": [{\"author\": \"s/Thomas L. Ambro, Circuit Judge\", \"type\": \"010combined\", \"text\": \"UNITED STATES COURT OF APPEALS FOR THE THIRD CIRCUIT\\n\\n No. 17-2886\\n\\n G.S., a minor, by his parents, J.S. and E.S.\\n\\n v.\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n (E.D. Pa. No. 2-16-cv-04782)\\n\\n ROSE TREE MEDIA SCHOOL DISTRICT\\n\\n v.\\n\\n E.S. and J.S., Parents and Natural Guardians of G.S., a Minor\\n (E.D. Pa. No. 2-16-cv-04849)\\n\\n Rose Tree Media School District,\\n Appellant\\n\\nPresent: AMBRO and JORDAN, Circuit Judges\\n\\n Motion by Amici to Convert a Not Precedential Opinion to Precedential.\\n\\n Respectfully,\\n Clerk/nmr\\n_______________________________O R D E R ____________________________\\nThe foregoing Motion by Amici to convert a Not Precedential Opinion to a Precedential\\nOpinion is granted.\\n\\n By the Court,\\n\\n s/Thomas L. Ambro, Circuit Judge\\n\\nDated: January 22, 2019\\n\\n\\n\\n\\n The Honorable Thomas I. Vanaskie, who authored the Court’s opinion in this matter,\\nretired from the Court on January 1, 2019 and did not participate in the consideration of\\nthe motion.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4360679/\", \"author_raw\": \"s/Thomas L. Ambro, Circuit Judge\"}]}"},"judge1":{"kind":"string","value":"AMBRO"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4583426/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":1,"string":"1"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: \nCourt: \nDate decided: \nOpinion type: \nHas dissenting opinion: