import type { Digest, HeldoutApproval, HeldoutAttempt, HeldoutCorpus, HeldoutPreregistration } from '../heldout/types.js'; import type { CalibrationArtifact } from '../calibration/types.js'; import type { QualificationIntegrityMetadata } from '../qualification/release.js'; import { type D17CalibrationMapping } from './calibration.js'; import { type D17MfLabel, type D17MfOutcome, type D17MfPoolId, type D17MfWorld } from './multifact.js'; /** * D17-MF: preregistered, calibrated probe of Jev's multi-fact degradation (#2850). * * Primary reasoning metrics are threshold-free of any calibrator: the raw native answer (P(yes) > 0.5) and the AUROC of * the raw P(yes) between yes rows and missing-link rows. The registered D17 member calibrator was fitted on the pool-b * grammar, so calibrated answers would confound pool contrasts with where that calibrator sets its threshold; calibrated * metrics serve only the calibration-under-shift rule. * * Calibration choice: collector artifact mode binds the registered D17 calibration set, and the member calibrator is * applied to the single fresh call per row. A calibrator fitted on the shifted pools would absorb exactly the * miscalibration under shift this probe measures. The calibrator is re-derived from the D17 seal and qualified at bundle * time, at collection end and at the scoring clock; it is never trusted unverified and never skipped. */ /** The registered D17 member calibrator's expiry: effectiveAt 2026-10-02T10:02:34.263Z plus the profile's 30 days. */ export declare const D17MF_ARTIFACT_EXPIRY = "2026-11-01T10:02:34.263Z"; export declare const D17MF_PROTOCOL: Readonly<{ schemaVersion: "decision-d17mf-protocol/v2"; issue: "roctinam/aiwg#2850"; study: "D17"; generator: "d17-multifact/v1"; design: Readonly<{ pools: readonly D17MfPoolId[]; hops: readonly [1, 3]; outcomes: readonly D17MfOutcome[]; layouts: string[]; counts: Readonly<{ missing: 220; yes: 110; 'relay-off': 40; control: 30; }>; developmentPerCell: 2; rows: number; keyCells: "equalized missing-link cells: 3 pools x 2 hops x 3 written encodings, plus pure absence at 3 hops; 220 rows each (Wilson 95% half-width 0.066 at p = 0.5)"; supportingCells: "equalized yes (110) and relay-off (40) cells and D17-faithful control cells (30)"; rule: "equalized cells state an exhaustive link-only rule; the D17-faithful control keeps the original D17 rule"; order: "equalized fact lines are shuffled uniformly; the rule line is last"; sizeBound: "one corpus stays inside the shared credential-scan traversal limit (100,000 nodes, 17 per row)"; limitation: "within a pool the link verb and the framing sentence co-vary (no verb x framing cross-cell fits the row bound), so H1 attributes a pool difference to the pool wording as a whole"; dispatchOrder: "development rows first, then test rows in a seeded Fisher-Yates permutation keyed by the corpus seed digest"; requestsPerRow: 1; request: "champion: one fresh call of jev-1.13.0 with the D17 DecisionDefinition"; }>; metrics: Readonly<{ primary: string[]; secondary: "calibrated accuracy, calibrated confidence and decile ECE through the registered D17 member calibrator; used only by the calibration-under-shift rule"; positions: "failure position as first, interior or last link (or relay); accuracy is reported by position"; }>; calibration: Readonly<{ mode: "artifact"; calibrator: "d17-single-call-isotonic"; binding: "approval.calibration.calibrationArtifactDigest = registered D17 calibration set digest"; verification: "the D17 calibration set is re-derived from its sealed calibration phase; the member artifact is qualified at bundle time, at collection end and at the scoring clock"; expiresAt: "2026-11-01T10:02:34.263Z"; profile: { readonly minimumTotalSamples: 380; readonly minimumPerSliceSamples: 95; readonly powerRule: null; readonly confidenceInterval: { readonly method: "wilson"; readonly level: 0.95; }; readonly maximumCalibrationError: 0.1; readonly maximumSelectiveRisk: 0.1; readonly expiresAfterDays: 30; }; }>; interval: Readonly<{ cell: "wilson"; difference: "newcombe-hybrid-score-independent"; auroc: "hanley-mcneil"; levelBps: 9500; }>; multiplicity: Readonly<{ method: "holm"; alpha: 0.05; test: "two-sided two-proportion z (pooled)"; families: string[]; }>; coverage: Readonly<{ minimumObservedFraction: 0.95; rule: "every preregistered test cell must reach it; otherwise the report is incomplete and every verdict is \"insufficient\""; }>; scoringClock: "collection end is bounded by the latest session start bound into frozen.json (digest-covered evidence) plus the preregistered session limit, across the run lineage; evaluatedAt is at least that bound and at most now; the collector refuses any session whose window passes the calibrator expiry; scoring happens at the exact approved source commit"; hypotheses: readonly (Readonly<{ id: "H1"; name: "wording"; claim: "Missing-link raw accuracy depends on the wording pool at fixed hops and encoding."; }> | Readonly<{ id: "H2"; name: "depth"; claim: "Raw accuracy falls from one relay hop to three at fixed pool, outcome and failure position (first or last)."; }> | Readonly<{ id: "H3"; name: "missing-link-polarity"; claim: "A missing link is read as established (permissive linking), while a disabled relay is handled."; }> | Readonly<{ id: "H3a"; name: "encoding"; claim: "The failure is specific to the contrastive verb rather than to missing links in general (pure absence is the baseline)."; }> | Readonly<{ id: "H4"; name: "layout"; claim: "At one hop and the last link, the D17-faithful rendering differs from the equalized rendering (rule wording, line order, decoys, names)."; }>)[]; decisionRules: Readonly<{ H1: "supported when, for some missing-link encoding, a pool-pair raw-accuracy contrast is Holm-significant (family-wise 0.05) with |difference| >= 0.10 at every hop level the encoding has"; H2: "supported when, for some outcome, raw accuracy(h3) - accuracy(h1), restricted to first- and last-position failures, has a Newcombe 95% upper bound below -0.05 in at least 2 of 3 pools"; H3: "supported when, in every pool (pooled over hops), relay-off minus missing-link raw accuracy has a 95% lower bound above 0.10 for some encoding and that encoding is answered \"yes\" on more than half its rows"; H3a: "\"contrastive-specific\" when, in at least 2 pools, contrastive raw accuracy is below both negation and the non-connective verb (95% upper bound below 0 and |difference| >= 0.15); \"general\" when the three written encodings are within 0.10 of each other and all below relay-off; otherwise \"mixed\"; the pure-absence baseline is reported against interior-position contrastive rows"; H4: "supported when some pool shows a Holm-significant raw-accuracy difference (d17-faithful minus equalized, one hop, last-link failures, missing-contrastive)"; replication: "the D17 failure replicates when pool-c d17-faithful missing-contrastive raw accuracy has a Wilson 95% upper bound at most 0.50"; calibrationUnderShift: "a cell is calibration-unreliable when mean calibrated confidence minus calibrated accuracy exceeds 0.10 and the calibrated accuracy upper bound is below the mean confidence"; }>; shortcutAudit: Readonly<{ population: "equalized test rows, per pool x hops, target gold yes/no"; folds: 5; limit: 0.6; learners: string[]; features: string[]; positiveControl: "the chain-first line order of the earlier layout must fail the audit (regression-tested)"; control: "d17-faithful rows are audited separately and reported; they reproduce D17 and are expected to be cue-solvable"; }>; budget: "shares the D17 study cap (USD 8) with the D17 runs: the approval attests all prior D17 and program spend as floors; this study budget is USD 5"; promotion: "none: a diagnostic probe of the provider; the study decision is always HOLD"; }>; /** Public and review seeds can regenerate gold from source; they never back a paid collection. */ export declare const D17MF_PUBLIC_SEEDS: readonly string[]; /** The same rule `validateHeldoutBundle` enforces at the collector boundary (shared in study-generators.ts). */ export declare function assertD17MultifactPrivateSeed(seed: unknown): void; type Prepared = ReturnType; interface Gold { schemaVersion: 'decision-d17mf-gold/v1'; labels: Record; worlds: Record; } export declare function d17MultifactFeatures(payload: string, pool: D17MfPoolId): { scalar: Record; tokens: Record; }; /** D29-style shortcut audit, counts and line order included: no surface learner may predict gold above the limit. */ export declare function d17MultifactShortcutAudit(corpus: HeldoutCorpus, gold: Gold): { schemaVersion: string; limit: 0.6; folds: 5; groups: { group: string; n: number; yes: number; scores: { scalarThreshold: number; tokenThreshold: number; depth2Tree: number; logistic: number; }; max: number; passes: boolean | null; }[]; equalizedPasses: boolean; equalizedMax: number; controlMax: number; }; export declare function prepareD17MultifactStudy(seed: string, moduleDigest: Digest, sourceDigests: Record): { corpus: HeldoutCorpus; preregistration: HeldoutPreregistration; gold: Gold; analysis: { schemaVersion: string; protocol: Readonly<{ schemaVersion: "decision-d17mf-protocol/v2"; issue: "roctinam/aiwg#2850"; study: "D17"; generator: "d17-multifact/v1"; design: Readonly<{ pools: readonly D17MfPoolId[]; hops: readonly [1, 3]; outcomes: readonly D17MfOutcome[]; layouts: string[]; counts: Readonly<{ missing: 220; yes: 110; 'relay-off': 40; control: 30; }>; developmentPerCell: 2; rows: number; keyCells: "equalized missing-link cells: 3 pools x 2 hops x 3 written encodings, plus pure absence at 3 hops; 220 rows each (Wilson 95% half-width 0.066 at p = 0.5)"; supportingCells: "equalized yes (110) and relay-off (40) cells and D17-faithful control cells (30)"; rule: "equalized cells state an exhaustive link-only rule; the D17-faithful control keeps the original D17 rule"; order: "equalized fact lines are shuffled uniformly; the rule line is last"; sizeBound: "one corpus stays inside the shared credential-scan traversal limit (100,000 nodes, 17 per row)"; limitation: "within a pool the link verb and the framing sentence co-vary (no verb x framing cross-cell fits the row bound), so H1 attributes a pool difference to the pool wording as a whole"; dispatchOrder: "development rows first, then test rows in a seeded Fisher-Yates permutation keyed by the corpus seed digest"; requestsPerRow: 1; request: "champion: one fresh call of jev-1.13.0 with the D17 DecisionDefinition"; }>; metrics: Readonly<{ primary: string[]; secondary: "calibrated accuracy, calibrated confidence and decile ECE through the registered D17 member calibrator; used only by the calibration-under-shift rule"; positions: "failure position as first, interior or last link (or relay); accuracy is reported by position"; }>; calibration: Readonly<{ mode: "artifact"; calibrator: "d17-single-call-isotonic"; binding: "approval.calibration.calibrationArtifactDigest = registered D17 calibration set digest"; verification: "the D17 calibration set is re-derived from its sealed calibration phase; the member artifact is qualified at bundle time, at collection end and at the scoring clock"; expiresAt: "2026-11-01T10:02:34.263Z"; profile: { readonly minimumTotalSamples: 380; readonly minimumPerSliceSamples: 95; readonly powerRule: null; readonly confidenceInterval: { readonly method: "wilson"; readonly level: 0.95; }; readonly maximumCalibrationError: 0.1; readonly maximumSelectiveRisk: 0.1; readonly expiresAfterDays: 30; }; }>; interval: Readonly<{ cell: "wilson"; difference: "newcombe-hybrid-score-independent"; auroc: "hanley-mcneil"; levelBps: 9500; }>; multiplicity: Readonly<{ method: "holm"; alpha: 0.05; test: "two-sided two-proportion z (pooled)"; families: string[]; }>; coverage: Readonly<{ minimumObservedFraction: 0.95; rule: "every preregistered test cell must reach it; otherwise the report is incomplete and every verdict is \"insufficient\""; }>; scoringClock: "collection end is bounded by the latest session start bound into frozen.json (digest-covered evidence) plus the preregistered session limit, across the run lineage; evaluatedAt is at least that bound and at most now; the collector refuses any session whose window passes the calibrator expiry; scoring happens at the exact approved source commit"; hypotheses: readonly (Readonly<{ id: "H1"; name: "wording"; claim: "Missing-link raw accuracy depends on the wording pool at fixed hops and encoding."; }> | Readonly<{ id: "H2"; name: "depth"; claim: "Raw accuracy falls from one relay hop to three at fixed pool, outcome and failure position (first or last)."; }> | Readonly<{ id: "H3"; name: "missing-link-polarity"; claim: "A missing link is read as established (permissive linking), while a disabled relay is handled."; }> | Readonly<{ id: "H3a"; name: "encoding"; claim: "The failure is specific to the contrastive verb rather than to missing links in general (pure absence is the baseline)."; }> | Readonly<{ id: "H4"; name: "layout"; claim: "At one hop and the last link, the D17-faithful rendering differs from the equalized rendering (rule wording, line order, decoys, names)."; }>)[]; decisionRules: Readonly<{ H1: "supported when, for some missing-link encoding, a pool-pair raw-accuracy contrast is Holm-significant (family-wise 0.05) with |difference| >= 0.10 at every hop level the encoding has"; H2: "supported when, for some outcome, raw accuracy(h3) - accuracy(h1), restricted to first- and last-position failures, has a Newcombe 95% upper bound below -0.05 in at least 2 of 3 pools"; H3: "supported when, in every pool (pooled over hops), relay-off minus missing-link raw accuracy has a 95% lower bound above 0.10 for some encoding and that encoding is answered \"yes\" on more than half its rows"; H3a: "\"contrastive-specific\" when, in at least 2 pools, contrastive raw accuracy is below both negation and the non-connective verb (95% upper bound below 0 and |difference| >= 0.15); \"general\" when the three written encodings are within 0.10 of each other and all below relay-off; otherwise \"mixed\"; the pure-absence baseline is reported against interior-position contrastive rows"; H4: "supported when some pool shows a Holm-significant raw-accuracy difference (d17-faithful minus equalized, one hop, last-link failures, missing-contrastive)"; replication: "the D17 failure replicates when pool-c d17-faithful missing-contrastive raw accuracy has a Wilson 95% upper bound at most 0.50"; calibrationUnderShift: "a cell is calibration-unreliable when mean calibrated confidence minus calibrated accuracy exceeds 0.10 and the calibrated accuracy upper bound is below the mean confidence"; }>; shortcutAudit: Readonly<{ population: "equalized test rows, per pool x hops, target gold yes/no"; folds: 5; limit: 0.6; learners: string[]; features: string[]; positiveControl: "the chain-first line order of the earlier layout must fail the audit (regression-tested)"; control: "d17-faithful rows are audited separately and reported; they reproduce D17 and are expected to be cue-solvable"; }>; budget: "shares the D17 study cap (USD 8) with the D17 runs: the approval attests all prior D17 and program spend as floors; this study budget is USD 5"; promotion: "none: a diagnostic probe of the provider; the study decision is always HOLD"; }>; sourceDigests: Record; auditDigest: `sha256:${string}`; dispatchOrderDigest: `sha256:${string}`; cells: { split: "calibration" | "tuning" | "test"; key: string; rule: "exhaustive" | "d17"; count: number; }[]; }; audit: { schemaVersion: string; limit: 0.6; folds: 5; groups: { group: string; n: number; yes: number; scores: { scalarThreshold: number; tokenThreshold: number; depth2Tree: number; logistic: number; }; max: number; passes: boolean | null; }[]; equalizedPasses: boolean; equalizedMax: number; controlMax: number; }; approvalTemplate: { budget: { calls: 16000; tokens: 30000000; usd: 5; }; calibration: { mode: string; calibrationArtifactDigest: null; }; priceBound: { inputUsdPerMTok: number; outputUsdPerMTok: number; perRequestUsd: number; evidenceReferences: string[]; approvalReference: null; }; schemaVersion: string; approved: boolean; study: import("../heldout/types.js").Study; runId: null; reviewer: null; approvalReference: null; sourceCommit: null; exactHeadCi: null; stagingHost: string; stagingWorkspace: null; model: string; servedModel: string; region: null; credentialRef: null; credentialResolverDigest: null; corpusDigest: `sha256:${string}`; preregistrationDigest: `sha256:${string}`; executionDigest: null; providerTermsReference: null; priorStudySpendUsd: null; priorPortfolioSpendUsd: null; }; reviewTemplate: { schemaVersion: string; reviewer: null; preregistrationReview: null; assessments: { assessmentId: string; rowId: string; cell: string; inputDigest: `sha256:${string}`; payload: string; reviewedAt: null; goldAuditLabel: null; goldAmbiguousOrIncorrect: null; rationale: null; }[]; instructions: string; }; }; /** Study budget: USD 5 cap (program-authorized for #2850, inside the shared USD 8 D17 cap); calls and tokens leave headroom at the 80% stop. */ export declare const D17MF_BUDGET: Readonly<{ calls: 16000; tokens: 30000000; usd: 5; }>; /** Worst-case plan from the actual projected request sizes and the approval price bound; fits against an allowance. */ export declare function d17MultifactPlan(prepared: Pick, approval: Pick): Promise<{ rows: number; firstAttempts: number; maximumAttempts: number; maximumRequestEstimateTokens: number; reservedTokens: number; reservedUsdMicros: number; }>; export declare function d17MultifactFit(plan: Pick>, 'maximumAttempts' | 'reservedTokens' | 'reservedUsdMicros'>, allowance: { calls: number; tokens: number; usdMicros: number; }): { allowance: { calls: number; tokens: number; usdMicros: number; }; headroom: { calls: number; tokens: number; usdMicros: number; }; fits: boolean; }; export declare function d17MultifactFreshAllowance(approval: HeldoutApproval): { calls: number; tokens: number; usdMicros: number; }; /** 40 complete development assessments agreeing with gold and the text oracle; the approval must cite the digest. */ export declare function validateD17MultifactReview(prepared: Prepared, review: unknown, trustedDigest: unknown, options?: { before?: string; }): { reviewer: string; preregistrationReview: string; assessments: Array<{ assessmentId: string; rowId: string; cell: string; inputDigest: string; payload: string; reviewedAt: string; goldAuditLabel: string; goldAmbiguousOrIncorrect: boolean; rationale: string; }>; }; /** * Blind-then-unblind material for the 40 development assessments, in the D17 development review material format: each item * carries `blind.payload` (shown first) and `unblind` (generator gold, independent text-oracle label, cell, latent world). * Development (`tuning`) rows only; it contains gold and must stay private (the CLI writes it mode 600). */ export declare function d17MultifactDevReviewMaterial(prepared: Prepared, options: { preparedDirectory: string; }): { schemaVersion: string; study: string; scope: string; preparedDirectory: string; seedDigest: `sha256:${string}`; reviewTemplateDigest: `sha256:${string}`; corpusDigest: `sha256:${string}`; goldDigest: `sha256:${string}`; preregistrationDigest: `sha256:${string}`; splitOfItems: string; itemCount: number; protocol: string[]; guide: { population: string; yes: string; no: string; authority: string; invalidGold: string; timing: string; independence: string; }; items: { assessmentId: string; rowId: string; cell: string; inputDigest: `sha256:${string}`; blind: { payload: string; }; unblind: { goldLabel: D17MfLabel; textOracleLabel: D17MfLabel; variant: string; cell: string; factors: { pool: D17MfPoolId; hops: 1 | 3; outcome: D17MfOutcome; layout: import("./multifact.js").D17MfLayout; rule: "exhaustive" | "d17"; }; latentWorld: { chain: string[]; decoys: string[]; failureKind: "link" | "relay" | null; failurePosition: number | null; targets: { [x: string]: number; }; day: number; quantity: number; }; }; }[]; }; export declare function newcombeDifference(k1: number, n1: number, k2: number, n2: number, levelBps?: number): { difference: number; lower: number; upper: number; } | null; export declare function twoProportionP(k1: number, n1: number, k2: number, n2: number): number | null; /** Holm step-down: adjusted p-values in the original order (monotone, capped at 1). */ export declare function holmAdjust(pValues: ReadonlyArray): Array; /** AUROC of scores between positives and negatives (ties count half) with the Hanley-McNeil 95% interval. */ export declare function auroc(positives: readonly number[], negatives: readonly number[]): { auroc: number; lower: number; upper: number; positives: number; negatives: number; } | null; export interface D17MfScoringContext { /** The registered D17 calibration set and its member artifact and mapping, already re-derived from the D17 seal by the host. */ set: { member: { artifactId: string; artifactDigest: Digest; mappingDigest: Digest; }; }; trustedCalibrationSetDigest: Digest; member: { artifact: CalibrationArtifact; mapping: D17CalibrationMapping; }; /** Collection-end bound from `d17MultifactCollectionEnd` over the run lineage; the scoring clock may not precede it. */ collectionEndedAt: string; nowEpochMs: number; } /** * Upper bound on the end of collection across a run lineage, from digest-covered evidence only: each session's * `collectionStartedAt` (bound into frozen.json, hence into the trusted evidence digest) plus the preregistered session * limit, which the collector never dispatches past. `qualification.json` times are not used: they are not digest-covered. */ export declare function d17MultifactCollectionEnd(frozen: ReadonlyArray<{ collectionStartedAt?: unknown; bundle: { preregistration: HeldoutPreregistration; }; }>): string; export declare function scoreD17Multifact(input: { corpus: HeldoutCorpus; preregistration: HeldoutPreregistration; attempts: readonly HeldoutAttempt[]; gold: unknown; integrity: QualificationIntegrityMetadata; approvedCalibration: unknown; calibrated: unknown; }, prepared: Prepared, context: D17MfScoringContext): Promise<{ schemaVersion: string; issue: string; scope: string; calibrated: boolean; primaryMetric: string; calibration: { mode: string; calibrationSetDigest: `sha256:${string}`; memberArtifactDigest: `sha256:${string}`; mappingDigest: `sha256:${string}`; compatibility: { action: import("../index.js").CompatibilityAction; state: import("../index.js").CompatibilityState; }; qualifiedAt: string; collectionEndedAt: string; expiresAt: string; }; corpusDigest: `sha256:${string}`; preregistrationDigest: `sha256:${string}`; analysisDigest: `sha256:${string}`; integrityDigest: `sha256:${string}`; auditDigest: `sha256:${string}`; coverage: { testRows: number; observed: number; developmentRows: number; minimumObservedFraction: 0.95; complete: boolean; }; overall: { n: number; observed: number; coverage: number | null; raw: { correct: number; accuracy: number | null; wilson95: [number, number] | null; saidYesRate: number | null; }; calibrated: { correct: number; accuracy: number | null; wilson95: [number, number] | null; meanConfidence: number | null; confidenceMinusAccuracy: number | null; ece: number | null; calibrationUnreliable: boolean | null; }; }; cells: { [k: string]: { n: number; observed: number; coverage: number | null; raw: { correct: number; accuracy: number | null; wilson95: [number, number] | null; saidYesRate: number | null; }; calibrated: { correct: number; accuracy: number | null; wilson95: [number, number] | null; meanConfidence: number | null; confidenceMinusAccuracy: number | null; ece: number | null; calibrationUnreliable: boolean | null; }; }; }; byFailurePosition: { [k: string]: { n: number; observed: number; coverage: number | null; raw: { correct: number; accuracy: number | null; wilson95: [number, number] | null; saidYesRate: number | null; }; calibrated: { correct: number; accuracy: number | null; wilson95: [number, number] | null; meanConfidence: number | null; confidenceMinusAccuracy: number | null; ece: number | null; calibrationUnreliable: boolean | null; }; }; }; auroc: { pool: D17MfPoolId; hops: 1 | 3; pooled: { auroc: number; lower: number; upper: number; positives: number; negatives: number; } | null; byEncoding: { [k: string]: { auroc: number; lower: number; upper: number; positives: number; negatives: number; } | null; }; }[]; hypotheses: { H1: { verdict: boolean | "insufficient"; byEncoding: { outcome: "missing-contrastive" | "missing-negation" | "missing-unrelated" | "missing-absence"; supported: boolean; }[]; tests: { holmP: number | null; meets: boolean; outcome: "missing-contrastive" | "missing-negation" | "missing-unrelated" | "missing-absence"; hops: number; pools: string; interval: { difference: number; lower: number; upper: number; } | null; p: number | null; }[]; }; H2: { verdict: boolean | "insufficient"; byOutcome: { outcome: "yes" | "relay-off" | "missing-contrastive" | "missing-negation" | "missing-unrelated"; matchedPositions: string; pools: { pool: D17MfPoolId; interval: { difference: number; lower: number; upper: number; } | null; }[]; supported: boolean; }[]; }; H3: { verdict: boolean | "insufficient"; byPool: { pool: D17MfPoolId; byEncoding: { outcome: "missing-contrastive" | "missing-negation" | "missing-unrelated" | "missing-absence"; interval: { difference: number; lower: number; upper: number; } | null; rawSaidYesRate: number | null; meets: boolean; }[]; meets: boolean; }[]; }; H3a: { verdict: string; byPool: { pool: D17MfPoolId; vsNegation: { difference: number; lower: number; upper: number; } | null; vsUnrelated: { difference: number; lower: number; upper: number; } | null; negVsUnrelated: { difference: number; lower: number; upper: number; } | null; contrastiveInteriorVsAbsence: { difference: number; lower: number; upper: number; } | null; specific: boolean; general: boolean; }[]; }; H4: { verdict: boolean | "insufficient"; byPool: { holmP: number | null; meets: boolean; pool: D17MfPoolId; matchedPosition: string; interval: { difference: number; lower: number; upper: number; } | null; unmatchedInterval: { difference: number; lower: number; upper: number; } | null; p: number | null; }[]; differences: string[]; }; replication: { verdict: boolean | "insufficient"; cell: { n: number; observed: number; coverage: number | null; raw: { correct: number; accuracy: number | null; wilson95: [number, number] | null; saidYesRate: number | null; }; calibrated: { correct: number; accuracy: number | null; wilson95: [number, number] | null; meanConfidence: number | null; confidenceMinusAccuracy: number | null; ece: number | null; calibrationUnreliable: boolean | null; }; }; }; calibrationUnderShift: { unreliableCells: string[]; }; }; decision: "HOLD"; promotion: string; }>; export type D17MultifactReport = Awaited>; export {}; //# sourceMappingURL=multifact-study.d.ts.map