/**
 * Trust gate — decides whether an ensemble's scores are allowed to be BELIEVED,
 * one level up from {@link aggregateJudgeVerdicts} (which only reduces ONE
 * artifact's raters to a composite). A composite is a number; this is the check
 * that the number means anything. It is the code "Enforced by" for the
 * measurement-validation skill's after-gate ("is this result allowed to be
 * believed").
 *
 * Three checks, each fail-loud and named in `trustReasons`:
 *   (1) inter-rater reliability over the corpus ≥ `irrFloor` — raters that
 *       disagree no better than chance carry no signal to optimize against.
 *   (2) per-item rater spread ≤ `spreadCeiling` — for EACH item, raters must
 *       converge on THAT item.
 *   (3) surviving raters per item ≥ `minSurvivors` — a mean over one or two
 *       raters is an anecdote, not an ensemble.
 *
 * CRITICAL metric semantics — per-item spread is rater disagreement about the
 * SAME item: `max(score) − min(score)` across the raters that scored THAT item
 * (max over its dimensions), never pooled across different items or across the
 * baseline/candidate sides. Pooling reads a genuine quality gap BETWEEN items as
 * "the raters split" and so trips the gate exactly when the finding is largest —
 * the failure mode the after-gate exists to prevent. The corpus IRR (check 1)
 * leans on the substrate's `interRaterReliability`, whose expected-disagreement
 * denominator already pools across items, so genuine item-to-item variation
 * RAISES reliability rather than lowering it.
 */
import { type JudgeVerdict } from '@tangle-network/agent-eval';
/** One item's raters: the per-judge verdicts {@link aggregateJudgeVerdicts}
 *  reduces, tagged with the item they scored so spread stays within-item. */
export interface TrustItem<D extends string = string> {
    /** Stable item identifier — surfaces in `perItemSpread` and `trustReasons`. */
    itemId: string;
    /** The raters' verdicts for THIS item (one per judge call). A failed judge
     *  (`perDimension: null`) is dropped before spread/IRR, never folded as 0. */
    verdicts: readonly JudgeVerdict<D>[];
}
/** Thresholds for {@link trustVerdicts}. All overridable; defaults are the
 *  conservative after-gate bar. */
export interface TrustThresholds {
    /** Minimum corpus inter-rater reliability (Krippendorff-style α). Below this
     *  the raters agree no better than chance. Default 0.2. */
    irrFloor?: number;
    /** Maximum per-item rater spread (`max − min` over a single item's surviving
     *  raters, across its dimensions). Above this the raters split ON THAT ITEM.
     *  Default 0.5. */
    spreadCeiling?: number;
    /** Minimum surviving (non-failed) raters required per item. Default 3. */
    minSurvivors?: number;
}
/** Result of the trust gate. `trustworthy` iff every check passed; `trustReasons`
 *  is empty iff `trustworthy`. */
export interface TrustVerdict {
    /** True iff IRR ≥ floor AND every item's spread ≤ ceiling AND every item has
     *  ≥ `minSurvivors` surviving raters. */
    trustworthy: boolean;
    /** One entry per FAILED check, each naming its number + the offending value.
     *  Empty iff `trustworthy`. */
    trustReasons: string[];
    /** Corpus inter-rater reliability actually measured (the check-1 value). */
    interRaterReliability: number;
    /** Per-item spread (`max − min` over surviving raters, max over dimensions),
     *  keyed by `itemId`. The check-2 input, surfaced for drill-down. */
    perItemSpread: Record<string, number>;
}
/**
 * Decide whether an ensemble's per-item verdicts are trustworthy enough to
 * believe a lift computed from them. Pure: no LLM, no I/O, no clock, no random —
 * the same `items` + `thresholds` always yield the same verdict.
 *
 * Sibling to {@link aggregateJudgeVerdicts}: that reduces ONE item's raters to a
 * composite; this audits the raters ACROSS items and reports whether the
 * composites are believable. Run it on the corpus of held-out items before
 * reporting any lift over their scores.
 *
 * @throws if `items` is empty — an empty corpus has no measurable trust, and a
 *   silent `trustworthy: true` over zero evidence is the exact lie the gate
 *   exists to refuse.
 */
export declare function trustVerdicts<D extends string>(items: readonly TrustItem<D>[], thresholds?: TrustThresholds): TrustVerdict;