agentfootprint/dist/types/context-bisect/arms/verdict.d.ts

The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.

/**
 * The arm verdict — the same three tiers, phrased for a substitution.
 *
 * ## Why not widen `verdictFor`
 *
 * `verdictFor` already carries an `action` word (`'ablating'` | `'restoring'`)
 * and a third would have been one line. It ends its NOT-CONFIRMED sentence with
 * "its ranking remains a correlational proxy only" — true of a suspect, which
 * was RANKED before it was probed, and meaningless for an arm, which was never
 * ranked at all. Widening the union would have forced that sentence onto the
 * new tier or edited a string three existing tests pin byte-for-byte. So the
 * tier LOGIC is shared (`probeFlipped`, the majority rule, the zero-tolerance
 * baseline gate) and only the prose is new.
 *
 * ## The tiers, in refusal order
 *
 * 1. **Unstable baseline** → inconclusive. The incumbent could not reproduce
 *    the reference answer across its own seeds, so a difference measured
 *    against it is measuring the scenario, not the arm. Zero tolerance, exactly
 *    as `bisect.ts` and `localize.ts` apply it: ONE un-intervened flip is
 *    enough, because the majority rule would let a 1-in-3 flaky scenario reach
 *    a causal verdict.
 * 2. **Arm did not take effect** → inconclusive. The run manifest contradicted
 *    what the arm declared. Any difference here is evidence about a
 *    configuration nobody meant to test.
 * 3. **Inside the null band** → inconclusive. A majority flip whose mean
 *    similarity still sits within the baseline arm's own seed-to-seed spread is
 *    not separable from noise. Only applied when the flip comparator and the
 *    band are the same instrument (see `NullBand.gates`).
 * 4. **Majority flip, outside the band, stable baseline** → confirmed. This is
 *    a causal claim of the same tier an ablation verdict makes: a
 *    counterfactual intervention, seeded reruns, variance reported, and a
 *    baseline that held.
 * 5. **Minority flips** → inconclusive. 6. **No flips** → not-confirmed.
 *
 * Every claim is bounded by the scenario and the comparator, and says so — an
 * arm confirmed on one question has been confirmed on one question.
 */
import type { AblationRunStats, AblationVerdict } from '../types.js';
import type { ArmApplication, NullBand } from './types.js';
/** Everything the verdict needs beyond the arm's own numbers. */
export interface ArmVerdictContext {
    readonly baselineArmId: string;
    /** The baseline arm reproduced the reference on EVERY seed. */
    readonly baselineStable: boolean;
    readonly baselineStats: AblationRunStats;
    readonly band: NullBand;
    /** Mean similarity fell below the band's floor. */
    readonly outsideNullBand: boolean;
    readonly application: ArmApplication;
}
/** Translate one arm's probe evidence into its verdict. See module docs. */
export declare function verdictForArm(armId: string, stats: AblationRunStats, context: ArmVerdictContext): AblationVerdict;
//# sourceMappingURL=verdict.d.ts.map