/**
 * Worked example: EXPERIMENTAL confidence calibration from review history.
 *
 * Calibration summarizes how often reviewers affirmed an extractor's proposals.
 * Both outputs below are experimental descriptive statistics (#279), not
 * validated probabilities or policy:
 *
 *   1. `deriveCalibration` reports per-decile affirmation rates and, only when a
 *      decile has enough samples AND a one-sided 95% Wilson lower bound on its
 *      accuracy clears the target, a `suggestedThreshold`. A thin history gets
 *      no threshold at all. Do not feed `suggestedThreshold` into an auto-accept
 *      policy (`autoAcceptMinConfidence` / `minConfidence`) as-is: it is not an
 *      evaluated gate.
 *
 *   2. `buildSurveyTrustBundle({ calibration: { experimentalConclusionValue:
 *      true, metrics } })` sets `conclusionConfidence.value` on affirmed claims
 *      to their extractor/field GROUP's affirmation rate. Every affirmed claim in
 *      the group gets the same base rate whatever its own confidence, so it is
 *      not a per-claim probability. Without the experimental flag no value is set.
 *
 * Calibration is advisory (ADR 0003 §4): it never changes claim status.
 *
 * Run: `node dist/examples/calibrated-auto-accept.js`
 */
export interface CalibratedAutoAcceptResult {
    /** Threshold from a 60-samples-per-decile history (enough evidence). */
    readonly suggestedThreshold: number | undefined;
    /** Threshold from a 10-samples-per-decile history (withheld: too thin). */
    readonly sparseHistoryThreshold: number | undefined;
    readonly groupAccuracy: number | undefined;
    /** Values with the experimental opt-in: the group base rate on each claim. */
    readonly producedValues: ReadonlyArray<number | undefined>;
    /** Values with `calibration` enabled but no experimental opt-in: none. */
    readonly defaultValues: ReadonlyArray<number | undefined>;
}
export declare function runCalibratedAutoAccept(): CalibratedAutoAcceptResult;