@tangle-network/agent-eval 0.200.1 → 0.201.0

package/dist/{jev-review-Cu9xtIu4.js → jev-review-DZEjDzlF.js}

@@ -89,10 +89,12 @@ function assessJevReview(review, raw) {
 		else if (supportProbability >= check.supportAtLeast) {
 			status = "supported";
 			reason = "support-threshold";
-		} else if (refutationProbability >= check.refuteAtLeast) if (check.coverage === "complete") {
-			status = "refuted";
-			reason = "refutation-threshold";
-		} else reason = "partial-negative-evidence";
+		} else if (refutationProbability >= check.refuteAtLeast) {
+			if (check.coverage === "complete") {
+				status = "refuted";
+				reason = "refutation-threshold";
+			} else reason = "partial-negative-evidence";
+		}
 		return {
 			question,
 			status,
@@ -152,4 +154,4 @@ function jevReviewFindings(review, result, options) {
 //#endregion
 export { jevReviewFindings as n, prepareJevReview as r, assessJevReview as t };
 
-//# sourceMappingURL=jev-review-Cu9xtIu4.js.map
+//# sourceMappingURL=jev-review-DZEjDzlF.js.map

package/dist/{jev-review-Cu9xtIu4.js.map → jev-review-DZEjDzlF.js.map}

@@ -1 +1 @@
-{"version":3,"file":"jev-review-Cu9xtIu4.js","names":[],"sources":["../src/jev-review.ts"],"sourcesContent":["import { z } from 'zod'\nimport {\n  ANALYST_SEVERITIES,\n  type AnalystFinding,\n  type EvidenceRef,\n  makeFinding,\n} from './analyst/types'\nimport type { JevQuestions, JevRequest, JevResult } from './jev-protocol'\nimport { parseJevRequest, parseJevResult } from './jev-protocol'\nimport { canonicalString, hashCanonical, jsonDocument } from './ledger-core/canonical'\nimport { deepFreezeCanonicalJson } from './ledger-core/deep-freeze'\n\nconst name = z.string().trim().min(1)\nconst probability = z.number().finite().gt(0).max(1)\nconst checkSchema = z\n  .object({\n    claim: name,\n    area: name,\n    subject: name,\n    severity: z.enum(ANALYST_SEVERITIES),\n    /** Choice labels or score-level keys, never scores invented from category order. */\n    supports: z.array(z.string()).min(1),\n    refutes: z.array(z.string()).min(1),\n    supportAtLeast: probability,\n    refuteAtLeast: probability,\n    /** Host-supplied coverage of the question's required evidence, not model self-assessment. */\n    coverage: z.enum(['complete', 'partial', 'missing']),\n    evidence: z.array(\n      z\n        .object({\n          kind: z.enum(['span', 'event', 'artifact', 'finding', 'metric']),\n          uri: name,\n          excerpt: z.string().optional(),\n        })\n        .strict(),\n    ),\n  })\n  .strict()\n  .refine((value) => value.supportAtLeast + value.refuteAtLeast > 1, {\n    message: 'Support and refutation thresholds must not overlap',\n  })\n\n/** Optional interpretation of native choices/scores. Policy and evidence belong to the caller. */\nexport type JevReviewCheck = z.infer<typeof checkSchema>\nexport interface JevReviewInput<Q extends JevQuestions = JevQuestions> {\n  version: string\n  request: JevRequest<Q>\n  checks: { [K in keyof Q]: JevReviewCheck }\n}\n\nexport interface PreparedJevReview<Q extends JevQuestions = JevQuestions>\n  extends JevReviewInput<Q> {\n  /** Binds questions, option order, context, evidence, thresholds and definition version. */\n  digest: string\n}\n\nexport interface JevReviewAssessment {\n  question: string\n  status: 'supported' | 'refuted' | 'unresolved'\n  reason:\n    | 'support-threshold'\n    | 'refutation-threshold'\n    | 'missing-evidence'\n    | 'partial-negative-evidence'\n    | 'below-threshold'\n    | 'ambiguous-thresholds'\n  /** Unnormalized marginal mass of caller-designated native alternatives. Not calibrated risk. */\n  supportProbability: number\n  refutationProbability: number\n  unresolvedProbability: number\n  modelConfidence: number | null\n  check: JevReviewCheck\n}\n\nexport interface JevReviewReport {\n  reviewDigest: string\n  requestedModel: string\n  servedModel: string\n  assessments: JevReviewAssessment[]\n}\n\nfunction alternatives(question: JevQuestions[string]): string[] {\n  if (question.type === 'noul') return ['true', 'false']\n  return question.type === 'choice'\n    ? Object.keys(question.criteria)\n    : question.criteria.map((_, index) => String(index))\n}\n\n/** Validate before paid admission; make a detached, frozen snapshot without rewriting native JSON. */\nexport function prepareJevReview<const Q extends JevQuestions>(\n  input: JevReviewInput<Q>,\n): PreparedJevReview<Q> {\n  if (!input.version?.trim()) throw new TypeError('Review version is required')\n  parseJevRequest(input.request)\n  // Document form drops only optional undefined object fields; canonicalization rejects loss.\n  const document = jsonDocument(input)\n  canonicalString(document)\n  // Canonical bytes are for hashing, not dispatch: option order can affect a classifier.\n  const snapshot = structuredClone(document) as JevReviewInput<Q>\n  const keys = Object.keys(snapshot.request.questions)\n  if (\n    !snapshot.checks ||\n    Object.keys(snapshot.checks).length !== keys.length ||\n    keys.some((key) => !Object.hasOwn(snapshot.checks, key))\n  ) {\n    throw new TypeError('Review checks must match the exact question names')\n  }\n  for (const key of keys) {\n    const check = checkSchema.parse(snapshot.checks[key])\n    const labels = [...check.supports, ...check.refutes]\n    const allowed = alternatives(snapshot.request.questions[key]!)\n    if (\n      new Set(labels).size !== labels.length ||\n      labels.some((label) => !allowed.includes(label))\n    ) {\n      throw new TypeError('Review alternatives must exist and be disjoint')\n    }\n    if (check.coverage !== 'missing' && check.evidence.length === 0) {\n      throw new TypeError('Review evidence references are required for non-missing coverage')\n    }\n    // Validation must not normalize a label into a different native option.\n    if (canonicalString(jsonDocument(check)) !== canonicalString(snapshot.checks[key])) {\n      throw new TypeError('Review metadata must not require normalization')\n    }\n  }\n  const order = keys.map((key) => [key, alternatives(snapshot.request.questions[key]!)])\n  return deepFreezeCanonicalJson({ ...snapshot, digest: hashCanonical({ snapshot, order }) })\n}\n\n/** Re-score the same retained distribution without new inference or any authorization effect. */\nexport function assessJevReview<Q extends JevQuestions>(\n  review: PreparedJevReview<Q>,\n  raw: unknown,\n): JevReviewReport {\n  const { digest, ...input } = review\n  const prepared = prepareJevReview(input)\n  if (prepared.digest !== digest) throw new TypeError('Review definition changed after preparation')\n  const result = parseJevResult(raw, prepared.request)\n  const assessments = Object.entries(prepared.checks).map(([question, check]) => {\n    const answer = result.answers[question]!\n    const probabilities: Record<string, number> =\n      answer.type === 'noul' ? { true: answer.noul, false: 1 - answer.noul } : answer.probabilities\n    const sum = (labels: string[]) =>\n      labels.reduce((total, label) => total + probabilities[label]!, 0)\n    const supportProbability = sum(check.supports)\n    const refutationProbability = sum(check.refutes)\n    const used = new Set([...check.supports, ...check.refutes])\n    const unresolvedProbability = sum(\n      Object.keys(probabilities).filter((label) => !used.has(label)),\n    )\n    let status: JevReviewAssessment['status'] = 'unresolved'\n    let reason: JevReviewAssessment['reason'] = 'below-threshold'\n    if (supportProbability > 1 || refutationProbability > 1 || unresolvedProbability > 1) {\n      throw new TypeError('Review probability mass exceeds one; do not silently normalize it')\n    }\n    if (check.coverage === 'missing') reason = 'missing-evidence'\n    else if (\n      supportProbability >= check.supportAtLeast &&\n      refutationProbability >= check.refuteAtLeast\n    ) {\n      reason = 'ambiguous-thresholds'\n    } else if (supportProbability >= check.supportAtLeast) {\n      status = 'supported'\n      reason = 'support-threshold'\n    } else if (refutationProbability >= check.refuteAtLeast) {\n      if (check.coverage === 'complete') {\n        status = 'refuted'\n        reason = 'refutation-threshold'\n      } else reason = 'partial-negative-evidence'\n    }\n    return {\n      question,\n      status,\n      reason,\n      supportProbability,\n      refutationProbability,\n      unresolvedProbability,\n      modelConfidence: answer.type === 'noul' ? null : answer.confidence,\n      check: structuredClone(check),\n    }\n  })\n  return {\n    reviewDigest: digest,\n    requestedModel: review.request.model,\n    servedModel: result.model,\n    assessments,\n  }\n}\n\n/** Ordinary analyst findings; a negative review is not a global safety certificate. */\nexport function jevReviewFindings<Q extends JevQuestions>(\n  review: PreparedJevReview<Q>,\n  result: JevResult<Q>,\n  options: { analystId: string; producedAt?: string },\n): AnalystFinding[] {\n  if (!options.analystId.trim()) throw new TypeError('Analyst id is required')\n  const report = assessJevReview(review, result)\n  return report.assessments\n    .filter((item) => item.status !== 'refuted')\n    .map((item) =>\n      makeFinding({\n        analyst_id: options.analystId,\n        ...(options.producedAt === undefined ? {} : { produced_at: options.producedAt }),\n        subject: item.check.subject,\n        area: item.status === 'unresolved' ? 'assessment-coverage' : item.check.area,\n        severity: item.status === 'unresolved' ? 'info' : item.check.severity,\n        claim:\n          item.status === 'supported'\n            ? `Model-supported hypothesis: ${item.check.claim}`\n            : `Unresolved review: ${item.check.claim}`,\n        evidence_refs: structuredClone(item.check.evidence) as EvidenceRef[],\n        // For unresolved findings, confidence describes the deterministic unresolved status only.\n        confidence: item.status === 'supported' ? item.supportProbability : 1,\n        derived_from_judge: true,\n        id_basis: hashCanonical([item.question, item.status, review.version, item.check.claim]),\n        metadata: {\n          review_digest: report.reviewDigest,\n          question: item.question,\n          requested_model: report.requestedModel,\n          served_model: report.servedModel,\n          assessment: item.status,\n          assessment_reason: item.reason,\n          evidence_coverage: item.check.coverage,\n          support_probability: item.supportProbability,\n          refutation_probability: item.refutationProbability,\n          unresolved_probability: item.unresolvedProbability,\n          model_confidence: item.modelConfidence,\n          calibration: 'not-established',\n          confidence_basis:\n            item.status === 'supported' ? 'model-support-mass' : 'deterministic-status',\n          native_answer: structuredClone(result.answers[item.question]),\n        },\n      }),\n    )\n}\n"],"mappings":";;;;;;AAYA,MAAM,OAAO,EAAE,OAAO,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC;AACpC,MAAM,cAAc,EAAE,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AACnD,MAAM,cAAc,EACjB,OAAO;CACN,OAAO;CACP,MAAM;CACN,SAAS;CACT,UAAU,EAAE,KAAK,kBAAkB;;CAEnC,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC;CACnC,SAAS,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC;CAClC,gBAAgB;CAChB,eAAe;;CAEf,UAAU,EAAE,KAAK;EAAC;EAAY;EAAW;CAAS,CAAC;CACnD,UAAU,EAAE,MACV,EACG,OAAO;EACN,MAAM,EAAE,KAAK;GAAC;GAAQ;GAAS;GAAY;GAAW;EAAQ,CAAC;EAC/D,KAAK;EACL,SAAS,EAAE,OAAO,CAAC,CAAC,SAAS;CAC/B,CAAC,CAAC,CACD,OAAO,CACZ;AACF,CAAC,CAAC,CACD,OAAO,CAAC,CACR,QAAQ,UAAU,MAAM,iBAAiB,MAAM,gBAAgB,GAAG,EACjE,SAAS,qDACX,CAAC;AAyCH,SAAS,aAAa,UAA0C;CAC9D,IAAI,SAAS,SAAS,QAAQ,OAAO,CAAC,QAAQ,OAAO;CACrD,OAAO,SAAS,SAAS,WACrB,OAAO,KAAK,SAAS,QAAQ,IAC7B,SAAS,SAAS,KAAK,GAAG,UAAU,OAAO,KAAK,CAAC;AACvD;;AAGA,SAAgB,iBACd,OACsB;CACtB,IAAI,CAAC,MAAM,SAAS,KAAK,GAAG,MAAM,IAAI,UAAU,4BAA4B;CAC5E,gBAAgB,MAAM,OAAO;CAE7B,MAAM,WAAW,aAAa,KAAK;CACnC,gBAAgB,QAAQ;CAExB,MAAM,WAAW,gBAAgB,QAAQ;CACzC,MAAM,OAAO,OAAO,KAAK,SAAS,QAAQ,SAAS;CACnD,IACE,CAAC,SAAS,UACV,OAAO,KAAK,SAAS,MAAM,CAAC,CAAC,WAAW,KAAK,UAC7C,KAAK,MAAM,QAAQ,CAAC,OAAO,OAAO,SAAS,QAAQ,GAAG,CAAC,GAEvD,MAAM,IAAI,UAAU,mDAAmD;CAEzE,KAAK,MAAM,OAAO,MAAM;EACtB,MAAM,QAAQ,YAAY,MAAM,SAAS,OAAO,IAAI;EACpD,MAAM,SAAS,CAAC,GAAG,MAAM,UAAU,GAAG,MAAM,OAAO;EACnD,MAAM,UAAU,aAAa,SAAS,QAAQ,UAAU,IAAK;EAC7D,IACE,IAAI,IAAI,MAAM,CAAC,CAAC,SAAS,OAAO,UAChC,OAAO,MAAM,UAAU,CAAC,QAAQ,SAAS,KAAK,CAAC,GAE/C,MAAM,IAAI,UAAU,gDAAgD;EAEtE,IAAI,MAAM,aAAa,aAAa,MAAM,SAAS,WAAW,GAC5D,MAAM,IAAI,UAAU,kEAAkE;EAGxF,IAAI,gBAAgB,aAAa,KAAK,CAAC,MAAM,gBAAgB,SAAS,OAAO,IAAI,GAC/E,MAAM,IAAI,UAAU,gDAAgD;CAExE;CACA,MAAM,QAAQ,KAAK,KAAK,QAAQ,CAAC,KAAK,aAAa,SAAS,QAAQ,UAAU,IAAK,CAAC,CAAC;CACrF,OAAO,wBAAwB;EAAE,GAAG;EAAU,QAAQ,cAAc;GAAE;GAAU;EAAM,CAAC;CAAE,CAAC;AAC5F;;AAGA,SAAgB,gBACd,QACA,KACiB;CACjB,MAAM,EAAE,QAAQ,GAAG,UAAU;CAC7B,MAAM,WAAW,iBAAiB,KAAK;CACvC,IAAI,SAAS,WAAW,QAAQ,MAAM,IAAI,UAAU,6CAA6C;CACjG,MAAM,SAAS,eAAe,KAAK,SAAS,OAAO;CACnD,MAAM,cAAc,OAAO,QAAQ,SAAS,MAAM,CAAC,CAAC,KAAK,CAAC,UAAU,WAAW;EAC7E,MAAM,SAAS,OAAO,QAAQ;EAC9B,MAAM,gBACJ,OAAO,SAAS,SAAS;GAAE,MAAM,OAAO;GAAM,OAAO,IAAI,OAAO;EAAK,IAAI,OAAO;EAClF,MAAM,OAAO,WACX,OAAO,QAAQ,OAAO,UAAU,QAAQ,cAAc,QAAS,CAAC;EAClE,MAAM,qBAAqB,IAAI,MAAM,QAAQ;EAC7C,MAAM,wBAAwB,IAAI,MAAM,OAAO;EAC/C,MAAM,uBAAO,IAAI,IAAI,CAAC,GAAG,MAAM,UAAU,GAAG,MAAM,OAAO,CAAC;EAC1D,MAAM,wBAAwB,IAC5B,OAAO,KAAK,aAAa,CAAC,CAAC,QAAQ,UAAU,CAAC,KAAK,IAAI,KAAK,CAAC,CAC/D;EACA,IAAI,SAAwC;EAC5C,IAAI,SAAwC;EAC5C,IAAI,qBAAqB,KAAK,wBAAwB,KAAK,wBAAwB,GACjF,MAAM,IAAI,UAAU,mEAAmE;EAEzF,IAAI,MAAM,aAAa,WAAW,SAAS;OACtC,IACH,sBAAsB,MAAM,kBAC5B,yBAAyB,MAAM,eAE/B,SAAS;OACJ,IAAI,sBAAsB,MAAM,gBAAgB;GACrD,SAAS;GACT,SAAS;EACX,OAAO,IAAI,yBAAyB,MAAM,eACxC,IAAI,MAAM,aAAa,YAAY;GACjC,SAAS;GACT,SAAS;EACX,OAAO,SAAS;EAElB,OAAO;GACL;GACA;GACA;GACA;GACA;GACA;GACA,iBAAiB,OAAO,SAAS,SAAS,OAAO,OAAO;GACxD,OAAO,gBAAgB,KAAK;EAC9B;CACF,CAAC;CACD,OAAO;EACL,cAAc;EACd,gBAAgB,OAAO,QAAQ;EAC/B,aAAa,OAAO;EACpB;CACF;AACF;;AAGA,SAAgB,kBACd,QACA,QACA,SACkB;CAClB,IAAI,CAAC,QAAQ,UAAU,KAAK,GAAG,MAAM,IAAI,UAAU,wBAAwB;CAC3E,MAAM,SAAS,gBAAgB,QAAQ,MAAM;CAC7C,OAAO,OAAO,YACX,QAAQ,SAAS,KAAK,WAAW,SAAS,CAAC,CAC3C,KAAK,SACJ,YAAY;EACV,YAAY,QAAQ;EACpB,GAAI,QAAQ,eAAe,KAAA,IAAY,CAAC,IAAI,EAAE,aAAa,QAAQ,WAAW;EAC9E,SAAS,KAAK,MAAM;EACpB,MAAM,KAAK,WAAW,eAAe,wBAAwB,KAAK,MAAM;EACxE,UAAU,KAAK,WAAW,eAAe,SAAS,KAAK,MAAM;EAC7D,OACE,KAAK,WAAW,cACZ,+BAA+B,KAAK,MAAM,UAC1C,sBAAsB,KAAK,MAAM;EACvC,eAAe,gBAAgB,KAAK,MAAM,QAAQ;EAElD,YAAY,KAAK,WAAW,cAAc,KAAK,qBAAqB;EACpE,oBAAoB;EACpB,UAAU,cAAc;GAAC,KAAK;GAAU,KAAK;GAAQ,OAAO;GAAS,KAAK,MAAM;EAAK,CAAC;EACtF,UAAU;GACR,eAAe,OAAO;GACtB,UAAU,KAAK;GACf,iBAAiB,OAAO;GACxB,cAAc,OAAO;GACrB,YAAY,KAAK;GACjB,mBAAmB,KAAK;GACxB,mBAAmB,KAAK,MAAM;GAC9B,qBAAqB,KAAK;GAC1B,wBAAwB,KAAK;GAC7B,wBAAwB,KAAK;GAC7B,kBAAkB,KAAK;GACvB,aAAa;GACb,kBACE,KAAK,WAAW,cAAc,uBAAuB;GACvD,eAAe,gBAAgB,OAAO,QAAQ,KAAK,SAAS;EAC9D;CACF,CAAC,CACH;AACJ"}
+{"version":3,"file":"jev-review-DZEjDzlF.js","names":[],"sources":["../src/jev-review.ts"],"sourcesContent":["import { z } from 'zod'\nimport {\n  ANALYST_SEVERITIES,\n  type AnalystFinding,\n  type EvidenceRef,\n  makeFinding,\n} from './analyst/types'\nimport type { JevQuestions, JevRequest, JevResult } from './jev-protocol'\nimport { parseJevRequest, parseJevResult } from './jev-protocol'\nimport { canonicalString, hashCanonical, jsonDocument } from './ledger-core/canonical'\nimport { deepFreezeCanonicalJson } from './ledger-core/deep-freeze'\n\nconst name = z.string().trim().min(1)\nconst probability = z.number().finite().gt(0).max(1)\nconst checkSchema = z\n  .object({\n    claim: name,\n    area: name,\n    subject: name,\n    severity: z.enum(ANALYST_SEVERITIES),\n    /** Choice labels or score-level keys, never scores invented from category order. */\n    supports: z.array(z.string()).min(1),\n    refutes: z.array(z.string()).min(1),\n    supportAtLeast: probability,\n    refuteAtLeast: probability,\n    /** Host-supplied coverage of the question's required evidence, not model self-assessment. */\n    coverage: z.enum(['complete', 'partial', 'missing']),\n    evidence: z.array(\n      z\n        .object({\n          kind: z.enum(['span', 'event', 'artifact', 'finding', 'metric']),\n          uri: name,\n          excerpt: z.string().optional(),\n        })\n        .strict(),\n    ),\n  })\n  .strict()\n  .refine((value) => value.supportAtLeast + value.refuteAtLeast > 1, {\n    message: 'Support and refutation thresholds must not overlap',\n  })\n\n/** Optional interpretation of native choices/scores. Policy and evidence belong to the caller. */\nexport type JevReviewCheck = z.infer<typeof checkSchema>\nexport interface JevReviewInput<Q extends JevQuestions = JevQuestions> {\n  version: string\n  request: JevRequest<Q>\n  checks: { [K in keyof Q]: JevReviewCheck }\n}\n\nexport interface PreparedJevReview<Q extends JevQuestions = JevQuestions>\n  extends JevReviewInput<Q> {\n  /** Binds questions, option order, context, evidence, thresholds and definition version. */\n  digest: string\n}\n\nexport interface JevReviewAssessment {\n  question: string\n  status: 'supported' | 'refuted' | 'unresolved'\n  reason:\n    | 'support-threshold'\n    | 'refutation-threshold'\n    | 'missing-evidence'\n    | 'partial-negative-evidence'\n    | 'below-threshold'\n    | 'ambiguous-thresholds'\n  /** Unnormalized marginal mass of caller-designated native alternatives. Not calibrated risk. */\n  supportProbability: number\n  refutationProbability: number\n  unresolvedProbability: number\n  modelConfidence: number | null\n  check: JevReviewCheck\n}\n\nexport interface JevReviewReport {\n  reviewDigest: string\n  requestedModel: string\n  servedModel: string\n  assessments: JevReviewAssessment[]\n}\n\nfunction alternatives(question: JevQuestions[string]): string[] {\n  if (question.type === 'noul') return ['true', 'false']\n  return question.type === 'choice'\n    ? Object.keys(question.criteria)\n    : question.criteria.map((_, index) => String(index))\n}\n\n/** Validate before paid admission; make a detached, frozen snapshot without rewriting native JSON. */\nexport function prepareJevReview<const Q extends JevQuestions>(\n  input: JevReviewInput<Q>,\n): PreparedJevReview<Q> {\n  if (!input.version?.trim()) throw new TypeError('Review version is required')\n  parseJevRequest(input.request)\n  // Document form drops only optional undefined object fields; canonicalization rejects loss.\n  const document = jsonDocument(input)\n  canonicalString(document)\n  // Canonical bytes are for hashing, not dispatch: option order can affect a classifier.\n  const snapshot = structuredClone(document) as JevReviewInput<Q>\n  const keys = Object.keys(snapshot.request.questions)\n  if (\n    !snapshot.checks ||\n    Object.keys(snapshot.checks).length !== keys.length ||\n    keys.some((key) => !Object.hasOwn(snapshot.checks, key))\n  ) {\n    throw new TypeError('Review checks must match the exact question names')\n  }\n  for (const key of keys) {\n    const check = checkSchema.parse(snapshot.checks[key])\n    const labels = [...check.supports, ...check.refutes]\n    const allowed = alternatives(snapshot.request.questions[key]!)\n    if (\n      new Set(labels).size !== labels.length ||\n      labels.some((label) => !allowed.includes(label))\n    ) {\n      throw new TypeError('Review alternatives must exist and be disjoint')\n    }\n    if (check.coverage !== 'missing' && check.evidence.length === 0) {\n      throw new TypeError('Review evidence references are required for non-missing coverage')\n    }\n    // Validation must not normalize a label into a different native option.\n    if (canonicalString(jsonDocument(check)) !== canonicalString(snapshot.checks[key])) {\n      throw new TypeError('Review metadata must not require normalization')\n    }\n  }\n  const order = keys.map((key) => [key, alternatives(snapshot.request.questions[key]!)])\n  return deepFreezeCanonicalJson({ ...snapshot, digest: hashCanonical({ snapshot, order }) })\n}\n\n/** Re-score the same retained distribution without new inference or any authorization effect. */\nexport function assessJevReview<Q extends JevQuestions>(\n  review: PreparedJevReview<Q>,\n  raw: unknown,\n): JevReviewReport {\n  const { digest, ...input } = review\n  const prepared = prepareJevReview(input)\n  if (prepared.digest !== digest) throw new TypeError('Review definition changed after preparation')\n  const result = parseJevResult(raw, prepared.request)\n  const assessments = Object.entries(prepared.checks).map(([question, check]) => {\n    const answer = result.answers[question]!\n    const probabilities: Record<string, number> =\n      answer.type === 'noul' ? { true: answer.noul, false: 1 - answer.noul } : answer.probabilities\n    const sum = (labels: string[]) =>\n      labels.reduce((total, label) => total + probabilities[label]!, 0)\n    const supportProbability = sum(check.supports)\n    const refutationProbability = sum(check.refutes)\n    const used = new Set([...check.supports, ...check.refutes])\n    const unresolvedProbability = sum(\n      Object.keys(probabilities).filter((label) => !used.has(label)),\n    )\n    let status: JevReviewAssessment['status'] = 'unresolved'\n    let reason: JevReviewAssessment['reason'] = 'below-threshold'\n    if (supportProbability > 1 || refutationProbability > 1 || unresolvedProbability > 1) {\n      throw new TypeError('Review probability mass exceeds one; do not silently normalize it')\n    }\n    if (check.coverage === 'missing') reason = 'missing-evidence'\n    else if (\n      supportProbability >= check.supportAtLeast &&\n      refutationProbability >= check.refuteAtLeast\n    ) {\n      reason = 'ambiguous-thresholds'\n    } else if (supportProbability >= check.supportAtLeast) {\n      status = 'supported'\n      reason = 'support-threshold'\n    } else if (refutationProbability >= check.refuteAtLeast) {\n      if (check.coverage === 'complete') {\n        status = 'refuted'\n        reason = 'refutation-threshold'\n      } else reason = 'partial-negative-evidence'\n    }\n    return {\n      question,\n      status,\n      reason,\n      supportProbability,\n      refutationProbability,\n      unresolvedProbability,\n      modelConfidence: answer.type === 'noul' ? null : answer.confidence,\n      check: structuredClone(check),\n    }\n  })\n  return {\n    reviewDigest: digest,\n    requestedModel: review.request.model,\n    servedModel: result.model,\n    assessments,\n  }\n}\n\n/** Ordinary analyst findings; a negative review is not a global safety certificate. */\nexport function jevReviewFindings<Q extends JevQuestions>(\n  review: PreparedJevReview<Q>,\n  result: JevResult<Q>,\n  options: { analystId: string; producedAt?: string },\n): AnalystFinding[] {\n  if (!options.analystId.trim()) throw new TypeError('Analyst id is required')\n  const report = assessJevReview(review, result)\n  return report.assessments\n    .filter((item) => item.status !== 'refuted')\n    .map((item) =>\n      makeFinding({\n        analyst_id: options.analystId,\n        ...(options.producedAt === undefined ? {} : { produced_at: options.producedAt }),\n        subject: item.check.subject,\n        area: item.status === 'unresolved' ? 'assessment-coverage' : item.check.area,\n        severity: item.status === 'unresolved' ? 'info' : item.check.severity,\n        claim:\n          item.status === 'supported'\n            ? `Model-supported hypothesis: ${item.check.claim}`\n            : `Unresolved review: ${item.check.claim}`,\n        evidence_refs: structuredClone(item.check.evidence) as EvidenceRef[],\n        // For unresolved findings, confidence describes the deterministic unresolved status only.\n        confidence: item.status === 'supported' ? item.supportProbability : 1,\n        derived_from_judge: true,\n        id_basis: hashCanonical([item.question, item.status, review.version, item.check.claim]),\n        metadata: {\n          review_digest: report.reviewDigest,\n          question: item.question,\n          requested_model: report.requestedModel,\n          served_model: report.servedModel,\n          assessment: item.status,\n          assessment_reason: item.reason,\n          evidence_coverage: item.check.coverage,\n          support_probability: item.supportProbability,\n          refutation_probability: item.refutationProbability,\n          unresolved_probability: item.unresolvedProbability,\n          model_confidence: item.modelConfidence,\n          calibration: 'not-established',\n          confidence_basis:\n            item.status === 'supported' ? 'model-support-mass' : 'deterministic-status',\n          native_answer: structuredClone(result.answers[item.question]),\n        },\n      }),\n    )\n}\n"],"mappings":";;;;;;AAYA,MAAM,OAAO,EAAE,OAAO,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC;AACpC,MAAM,cAAc,EAAE,OAAO,CAAC,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC;AACnD,MAAM,cAAc,EACjB,OAAO;CACN,OAAO;CACP,MAAM;CACN,SAAS;CACT,UAAU,EAAE,KAAK,kBAAkB;;CAEnC,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC;CACnC,SAAS,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC;CAClC,gBAAgB;CAChB,eAAe;;CAEf,UAAU,EAAE,KAAK;EAAC;EAAY;EAAW;CAAS,CAAC;CACnD,UAAU,EAAE,MACV,EACG,OAAO;EACN,MAAM,EAAE,KAAK;GAAC;GAAQ;GAAS;GAAY;GAAW;EAAQ,CAAC;EAC/D,KAAK;EACL,SAAS,EAAE,OAAO,CAAC,CAAC,SAAS;CAC/B,CAAC,CAAC,CACD,OAAO,CACZ;AACF,CAAC,CAAC,CACD,OAAO,CAAC,CACR,QAAQ,UAAU,MAAM,iBAAiB,MAAM,gBAAgB,GAAG,EACjE,SAAS,qDACX,CAAC;AAyCH,SAAS,aAAa,UAA0C;CAC9D,IAAI,SAAS,SAAS,QAAQ,OAAO,CAAC,QAAQ,OAAO;CACrD,OAAO,SAAS,SAAS,WACrB,OAAO,KAAK,SAAS,QAAQ,IAC7B,SAAS,SAAS,KAAK,GAAG,UAAU,OAAO,KAAK,CAAC;AACvD;;AAGA,SAAgB,iBACd,OACsB;CACtB,IAAI,CAAC,MAAM,SAAS,KAAK,GAAG,MAAM,IAAI,UAAU,4BAA4B;CAC5E,gBAAgB,MAAM,OAAO;CAE7B,MAAM,WAAW,aAAa,KAAK;CACnC,gBAAgB,QAAQ;CAExB,MAAM,WAAW,gBAAgB,QAAQ;CACzC,MAAM,OAAO,OAAO,KAAK,SAAS,QAAQ,SAAS;CACnD,IACE,CAAC,SAAS,UACV,OAAO,KAAK,SAAS,MAAM,CAAC,CAAC,WAAW,KAAK,UAC7C,KAAK,MAAM,QAAQ,CAAC,OAAO,OAAO,SAAS,QAAQ,GAAG,CAAC,GAEvD,MAAM,IAAI,UAAU,mDAAmD;CAEzE,KAAK,MAAM,OAAO,MAAM;EACtB,MAAM,QAAQ,YAAY,MAAM,SAAS,OAAO,IAAI;EACpD,MAAM,SAAS,CAAC,GAAG,MAAM,UAAU,GAAG,MAAM,OAAO;EACnD,MAAM,UAAU,aAAa,SAAS,QAAQ,UAAU,IAAK;EAC7D,IACE,IAAI,IAAI,MAAM,CAAC,CAAC,SAAS,OAAO,UAChC,OAAO,MAAM,UAAU,CAAC,QAAQ,SAAS,KAAK,CAAC,GAE/C,MAAM,IAAI,UAAU,gDAAgD;EAEtE,IAAI,MAAM,aAAa,aAAa,MAAM,SAAS,WAAW,GAC5D,MAAM,IAAI,UAAU,kEAAkE;EAGxF,IAAI,gBAAgB,aAAa,KAAK,CAAC,MAAM,gBAAgB,SAAS,OAAO,IAAI,GAC/E,MAAM,IAAI,UAAU,gDAAgD;CAExE;CACA,MAAM,QAAQ,KAAK,KAAK,QAAQ,CAAC,KAAK,aAAa,SAAS,QAAQ,UAAU,IAAK,CAAC,CAAC;CACrF,OAAO,wBAAwB;EAAE,GAAG;EAAU,QAAQ,cAAc;GAAE;GAAU;EAAM,CAAC;CAAE,CAAC;AAC5F;;AAGA,SAAgB,gBACd,QACA,KACiB;CACjB,MAAM,EAAE,QAAQ,GAAG,UAAU;CAC7B,MAAM,WAAW,iBAAiB,KAAK;CACvC,IAAI,SAAS,WAAW,QAAQ,MAAM,IAAI,UAAU,6CAA6C;CACjG,MAAM,SAAS,eAAe,KAAK,SAAS,OAAO;CACnD,MAAM,cAAc,OAAO,QAAQ,SAAS,MAAM,CAAC,CAAC,KAAK,CAAC,UAAU,WAAW;EAC7E,MAAM,SAAS,OAAO,QAAQ;EAC9B,MAAM,gBACJ,OAAO,SAAS,SAAS;GAAE,MAAM,OAAO;GAAM,OAAO,IAAI,OAAO;EAAK,IAAI,OAAO;EAClF,MAAM,OAAO,WACX,OAAO,QAAQ,OAAO,UAAU,QAAQ,cAAc,QAAS,CAAC;EAClE,MAAM,qBAAqB,IAAI,MAAM,QAAQ;EAC7C,MAAM,wBAAwB,IAAI,MAAM,OAAO;EAC/C,MAAM,uBAAO,IAAI,IAAI,CAAC,GAAG,MAAM,UAAU,GAAG,MAAM,OAAO,CAAC;EAC1D,MAAM,wBAAwB,IAC5B,OAAO,KAAK,aAAa,CAAC,CAAC,QAAQ,UAAU,CAAC,KAAK,IAAI,KAAK,CAAC,CAC/D;EACA,IAAI,SAAwC;EAC5C,IAAI,SAAwC;EAC5C,IAAI,qBAAqB,KAAK,wBAAwB,KAAK,wBAAwB,GACjF,MAAM,IAAI,UAAU,mEAAmE;EAEzF,IAAI,MAAM,aAAa,WAAW,SAAS;OACtC,IACH,sBAAsB,MAAM,kBAC5B,yBAAyB,MAAM,eAE/B,SAAS;OACJ,IAAI,sBAAsB,MAAM,gBAAgB;GACrD,SAAS;GACT,SAAS;EACX,OAAO,IAAI,yBAAyB,MAAM,eAAe;GACvD,IAAI,MAAM,aAAa,YAAY;IACjC,SAAS;IACT,SAAS;GACX,OAAO,SAAS;EAClB;EACA,OAAO;GACL;GACA;GACA;GACA;GACA;GACA;GACA,iBAAiB,OAAO,SAAS,SAAS,OAAO,OAAO;GACxD,OAAO,gBAAgB,KAAK;EAC9B;CACF,CAAC;CACD,OAAO;EACL,cAAc;EACd,gBAAgB,OAAO,QAAQ;EAC/B,aAAa,OAAO;EACpB;CACF;AACF;;AAGA,SAAgB,kBACd,QACA,QACA,SACkB;CAClB,IAAI,CAAC,QAAQ,UAAU,KAAK,GAAG,MAAM,IAAI,UAAU,wBAAwB;CAC3E,MAAM,SAAS,gBAAgB,QAAQ,MAAM;CAC7C,OAAO,OAAO,YACX,QAAQ,SAAS,KAAK,WAAW,SAAS,CAAC,CAC3C,KAAK,SACJ,YAAY;EACV,YAAY,QAAQ;EACpB,GAAI,QAAQ,eAAe,KAAA,IAAY,CAAC,IAAI,EAAE,aAAa,QAAQ,WAAW;EAC9E,SAAS,KAAK,MAAM;EACpB,MAAM,KAAK,WAAW,eAAe,wBAAwB,KAAK,MAAM;EACxE,UAAU,KAAK,WAAW,eAAe,SAAS,KAAK,MAAM;EAC7D,OACE,KAAK,WAAW,cACZ,+BAA+B,KAAK,MAAM,UAC1C,sBAAsB,KAAK,MAAM;EACvC,eAAe,gBAAgB,KAAK,MAAM,QAAQ;EAElD,YAAY,KAAK,WAAW,cAAc,KAAK,qBAAqB;EACpE,oBAAoB;EACpB,UAAU,cAAc;GAAC,KAAK;GAAU,KAAK;GAAQ,OAAO;GAAS,KAAK,MAAM;EAAK,CAAC;EACtF,UAAU;GACR,eAAe,OAAO;GACtB,UAAU,KAAK;GACf,iBAAiB,OAAO;GACxB,cAAc,OAAO;GACrB,YAAY,KAAK;GACjB,mBAAmB,KAAK;GACxB,mBAAmB,KAAK,MAAM;GAC9B,qBAAqB,KAAK;GAC1B,wBAAwB,KAAK;GAC7B,wBAAwB,KAAK;GAC7B,kBAAkB,KAAK;GACvB,aAAa;GACb,kBACE,KAAK,WAAW,cAAc,uBAAuB;GACvD,eAAe,gBAAgB,OAAO,QAAQ,KAAK,SAAS;EAC9D;CACF,CAAC,CACH;AACJ"}

package/dist/jev.d.ts

@@ -5,8 +5,8 @@ import { EvaluationAnalystOptions, EvaluationContext, EvaluationJudgeOptions, Ev
 import { a as JevQuestion, c as JevResponseError, d as JevState, f as jevUsage, h as parseJevResult, i as JevJson, l as JevResult, m as parseJevRequest, n as JevAnswerFor, o as JevQuestions, p as parseJevQuestions, r as JevDescription, s as JevRequest, t as JevAnswer, u as JevScoreCriteria } from "./jev-protocol-CpKI7XSu.js";
 import { a as PreparedJevReview, c as prepareJevReview, i as JevReviewReport, n as JevReviewCheck, o as assessJevReview, r as JevReviewInput, s as jevReviewFindings, t as JevReviewAssessment } from "./jev-review-D4ynCORp.js";
 //#region src/jev.d.ts
-type JevEvaluate = EvaluatorOptions<JevRequest, unknown>['execute'];
-interface JevEvaluatorOptions {
+export type JevEvaluate = EvaluatorOptions<JevRequest, unknown>['execute'];
+export interface JevEvaluatorOptions {
   evaluate: JevEvaluate;
   costLedger?: EvaluatorOptions<JevRequest, unknown>['costLedger'];
   maximumCharge?: EvaluatorOptions<JevRequest, unknown>['maximumCharge'];
@@ -17,18 +17,18 @@ interface JevEvaluatorOptions {
   acceptModel?: (requested: string, served: string) => boolean;
 }
 /** Configure transport once; supply native state, questions, and model on every invocation. */
-declare function jevEvaluator(options: JevEvaluatorOptions): <const Q extends JevQuestions>(request: JevRequest<Q>, context?: EvaluationContext) => Promise<EvaluationResult<JevResult<Q>>>;
+export declare function jevEvaluator(options: JevEvaluatorOptions): <const Q extends JevQuestions>(request: JevRequest<Q>, context?: EvaluationContext) => Promise<EvaluationResult<JevResult<Q>>>;
 type Input<A, S extends Scenario> = {
   artifact: A;
   scenario: S;
 };
 type QuestionSource<I, Q extends JevQuestions> = Q | ((input: I) => Q | Promise<Q>);
-interface JevOptions extends JevEvaluatorOptions {
+export interface JevOptions extends JevEvaluatorOptions {
   model: string;
   version: string;
   questions: JevQuestions;
 }
-interface JevJudgeOptions<A, S extends Scenario = Scenario, Q extends JevQuestions = JevQuestions> extends JevEvaluatorOptions {
+export interface JevJudgeOptions<A, S extends Scenario = Scenario, Q extends JevQuestions = JevQuestions> extends JevEvaluatorOptions {
   model: string;
   version: string;
   questions: QuestionSource<Input<A, S>, Q>;
@@ -40,10 +40,10 @@ interface JevJudgeOptions<A, S extends Scenario = Scenario, Q extends JevQuestio
   appliesTo?: (scenario: S) => boolean;
 }
 /** Optional convention. Choice utilities and non-uniform scales belong in an explicit map. */
-declare function normalizedJevScore(result: JevResult, weights?: Record<string, number>): JudgeScore;
+export declare function normalizedJevScore(result: JevResult, weights?: Record<string, number>): JudgeScore;
 /** Convenience around the public evaluator. No domain questions, thresholds, or prose. */
-declare function jevJudge<A, S extends Scenario = Scenario, Q extends JevQuestions = JevQuestions>(name: string, options: JevJudgeOptions<A, S, Q>): JudgeConfig<A, S>;
-interface JevAnalystOptions<I, Q extends JevQuestions = JevQuestions> extends JevEvaluatorOptions {
+export declare function jevJudge<A, S extends Scenario = Scenario, Q extends JevQuestions = JevQuestions>(name: string, options: JevJudgeOptions<A, S, Q>): JudgeConfig<A, S>;
+export interface JevAnalystOptions<I, Q extends JevQuestions = JevQuestions> extends JevEvaluatorOptions {
   id: string;
   description: string;
   inputKind: Analyst<I>['inputKind'];
@@ -54,7 +54,7 @@ interface JevAnalystOptions<I, Q extends JevQuestions = JevQuestions> extends Je
   findings: (value: JevResult<Q>, input: I, context: AnalystContext) => AnalystFinding[] | Promise<AnalystFinding[]>;
   record?: (result: EvaluationResult<JevResult<Q>>, input: I, context: AnalystContext) => void | Promise<void>;
 }
-declare function jevAnalyst<I, Q extends JevQuestions = JevQuestions>(options: JevAnalystOptions<I, Q>): Analyst<I>;
+export declare function jevAnalyst<I, Q extends JevQuestions = JevQuestions>(options: JevAnalystOptions<I, Q>): Analyst<I>;
 //#endregion
-export { EvaluationAnalystOptions, EvaluationContext, EvaluationJudgeOptions, EvaluationResult, Evaluator, EvaluatorOptions, JevAnalystOptions, JevAnswer, JevAnswerFor, JevDescription, JevEvaluate, JevEvaluatorOptions, JevJson, JevJudgeOptions, JevOptions, JevQuestion, JevQuestions, JevRequest, JevResponseError, JevResult, JevReviewAssessment, JevReviewCheck, JevReviewInput, JevReviewReport, JevScoreCriteria, JevState, PreparedJevReview, asAnalyst, asJudge, assessJevReview, createEvaluator, jevAnalyst, jevEvaluator, jevJudge, jevReviewFindings, jevUsage, normalizedJevScore, parseJevQuestions, parseJevRequest, parseJevResult, prepareJevReview };
+export { EvaluationAnalystOptions, EvaluationContext, EvaluationJudgeOptions, EvaluationResult, Evaluator, EvaluatorOptions, JevAnswer, JevAnswerFor, JevDescription, JevJson, JevQuestion, JevQuestions, JevRequest, JevResponseError, JevResult, JevReviewAssessment, JevReviewCheck, JevReviewInput, JevReviewReport, JevScoreCriteria, JevState, PreparedJevReview, asAnalyst, asJudge, assessJevReview, createEvaluator, jevReviewFindings, jevUsage, parseJevQuestions, parseJevRequest, parseJevResult, prepareJevReview };
 //# sourceMappingURL=jev.d.ts.map

package/dist/jev.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"jev.d.ts","names":[],"sources":["../src/jev.ts"],"mappings":";;;;;;;KAeY,cAAc,iBAAiB;UAC1B;EACf,UAAU;EACV,aAAa,iBAAiB;EAC9B,gBAAgB,iBAAiB;EACjC,UAAU;EACV,WAAW,sBAAsB;EACjC,oBAAoB,OAAO,UAAU;;EAErC,eAAe,mBAAmB;;;iBAIpB,aAAa,SAAS,6BA2BhB,UAAU,cAAY,SAC/B,WAAW,IAAE,UACZ,sBACT,QAAQ,iBAAiB,UAAU;KAUnC,MAAM,GAAG,UAAU;EAAc,UAAU;EAAG,UAAU;;KACxD,eAAe,GAAG,UAAU,gBAAgB,MAAM,OAAO,MAAM,IAAI,QAAQ;UAC/D,mBAAmB;EAClC;EACA;EACA,WAAW;;UAEI,gBACf,GACA,UAAU,WAAW,UACrB,UAAU,eAAe,sBACjB;EACR;EACA;EACA,WAAW,eAAe,MAAM,GAAG,IAAI;EACvC,cAAc,OAAO,MAAM,GAAG,IAAI,SAAS,sBAAsB,WAAW,QAAQ;EACpF,aAAa,YAAY,GAAG;EAC5B,UAAU;EACV,OAAO,OAAO,UAAU,IAAI,OAAO,MAAM,GAAG,OAAO,aAAa,QAAQ;EACxE,UAAU,QAAQ,iBAAiB,UAAU,KAAK,OAAO,MAAM,GAAG,cAAc;EAChF,aAAa,UAAU;;;iBA0BT,mBACd,QAAQ,WACR,UAAU,yBACT;;iBAgCa,SAAS,GAAG,UAAU,WAAW,UAAU,UAAU,eAAe,cAClF,cACA,SAAS,gBAAgB,GAAG,GAAG,KAC9B,YAAY,GAAG;UAqDD,kBAAkB,GAAG,UAAU,eAAe,sBACrD;EACR;EACA;EACA,WAAW,QAAQ;EACnB;EACA;EACA,WAAW,MAAM,OAAO,GAAG,SAAS,mBAAmB,IAAI,QAAQ;EACnE,cAAc,OAAO,GAAG,SAAS,mBAAmB,WAAW,QAAQ;EACvE,WACE,OAAO,UAAU,IACjB,OAAO,GACP,SAAS,mBACN,mBAAmB,QAAQ;EAChC,UACE,QAAQ,iBAAiB,UAAU,KACnC,OAAO,GACP,SAAS,0BACC;;iBAGE,WAAW,GAAG,UAAU,eAAe,cACrD,SAAS,kBAAkB,GAAG,KAC7B,QAAQ"}
+{"version":3,"file":"jev.d.ts","names":[],"sources":["../src/jev.ts"],"mappings":";;;;;;;YAeY,cAAc,iBAAiB;iBAC1B;EACf,UAAU;EACV,aAAa,iBAAiB;EAC9B,gBAAgB,iBAAiB;EACjC,UAAU;EACV,WAAW,sBAAsB;EACjC,oBAAoB,OAAO,UAAU;;EAErC,eAAe,mBAAmB;;;wBAIpB,aAAa,SAAS,6BA2BhB,UAAU,cAAY,SAC/B,WAAW,IAAE,UACZ,sBACT,QAAQ,iBAAiB,UAAU;KAUnC,MAAM,GAAG,UAAU;EAAc,UAAU;EAAG,UAAU;;KACxD,eAAe,GAAG,UAAU,gBAAgB,MAAM,OAAO,MAAM,IAAI,QAAQ;iBAC/D,mBAAmB;EAClC;EACA;EACA,WAAW;;iBAEI,gBACf,GACA,UAAU,WAAW,UACrB,UAAU,eAAe,sBACjB;EACR;EACA;EACA,WAAW,eAAe,MAAM,GAAG,IAAI;EACvC,cAAc,OAAO,MAAM,GAAG,IAAI,SAAS,sBAAsB,WAAW,QAAQ;EACpF,aAAa,YAAY,GAAG;EAC5B,UAAU;EACV,OAAO,OAAO,UAAU,IAAI,OAAO,MAAM,GAAG,OAAO,aAAa,QAAQ;EACxE,UAAU,QAAQ,iBAAiB,UAAU,KAAK,OAAO,MAAM,GAAG,cAAc;EAChF,aAAa,UAAU;;;wBA0BT,mBACd,QAAQ,WACR,UAAU,yBACT;;wBAgCa,SAAS,GAAG,UAAU,WAAW,UAAU,UAAU,eAAe,cAClF,cACA,SAAS,gBAAgB,GAAG,GAAG,KAC9B,YAAY,GAAG;iBAqDD,kBAAkB,GAAG,UAAU,eAAe,sBACrD;EACR;EACA;EACA,WAAW,QAAQ;EACnB;EACA;EACA,WAAW,MAAM,OAAO,GAAG,SAAS,mBAAmB,IAAI,QAAQ;EACnE,cAAc,OAAO,GAAG,SAAS,mBAAmB,WAAW,QAAQ;EACvE,WACE,OAAO,UAAU,IACjB,OAAO,GACP,SAAS,mBACN,mBAAmB,QAAQ;EAChC,UACE,QAAQ,iBAAiB,UAAU,KACnC,OAAO,GACP,SAAS,0BACC;;wBAGE,WAAW,GAAG,UAAU,eAAe,cACrD,SAAS,kBAAkB,GAAG,KAC7B,QAAQ"}

package/dist/jev.js

@@ -1,9 +1,9 @@
 import { o as jsonDocument } from "./canonical-BsZVgBhW.js";
-import { s as weightedComposite } from "./descriptive-1V17A-qa.js";
+import { s as weightedComposite } from "./descriptive-D9LUFk1-.js";
 import { n as contentHash } from "./verdict-cache-BQEsVy9n.js";
 import { asAnalyst, asJudge, createEvaluator } from "./evaluation.js";
 import { JevResponseError, jevUsage, parseJevQuestions, parseJevRequest, parseJevResult } from "./jev-protocol.js";
-import { n as jevReviewFindings, r as prepareJevReview, t as assessJevReview } from "./jev-review-Cu9xtIu4.js";
+import { n as jevReviewFindings, r as prepareJevReview, t as assessJevReview } from "./jev-review-DZEjDzlF.js";
 //#region src/jev.ts
 /** Configure transport once; supply native state, questions, and model on every invocation. */
 function jevEvaluator(options) {

package/dist/{judge-calibration-DYmaBtJr.js → judge-calibration-C5zgtiJT.js}

@@ -1,5 +1,5 @@
 import { t as mulberry32 } from "./random-Dn5fPWkt.js";
-import { a as spearmanR, r as pearsonR } from "./descriptive-1V17A-qa.js";
+import { a as spearmanR, r as pearsonR } from "./descriptive-D9LUFk1-.js";
 //#region src/judge-calibration.ts
 /**
 * Judge calibration — measure judge quality against human gold + bias.
@@ -350,4 +350,4 @@ function quantile(sorted, q) {
 //#endregion
 export { selfPreference as a, positionalBias as i, calibrateJudgeContinuous as n, verbosityBias as o, continuousAgreement as r, calibrateJudge as t };
 
-//# sourceMappingURL=judge-calibration-DYmaBtJr.js.map
+//# sourceMappingURL=judge-calibration-C5zgtiJT.js.map

package/dist/{judge-calibration-DYmaBtJr.js.map → judge-calibration-C5zgtiJT.js.map}

@@ -1 +1 @@
-{"version":3,"file":"judge-calibration-DYmaBtJr.js","names":[],"sources":["../src/judge-calibration.ts"],"sourcesContent":["/**\n * Judge calibration — measure judge quality against human gold + bias.\n *\n * Workflow:\n *   1. Build a golden set: {itemId, humanScore}[].\n *   2. Run candidate judges; each produces {itemId, score}.\n *   3. `calibrateJudge(golden, candidate)` reports κ + Pearson + MAE.\n *   4. `calibrateJudgeContinuous(golden, candidate)` adds quadratic-weighted\n *      κ over the un-rounded [0,1] scores plus ICC(2,1), Pearson, Spearman,\n *      and bootstrap CIs — use this for fine-grained judges where rounding\n *      to int discards information (e.g. 0.78 vs 0.81 both round to 1 and\n *      look \"perfectly agreed\" to integer κ).\n *   5. Run bias probes (positional, verbosity, self-preference) to\n *      detect systematic score inflation.\n *   6. For N≥2 judges on the same items, `continuousAgreement(scores)`\n *      reports ICC(2,1) + κ_w + Pearson + Spearman with bootstrap CIs.\n *\n * Returns actionable diagnostics, not a single number. Consumers then\n * decide whether to trust the judge, retrain it, or add a tie-breaker.\n */\n\nimport { pearsonR, spearmanR } from './statistics/descriptive'\nimport { mulberry32 } from './statistics/random'\n\nexport interface GoldenItem {\n  itemId: string\n  humanScore: number\n  /** Optional group used for per-group bias audits (e.g. model-of-output family). */\n  group?: string\n}\n\nexport interface CandidateScore {\n  itemId: string\n  score: number\n  /** Optional — enables positional-bias analysis (did order matter?). */\n  positionOfAInput?: 'first' | 'second'\n}\n\nexport interface CalibrationResult {\n  n: number\n  pearson: number\n  /** Cohen's κ with quadratic weights over integer-rounded scores. */\n  kappa: number\n  /** Mean absolute error vs human. */\n  mae: number\n  /** Worst-5 miscalibrations (largest |judge - human|). */\n  worstItems: Array<{ itemId: string; judge: number; human: number; delta: number }>\n}\n\n/**\n * Measure judge quality against human gold labels: computes Cohen's κ, Pearson correlation, and MAE over matched item ids.\n */\nexport function calibrateJudge(\n  golden: GoldenItem[],\n  candidate: CandidateScore[],\n): CalibrationResult {\n  const map = new Map<string, { h: number; j: number }>()\n  for (const g of golden) map.set(g.itemId, { h: g.humanScore, j: NaN })\n  for (const c of candidate) {\n    const entry = map.get(c.itemId)\n    if (entry) entry.j = c.score\n  }\n  const common = [...map.values()].filter((v) => Number.isFinite(v.j))\n  const n = common.length\n  if (n < 2) {\n    return { n, pearson: NaN, kappa: NaN, mae: NaN, worstItems: [] }\n  }\n  const humans = common.map((c) => c.h)\n  const judges = common.map((c) => c.j)\n  const pearson = pearsonR(humans, judges)\n  const kappa = weightedKappa(humans.map(Math.round), judges.map(Math.round))\n  const absDiffs = common.map((c) => Math.abs(c.j - c.h))\n  const mae = absDiffs.reduce((a, b) => a + b, 0) / n\n  const worst = [...map.entries()]\n    .filter(([, v]) => Number.isFinite(v.j))\n    .map(([itemId, v]) => ({ itemId, judge: v.j, human: v.h, delta: Math.abs(v.j - v.h) }))\n    .sort((a, b) => b.delta - a.delta)\n    .slice(0, 5)\n  return { n, pearson, kappa, mae, worstItems: worst }\n}\n\nexport interface PositionalBiasResult {\n  /**\n   * Score delta (first-position - second-position) averaged across items\n   * presented in both positions. Non-zero = positional bias.\n   */\n  avgDelta: number\n  n: number\n}\n\n/**\n * Feed the same items to the judge twice with A/B swapped and pass all\n * results here. Items that don't appear in both positions are ignored.\n */\nexport function positionalBias(scores: CandidateScore[]): PositionalBiasResult {\n  const pairs = new Map<string, { first?: number; second?: number }>()\n  for (const s of scores) {\n    const slot = pairs.get(s.itemId) ?? {}\n    if (s.positionOfAInput === 'first') slot.first = s.score\n    else if (s.positionOfAInput === 'second') slot.second = s.score\n    pairs.set(s.itemId, slot)\n  }\n  const deltas: number[] = []\n  for (const { first, second } of pairs.values()) {\n    if (first !== undefined && second !== undefined) deltas.push(first - second)\n  }\n  if (deltas.length === 0) return { avgDelta: 0, n: 0 }\n  return { avgDelta: deltas.reduce((a, b) => a + b, 0) / deltas.length, n: deltas.length }\n}\n\nexport interface VerbosityBiasResult {\n  /** Pearson correlation between output length and score. Strong positive = verbosity bias. */\n  pearson: number\n  n: number\n}\n\nexport function verbosityBias(\n  samples: Array<{ outputLen: number; score: number }>,\n): VerbosityBiasResult {\n  const n = samples.length\n  if (n < 3) return { pearson: NaN, n }\n  return {\n    pearson: pearsonR(\n      samples.map((s) => s.outputLen),\n      samples.map((s) => s.score),\n    ),\n    n,\n  }\n}\n\nexport interface SelfPreferenceResult {\n  /** Mean judge score when judge's family matches output's family. */\n  inFamilyMean: number\n  outOfFamilyMean: number\n  deltaMean: number\n  n: number\n}\n\n/**\n * Pass the same scenarios scored with judge-model X grading outputs from\n * model X (in-family) and model Y (out-of-family). Non-zero delta\n * indicates self-preference.\n */\nexport function selfPreference(\n  samples: Array<{ score: number; inFamily: boolean }>,\n): SelfPreferenceResult {\n  const inF = samples.filter((s) => s.inFamily).map((s) => s.score)\n  const outF = samples.filter((s) => !s.inFamily).map((s) => s.score)\n  if (inF.length === 0 || outF.length === 0)\n    return { inFamilyMean: 0, outOfFamilyMean: 0, deltaMean: 0, n: 0 }\n  const inMean = inF.reduce((a, b) => a + b, 0) / inF.length\n  const outMean = outF.reduce((a, b) => a + b, 0) / outF.length\n  return {\n    inFamilyMean: inMean,\n    outOfFamilyMean: outMean,\n    deltaMean: inMean - outMean,\n    n: samples.length,\n  }\n}\n\n// ── Helpers ──────────────────────────────────────────────────────────\n\n/** Quadratic weighted Cohen's κ over bounded integer scores. */\nfunction weightedKappa(a: number[], b: number[]): number {\n  if (a.length !== b.length || a.length === 0) return NaN\n  const min = Math.min(...a, ...b)\n  const max = Math.max(...a, ...b)\n  const K = max - min + 1\n  if (K < 2) return 1\n  const observed: number[][] = Array.from({ length: K }, () => new Array(K).fill(0))\n  const rowMarg = new Array(K).fill(0)\n  const colMarg = new Array(K).fill(0)\n  for (let i = 0; i < a.length; i++) {\n    const ai = a[i]! - min\n    const bi = b[i]! - min\n    const row = observed[ai]!\n    row[bi] = (row[bi] ?? 0) + 1\n    rowMarg[ai]++\n    colMarg[bi]++\n  }\n  let num = 0\n  let den = 0\n  for (let i = 0; i < K; i++) {\n    for (let j = 0; j < K; j++) {\n      const w = (i - j) ** 2 / (K - 1) ** 2\n      const expected = (rowMarg[i] * colMarg[j]) / a.length\n      num += w * observed[i]![j]!\n      den += w * expected\n    }\n  }\n  if (den === 0) return 1\n  return 1 - num / den\n}\n\n// ── Continuous-value inter-rater agreement ──────────────────────────\n//\n// `weightedKappa` above quantises to integers. For [0,1] judges that is\n// lossy: 0.78 and 0.81 both round to 1 and look identical to integer κ.\n// `continuousAgreement` keeps the original magnitudes:\n//\n//   - κ_w   : Cohen's weighted κ generalised to continuous scores. For two\n//             raters, weighted κ = 1 − Σ w_ij·o_ij / Σ w_ij·e_ij collapses\n//             into the closed form below when each \"category\" is the score\n//             itself (Janson & Olsson 2001; Cohen 1968 quadratic weights).\n//   - ICC   : Intraclass Correlation Coefficient, ICC(2,1) per Shrout &\n//             Fleiss (1979) — two-way random effects, absolute agreement,\n//             single rater. The right reliability coefficient when judges\n//             are a random sample of the judge population.\n//   - r, ρ  : Pearson + Spearman for sanity-check. Pearson catches linear\n//             association regardless of scale; Spearman catches monotone\n//             association regardless of distribution.\n//   - CIs   : Bootstrap percentile CIs over items (rows). Bias is preserved\n//             because we resample the full row, i.e. a judge's vector\n//             stays internally consistent within each bootstrap replicate.\n//\n// References:\n//   - Shrout, P. E. & Fleiss, J. L. (1979). Intraclass correlations: uses\n//     in assessing rater reliability. Psychological Bulletin, 86(2), 420.\n//   - McGraw, K. O. & Wong, S. P. (1996). Forming inferences about some\n//     intraclass correlation coefficients. Psychological Methods, 1, 30.\n//   - Janson, H. & Olsson, U. (2001). A measure of agreement for interval\n//     or nominal multivariate observations. Educ. Psychol. Meas., 61, 277.\n\nexport interface ContinuousAgreement {\n  /** Cohen's κ_w with quadratic weights, computed on raw [0,1] scores. */\n  weightedKappa: number\n  /** ICC(2,1): two-way random effects, absolute agreement, single rater. */\n  icc: number\n  /** Pearson product-moment correlation (averaged over rater pairs if N>2). */\n  pearson: number\n  /** Spearman rank correlation (averaged over rater pairs if N>2). */\n  spearman: number\n  /** 95% bootstrap percentile CIs over items. */\n  ci: {\n    icc: [number, number]\n    weightedKappa: [number, number]\n  }\n  /** Number of complete items (no NaN across raters). */\n  n: number\n  /** Number of raters. */\n  raters: number\n}\n\nexport interface ContinuousAgreementOptions {\n  /** Bootstrap iterations. Default 1000. Set to 0 to skip CIs (CI = [NaN, NaN]). */\n  bootstrap?: number\n  /** κ weighting scheme. Default 'quadratic'. */\n  weights?: 'linear' | 'quadratic'\n  /** PRNG seed for reproducible bootstrap. Default 0xC0FFEE. */\n  seed?: number\n  /** Confidence level for percentile CI. Default 0.95. */\n  ciLevel?: number\n}\n\n/**\n * Inter-rater agreement on continuous (typically [0,1]) scores.\n *\n * `scores` has shape [n_items][n_raters]. Rows with any non-finite entry\n * are dropped. Returns NaN metrics if fewer than 2 raters or 2 complete\n * items remain.\n */\nexport function continuousAgreement(\n  scores: number[][],\n  opts: ContinuousAgreementOptions = {},\n): ContinuousAgreement {\n  const bootstrap = opts.bootstrap ?? 1000\n  const weights = opts.weights ?? 'quadratic'\n  const seed = opts.seed ?? 0xc0ffee\n  const ciLevel = opts.ciLevel ?? 0.95\n\n  const matrix = scores.filter((row) => row.length >= 2 && row.every((v) => Number.isFinite(v)))\n  const raters = matrix[0]?.length ?? 0\n  // All rows must have the same rater count, else drop the offenders.\n  const clean = matrix.filter((row) => row.length === raters)\n  const nClean = clean.length\n\n  if (nClean < 2 || raters < 2) {\n    return {\n      weightedKappa: NaN,\n      icc: NaN,\n      pearson: NaN,\n      spearman: NaN,\n      ci: { icc: [NaN, NaN], weightedKappa: [NaN, NaN] },\n      n: nClean,\n      raters,\n    }\n  }\n\n  const kappa = continuousWeightedKappa(clean, weights)\n  const icc = icc21(clean)\n  const pearson = avgPairwise(clean, pearsonR)\n  const spearman = avgPairwise(clean, spearmanR)\n\n  const ciIcc: [number, number] = [NaN, NaN]\n  const ciKappa: [number, number] = [NaN, NaN]\n  if (bootstrap > 0) {\n    const rng = mulberry32(seed)\n    const iccs: number[] = []\n    const kappas: number[] = []\n    for (let b = 0; b < bootstrap; b++) {\n      const sample: number[][] = new Array(nClean)\n      for (let i = 0; i < nClean; i++) {\n        sample[i] = clean[Math.floor(rng() * nClean)]!\n      }\n      const iccB = icc21(sample)\n      const kB = continuousWeightedKappa(sample, weights)\n      if (Number.isFinite(iccB)) iccs.push(iccB)\n      if (Number.isFinite(kB)) kappas.push(kB)\n    }\n    const [lo, hi] = percentileBounds(ciLevel)\n    if (iccs.length > 0) {\n      iccs.sort((a, b) => a - b)\n      ciIcc[0] = quantile(iccs, lo)\n      ciIcc[1] = quantile(iccs, hi)\n    }\n    if (kappas.length > 0) {\n      kappas.sort((a, b) => a - b)\n      ciKappa[0] = quantile(kappas, lo)\n      ciKappa[1] = quantile(kappas, hi)\n    }\n  }\n\n  return {\n    weightedKappa: kappa,\n    icc,\n    pearson,\n    spearman,\n    ci: { icc: ciIcc, weightedKappa: ciKappa },\n    n: nClean,\n    raters,\n  }\n}\n\nexport interface ContinuousCalibrationResult extends CalibrationResult {\n  /** Cohen's κ_w computed on raw (un-rounded) scores. */\n  weightedKappaContinuous: number\n  /** ICC(2,1) treating golden + candidate as two raters. */\n  icc: number\n  spearman: number\n  ci: {\n    icc: [number, number]\n    weightedKappa: [number, number]\n  }\n}\n\n/**\n * Extends `calibrateJudge` with continuous-value agreement metrics while\n * retaining its base calibration summary.\n */\nexport function calibrateJudgeContinuous(\n  golden: GoldenItem[],\n  candidate: CandidateScore[],\n  opts: ContinuousAgreementOptions = {},\n): ContinuousCalibrationResult {\n  const base = calibrateJudge(golden, candidate)\n  const map = new Map<string, { h: number; j: number }>()\n  for (const g of golden) map.set(g.itemId, { h: g.humanScore, j: NaN })\n  for (const c of candidate) {\n    const entry = map.get(c.itemId)\n    if (entry) entry.j = c.score\n  }\n  const rows: number[][] = []\n  for (const v of map.values()) {\n    if (Number.isFinite(v.j)) rows.push([v.h, v.j])\n  }\n  const agreement = continuousAgreement(rows, opts)\n  return {\n    ...base,\n    weightedKappaContinuous: agreement.weightedKappa,\n    icc: agreement.icc,\n    spearman: agreement.spearman,\n    ci: agreement.ci,\n  }\n}\n\n// ── Continuous-agreement internals ──────────────────────────────────\n\n/**\n * Quadratic-weighted κ on continuous scores. With weights w(x,y) = (x-y)^2\n * (or |x-y| for linear) the formula collapses to:\n *\n *   κ_w = 1 − E_obs[w] / E_exp[w]\n *\n * where E_obs averages w over paired (a_i, b_i) and E_exp averages w over\n * the independent product distribution (sum_{i,j} w(a_i, b_j) / n^2).\n * The normalisation by (max-min)^2 in the integer version cancels in the\n * ratio, so we don't need it here. Generalises to N raters by averaging κ_w\n * over all rater pairs (mean pairwise weighted agreement).\n */\nfunction continuousWeightedKappa(rows: number[][], scheme: 'linear' | 'quadratic'): number {\n  if (rows.length === 0) return NaN\n  const raters = rows[0]!.length\n  if (raters < 2) return NaN\n  const wFn =\n    scheme === 'linear'\n      ? (x: number, y: number) => Math.abs(x - y)\n      : (x: number, y: number) => (x - y) ** 2\n  let sum = 0\n  let pairs = 0\n  for (let r1 = 0; r1 < raters; r1++) {\n    for (let r2 = r1 + 1; r2 < raters; r2++) {\n      const a = rows.map((row) => row[r1]!)\n      const b = rows.map((row) => row[r2]!)\n      const n = a.length\n      let obs = 0\n      for (let i = 0; i < n; i++) obs += wFn(a[i]!, b[i]!)\n      obs /= n\n      // Expected under independence: average of w over all i,j cross pairs.\n      let exp = 0\n      for (let i = 0; i < n; i++) {\n        for (let j = 0; j < n; j++) exp += wFn(a[i]!, b[j]!)\n      }\n      exp /= n * n\n      if (exp === 0) {\n        // Degenerate: at least one rater is constant. Convention: perfect\n        // agreement iff observed disagreement is also zero, else 0.\n        sum += obs === 0 ? 1 : 0\n      } else {\n        sum += 1 - obs / exp\n      }\n      pairs++\n    }\n  }\n  return pairs === 0 ? NaN : sum / pairs\n}\n\n/**\n * ICC(2,1) — two-way random effects, absolute agreement, single rater.\n *\n *   ICC(2,1) = (MSR − MSE) / (MSR + (k−1)·MSE + k·(MSC − MSE)/n)\n *\n * where MSR = between-rows MS, MSC = between-columns MS, MSE = residual MS,\n * n = rows (items), k = columns (raters).\n */\nfunction icc21(rows: number[][]): number {\n  const n = rows.length\n  if (n < 2) return NaN\n  const k = rows[0]!.length\n  if (k < 2) return NaN\n\n  // Row means.\n  const rowMeans = rows.map((row) => row.reduce((s, v) => s + v, 0) / k)\n  // Column means.\n  const colMeans = new Array(k).fill(0)\n  for (let j = 0; j < k; j++) {\n    let s = 0\n    for (let i = 0; i < n; i++) s += rows[i]![j]!\n    colMeans[j] = s / n\n  }\n  // Grand mean.\n  let grand = 0\n  for (let i = 0; i < n; i++) grand += rowMeans[i]!\n  grand /= n\n\n  let ssR = 0\n  for (let i = 0; i < n; i++) ssR += (rowMeans[i]! - grand) ** 2\n  ssR *= k\n  let ssC = 0\n  for (let j = 0; j < k; j++) ssC += (colMeans[j]! - grand) ** 2\n  ssC *= n\n  let ssT = 0\n  for (let i = 0; i < n; i++) {\n    for (let j = 0; j < k; j++) ssT += (rows[i]![j]! - grand) ** 2\n  }\n  const ssE = ssT - ssR - ssC\n\n  const dfR = n - 1\n  const dfC = k - 1\n  const dfE = (n - 1) * (k - 1)\n  const msR = ssR / dfR\n  const msC = ssC / dfC\n  const msE = dfE > 0 ? ssE / dfE : 0\n\n  const denom = msR + (k - 1) * msE + (k * (msC - msE)) / n\n  if (denom === 0) {\n    // Degenerate (all values equal): convention = 1 if rows identical,\n    // else 0. Identical rows ⇒ msR = 0 too, so msR − msE near 0.\n    return msR === 0 && msE === 0 ? 1 : 0\n  }\n  return (msR - msE) / denom\n}\n\n/** Average pairwise statistic over all rater pairs. */\nfunction avgPairwise(rows: number[][], fn: (a: number[], b: number[]) => number): number {\n  const k = rows[0]?.length ?? 0\n  if (k < 2) return NaN\n  let sum = 0\n  let pairs = 0\n  for (let i = 0; i < k; i++) {\n    for (let j = i + 1; j < k; j++) {\n      const a = rows.map((row) => row[i]!)\n      const b = rows.map((row) => row[j]!)\n      const r = fn(a, b)\n      if (Number.isFinite(r)) {\n        sum += r\n        pairs++\n      }\n    }\n  }\n  return pairs === 0 ? NaN : sum / pairs\n}\n\nfunction percentileBounds(ciLevel: number): [number, number] {\n  const tail = (1 - ciLevel) / 2\n  return [tail, 1 - tail]\n}\n\n/** Linear-interpolated quantile of a pre-sorted ascending array. */\nfunction quantile(sorted: number[], q: number): number {\n  if (sorted.length === 0) return NaN\n  if (sorted.length === 1) return sorted[0]!\n  const pos = q * (sorted.length - 1)\n  const lo = Math.floor(pos)\n  const hi = Math.ceil(pos)\n  if (lo === hi) return sorted[lo]!\n  const frac = pos - lo\n  return sorted[lo]! * (1 - frac) + sorted[hi]! * frac\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;AAoDA,SAAgB,eACd,QACA,WACmB;CACnB,MAAM,sBAAM,IAAI,IAAsC;CACtD,KAAK,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,QAAQ;EAAE,GAAG,EAAE;EAAY,GAAG;CAAI,CAAC;CACrE,KAAK,MAAM,KAAK,WAAW;EACzB,MAAM,QAAQ,IAAI,IAAI,EAAE,MAAM;EAC9B,IAAI,OAAO,MAAM,IAAI,EAAE;CACzB;CACA,MAAM,SAAS,CAAC,GAAG,IAAI,OAAO,CAAC,CAAC,CAAC,QAAQ,MAAM,OAAO,SAAS,EAAE,CAAC,CAAC;CACnE,MAAM,IAAI,OAAO;CACjB,IAAI,IAAI,GACN,OAAO;EAAE;EAAG,SAAS;EAAK,OAAO;EAAK,KAAK;EAAK,YAAY,CAAC;CAAE;CAEjE,MAAM,SAAS,OAAO,KAAK,MAAM,EAAE,CAAC;CACpC,MAAM,SAAS,OAAO,KAAK,MAAM,EAAE,CAAC;CAUpC,OAAO;EAAE;EAAG,SATI,SAAS,QAAQ,MASf;EAAG,OARP,cAAc,OAAO,IAAI,KAAK,KAAK,GAAG,OAAO,IAAI,KAAK,KAAK,CAQhD;EAAG,KAPX,OAAO,KAAK,MAAM,KAAK,IAAI,EAAE,IAAI,EAAE,CAAC,CAClC,CAAC,CAAC,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;EAMjB,YALnB,CAAC,GAAG,IAAI,QAAQ,CAAC,CAAC,CAC7B,QAAQ,GAAG,OAAO,OAAO,SAAS,EAAE,CAAC,CAAC,CAAC,CACvC,KAAK,CAAC,QAAQ,QAAQ;GAAE;GAAQ,OAAO,EAAE;GAAG,OAAO,EAAE;GAAG,OAAO,KAAK,IAAI,EAAE,IAAI,EAAE,CAAC;EAAE,EAAE,CAAC,CACtF,MAAM,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CACjC,MAAM,GAAG,CACqC;CAAE;AACrD;;;;;AAeA,SAAgB,eAAe,QAAgD;CAC7E,MAAM,wBAAQ,IAAI,IAAiD;CACnE,KAAK,MAAM,KAAK,QAAQ;EACtB,MAAM,OAAO,MAAM,IAAI,EAAE,MAAM,KAAK,CAAC;EACrC,IAAI,EAAE,qBAAqB,SAAS,KAAK,QAAQ,EAAE;OAC9C,IAAI,EAAE,qBAAqB,UAAU,KAAK,SAAS,EAAE;EAC1D,MAAM,IAAI,EAAE,QAAQ,IAAI;CAC1B;CACA,MAAM,SAAmB,CAAC;CAC1B,KAAK,MAAM,EAAE,OAAO,YAAY,MAAM,OAAO,GAC3C,IAAI,UAAU,KAAA,KAAa,WAAW,KAAA,GAAW,OAAO,KAAK,QAAQ,MAAM;CAE7E,IAAI,OAAO,WAAW,GAAG,OAAO;EAAE,UAAU;EAAG,GAAG;CAAE;CACpD,OAAO;EAAE,UAAU,OAAO,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,OAAO;EAAQ,GAAG,OAAO;CAAO;AACzF;AAQA,SAAgB,cACd,SACqB;CACrB,MAAM,IAAI,QAAQ;CAClB,IAAI,IAAI,GAAG,OAAO;EAAE,SAAS;EAAK;CAAE;CACpC,OAAO;EACL,SAAS,SACP,QAAQ,KAAK,MAAM,EAAE,SAAS,GAC9B,QAAQ,KAAK,MAAM,EAAE,KAAK,CAC5B;EACA;CACF;AACF;;;;;;AAeA,SAAgB,eACd,SACsB;CACtB,MAAM,MAAM,QAAQ,QAAQ,MAAM,EAAE,QAAQ,CAAC,CAAC,KAAK,MAAM,EAAE,KAAK;CAChE,MAAM,OAAO,QAAQ,QAAQ,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,MAAM,EAAE,KAAK;CAClE,IAAI,IAAI,WAAW,KAAK,KAAK,WAAW,GACtC,OAAO;EAAE,cAAc;EAAG,iBAAiB;EAAG,WAAW;EAAG,GAAG;CAAE;CACnE,MAAM,SAAS,IAAI,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,IAAI;CACpD,MAAM,UAAU,KAAK,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,KAAK;CACvD,OAAO;EACL,cAAc;EACd,iBAAiB;EACjB,WAAW,SAAS;EACpB,GAAG,QAAQ;CACb;AACF;;AAKA,SAAS,cAAc,GAAa,GAAqB;CACvD,IAAI,EAAE,WAAW,EAAE,UAAU,EAAE,WAAW,GAAG,OAAO;CACpD,MAAM,MAAM,KAAK,IAAI,GAAG,GAAG,GAAG,CAAC;CAE/B,MAAM,IADM,KAAK,IAAI,GAAG,GAAG,GAAG,CAClB,IAAI,MAAM;CACtB,IAAI,IAAI,GAAG,OAAO;CAClB,MAAM,WAAuB,MAAM,KAAK,EAAE,QAAQ,EAAE,SAAS,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;CACjF,MAAM,UAAU,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACnC,MAAM,UAAU,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACnC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;EACjC,MAAM,KAAK,EAAE,KAAM;EACnB,MAAM,KAAK,EAAE,KAAM;EACnB,MAAM,MAAM,SAAS;EACrB,IAAI,OAAO,IAAI,OAAO,KAAK;EAC3B,QAAQ,GAAG;EACX,QAAQ,GAAG;CACb;CACA,IAAI,MAAM;CACV,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAC1B,MAAM,KAAK,IAAI,MAAM,KAAK,IAAI,MAAM;EACpC,MAAM,WAAY,QAAQ,KAAK,QAAQ,KAAM,EAAE;EAC/C,OAAO,IAAI,SAAS,EAAE,CAAE;EACxB,OAAO,IAAI;CACb;CAEF,IAAI,QAAQ,GAAG,OAAO;CACtB,OAAO,IAAI,MAAM;AACnB;;;;;;;;AAqEA,SAAgB,oBACd,QACA,OAAmC,CAAC,GACf;CACrB,MAAM,YAAY,KAAK,aAAa;CACpC,MAAM,UAAU,KAAK,WAAW;CAChC,MAAM,OAAO,KAAK,QAAQ;CAC1B,MAAM,UAAU,KAAK,WAAW;CAEhC,MAAM,SAAS,OAAO,QAAQ,QAAQ,IAAI,UAAU,KAAK,IAAI,OAAO,MAAM,OAAO,SAAS,CAAC,CAAC,CAAC;CAC7F,MAAM,SAAS,OAAO,EAAE,EAAE,UAAU;CAEpC,MAAM,QAAQ,OAAO,QAAQ,QAAQ,IAAI,WAAW,MAAM;CAC1D,MAAM,SAAS,MAAM;CAErB,IAAI,SAAS,KAAK,SAAS,GACzB,OAAO;EACL,eAAe;EACf,KAAK;EACL,SAAS;EACT,UAAU;EACV,IAAI;GAAE,KAAK,CAAC,KAAK,GAAG;GAAG,eAAe,CAAC,KAAK,GAAG;EAAE;EACjD,GAAG;EACH;CACF;CAGF,MAAM,QAAQ,wBAAwB,OAAO,OAAO;CACpD,MAAM,MAAM,MAAM,KAAK;CACvB,MAAM,UAAU,YAAY,OAAO,QAAQ;CAC3C,MAAM,WAAW,YAAY,OAAO,SAAS;CAE7C,MAAM,QAA0B,CAAC,KAAK,GAAG;CACzC,MAAM,UAA4B,CAAC,KAAK,GAAG;CAC3C,IAAI,YAAY,GAAG;EACjB,MAAM,MAAM,WAAW,IAAI;EAC3B,MAAM,OAAiB,CAAC;EACxB,MAAM,SAAmB,CAAC;EAC1B,KAAK,IAAI,IAAI,GAAG,IAAI,WAAW,KAAK;GAClC,MAAM,SAAqB,IAAI,MAAM,MAAM;GAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,QAAQ,KAC1B,OAAO,KAAK,MAAM,KAAK,MAAM,IAAI,IAAI,MAAM;GAE7C,MAAM,OAAO,MAAM,MAAM;GACzB,MAAM,KAAK,wBAAwB,QAAQ,OAAO;GAClD,IAAI,OAAO,SAAS,IAAI,GAAG,KAAK,KAAK,IAAI;GACzC,IAAI,OAAO,SAAS,EAAE,GAAG,OAAO,KAAK,EAAE;EACzC;EACA,MAAM,CAAC,IAAI,MAAM,iBAAiB,OAAO;EACzC,IAAI,KAAK,SAAS,GAAG;GACnB,KAAK,MAAM,GAAG,MAAM,IAAI,CAAC;GACzB,MAAM,KAAK,SAAS,MAAM,EAAE;GAC5B,MAAM,KAAK,SAAS,MAAM,EAAE;EAC9B;EACA,IAAI,OAAO,SAAS,GAAG;GACrB,OAAO,MAAM,GAAG,MAAM,IAAI,CAAC;GAC3B,QAAQ,KAAK,SAAS,QAAQ,EAAE;GAChC,QAAQ,KAAK,SAAS,QAAQ,EAAE;EAClC;CACF;CAEA,OAAO;EACL,eAAe;EACf;EACA;EACA;EACA,IAAI;GAAE,KAAK;GAAO,eAAe;EAAQ;EACzC,GAAG;EACH;CACF;AACF;;;;;AAkBA,SAAgB,yBACd,QACA,WACA,OAAmC,CAAC,GACP;CAC7B,MAAM,OAAO,eAAe,QAAQ,SAAS;CAC7C,MAAM,sBAAM,IAAI,IAAsC;CACtD,KAAK,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,QAAQ;EAAE,GAAG,EAAE;EAAY,GAAG;CAAI,CAAC;CACrE,KAAK,MAAM,KAAK,WAAW;EACzB,MAAM,QAAQ,IAAI,IAAI,EAAE,MAAM;EAC9B,IAAI,OAAO,MAAM,IAAI,EAAE;CACzB;CACA,MAAM,OAAmB,CAAC;CAC1B,KAAK,MAAM,KAAK,IAAI,OAAO,GACzB,IAAI,OAAO,SAAS,EAAE,CAAC,GAAG,KAAK,KAAK,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC;CAEhD,MAAM,YAAY,oBAAoB,MAAM,IAAI;CAChD,OAAO;EACL,GAAG;EACH,yBAAyB,UAAU;EACnC,KAAK,UAAU;EACf,UAAU,UAAU;EACpB,IAAI,UAAU;CAChB;AACF;;;;;;;;;;;;;AAgBA,SAAS,wBAAwB,MAAkB,QAAwC;CACzF,IAAI,KAAK,WAAW,GAAG,OAAO;CAC9B,MAAM,SAAS,KAAK,EAAE,CAAE;CACxB,IAAI,SAAS,GAAG,OAAO;CACvB,MAAM,MACJ,WAAW,YACN,GAAW,MAAc,KAAK,IAAI,IAAI,CAAC,KACvC,GAAW,OAAe,IAAI,MAAM;CAC3C,IAAI,MAAM;CACV,IAAI,QAAQ;CACZ,KAAK,IAAI,KAAK,GAAG,KAAK,QAAQ,MAC5B,KAAK,IAAI,KAAK,KAAK,GAAG,KAAK,QAAQ,MAAM;EACvC,MAAM,IAAI,KAAK,KAAK,QAAQ,IAAI,GAAI;EACpC,MAAM,IAAI,KAAK,KAAK,QAAQ,IAAI,GAAI;EACpC,MAAM,IAAI,EAAE;EACZ,IAAI,MAAM;EACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,OAAO,IAAI,EAAE,IAAK,EAAE,EAAG;EACnD,OAAO;EAEP,IAAI,MAAM;EACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,OAAO,IAAI,EAAE,IAAK,EAAE,EAAG;EAErD,OAAO,IAAI;EACX,IAAI,QAAQ,GAGV,OAAO,QAAQ,IAAI,IAAI;OAEvB,OAAO,IAAI,MAAM;EAEnB;CACF;CAEF,OAAO,UAAU,IAAI,MAAM,MAAM;AACnC;;;;;;;;;AAUA,SAAS,MAAM,MAA0B;CACvC,MAAM,IAAI,KAAK;CACf,IAAI,IAAI,GAAG,OAAO;CAClB,MAAM,IAAI,KAAK,EAAE,CAAE;CACnB,IAAI,IAAI,GAAG,OAAO;CAGlB,MAAM,WAAW,KAAK,KAAK,QAAQ,IAAI,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC;CAErE,MAAM,WAAW,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACpC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAC1B,IAAI,IAAI;EACR,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE,CAAE;EAC1C,SAAS,KAAK,IAAI;CACpB;CAEA,IAAI,QAAQ;CACZ,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,SAAS,SAAS;CAC9C,SAAS;CAET,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,SAAS,KAAM,UAAU;CAC7D,OAAO;CACP,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,SAAS,KAAM,UAAU;CAC7D,OAAO;CACP,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,KAAK,EAAE,CAAE,KAAM,UAAU;CAE/D,MAAM,MAAM,MAAM,MAAM;CAExB,MAAM,MAAM,IAAI;CAChB,MAAM,MAAM,IAAI;CAChB,MAAM,OAAO,IAAI,MAAM,IAAI;CAC3B,MAAM,MAAM,MAAM;CAClB,MAAM,MAAM,MAAM;CAClB,MAAM,MAAM,MAAM,IAAI,MAAM,MAAM;CAElC,MAAM,QAAQ,OAAO,IAAI,KAAK,MAAO,KAAK,MAAM,OAAQ;CACxD,IAAI,UAAU,GAGZ,OAAO,QAAQ,KAAK,QAAQ,IAAI,IAAI;CAEtC,QAAQ,MAAM,OAAO;AACvB;;AAGA,SAAS,YAAY,MAAkB,IAAkD;CACvF,MAAM,IAAI,KAAK,EAAE,EAAE,UAAU;CAC7B,IAAI,IAAI,GAAG,OAAO;CAClB,IAAI,MAAM;CACV,IAAI,QAAQ;CACZ,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAG9B,MAAM,IAAI,GAFA,KAAK,KAAK,QAAQ,IAAI,EAEnB,GADH,KAAK,KAAK,QAAQ,IAAI,EAChB,CAAC;EACjB,IAAI,OAAO,SAAS,CAAC,GAAG;GACtB,OAAO;GACP;EACF;CACF;CAEF,OAAO,UAAU,IAAI,MAAM,MAAM;AACnC;AAEA,SAAS,iBAAiB,SAAmC;CAC3D,MAAM,QAAQ,IAAI,WAAW;CAC7B,OAAO,CAAC,MAAM,IAAI,IAAI;AACxB;;AAGA,SAAS,SAAS,QAAkB,GAAmB;CACrD,IAAI,OAAO,WAAW,GAAG,OAAO;CAChC,IAAI,OAAO,WAAW,GAAG,OAAO,OAAO;CACvC,MAAM,MAAM,KAAK,OAAO,SAAS;CACjC,MAAM,KAAK,KAAK,MAAM,GAAG;CACzB,MAAM,KAAK,KAAK,KAAK,GAAG;CACxB,IAAI,OAAO,IAAI,OAAO,OAAO;CAC7B,MAAM,OAAO,MAAM;CACnB,OAAO,OAAO,OAAQ,IAAI,QAAQ,OAAO,MAAO;AAClD"}
+{"version":3,"file":"judge-calibration-C5zgtiJT.js","names":[],"sources":["../src/judge-calibration.ts"],"sourcesContent":["/**\n * Judge calibration — measure judge quality against human gold + bias.\n *\n * Workflow:\n *   1. Build a golden set: {itemId, humanScore}[].\n *   2. Run candidate judges; each produces {itemId, score}.\n *   3. `calibrateJudge(golden, candidate)` reports κ + Pearson + MAE.\n *   4. `calibrateJudgeContinuous(golden, candidate)` adds quadratic-weighted\n *      κ over the un-rounded [0,1] scores plus ICC(2,1), Pearson, Spearman,\n *      and bootstrap CIs — use this for fine-grained judges where rounding\n *      to int discards information (e.g. 0.78 vs 0.81 both round to 1 and\n *      look \"perfectly agreed\" to integer κ).\n *   5. Run bias probes (positional, verbosity, self-preference) to\n *      detect systematic score inflation.\n *   6. For N≥2 judges on the same items, `continuousAgreement(scores)`\n *      reports ICC(2,1) + κ_w + Pearson + Spearman with bootstrap CIs.\n *\n * Returns actionable diagnostics, not a single number. Consumers then\n * decide whether to trust the judge, retrain it, or add a tie-breaker.\n */\n\nimport { pearsonR, spearmanR } from './statistics/descriptive'\nimport { mulberry32 } from './statistics/random'\n\nexport interface GoldenItem {\n  itemId: string\n  humanScore: number\n  /** Optional group used for per-group bias audits (e.g. model-of-output family). */\n  group?: string\n}\n\nexport interface CandidateScore {\n  itemId: string\n  score: number\n  /** Optional — enables positional-bias analysis (did order matter?). */\n  positionOfAInput?: 'first' | 'second'\n}\n\nexport interface CalibrationResult {\n  n: number\n  pearson: number\n  /** Cohen's κ with quadratic weights over integer-rounded scores. */\n  kappa: number\n  /** Mean absolute error vs human. */\n  mae: number\n  /** Worst-5 miscalibrations (largest |judge - human|). */\n  worstItems: Array<{ itemId: string; judge: number; human: number; delta: number }>\n}\n\n/**\n * Measure judge quality against human gold labels: computes Cohen's κ, Pearson correlation, and MAE over matched item ids.\n */\nexport function calibrateJudge(\n  golden: GoldenItem[],\n  candidate: CandidateScore[],\n): CalibrationResult {\n  const map = new Map<string, { h: number; j: number }>()\n  for (const g of golden) map.set(g.itemId, { h: g.humanScore, j: NaN })\n  for (const c of candidate) {\n    const entry = map.get(c.itemId)\n    if (entry) entry.j = c.score\n  }\n  const common = [...map.values()].filter((v) => Number.isFinite(v.j))\n  const n = common.length\n  if (n < 2) {\n    return { n, pearson: NaN, kappa: NaN, mae: NaN, worstItems: [] }\n  }\n  const humans = common.map((c) => c.h)\n  const judges = common.map((c) => c.j)\n  const pearson = pearsonR(humans, judges)\n  const kappa = weightedKappa(humans.map(Math.round), judges.map(Math.round))\n  const absDiffs = common.map((c) => Math.abs(c.j - c.h))\n  const mae = absDiffs.reduce((a, b) => a + b, 0) / n\n  const worst = [...map.entries()]\n    .filter(([, v]) => Number.isFinite(v.j))\n    .map(([itemId, v]) => ({ itemId, judge: v.j, human: v.h, delta: Math.abs(v.j - v.h) }))\n    .sort((a, b) => b.delta - a.delta)\n    .slice(0, 5)\n  return { n, pearson, kappa, mae, worstItems: worst }\n}\n\nexport interface PositionalBiasResult {\n  /**\n   * Score delta (first-position - second-position) averaged across items\n   * presented in both positions. Non-zero = positional bias.\n   */\n  avgDelta: number\n  n: number\n}\n\n/**\n * Feed the same items to the judge twice with A/B swapped and pass all\n * results here. Items that don't appear in both positions are ignored.\n */\nexport function positionalBias(scores: CandidateScore[]): PositionalBiasResult {\n  const pairs = new Map<string, { first?: number; second?: number }>()\n  for (const s of scores) {\n    const slot = pairs.get(s.itemId) ?? {}\n    if (s.positionOfAInput === 'first') slot.first = s.score\n    else if (s.positionOfAInput === 'second') slot.second = s.score\n    pairs.set(s.itemId, slot)\n  }\n  const deltas: number[] = []\n  for (const { first, second } of pairs.values()) {\n    if (first !== undefined && second !== undefined) deltas.push(first - second)\n  }\n  if (deltas.length === 0) return { avgDelta: 0, n: 0 }\n  return { avgDelta: deltas.reduce((a, b) => a + b, 0) / deltas.length, n: deltas.length }\n}\n\nexport interface VerbosityBiasResult {\n  /** Pearson correlation between output length and score. Strong positive = verbosity bias. */\n  pearson: number\n  n: number\n}\n\nexport function verbosityBias(\n  samples: Array<{ outputLen: number; score: number }>,\n): VerbosityBiasResult {\n  const n = samples.length\n  if (n < 3) return { pearson: NaN, n }\n  return {\n    pearson: pearsonR(\n      samples.map((s) => s.outputLen),\n      samples.map((s) => s.score),\n    ),\n    n,\n  }\n}\n\nexport interface SelfPreferenceResult {\n  /** Mean judge score when judge's family matches output's family. */\n  inFamilyMean: number\n  outOfFamilyMean: number\n  deltaMean: number\n  n: number\n}\n\n/**\n * Pass the same scenarios scored with judge-model X grading outputs from\n * model X (in-family) and model Y (out-of-family). Non-zero delta\n * indicates self-preference.\n */\nexport function selfPreference(\n  samples: Array<{ score: number; inFamily: boolean }>,\n): SelfPreferenceResult {\n  const inF = samples.filter((s) => s.inFamily).map((s) => s.score)\n  const outF = samples.filter((s) => !s.inFamily).map((s) => s.score)\n  if (inF.length === 0 || outF.length === 0)\n    return { inFamilyMean: 0, outOfFamilyMean: 0, deltaMean: 0, n: 0 }\n  const inMean = inF.reduce((a, b) => a + b, 0) / inF.length\n  const outMean = outF.reduce((a, b) => a + b, 0) / outF.length\n  return {\n    inFamilyMean: inMean,\n    outOfFamilyMean: outMean,\n    deltaMean: inMean - outMean,\n    n: samples.length,\n  }\n}\n\n// ── Helpers ──────────────────────────────────────────────────────────\n\n/** Quadratic weighted Cohen's κ over bounded integer scores. */\nfunction weightedKappa(a: number[], b: number[]): number {\n  if (a.length !== b.length || a.length === 0) return NaN\n  const min = Math.min(...a, ...b)\n  const max = Math.max(...a, ...b)\n  const K = max - min + 1\n  if (K < 2) return 1\n  const observed: number[][] = Array.from({ length: K }, () => new Array(K).fill(0))\n  const rowMarg = new Array(K).fill(0)\n  const colMarg = new Array(K).fill(0)\n  for (let i = 0; i < a.length; i++) {\n    const ai = a[i]! - min\n    const bi = b[i]! - min\n    const row = observed[ai]!\n    row[bi] = (row[bi] ?? 0) + 1\n    rowMarg[ai]++\n    colMarg[bi]++\n  }\n  let num = 0\n  let den = 0\n  for (let i = 0; i < K; i++) {\n    for (let j = 0; j < K; j++) {\n      const w = (i - j) ** 2 / (K - 1) ** 2\n      const expected = (rowMarg[i] * colMarg[j]) / a.length\n      num += w * observed[i]![j]!\n      den += w * expected\n    }\n  }\n  if (den === 0) return 1\n  return 1 - num / den\n}\n\n// ── Continuous-value inter-rater agreement ──────────────────────────\n//\n// `weightedKappa` above quantises to integers. For [0,1] judges that is\n// lossy: 0.78 and 0.81 both round to 1 and look identical to integer κ.\n// `continuousAgreement` keeps the original magnitudes:\n//\n//   - κ_w   : Cohen's weighted κ generalised to continuous scores. For two\n//             raters, weighted κ = 1 − Σ w_ij·o_ij / Σ w_ij·e_ij collapses\n//             into the closed form below when each \"category\" is the score\n//             itself (Janson & Olsson 2001; Cohen 1968 quadratic weights).\n//   - ICC   : Intraclass Correlation Coefficient, ICC(2,1) per Shrout &\n//             Fleiss (1979) — two-way random effects, absolute agreement,\n//             single rater. The right reliability coefficient when judges\n//             are a random sample of the judge population.\n//   - r, ρ  : Pearson + Spearman for sanity-check. Pearson catches linear\n//             association regardless of scale; Spearman catches monotone\n//             association regardless of distribution.\n//   - CIs   : Bootstrap percentile CIs over items (rows). Bias is preserved\n//             because we resample the full row, i.e. a judge's vector\n//             stays internally consistent within each bootstrap replicate.\n//\n// References:\n//   - Shrout, P. E. & Fleiss, J. L. (1979). Intraclass correlations: uses\n//     in assessing rater reliability. Psychological Bulletin, 86(2), 420.\n//   - McGraw, K. O. & Wong, S. P. (1996). Forming inferences about some\n//     intraclass correlation coefficients. Psychological Methods, 1, 30.\n//   - Janson, H. & Olsson, U. (2001). A measure of agreement for interval\n//     or nominal multivariate observations. Educ. Psychol. Meas., 61, 277.\n\nexport interface ContinuousAgreement {\n  /** Cohen's κ_w with quadratic weights, computed on raw [0,1] scores. */\n  weightedKappa: number\n  /** ICC(2,1): two-way random effects, absolute agreement, single rater. */\n  icc: number\n  /** Pearson product-moment correlation (averaged over rater pairs if N>2). */\n  pearson: number\n  /** Spearman rank correlation (averaged over rater pairs if N>2). */\n  spearman: number\n  /** 95% bootstrap percentile CIs over items. */\n  ci: {\n    icc: [number, number]\n    weightedKappa: [number, number]\n  }\n  /** Number of complete items (no NaN across raters). */\n  n: number\n  /** Number of raters. */\n  raters: number\n}\n\nexport interface ContinuousAgreementOptions {\n  /** Bootstrap iterations. Default 1000. Set to 0 to skip CIs (CI = [NaN, NaN]). */\n  bootstrap?: number\n  /** κ weighting scheme. Default 'quadratic'. */\n  weights?: 'linear' | 'quadratic'\n  /** PRNG seed for reproducible bootstrap. Default 0xC0FFEE. */\n  seed?: number\n  /** Confidence level for percentile CI. Default 0.95. */\n  ciLevel?: number\n}\n\n/**\n * Inter-rater agreement on continuous (typically [0,1]) scores.\n *\n * `scores` has shape [n_items][n_raters]. Rows with any non-finite entry\n * are dropped. Returns NaN metrics if fewer than 2 raters or 2 complete\n * items remain.\n */\nexport function continuousAgreement(\n  scores: number[][],\n  opts: ContinuousAgreementOptions = {},\n): ContinuousAgreement {\n  const bootstrap = opts.bootstrap ?? 1000\n  const weights = opts.weights ?? 'quadratic'\n  const seed = opts.seed ?? 0xc0ffee\n  const ciLevel = opts.ciLevel ?? 0.95\n\n  const matrix = scores.filter((row) => row.length >= 2 && row.every((v) => Number.isFinite(v)))\n  const raters = matrix[0]?.length ?? 0\n  // All rows must have the same rater count, else drop the offenders.\n  const clean = matrix.filter((row) => row.length === raters)\n  const nClean = clean.length\n\n  if (nClean < 2 || raters < 2) {\n    return {\n      weightedKappa: NaN,\n      icc: NaN,\n      pearson: NaN,\n      spearman: NaN,\n      ci: { icc: [NaN, NaN], weightedKappa: [NaN, NaN] },\n      n: nClean,\n      raters,\n    }\n  }\n\n  const kappa = continuousWeightedKappa(clean, weights)\n  const icc = icc21(clean)\n  const pearson = avgPairwise(clean, pearsonR)\n  const spearman = avgPairwise(clean, spearmanR)\n\n  const ciIcc: [number, number] = [NaN, NaN]\n  const ciKappa: [number, number] = [NaN, NaN]\n  if (bootstrap > 0) {\n    const rng = mulberry32(seed)\n    const iccs: number[] = []\n    const kappas: number[] = []\n    for (let b = 0; b < bootstrap; b++) {\n      const sample: number[][] = new Array(nClean)\n      for (let i = 0; i < nClean; i++) {\n        sample[i] = clean[Math.floor(rng() * nClean)]!\n      }\n      const iccB = icc21(sample)\n      const kB = continuousWeightedKappa(sample, weights)\n      if (Number.isFinite(iccB)) iccs.push(iccB)\n      if (Number.isFinite(kB)) kappas.push(kB)\n    }\n    const [lo, hi] = percentileBounds(ciLevel)\n    if (iccs.length > 0) {\n      iccs.sort((a, b) => a - b)\n      ciIcc[0] = quantile(iccs, lo)\n      ciIcc[1] = quantile(iccs, hi)\n    }\n    if (kappas.length > 0) {\n      kappas.sort((a, b) => a - b)\n      ciKappa[0] = quantile(kappas, lo)\n      ciKappa[1] = quantile(kappas, hi)\n    }\n  }\n\n  return {\n    weightedKappa: kappa,\n    icc,\n    pearson,\n    spearman,\n    ci: { icc: ciIcc, weightedKappa: ciKappa },\n    n: nClean,\n    raters,\n  }\n}\n\nexport interface ContinuousCalibrationResult extends CalibrationResult {\n  /** Cohen's κ_w computed on raw (un-rounded) scores. */\n  weightedKappaContinuous: number\n  /** ICC(2,1) treating golden + candidate as two raters. */\n  icc: number\n  spearman: number\n  ci: {\n    icc: [number, number]\n    weightedKappa: [number, number]\n  }\n}\n\n/**\n * Extends `calibrateJudge` with continuous-value agreement metrics while\n * retaining its base calibration summary.\n */\nexport function calibrateJudgeContinuous(\n  golden: GoldenItem[],\n  candidate: CandidateScore[],\n  opts: ContinuousAgreementOptions = {},\n): ContinuousCalibrationResult {\n  const base = calibrateJudge(golden, candidate)\n  const map = new Map<string, { h: number; j: number }>()\n  for (const g of golden) map.set(g.itemId, { h: g.humanScore, j: NaN })\n  for (const c of candidate) {\n    const entry = map.get(c.itemId)\n    if (entry) entry.j = c.score\n  }\n  const rows: number[][] = []\n  for (const v of map.values()) {\n    if (Number.isFinite(v.j)) rows.push([v.h, v.j])\n  }\n  const agreement = continuousAgreement(rows, opts)\n  return {\n    ...base,\n    weightedKappaContinuous: agreement.weightedKappa,\n    icc: agreement.icc,\n    spearman: agreement.spearman,\n    ci: agreement.ci,\n  }\n}\n\n// ── Continuous-agreement internals ──────────────────────────────────\n\n/**\n * Quadratic-weighted κ on continuous scores. With weights w(x,y) = (x-y)^2\n * (or |x-y| for linear) the formula collapses to:\n *\n *   κ_w = 1 − E_obs[w] / E_exp[w]\n *\n * where E_obs averages w over paired (a_i, b_i) and E_exp averages w over\n * the independent product distribution (sum_{i,j} w(a_i, b_j) / n^2).\n * The normalisation by (max-min)^2 in the integer version cancels in the\n * ratio, so we don't need it here. Generalises to N raters by averaging κ_w\n * over all rater pairs (mean pairwise weighted agreement).\n */\nfunction continuousWeightedKappa(rows: number[][], scheme: 'linear' | 'quadratic'): number {\n  if (rows.length === 0) return NaN\n  const raters = rows[0]!.length\n  if (raters < 2) return NaN\n  const wFn =\n    scheme === 'linear'\n      ? (x: number, y: number) => Math.abs(x - y)\n      : (x: number, y: number) => (x - y) ** 2\n  let sum = 0\n  let pairs = 0\n  for (let r1 = 0; r1 < raters; r1++) {\n    for (let r2 = r1 + 1; r2 < raters; r2++) {\n      const a = rows.map((row) => row[r1]!)\n      const b = rows.map((row) => row[r2]!)\n      const n = a.length\n      let obs = 0\n      for (let i = 0; i < n; i++) obs += wFn(a[i]!, b[i]!)\n      obs /= n\n      // Expected under independence: average of w over all i,j cross pairs.\n      let exp = 0\n      for (let i = 0; i < n; i++) {\n        for (let j = 0; j < n; j++) exp += wFn(a[i]!, b[j]!)\n      }\n      exp /= n * n\n      if (exp === 0) {\n        // Degenerate: at least one rater is constant. Convention: perfect\n        // agreement iff observed disagreement is also zero, else 0.\n        sum += obs === 0 ? 1 : 0\n      } else {\n        sum += 1 - obs / exp\n      }\n      pairs++\n    }\n  }\n  return pairs === 0 ? NaN : sum / pairs\n}\n\n/**\n * ICC(2,1) — two-way random effects, absolute agreement, single rater.\n *\n *   ICC(2,1) = (MSR − MSE) / (MSR + (k−1)·MSE + k·(MSC − MSE)/n)\n *\n * where MSR = between-rows MS, MSC = between-columns MS, MSE = residual MS,\n * n = rows (items), k = columns (raters).\n */\nfunction icc21(rows: number[][]): number {\n  const n = rows.length\n  if (n < 2) return NaN\n  const k = rows[0]!.length\n  if (k < 2) return NaN\n\n  // Row means.\n  const rowMeans = rows.map((row) => row.reduce((s, v) => s + v, 0) / k)\n  // Column means.\n  const colMeans = new Array(k).fill(0)\n  for (let j = 0; j < k; j++) {\n    let s = 0\n    for (let i = 0; i < n; i++) s += rows[i]![j]!\n    colMeans[j] = s / n\n  }\n  // Grand mean.\n  let grand = 0\n  for (let i = 0; i < n; i++) grand += rowMeans[i]!\n  grand /= n\n\n  let ssR = 0\n  for (let i = 0; i < n; i++) ssR += (rowMeans[i]! - grand) ** 2\n  ssR *= k\n  let ssC = 0\n  for (let j = 0; j < k; j++) ssC += (colMeans[j]! - grand) ** 2\n  ssC *= n\n  let ssT = 0\n  for (let i = 0; i < n; i++) {\n    for (let j = 0; j < k; j++) ssT += (rows[i]![j]! - grand) ** 2\n  }\n  const ssE = ssT - ssR - ssC\n\n  const dfR = n - 1\n  const dfC = k - 1\n  const dfE = (n - 1) * (k - 1)\n  const msR = ssR / dfR\n  const msC = ssC / dfC\n  const msE = dfE > 0 ? ssE / dfE : 0\n\n  const denom = msR + (k - 1) * msE + (k * (msC - msE)) / n\n  if (denom === 0) {\n    // Degenerate (all values equal): convention = 1 if rows identical,\n    // else 0. Identical rows ⇒ msR = 0 too, so msR − msE near 0.\n    return msR === 0 && msE === 0 ? 1 : 0\n  }\n  return (msR - msE) / denom\n}\n\n/** Average pairwise statistic over all rater pairs. */\nfunction avgPairwise(rows: number[][], fn: (a: number[], b: number[]) => number): number {\n  const k = rows[0]?.length ?? 0\n  if (k < 2) return NaN\n  let sum = 0\n  let pairs = 0\n  for (let i = 0; i < k; i++) {\n    for (let j = i + 1; j < k; j++) {\n      const a = rows.map((row) => row[i]!)\n      const b = rows.map((row) => row[j]!)\n      const r = fn(a, b)\n      if (Number.isFinite(r)) {\n        sum += r\n        pairs++\n      }\n    }\n  }\n  return pairs === 0 ? NaN : sum / pairs\n}\n\nfunction percentileBounds(ciLevel: number): [number, number] {\n  const tail = (1 - ciLevel) / 2\n  return [tail, 1 - tail]\n}\n\n/** Linear-interpolated quantile of a pre-sorted ascending array. */\nfunction quantile(sorted: number[], q: number): number {\n  if (sorted.length === 0) return NaN\n  if (sorted.length === 1) return sorted[0]!\n  const pos = q * (sorted.length - 1)\n  const lo = Math.floor(pos)\n  const hi = Math.ceil(pos)\n  if (lo === hi) return sorted[lo]!\n  const frac = pos - lo\n  return sorted[lo]! * (1 - frac) + sorted[hi]! * frac\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;AAoDA,SAAgB,eACd,QACA,WACmB;CACnB,MAAM,sBAAM,IAAI,IAAsC;CACtD,KAAK,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,QAAQ;EAAE,GAAG,EAAE;EAAY,GAAG;CAAI,CAAC;CACrE,KAAK,MAAM,KAAK,WAAW;EACzB,MAAM,QAAQ,IAAI,IAAI,EAAE,MAAM;EAC9B,IAAI,OAAO,MAAM,IAAI,EAAE;CACzB;CACA,MAAM,SAAS,CAAC,GAAG,IAAI,OAAO,CAAC,CAAC,CAAC,QAAQ,MAAM,OAAO,SAAS,EAAE,CAAC,CAAC;CACnE,MAAM,IAAI,OAAO;CACjB,IAAI,IAAI,GACN,OAAO;EAAE;EAAG,SAAS;EAAK,OAAO;EAAK,KAAK;EAAK,YAAY,CAAC;CAAE;CAEjE,MAAM,SAAS,OAAO,KAAK,MAAM,EAAE,CAAC;CACpC,MAAM,SAAS,OAAO,KAAK,MAAM,EAAE,CAAC;CAUpC,OAAO;EAAE;EAAG,SATI,SAAS,QAAQ,MASf;EAAG,OARP,cAAc,OAAO,IAAI,KAAK,KAAK,GAAG,OAAO,IAAI,KAAK,KAAK,CAQhD;EAAG,KAPX,OAAO,KAAK,MAAM,KAAK,IAAI,EAAE,IAAI,EAAE,CAAC,CAClC,CAAC,CAAC,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;EAMjB,YALnB,CAAC,GAAG,IAAI,QAAQ,CAAC,CAAC,CAC7B,QAAQ,GAAG,OAAO,OAAO,SAAS,EAAE,CAAC,CAAC,CAAC,CACvC,KAAK,CAAC,QAAQ,QAAQ;GAAE;GAAQ,OAAO,EAAE;GAAG,OAAO,EAAE;GAAG,OAAO,KAAK,IAAI,EAAE,IAAI,EAAE,CAAC;EAAE,EAAE,CAAC,CACtF,MAAM,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CACjC,MAAM,GAAG,CACqC;CAAE;AACrD;;;;;AAeA,SAAgB,eAAe,QAAgD;CAC7E,MAAM,wBAAQ,IAAI,IAAiD;CACnE,KAAK,MAAM,KAAK,QAAQ;EACtB,MAAM,OAAO,MAAM,IAAI,EAAE,MAAM,KAAK,CAAC;EACrC,IAAI,EAAE,qBAAqB,SAAS,KAAK,QAAQ,EAAE;OAC9C,IAAI,EAAE,qBAAqB,UAAU,KAAK,SAAS,EAAE;EAC1D,MAAM,IAAI,EAAE,QAAQ,IAAI;CAC1B;CACA,MAAM,SAAmB,CAAC;CAC1B,KAAK,MAAM,EAAE,OAAO,YAAY,MAAM,OAAO,GAC3C,IAAI,UAAU,KAAA,KAAa,WAAW,KAAA,GAAW,OAAO,KAAK,QAAQ,MAAM;CAE7E,IAAI,OAAO,WAAW,GAAG,OAAO;EAAE,UAAU;EAAG,GAAG;CAAE;CACpD,OAAO;EAAE,UAAU,OAAO,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,OAAO;EAAQ,GAAG,OAAO;CAAO;AACzF;AAQA,SAAgB,cACd,SACqB;CACrB,MAAM,IAAI,QAAQ;CAClB,IAAI,IAAI,GAAG,OAAO;EAAE,SAAS;EAAK;CAAE;CACpC,OAAO;EACL,SAAS,SACP,QAAQ,KAAK,MAAM,EAAE,SAAS,GAC9B,QAAQ,KAAK,MAAM,EAAE,KAAK,CAC5B;EACA;CACF;AACF;;;;;;AAeA,SAAgB,eACd,SACsB;CACtB,MAAM,MAAM,QAAQ,QAAQ,MAAM,EAAE,QAAQ,CAAC,CAAC,KAAK,MAAM,EAAE,KAAK;CAChE,MAAM,OAAO,QAAQ,QAAQ,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,MAAM,EAAE,KAAK;CAClE,IAAI,IAAI,WAAW,KAAK,KAAK,WAAW,GACtC,OAAO;EAAE,cAAc;EAAG,iBAAiB;EAAG,WAAW;EAAG,GAAG;CAAE;CACnE,MAAM,SAAS,IAAI,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,IAAI;CACpD,MAAM,UAAU,KAAK,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,KAAK;CACvD,OAAO;EACL,cAAc;EACd,iBAAiB;EACjB,WAAW,SAAS;EACpB,GAAG,QAAQ;CACb;AACF;;AAKA,SAAS,cAAc,GAAa,GAAqB;CACvD,IAAI,EAAE,WAAW,EAAE,UAAU,EAAE,WAAW,GAAG,OAAO;CACpD,MAAM,MAAM,KAAK,IAAI,GAAG,GAAG,GAAG,CAAC;CAE/B,MAAM,IADM,KAAK,IAAI,GAAG,GAAG,GAAG,CAClB,IAAI,MAAM;CACtB,IAAI,IAAI,GAAG,OAAO;CAClB,MAAM,WAAuB,MAAM,KAAK,EAAE,QAAQ,EAAE,SAAS,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;CACjF,MAAM,UAAU,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACnC,MAAM,UAAU,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACnC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;EACjC,MAAM,KAAK,EAAE,KAAM;EACnB,MAAM,KAAK,EAAE,KAAM;EACnB,MAAM,MAAM,SAAS;EACrB,IAAI,OAAO,IAAI,OAAO,KAAK;EAC3B,QAAQ,GAAG;EACX,QAAQ,GAAG;CACb;CACA,IAAI,MAAM;CACV,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAC1B,MAAM,KAAK,IAAI,MAAM,KAAK,IAAI,MAAM;EACpC,MAAM,WAAY,QAAQ,KAAK,QAAQ,KAAM,EAAE;EAC/C,OAAO,IAAI,SAAS,EAAE,CAAE;EACxB,OAAO,IAAI;CACb;CAEF,IAAI,QAAQ,GAAG,OAAO;CACtB,OAAO,IAAI,MAAM;AACnB;;;;;;;;AAqEA,SAAgB,oBACd,QACA,OAAmC,CAAC,GACf;CACrB,MAAM,YAAY,KAAK,aAAa;CACpC,MAAM,UAAU,KAAK,WAAW;CAChC,MAAM,OAAO,KAAK,QAAQ;CAC1B,MAAM,UAAU,KAAK,WAAW;CAEhC,MAAM,SAAS,OAAO,QAAQ,QAAQ,IAAI,UAAU,KAAK,IAAI,OAAO,MAAM,OAAO,SAAS,CAAC,CAAC,CAAC;CAC7F,MAAM,SAAS,OAAO,EAAE,EAAE,UAAU;CAEpC,MAAM,QAAQ,OAAO,QAAQ,QAAQ,IAAI,WAAW,MAAM;CAC1D,MAAM,SAAS,MAAM;CAErB,IAAI,SAAS,KAAK,SAAS,GACzB,OAAO;EACL,eAAe;EACf,KAAK;EACL,SAAS;EACT,UAAU;EACV,IAAI;GAAE,KAAK,CAAC,KAAK,GAAG;GAAG,eAAe,CAAC,KAAK,GAAG;EAAE;EACjD,GAAG;EACH;CACF;CAGF,MAAM,QAAQ,wBAAwB,OAAO,OAAO;CACpD,MAAM,MAAM,MAAM,KAAK;CACvB,MAAM,UAAU,YAAY,OAAO,QAAQ;CAC3C,MAAM,WAAW,YAAY,OAAO,SAAS;CAE7C,MAAM,QAA0B,CAAC,KAAK,GAAG;CACzC,MAAM,UAA4B,CAAC,KAAK,GAAG;CAC3C,IAAI,YAAY,GAAG;EACjB,MAAM,MAAM,WAAW,IAAI;EAC3B,MAAM,OAAiB,CAAC;EACxB,MAAM,SAAmB,CAAC;EAC1B,KAAK,IAAI,IAAI,GAAG,IAAI,WAAW,KAAK;GAClC,MAAM,SAAqB,IAAI,MAAM,MAAM;GAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,QAAQ,KAC1B,OAAO,KAAK,MAAM,KAAK,MAAM,IAAI,IAAI,MAAM;GAE7C,MAAM,OAAO,MAAM,MAAM;GACzB,MAAM,KAAK,wBAAwB,QAAQ,OAAO;GAClD,IAAI,OAAO,SAAS,IAAI,GAAG,KAAK,KAAK,IAAI;GACzC,IAAI,OAAO,SAAS,EAAE,GAAG,OAAO,KAAK,EAAE;EACzC;EACA,MAAM,CAAC,IAAI,MAAM,iBAAiB,OAAO;EACzC,IAAI,KAAK,SAAS,GAAG;GACnB,KAAK,MAAM,GAAG,MAAM,IAAI,CAAC;GACzB,MAAM,KAAK,SAAS,MAAM,EAAE;GAC5B,MAAM,KAAK,SAAS,MAAM,EAAE;EAC9B;EACA,IAAI,OAAO,SAAS,GAAG;GACrB,OAAO,MAAM,GAAG,MAAM,IAAI,CAAC;GAC3B,QAAQ,KAAK,SAAS,QAAQ,EAAE;GAChC,QAAQ,KAAK,SAAS,QAAQ,EAAE;EAClC;CACF;CAEA,OAAO;EACL,eAAe;EACf;EACA;EACA;EACA,IAAI;GAAE,KAAK;GAAO,eAAe;EAAQ;EACzC,GAAG;EACH;CACF;AACF;;;;;AAkBA,SAAgB,yBACd,QACA,WACA,OAAmC,CAAC,GACP;CAC7B,MAAM,OAAO,eAAe,QAAQ,SAAS;CAC7C,MAAM,sBAAM,IAAI,IAAsC;CACtD,KAAK,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,QAAQ;EAAE,GAAG,EAAE;EAAY,GAAG;CAAI,CAAC;CACrE,KAAK,MAAM,KAAK,WAAW;EACzB,MAAM,QAAQ,IAAI,IAAI,EAAE,MAAM;EAC9B,IAAI,OAAO,MAAM,IAAI,EAAE;CACzB;CACA,MAAM,OAAmB,CAAC;CAC1B,KAAK,MAAM,KAAK,IAAI,OAAO,GACzB,IAAI,OAAO,SAAS,EAAE,CAAC,GAAG,KAAK,KAAK,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC;CAEhD,MAAM,YAAY,oBAAoB,MAAM,IAAI;CAChD,OAAO;EACL,GAAG;EACH,yBAAyB,UAAU;EACnC,KAAK,UAAU;EACf,UAAU,UAAU;EACpB,IAAI,UAAU;CAChB;AACF;;;;;;;;;;;;;AAgBA,SAAS,wBAAwB,MAAkB,QAAwC;CACzF,IAAI,KAAK,WAAW,GAAG,OAAO;CAC9B,MAAM,SAAS,KAAK,EAAE,CAAE;CACxB,IAAI,SAAS,GAAG,OAAO;CACvB,MAAM,MACJ,WAAW,YACN,GAAW,MAAc,KAAK,IAAI,IAAI,CAAC,KACvC,GAAW,OAAe,IAAI,MAAM;CAC3C,IAAI,MAAM;CACV,IAAI,QAAQ;CACZ,KAAK,IAAI,KAAK,GAAG,KAAK,QAAQ,MAC5B,KAAK,IAAI,KAAK,KAAK,GAAG,KAAK,QAAQ,MAAM;EACvC,MAAM,IAAI,KAAK,KAAK,QAAQ,IAAI,GAAI;EACpC,MAAM,IAAI,KAAK,KAAK,QAAQ,IAAI,GAAI;EACpC,MAAM,IAAI,EAAE;EACZ,IAAI,MAAM;EACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,OAAO,IAAI,EAAE,IAAK,EAAE,EAAG;EACnD,OAAO;EAEP,IAAI,MAAM;EACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,OAAO,IAAI,EAAE,IAAK,EAAE,EAAG;EAErD,OAAO,IAAI;EACX,IAAI,QAAQ,GAGV,OAAO,QAAQ,IAAI,IAAI;OAEvB,OAAO,IAAI,MAAM;EAEnB;CACF;CAEF,OAAO,UAAU,IAAI,MAAM,MAAM;AACnC;;;;;;;;;AAUA,SAAS,MAAM,MAA0B;CACvC,MAAM,IAAI,KAAK;CACf,IAAI,IAAI,GAAG,OAAO;CAClB,MAAM,IAAI,KAAK,EAAE,CAAE;CACnB,IAAI,IAAI,GAAG,OAAO;CAGlB,MAAM,WAAW,KAAK,KAAK,QAAQ,IAAI,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC;CAErE,MAAM,WAAW,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC;CACpC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAC1B,IAAI,IAAI;EACR,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE,CAAE;EAC1C,SAAS,KAAK,IAAI;CACpB;CAEA,IAAI,QAAQ;CACZ,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,SAAS,SAAS;CAC9C,SAAS;CAET,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,SAAS,KAAM,UAAU;CAC7D,OAAO;CACP,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,SAAS,KAAM,UAAU;CAC7D,OAAO;CACP,IAAI,MAAM;CACV,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,QAAQ,KAAK,EAAE,CAAE,KAAM,UAAU;CAE/D,MAAM,MAAM,MAAM,MAAM;CAExB,MAAM,MAAM,IAAI;CAChB,MAAM,MAAM,IAAI;CAChB,MAAM,OAAO,IAAI,MAAM,IAAI;CAC3B,MAAM,MAAM,MAAM;CAClB,MAAM,MAAM,MAAM;CAClB,MAAM,MAAM,MAAM,IAAI,MAAM,MAAM;CAElC,MAAM,QAAQ,OAAO,IAAI,KAAK,MAAO,KAAK,MAAM,OAAQ;CACxD,IAAI,UAAU,GAGZ,OAAO,QAAQ,KAAK,QAAQ,IAAI,IAAI;CAEtC,QAAQ,MAAM,OAAO;AACvB;;AAGA,SAAS,YAAY,MAAkB,IAAkD;CACvF,MAAM,IAAI,KAAK,EAAE,EAAE,UAAU;CAC7B,IAAI,IAAI,GAAG,OAAO;CAClB,IAAI,MAAM;CACV,IAAI,QAAQ;CACZ,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KACrB,KAAK,IAAI,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EAG9B,MAAM,IAAI,GAFA,KAAK,KAAK,QAAQ,IAAI,EAEnB,GADH,KAAK,KAAK,QAAQ,IAAI,EAChB,CAAC;EACjB,IAAI,OAAO,SAAS,CAAC,GAAG;GACtB,OAAO;GACP;EACF;CACF;CAEF,OAAO,UAAU,IAAI,MAAM,MAAM;AACnC;AAEA,SAAS,iBAAiB,SAAmC;CAC3D,MAAM,QAAQ,IAAI,WAAW;CAC7B,OAAO,CAAC,MAAM,IAAI,IAAI;AACxB;;AAGA,SAAS,SAAS,QAAkB,GAAmB;CACrD,IAAI,OAAO,WAAW,GAAG,OAAO;CAChC,IAAI,OAAO,WAAW,GAAG,OAAO,OAAO;CACvC,MAAM,MAAM,KAAK,OAAO,SAAS;CACjC,MAAM,KAAK,KAAK,MAAM,GAAG;CACzB,MAAM,KAAK,KAAK,KAAK,GAAG;CACxB,IAAI,OAAO,IAAI,OAAO,OAAO;CAC7B,MAAM,OAAO,MAAM;CACnB,OAAO,OAAO,OAAQ,IAAI,QAAQ,OAAO,MAAO;AAClD"}