{
  "id": "RST-2026-0016",
  "kind": "result",
  "label": "Run 3: valid novelty and repair up for the PACC runtime with thinking on; governance flat; breadth not reduced (32 rows)",
  "created_at": "2026-09-11",
  "updated_at": "2026-09-11",
  "values": {
    "eml_status": "STABLE",
    "eml_evidence_level": "E3",
    "eml_object_version": "0.1",
    "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0016/",
    "eml_provenance": {
      "source": "EveMissLab research collection: Adaptive Epistemic Systems (真本體論13)",
      "extracted_by": "Splice (Claude Code), reading the canonical UTF-8 sources and each lab's own result reports",
      "extracted_at": "2026-09-11",
      "generator": "tools/extract_aes/extract.py",
      "claim_boundary": "status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports"
    },
    "eml_summary": "C vs B: valid novelty +0.0687, repair +0.0153, semantic novelty +0.0166, derived coherence -0.0063, intent -0.0053, supersession -0.0059; C vs A: valid novelty +0.0375, repair +0.0466; label-free breadth ratio C 1.047 / A 0.960 / B 0.973.",
    "eml_summary_zh": "C 相對 B：有效新穎度 +0.0687、修復 +0.0153、語義新穎度 +0.0166、衍生一致性 -0.0063、意圖 -0.0053、supersession -0.0059；C 相對 A：有效新穎度 +0.0375、修復 +0.0466；標籤無關廣度比 C 1.047／A 0.960／B 0.973。",
    "eml_label_zh": "第三次執行：開啟思考後 PACC runtime 的有效新穎度與修復上升；治理持平；廣度未縮減（32 筆）",
    "eml_primary_domain": "Evaluation",
    "eml_program_id": "PRG-2026-0001",
    "eml_data_basis": "REAL MODEL",
    "eml_result_type": "MIXED",
    "eml_metrics": {
      "deltas": {
        "C-B": {
          "hard_adherence": -0.0069,
          "derived_coherence": -0.0063,
          "intent_persistence": -0.0053,
          "supersession_alignment": -0.0059,
          "repair_success": 0.0153,
          "usefulness": 0.0044,
          "semantic_novelty": 0.0166,
          "valid_novelty": 0.0687,
          "literal_check_mean": 0.0
        },
        "C-A": {
          "hard_adherence": -0.0038,
          "derived_coherence": -0.0013,
          "intent_persistence": -0.0041,
          "supersession_alignment": -0.0034,
          "repair_success": 0.0466,
          "usefulness": -0.0003,
          "semantic_novelty": 0.0128,
          "valid_novelty": 0.0375,
          "literal_check_mean": 0.0
        },
        "B-A": {
          "hard_adherence": 0.0031,
          "derived_coherence": 0.005,
          "intent_persistence": 0.0012,
          "supersession_alignment": 0.0025,
          "repair_success": 0.0312,
          "usefulness": -0.0047,
          "semantic_novelty": -0.0037,
          "valid_novelty": -0.0312,
          "literal_check_mean": 0.0
        }
      },
      "paired_wins_ties_losses": {
        "C-B": {
          "hard_adherence": "1-28-3",
          "derived_coherence": "1-26-5",
          "intent_persistence": "0-29-3",
          "supersession_alignment": "1-27-4",
          "repair_success": "1-29-2",
          "usefulness": "5-22-5",
          "semantic_novelty": "7-18-7",
          "valid_novelty": "6-21-5"
        },
        "C-A": {
          "hard_adherence": "0-29-3",
          "derived_coherence": "2-26-4",
          "intent_persistence": "0-30-2",
          "supersession_alignment": "1-28-3",
          "repair_success": "2-28-2",
          "usefulness": "6-22-4",
          "semantic_novelty": "8-18-6",
          "valid_novelty": "5-20-7"
        }
      },
      "breadth_label_free": {
        "A_llm_only": {
          "cluster_entropy_mean": 0.75,
          "breadth_ratio_mean": 0.9597,
          "selected_mean_pairwise_distance_mean": 0.2079
        },
        "B_hard_verifier": {
          "cluster_entropy_mean": 0.6875,
          "breadth_ratio_mean": 0.9727,
          "selected_mean_pairwise_distance_mean": 0.2087
        },
        "C_pacc_runtime": {
          "cluster_entropy_mean": 0.875,
          "breadth_ratio_mean": 1.0474,
          "selected_mean_pairwise_distance_mean": 0.2275
        }
      },
      "selection_agreement": {
        "A=B": 0.5625,
        "A=C": 0.46875,
        "B=C": 0.46875,
        "all_same": 0.34375
      }
    },
    "eml_interpretation": "The valid-novelty half of the synthetic prediction appears in the means, at a third of the synthetic size, once the model reasons — carried by a few large single-task wins (per-pair 6–21–5 vs B); the coherence/intent half and the breadth-loss prediction do not appear. Unreplicated: a same-size gain in run 1 vanished at 64 rows.",
    "eml_limitations": [
      "Descriptive; 32 rows; same-model judge; one model family; single thinking budget."
    ],
    "eml_authors": [
      "Neo.K (EveMissLab)"
    ],
    "eml_ai_collaborators": [
      "Sol (GPT-5.6, OpenAI ChatGPT)"
    ]
  },
  "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0016/",
  "json": "/ai/results/RST-2026-0016/index.json",
  "relations": [
    {
      "id": "REL-2026-0351",
      "predicate": "qualifies",
      "source": "RST-2026-0016",
      "target": "THY-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0350",
      "predicate": "produces",
      "source": "EXP-2026-0025",
      "target": "RST-2026-0016",
      "status": "ACTIVE"
    }
  ],
  "snapshot": {
    "snapshot_id": "AI-SNAPSHOT-v0.1-fe85b9694a45",
    "created_at": "2026-09-11T05:00:27Z",
    "format_version": "0.1",
    "sedb_baseline": "v0.4B contract; static source content/ai/",
    "generator_version": "evemisslab-com ai_research 0.1",
    "object_count": 124,
    "relation_count": 499,
    "artifact_count": 58
  }
}