{
  "id": "BEN-2026-0003",
  "kind": "benchmark",
  "label": "PACC-LLM Hybrid A/B/C benchmark",
  "created_at": "2026-09-09",
  "updated_at": "2026-09-09",
  "values": {
    "eml_status": "EXPERIMENTAL",
    "eml_evidence_level": "E2",
    "eml_object_version": "0.1",
    "eml_canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0003/",
    "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": "Three conditions over identical candidate pools: A generator-only, B hard verifier, C PACC runtime (plus post-hoc D 'elastic'). v0.1: 7 categories × 28 tasks × 8 pools × 112 candidates (1,568 shared pool instances). Metrics: explicit hard adherence, derived coherence, soft-intent satisfaction, long-horizon retention, raw and valid novelty, pattern entropy. v0.2: 16 hand-authored natural-language tasks, equal accounted budgets, gold rubric visible only to a condition-blind judge.",
    "eml_summary_zh": "三種條件跑在完全相同的候選池上：A 純生成器、B 硬驗證器、C PACC runtime（另有事後的 D「elastic」）。v0.1：7 類 × 28 題 × 8 池 × 112 候選（1,568 個共享池實例）。指標：明示硬約束遵守、衍生一致性、軟意圖滿足、長程保持、原始與有效新穎度、pattern entropy。v0.2：16 個手寫自然語言任務、相同計費預算、只有對條件盲的評審看得到 gold rubric。",
    "eml_label_zh": "PACC-LLM 混合 A/B/C benchmark",
    "eml_primary_domain": "Evaluation",
    "eml_domains": [
      "Reasoning"
    ],
    "eml_program_id": "PRG-2026-0001",
    "eml_purpose": "Separate 'more rejection' from genuine gains in derived dependency coherence, intent handling and constraint-satisfying novelty.",
    "eml_metrics": [
      "explicit hard adherence",
      "derived coherence",
      "soft-intent satisfaction",
      "long-horizon retention",
      "raw novelty",
      "valid novelty",
      "pattern entropy"
    ],
    "eml_limitations": [
      "A single-model judge is not human evaluation; nothing about real models is measured until a live run exists."
    ],
    "eml_authors": [
      "Neo.K (EveMissLab)"
    ],
    "eml_ai_collaborators": [
      "Sol (GPT-5.6, OpenAI ChatGPT)"
    ]
  },
  "canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0003/",
  "json": "/ai/benchmarks/BEN-2026-0003/index.json",
  "relations": [
    {
      "id": "REL-2026-0091",
      "predicate": "evaluates",
      "source": "BEN-2026-0003",
      "target": "THY-2026-0005",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0314",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0021",
      "target": "BEN-2026-0003",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0321",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0022",
      "target": "BEN-2026-0003",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0327",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0023",
      "target": "BEN-2026-0003",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0335",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0024",
      "target": "BEN-2026-0003",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0344",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0025",
      "target": "BEN-2026-0003",
      "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
  }
}