{
  "id": "CLM-2026-0104",
  "kind": "claim",
  "label": "F4 — Scaffolding separation",
  "created_at": "2026-09-02",
  "updated_at": "2026-09-02",
  "values": {
    "eml_status": "EXPERIMENTAL",
    "eml_evidence_level": "E2",
    "eml_object_version": "0.1",
    "eml_canonical_url": "https://evemisslab.com/ai/claims/CLM-2026-0104/",
    "eml_provenance": {
      "source": "EveMissLab research collection: Intelligence Physical Metrology (真本體論13)",
      "extracted_by": "Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports",
      "extracted_at": "2026-09-11",
      "generator": "tools/extract_all.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": "If scaffolding does not change the structure of the capability source, SSR ≈ 1 should hold across most tasks and test-time compute budgets. If a large share of benchmark quality appears only under multi-sample, tool, verifier or loop conditions, the distinction between model-native and system capability is empirically necessary. First data point: three easy tasks on a local 9B model gave SSR = 1.0 — consistent with 'no gap' on tasks the native pass already solves, and uninformative beyond that because the quality axis was confounded by format compliance.",
    "eml_summary_zh": "若鷹架不改變能力來源的結構，則 SSR ≈ 1 應在多數任務與 test-time 算力預算下成立。若大量 benchmark 品質只在多樣本、工具、驗證器或迴圈條件下出現，模型原生與系統能力的區分就具有實證必要性。第一個數據點：本地 9B 模型在三個簡單任務上 SSR = 1.0——與「原生單次已解的任務沒有落差」一致，此外沒有更多訊息，因為品質軸被格式服從性混淆。",
    "eml_label_zh": "F4——鷹架分離",
    "eml_primary_domain": "Evaluation",
    "eml_program_id": "PRG-2026-0101",
    "eml_data_basis": "THEORY",
    "eml_falsification_conditions": [
      "Falsified for the separation's necessity if Q_F ≈ Q_SP holds across most tasks, models and budgets; supported if the gap is common. The 2026-09-03 pilot is one uninformative-to-weak point on the 'no gap' side."
    ],
    "eml_tags": [
      "falsifiable proposition",
      "IPM v0.1 canonical index §23",
      "Paper 10"
    ],
    "eml_authors": [
      "Neo.K (EveMissLab)"
    ],
    "eml_ai_collaborators": [
      "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)"
    ]
  },
  "canonical_url": "https://evemisslab.com/ai/claims/CLM-2026-0104/",
  "json": "/ai/claims/CLM-2026-0104/index.json",
  "relations": [
    {
      "id": "REL-2026-0386",
      "predicate": "belongs_to",
      "source": "CLM-2026-0104",
      "target": "RES-2026-0103",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0387",
      "predicate": "contains",
      "source": "THY-2026-0110",
      "target": "CLM-2026-0104",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0441",
      "predicate": "formalizes",
      "source": "PAP-2026-0111",
      "target": "CLM-2026-0104",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0442",
      "predicate": "formalizes",
      "source": "PAP-2026-0110",
      "target": "CLM-2026-0104",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0464",
      "predicate": "tests",
      "source": "EXP-2026-0101",
      "target": "CLM-2026-0104",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0480",
      "predicate": "tests",
      "source": "EXP-2026-0103",
      "target": "CLM-2026-0104",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0487",
      "predicate": "qualifies",
      "source": "RST-2026-0101",
      "target": "CLM-2026-0104",
      "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
  }
}