{ "id": "BEN-2026-0001", "kind": "benchmark", "label": "PACC micro-lab protocol v0.1 (frozen gates)", "created_at": "2026-09-08", "updated_at": "2026-09-09", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0001/", "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": "The preregistered decision rule reused unchanged from v0.1 to v0.13: E0 purity, held-out representation distance D_R = E[JS(Φ(S_N), S_P)] ≤ 0.05, update commutation D_U ≤ 0.05, off-manifold intervention D_I ≤ 0.08, action agreement ≥ 0.85, a shuffled-target negative control the real map must beat, a design-independence rule (agreement ≥ 0.999 and R² ≥ 0.995 collapse two designs into one family), verdict levels 0–3, and a strong PACC-A gate of at least three independent convergent families.", "eml_summary_zh": "從 v0.1 到 v0.13 原封重用的預登記判決規則：E0 純度、held-out 表徵距離 D_R = E[JS(Φ(S_N), S_P)] ≤ 0.05、更新交換 D_U ≤ 0.05、離流形干預 D_I ≤ 0.08、行動一致度 ≥ 0.85、真實映射必須勝過的 shuffled-target 負控制、設計獨立規則（一致度 ≥ 0.999 且 R² ≥ 0.995 即視為同一家族）、判決等級 0–3，以及至少三個獨立收斂家族的強 PACC-A 門檻。", "eml_label_zh": "PACC 微型實驗室協定 v0.1（凍結門檻）", "eml_primary_domain": "Evaluation", "eml_domains": [ "Model Representation" ], "eml_program_id": "PRG-2026-0001", "eml_purpose": "Make 'similar' and 'probability-like' non-negotiable after the data are seen.", "eml_tasks": [ "Sequential evidence integration over 4 hidden hypotheses × 6 binary prototypes (uniform reliability 0.80; heterogeneous 0.60–0.95 with only ordinal strengths 1–3 given to non-probabilistic systems; adversarial geometry from v0.2).", "Learned source reliability without an oracle (v0.3).", "Correlated source clusters with latent shared inversion, q swept 0.06–0.42 (v0.4–v0.13).", "Dynamic-world regime switches (E4, descriptive only)." ], "eml_metrics": [ "action agreement", "held-out JS D_R", "update-commutation JS D_U", "intervention JS D_I", "shuffled/constant/broken-composition control JS", "cross-family R²", "basin coverage, transition JS, cocycle path JS, reverse fidelity" ], "eml_evaluation_protocol": "Mapper fit on training episodes/worlds only; every gate frozen before the run; secondary multi-seed stresses are labelled post-hoc and never modify the primary decision rule.", "eml_baseline_models": [ "Exact Bayesian posterior", "Beta-Bernoulli source-quality reference", "joint-likelihood common-cause reference", "Bayesian HMM (dynamic world)" ], "eml_limitations": [ "Does not measure LLM equivalence, resource efficiency, hidden-cluster learning, or whether probability is an observer projection; E4 dynamic-world numbers make no superiority claim.", "Synthetic data and theoretical reasoning throughout: theoretically possible is not actually possible." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0001/", "json": "/ai/benchmarks/BEN-2026-0001/index.json", "relations": [ { "id": "REL-2026-0088", "predicate": "evaluates", "source": "BEN-2026-0001", "target": "THY-2026-0005", "status": "ACTIVE" }, { "id": "REL-2026-0157", "predicate": "uses_benchmark", "source": "EXP-2026-0008", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0170", "predicate": "uses_benchmark", "source": "EXP-2026-0009", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0183", "predicate": "uses_benchmark", "source": "EXP-2026-0010", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0194", "predicate": "uses_benchmark", "source": "EXP-2026-0011", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0207", "predicate": "uses_benchmark", "source": "EXP-2026-0012", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0218", "predicate": "uses_benchmark", "source": "EXP-2026-0013", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0231", "predicate": "uses_benchmark", "source": "EXP-2026-0014", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0242", "predicate": "uses_benchmark", "source": "EXP-2026-0015", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0255", "predicate": "uses_benchmark", "source": "EXP-2026-0016", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0266", "predicate": "uses_benchmark", "source": "EXP-2026-0017", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0279", "predicate": "uses_benchmark", "source": "EXP-2026-0018", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0292", "predicate": "uses_benchmark", "source": "EXP-2026-0019", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0303", "predicate": "uses_benchmark", "source": "EXP-2026-0020", "target": "BEN-2026-0001", "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 } }