{ "id": "EXP-2026-0010", "kind": "experiment", "label": "PACC-Lab v0.3 — learned source reliability without an oracle", "created_at": "2026-09-09", "updated_at": "2026-09-09", "values": { "eml_status": "STABLE", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0010/", "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": "Both sides lose the source-quality oracle: the Bayesian reference learns Beta-Bernoulli source quality; the non-probabilistic systems learn a qualitative reputation (trust, friction, streak, familiarity). Fitted on training worlds and evaluated on unseen source-quality permutations, the reputation state maps to the Beta-Bernoulli state with JS ≈ 0.00714 versus 0.017–0.018 for shuffled/constant controls, and feedback-update commutation ≈ 0.00130 — stable 6/6 across seeds. Task-state convergence is architecture- and seed-sensitive: at exact primary scale N0/N1 4/4, N2 3/4, N3 2/4.", "eml_summary_zh": "雙方都失去來源品質 oracle：Bayesian 參考學 Beta-Bernoulli 來源品質；非概率系統學定性聲譽（信任、摩擦、連勝、熟悉度）。在訓練世界上擬合、在未見過的來源品質排列上評估，聲譽狀態映射到 Beta-Bernoulli 狀態的 JS ≈ 0.00714，shuffled／constant 控制組為 0.017–0.018，回饋更新交換 ≈ 0.00130——跨 seed 穩定 6/6。任務狀態收斂則依架構與 seed 而異：在主要規模下 N0/N1 4/4、N2 3/4、N3 2/4。", "eml_label_zh": "PACC-Lab v0.3——無 oracle 的來源可靠度學習", "eml_primary_domain": "Model Representation", "eml_domains": [ "Evaluation", "Formal AI" ], "eml_program_id": "PRG-2026-0001", "eml_hypothesis": "Convergence survives when source reliability must be learned from delayed feedback rather than given.", "eml_metrics": { "verdict": "RELIABILITY-STATE CONVERGENCE ROBUST; TASK CONVERGENCE PARTIAL / BASIN-SENSITIVE", "primary_scale": "20 worlds / 280 episodes / 28 observations", "reliability_mapping_js": 0.007136, "control_js": "0.017–0.018", "feedback_commutation_js": 0.001298, "reliability_independent_families": 1, "task_pass_at_primary_scale": { "N0": "4/4", "N1": "4/4", "N2": "3/4", "N3": "2/4" } }, "eml_interpretation": "Calibration-state convergence can be robust while task-state convergence has architecture-dependent basins. A first fixed-quality diagnostic was rejected because Beta means became near-constant and shuffled targets fit almost as well — that redesign is part of the evidence.", "eml_limitations": [ "All four wrappers share one NonProbReputationLedger, so reliability convergence counts as one family, not four.", "Does not prove Beta-Bernoulli learning and qualitative reputation universally equivalent." ], "eml_random_seeds": [ "20260909", "6 secondary seeds (smaller)", "4 seeds at exact primary scale" ], "eml_run_count": 3, "eml_result_type": "MIXED", "eml_controls": [ "shuffled-target mapping", "constant prediction", "broken composition (v0.6+)", "target-local refit (v0.7+)" ], "eml_software_environment": "Python; deterministic seeded generators; no network, no LLM.", "eml_reproduction_instructions": "Extract the version's FINAL bundle; python -m pytest -q; run the version's primary script with the recorded seed; docs/PACC_LAB_v0.N_RESULTS.md and docs/EXPERIMENT_PROTOCOL_v0.N.md are inside the bundle.", "eml_completed_at": "2026-09-09", "eml_data_basis": "SYNTHETIC", "eml_model_ids": [ "MOD-2026-0001", "MOD-2026-0002", "MOD-2026-0003", "MOD-2026-0004", "MOD-2026-0005" ], "eml_dataset_ids": [ "DAT-2026-0001" ], "eml_benchmark_ids": [ "BEN-2026-0001" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0010/", "json": "/ai/experiments/EXP-2026-0010/index.json", "relations": [ { "id": "REL-2026-0182", "predicate": "runs_on", "source": "EXP-2026-0010", "target": "SYS-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0183", "predicate": "uses_benchmark", "source": "EXP-2026-0010", "target": "BEN-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0184", "predicate": "uses_dataset", "source": "EXP-2026-0010", "target": "DAT-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0185", "predicate": "uses_model", "source": "EXP-2026-0010", "target": "MOD-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0186", "predicate": "uses_model", "source": "EXP-2026-0010", "target": "MOD-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0187", "predicate": "uses_model", "source": "EXP-2026-0010", "target": "MOD-2026-0003", "status": "ACTIVE" }, { "id": "REL-2026-0188", "predicate": "uses_model", "source": "EXP-2026-0010", "target": "MOD-2026-0004", "status": "ACTIVE" }, { "id": "REL-2026-0189", "predicate": "uses_model", "source": "EXP-2026-0010", "target": "MOD-2026-0005", "status": "ACTIVE" }, { "id": "REL-2026-0190", "predicate": "tests", "source": "EXP-2026-0010", "target": "THY-2026-0005", "status": "ACTIVE" }, { "id": "REL-2026-0191", "predicate": "extends", "source": "EXP-2026-0010", "target": "EXP-2026-0009", "status": "ACTIVE" }, { "id": "REL-2026-0192", "predicate": "produced", "source": "EXP-2026-0010", "target": "ART-2026-0023", "status": "ACTIVE" }, { "id": "REL-2026-0202", "predicate": "extends", "source": "EXP-2026-0011", "target": "EXP-2026-0010", "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 } }