{ "id": "EXP-2026-0021", "kind": "experiment", "label": "PACC-Hybrid v0.1 — synthetic A/B/C architecture witness", "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-2026-0021/", "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": "Over 1,568 identical candidate pools, generator-only (A), hard verifier (B) and PACC runtime (C) are scored on hard adherence, derived coherence, soft-intent satisfaction, long-horizon retention, novelty and pattern entropy. B already saturates literal hard adherence (1.0); C adds derived coherence +0.2085, long-horizon retention +0.0142 and valid novelty +0.1964 over B, loses 0.0076 soft-intent satisfaction, and in the pure-creative control raises pointwise novelty (0.9864 vs 0.8889) while collapsing pattern entropy (0.2284 vs 0.7199). A post-hoc 'elastic' exploration policy (D) restores entropy to 0.7638 with derived coherence still 1.0. Zero real LLM calls; eight seeds sign-stable.", "eml_summary_zh": "在 1,568 個完全相同的候選池上，純生成器（A）、硬驗證器（B）、PACC runtime（C）以硬約束遵守、衍生一致性、軟意圖滿足、長程保持、新穎度與 pattern entropy 計分。B 已經把字面硬約束遵守飽和到 1.0；C 相對 B 衍生一致性 +0.2085、長程保持 +0.0142、有效新穎度 +0.1964、軟意圖滿足 −0.0076，並在純創意控制組中提高逐點新穎度（0.9864 vs 0.8889）卻讓 pattern entropy 塌縮（0.2284 vs 0.7199）。事後的「elastic」探索策略（D）在衍生一致性仍為 1.0 下把 entropy 恢復到 0.7638。零次真實 LLM 呼叫；八個 seed 符號穩定。", "eml_label_zh": "PACC-Hybrid v0.1——合成 A/B/C 架構見證", "eml_primary_domain": "Reasoning", "eml_domains": [ "Evaluation" ], "eml_program_id": "PRG-2026-0001", "eml_hypothesis": "A PACC-style commit space changes selection quality beyond what a hard verifier achieves, and any creative-breadth loss is separable from the commit constraints.", "eml_metrics": { "verdict": "SYNTHETIC_PARETO_WITNESS_REASONING_UP_BREADTH_COLLAPSE_MITIGATABLE", "scale": "7 categories × 28 tasks × 8 pools × 112 candidates; 1568 pool instances; 0 LLM calls", "overall": { "A": { "hard": 0.9936, "derived": 0.7902, "soft": 0.7878, "long_horizon": 0.9648, "valid_novelty": 0.5487 }, "B": { "hard": 1.0, "derived": 0.7915, "soft": 0.7859, "long_horizon": 0.9676, "valid_novelty": 0.551 }, "C": { "hard": 1.0, "derived": 1.0, "soft": 0.7783, "long_horizon": 0.9818, "valid_novelty": 0.7474 } }, "pure_creative": { "A": { "raw_novelty": 0.8889, "pattern_entropy": 0.7199 }, "C": { "raw_novelty": 0.9864, "pattern_entropy": 0.2284 }, "D_elastic_posthoc": { "raw_novelty": 0.9225, "pattern_entropy": 0.7638 } }, "eight_seed_deltas": { "C_minus_B_derived": { "mean": 0.1865, "sign": "8/8 positive" }, "C_minus_A_pattern_entropy": { "mean": -0.3894, "sign": "8/8 negative" } }, "B_literal_fallback_rate": 0.286 }, "eml_interpretation": "Not a simple reasoning-up / imagination-down trade-off: coherence and valid novelty rise, soft-preference fit dips slightly, and the breadth tax is a selection-policy effect that separating exploration from commitment recovers. The elastic diagnostic is post-hoc and not part of the primary result.", "eml_limitations": [ "Controlled synthetic witness only; does not demonstrate that a frontier LLM shows the same effect." ], "eml_controls": [ "identical candidate pools for A/B/C", "pure-creative negative control", "post-hoc elastic diagnostic labelled as such" ], "eml_random_seeds": [ "20260909", "8 fixed secondary seeds" ], "eml_run_count": 9, "eml_result_type": "MIXED", "eml_software_environment": "Python; synthetic generators and scorers; no network, no LLM.", "eml_reproduction_instructions": "Extract PACC-Hybrid-Lab_v0.1_SYNTHETIC_FINAL.zip; python -m pytest -q; results in results/*.json and docs/PACC_HYBRID_v0.1_RESULTS.md.", "eml_completed_at": "2026-09-09", "eml_data_basis": "SYNTHETIC", "eml_dataset_ids": [ "DAT-2026-0002" ], "eml_benchmark_ids": [ "BEN-2026-0003" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0021/", "json": "/ai/experiments/EXP-2026-0021/index.json", "relations": [ { "id": "REL-2026-0313", "predicate": "runs_on", "source": "EXP-2026-0021", "target": "SYS-2026-0003", "status": "ACTIVE" }, { "id": "REL-2026-0314", "predicate": "uses_benchmark", "source": "EXP-2026-0021", "target": "BEN-2026-0003", "status": "ACTIVE" }, { "id": "REL-2026-0315", "predicate": "uses_dataset", "source": "EXP-2026-0021", "target": "DAT-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0316", "predicate": "tests", "source": "EXP-2026-0021", "target": "THY-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0317", "predicate": "produced", "source": "EXP-2026-0021", "target": "ART-2026-0034", "status": "ACTIVE" }, { "id": "REL-2026-0318", "predicate": "produces", "source": "EXP-2026-0021", "target": "RST-2026-0013", "status": "ACTIVE" }, { "id": "REL-2026-0322", "predicate": "extends", "source": "EXP-2026-0022", "target": "EXP-2026-0021", "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 } }