{ "section": "results", "kind": "result", "canonical": "https://evemisslab.com/ai/results/", "count": 18, "records": [ { "id": "RST-2026-0014", "kind": "result", "label": "Real local-model A/B/C table (Qwythos-9B-v2)", "created_at": "2026-09-11", "updated_at": "2026-09-11", "values": { "eml_status": "STABLE", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0014/", "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 v0.2 protocol executed for the first time on a real language model — a local open-weight 9B (Qwythos-9B-v2, Q4_K_M, Ollama, thinking off) as generator, selector and judge; 16 tasks × 2 repetitions × 4 candidates, 380 calls, 32 rows per condition. The PACC runtime (C) gains on supersession alignment (+0.031 vs B, +0.097 vs A) and repair success (+0.070 / +0.094), the two axes the canonical-intent compilation step exists for; derived coherence (+0.011) and intent persistence (−0.002) do not move; valid novelty is slightly lower (−0.045 vs B). Most per-task pairs are ties because the 9B judge saturates near 1.0, and with two repetitions per task the judge's free-text pattern labels never repeat, so creative breadth is not measurable. The conditions chose different candidates in 69 % of task × repetition pairs.", "eml_summary_zh": "v0.2 協定第一次在真實語言模型上執行——本地開放權重 9B（Qwythos-9B-v2、Q4_K_M、Ollama、關閉思考）同時當生成器、選擇器與評審；16 題 × 2 次 × 4 候選，380 次呼叫，每條件 32 筆。PACC runtime（C）在 supersession 對齊（相對 B +0.031、相對 A +0.097）與修復成功率（+0.070／+0.094）上升——正是 canonical intent 編譯步驟存在的那兩個軸；衍生一致性（+0.011）與意圖持續（−0.002）沒有動；有效新穎度略低（相對 B −0.045）。多數逐題配對是平手，因為 9B 評審在接近 1.0 處飽和；每題只重複兩次，評審的自由文字 pattern 標籤從不重複，所以創造廣度量不出來。三個條件在 69 % 的題 × 次配對中選了不同的候選。", "eml_label_zh": "真實本地模型 A/B/C 表（Qwythos-9B-v2）", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "REAL MODEL", "eml_result_type": "MIXED", "eml_metrics": { "overall": { "A_llm_only": { "hard_adherence": 0.9875, "derived_coherence": 0.9812, "intent_persistence": 0.9875, "supersession_alignment": 0.8094, "repair_success": 0.775, "usefulness": 0.9528, "semantic_novelty": 0.8084, "valid_novelty": 0.8475, "literal_check_mean": 0.9792, "within_task_pattern_entropy_mean": 1.0 }, "B_hard_verifier": { "hard_adherence": 0.9859, "derived_coherence": 0.9797, "intent_persistence": 0.9875, "supersession_alignment": 0.875, "repair_success": 0.7984, "usefulness": 0.9503, "semantic_novelty": 0.7725, "valid_novelty": 0.8606, "literal_check_mean": 0.9792, "within_task_pattern_entropy_mean": 1.0 }, "C_pacc_runtime": { "hard_adherence": 1.0, "derived_coherence": 0.9906, "intent_persistence": 0.9853, "supersession_alignment": 0.9062, "repair_success": 0.8688, "usefulness": 0.9516, "semantic_novelty": 0.7897, "valid_novelty": 0.8153, "literal_check_mean": 0.9792, "within_task_pattern_entropy_mean": 1.0 } }, "deltas": { "C-B": { "hard_adherence": 0.0141, "derived_coherence": 0.0109, "intent_persistence": -0.0022, "supersession_alignment": 0.0312, "repair_success": 0.0703, "usefulness": 0.0012, "semantic_novelty": 0.0172, "valid_novelty": -0.0453, "literal_check_mean": 0.0, "within_task_pattern_entropy_mean": 0.0 }, "C-A": { "hard_adherence": 0.0125, "derived_coherence": 0.0094, "intent_persistence": -0.0022, "supersession_alignment": 0.0969, "repair_success": 0.0938, "usefulness": -0.0012, "semantic_novelty": -0.0188, "valid_novelty": -0.0322, "literal_check_mean": 0.0, "within_task_pattern_entropy_mean": 0.0 }, "B-A": { "hard_adherence": -0.0016, "derived_coherence": -0.0016, "intent_persistence": 0.0, "supersession_alignment": 0.0656, "repair_success": 0.0234, "usefulness": -0.0025, "semantic_novelty": -0.0359, "valid_novelty": 0.0131, "literal_check_mean": 0.0, "within_task_pattern_entropy_mean": 0.0 } }, "selection_agreement": { "A=B": 0.5625, "A=C": 0.40625, "B=C": 0.46875, "all_same": 0.3125 } }, "eml_interpretation": "Against the v0.2 predeclared interpretation: the predicted coherence and intent-persistence gains over B are not observed; raw novelty did not decrease (semantic novelty +0.017 vs B); the predicted breadth collapse cannot be tested at this repetition count. What did appear — governance gains on supersession and repair with a valid-novelty cost concentrated in multi_constraint and repair tasks — is mechanism-consistent but small, untested statistically, and runs opposite to the synthetic v0.1 valid-novelty picture (+0.196 there). One model, one run, one same-model judge: a first real data point, not a verdict on the architecture.", "eml_limitations": [ "Descriptive deltas from one local run with a same-model judge." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0014/", "json": "/ai/results/RST-2026-0014/index.json" }, { "id": "RST-2026-0015", "kind": "result", "label": "Run 2: no reliable condition difference; breadth not reduced (64 rows)", "created_at": "2026-09-11", "updated_at": "2026-09-11", "values": { "eml_status": "STABLE", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0015/", "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": "C vs B: supersession +0.0005, repair -0.0125, derived coherence -0.0075, intent -0.0114, valid novelty -0.0187; label-free breadth: cluster entropy C 0.923 / A 0.909 / B 0.864.", "eml_summary_zh": "C 相對 B：supersession +0.0005、修復 -0.0125、衍生一致性 -0.0075、意圖 -0.0114、有效新穎度 -0.0187；標籤無關廣度：群熵 C 0.923／A 0.909／B 0.864。", "eml_label_zh": "第二次執行：條件間無可靠差異；廣度未縮減（64 筆）", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "REAL MODEL", "eml_result_type": "NEGATIVE", "eml_metrics": { "deltas": { "C-B": { "hard_adherence": -0.0144, "derived_coherence": -0.0075, "intent_persistence": -0.0114, "supersession_alignment": 0.0005, "repair_success": -0.0125, "usefulness": -0.012, "semantic_novelty": 0.0117, "valid_novelty": -0.0187, "literal_check_mean": -0.0052 }, "C-A": { "hard_adherence": -0.0222, "derived_coherence": -0.0247, "intent_persistence": -0.0157, "supersession_alignment": -0.0294, "repair_success": -0.0423, "usefulness": -0.0192, "semantic_novelty": -0.0106, "valid_novelty": 0.0236, "literal_check_mean": 0.0 }, "B-A": { "hard_adherence": -0.0078, "derived_coherence": -0.0172, "intent_persistence": -0.0043, "supersession_alignment": -0.0298, "repair_success": -0.0298, "usefulness": -0.0072, "semantic_novelty": -0.0223, "valid_novelty": 0.0423, "literal_check_mean": 0.0052 } }, "breadth_label_free": { "A_llm_only": { "cluster_entropy_mean": 0.9091, "breadth_ratio_mean": 0.9475, "selected_mean_pairwise_distance_mean": 0.1909 }, "B_hard_verifier": { "cluster_entropy_mean": 0.8635, "breadth_ratio_mean": 0.9411, "selected_mean_pairwise_distance_mean": 0.1921 }, "C_pacc_runtime": { "cluster_entropy_mean": 0.9227, "breadth_ratio_mean": 0.9745, "selected_mean_pairwise_distance_mean": 0.1964 } }, "selection_agreement": { "A=B": 0.546875, "A=C": 0.546875, "B=C": 0.46875, "all_same": 0.34375 } }, "eml_interpretation": "The first run's governance gains did not replicate; the three conditions are practically equivalent on this model, and the PACC runtime does not narrow creative breadth.", "eml_limitations": [ "Descriptive; same-model judge; one model family; thinking off." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0015/", "json": "/ai/results/RST-2026-0015/index.json" }, { "id": "RST-2026-0016", "kind": "result", "label": "Run 3: valid novelty and repair up for the PACC runtime with thinking on; governance flat; breadth not reduced (32 rows)", "created_at": "2026-09-11", "updated_at": "2026-09-11", "values": { "eml_status": "STABLE", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0016/", "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": "C vs B: valid novelty +0.0687, repair +0.0153, semantic novelty +0.0166, derived coherence -0.0063, intent -0.0053, supersession -0.0059; C vs A: valid novelty +0.0375, repair +0.0466; label-free breadth ratio C 1.047 / A 0.960 / B 0.973.", "eml_summary_zh": "C 相對 B：有效新穎度 +0.0687、修復 +0.0153、語義新穎度 +0.0166、衍生一致性 -0.0063、意圖 -0.0053、supersession -0.0059；C 相對 A：有效新穎度 +0.0375、修復 +0.0466；標籤無關廣度比 C 1.047／A 0.960／B 0.973。", "eml_label_zh": "第三次執行：開啟思考後 PACC runtime 的有效新穎度與修復上升；治理持平；廣度未縮減（32 筆）", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "REAL MODEL", "eml_result_type": "MIXED", "eml_metrics": { "deltas": { "C-B": { "hard_adherence": -0.0069, "derived_coherence": -0.0063, "intent_persistence": -0.0053, "supersession_alignment": -0.0059, "repair_success": 0.0153, "usefulness": 0.0044, "semantic_novelty": 0.0166, "valid_novelty": 0.0687, "literal_check_mean": 0.0 }, "C-A": { "hard_adherence": -0.0038, "derived_coherence": -0.0013, "intent_persistence": -0.0041, "supersession_alignment": -0.0034, "repair_success": 0.0466, "usefulness": -0.0003, "semantic_novelty": 0.0128, "valid_novelty": 0.0375, "literal_check_mean": 0.0 }, "B-A": { "hard_adherence": 0.0031, "derived_coherence": 0.005, "intent_persistence": 0.0012, "supersession_alignment": 0.0025, "repair_success": 0.0312, "usefulness": -0.0047, "semantic_novelty": -0.0037, "valid_novelty": -0.0312, "literal_check_mean": 0.0 } }, "paired_wins_ties_losses": { "C-B": { "hard_adherence": "1-28-3", "derived_coherence": "1-26-5", "intent_persistence": "0-29-3", "supersession_alignment": "1-27-4", "repair_success": "1-29-2", "usefulness": "5-22-5", "semantic_novelty": "7-18-7", "valid_novelty": "6-21-5" }, "C-A": { "hard_adherence": "0-29-3", "derived_coherence": "2-26-4", "intent_persistence": "0-30-2", "supersession_alignment": "1-28-3", "repair_success": "2-28-2", "usefulness": "6-22-4", "semantic_novelty": "8-18-6", "valid_novelty": "5-20-7" } }, "breadth_label_free": { "A_llm_only": { "cluster_entropy_mean": 0.75, "breadth_ratio_mean": 0.9597, "selected_mean_pairwise_distance_mean": 0.2079 }, "B_hard_verifier": { "cluster_entropy_mean": 0.6875, "breadth_ratio_mean": 0.9727, "selected_mean_pairwise_distance_mean": 0.2087 }, "C_pacc_runtime": { "cluster_entropy_mean": 0.875, "breadth_ratio_mean": 1.0474, "selected_mean_pairwise_distance_mean": 0.2275 } }, "selection_agreement": { "A=B": 0.5625, "A=C": 0.46875, "B=C": 0.46875, "all_same": 0.34375 } }, "eml_interpretation": "The valid-novelty half of the synthetic prediction appears in the means, at a third of the synthetic size, once the model reasons — carried by a few large single-task wins (per-pair 6–21–5 vs B); the coherence/intent half and the breadth-loss prediction do not appear. Unreplicated: a same-size gain in run 1 vanished at 64 rows.", "eml_limitations": [ "Descriptive; 32 rows; same-model judge; one model family; single thinking budget." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0016/", "json": "/ai/results/RST-2026-0016/index.json" }, { "id": "RST-2026-0007", "kind": "result", "label": "v0.2 adversarial geometry: N3 converges, N2 crosses the representation gate", "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/results/RST-2026-0007/", "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": "N3 held-out JS 0.014454 (Level 3); N2 held-out JS 0.053327 > 0.05 (Level 1); N0/N1 0.023921 (Level 3).", "eml_summary_zh": "N3 held-out JS 0.014454（Level 3）；N2 held-out JS 0.053327 > 0.05（Level 1）；N0/N1 0.023921（Level 3）。", "eml_label_zh": "v0.2 對抗幾何：N3 收斂、N2 越過表徵門檻", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "MIXED", "eml_metrics": { "n2_heldout_js": 0.053327, "gate": 0.05, "n3_heldout_js": 0.014454 }, "eml_interpretation": "Convergence is basin-dependent; the preregistered threshold did its job without being moved.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0007/", "json": "/ai/results/RST-2026-0007/index.json" }, { "id": "RST-2026-0008", "kind": "result", "label": "v0.4: latent dependence coordinate not recovered", "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/results/RST-2026-0008/", "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": "Dependence-coordinate pass count 0 for all four systems in every seed; in high correlation real JS ≈ 0.0398 is below the 0.05 absolute gate but no better than shuffled (≈ 0.0400) or constant (≈ 0.0397).", "eml_summary_zh": "四個系統在每個 seed 下依賴座標通過數皆為 0；高相關下真實 JS ≈ 0.0398 低於 0.05 絕對門檻，但不比 shuffled（≈ 0.0400）或 constant（≈ 0.0397）好。", "eml_label_zh": "v0.4：潛在依賴座標無法重建", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "NEGATIVE", "eml_metrics": { "dependence_pass": 0, "systems": 4 }, "eml_interpretation": "Low absolute error ⇏ meaningful coordinate map; the negative-control gate is what stops a near-baseline predictor from being mislabelled latent-state equivalence.", "eml_limitations": [ "'contradicts' the universal direct-affine reading only; the task-level reading survives." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0008/", "json": "/ai/results/RST-2026-0008/index.json" }, { "id": "RST-2026-0009", "kind": "result", "label": "v0.6: composed coordinate 4/4, direct 0/4", "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/results/RST-2026-0009/", "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": "Composed latent JS ≪ shuffled/constant and ≪ broken composition for every family and geometry (e.g. 0.003603 vs 0.061508 vs 0.058196, moderate N0).", "eml_summary_zh": "每個家族與幾何下組合潛在 JS 都 ≪ shuffled／constant 且 ≪ 弄壞的組合（例如中相關 N0：0.003603 vs 0.061508 vs 0.058196）。", "eml_label_zh": "v0.6：組合座標 4/4、直接映射 0/4", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "POSITIVE", "eml_metrics": { "composed_pass": "4/4", "direct_pass": "0/4" }, "eml_interpretation": "The latent probability coordinate is hierarchical/compositional relative to these non-probabilistic states rather than directly affine in the raw canonical state.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0009/", "json": "/ai/results/RST-2026-0009/index.json" }, { "id": "RST-2026-0010", "kind": "result", "label": "v0.8 basin map", "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/results/RST-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": "Frozen chart fitted at q* = 0.20: N0/N1/N3 pass on {0.06 … 0.33}, N2 on {0.06 … 0.30}; first failing gate at the edge is negative-control discrimination (ratio ≈ 0.858 at q = 0.36 for N0/N1); local refit 9/9.", "eml_summary_zh": "在 q* = 0.20 擬合的凍結 chart：N0/N1/N3 在 {0.06 … 0.33} 通過、N2 在 {0.06 … 0.30}；邊緣最先失敗的門檻是負控制判別（N0/N1 在 q = 0.36 比值 ≈ 0.858）；本地重擬合 9/9。", "eml_label_zh": "v0.8 吸引域圖", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "MIXED", "eml_metrics": { "N0_N1_N3_first_fail_q": 0.36, "N2_first_fail_q": 0.33 }, "eml_interpretation": "Shared composed coordinate + family-specific finite basins.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0010/", "json": "/ai/results/RST-2026-0010/index.json" }, { "id": "RST-2026-0011", "kind": "result", "label": "v0.10 cocycle: path disagreement ≈ 10⁻⁵ vs control ≈ 10⁻¹", "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/results/RST-2026-0011/", "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": "Direct-vs-composed latent JS 3.5×10⁻⁵ (N0/N1), 4.0×10⁻⁵ (N2), 2.7×10⁻⁵ (N3); real/shuffled ratio ≈ 3×10⁻⁴; both paths accurate to chart C.", "eml_summary_zh": "直接 vs 組合的潛在 JS：3.5×10⁻⁵（N0/N1）、4.0×10⁻⁵（N2）、2.7×10⁻⁵（N3）；真實／shuffled 比 ≈ 3×10⁻⁴；兩條路徑對 chart C 都準確。", "eml_label_zh": "v0.10 cocycle：路徑分歧 ≈ 10⁻⁵ vs 控制 ≈ 10⁻¹", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "POSITIVE", "eml_metrics": { "families_pass": "4/4", "secondary_pass_rate": 1.0 }, "eml_interpretation": "Forward cocycle coherence is robust where three charts overlap.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0011/", "json": "/ai/results/RST-2026-0011/index.json" }, { "id": "RST-2026-0012", "kind": "result", "label": "v0.11 reverse destination bias", "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/results/RST-2026-0012/", "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": "Reverse paths agree with each other (latent JS ≈ 10⁻⁵) but both land ≈ 0.011–0.015 from the true chart-A coordinate, above the 0.01 gate, for every family and at every scale tested.", "eml_summary_zh": "反向路徑彼此一致（潛在 JS ≈ 10⁻⁵），但兩者都落在離真正 chart-A 座標 ≈ 0.011–0.015 處，高於 0.01 門檻，所有家族、所有測試規模皆然。", "eml_label_zh": "v0.11 反向目的偏差", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "MIXED", "eml_metrics": { "reverse_pass": "0/4 primary+secondary, 0/3 large", "path_coherence": "≈1e-5" }, "eml_interpretation": "Path coherence is not enough for atlas closure; the bias is the object v0.12–v0.13 then tried to explain.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0012/", "json": "/ai/results/RST-2026-0012/index.json" }, { "id": "RST-2026-0013", "kind": "result", "label": "Hybrid v0.1 A/B/C deltas", "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/results/RST-2026-0013/", "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": "C − B: derived coherence +0.2085, long-horizon retention +0.0142, valid novelty +0.1964, soft-intent −0.0076; C − A pattern entropy −0.4915 (pure creative), recovered to 0.7638 by post-hoc elastic selection.", "eml_summary_zh": "C − B：衍生一致性 +0.2085、長程保持 +0.0142、有效新穎度 +0.1964、軟意圖 −0.0076；C − A pattern entropy −0.4915（純創意），事後 elastic 選擇恢復到 0.7638。", "eml_label_zh": "Hybrid v0.1 A/B/C 差值", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "MIXED", "eml_metrics": { "derived_delta_C_B": 0.2085, "valid_novelty_delta_C_B": 0.1964, "soft_delta_C_B": -0.0076, "entropy_delta_C_A": -0.4915, "elastic_entropy": 0.7638 }, "eml_interpretation": "Gains come from derived dependency coherence and constraint-satisfying novelty, not from more rejection; the breadth cost is mitigable without relaxing commit constraints.", "eml_limitations": [ "Synthetic scoring; a real-model result is required before any claim about language models." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0013/", "json": "/ai/results/RST-2026-0013/index.json" }, { "id": "RST-2026-0001", "kind": "result", "label": "R1 comparison table", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-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": "AER-0: 0 stale, 3 recomputations, 0 stable refreshes, 6 workflow reuses, blocks the no-provenance fact, catches the conflicting write. B4: 0 stale, 2 recomputations, 0 stable refreshes, 6 reuses, blocks neither.", "eml_summary_zh": "AER-0：0 過期、3 次重算、0 次穩定節點刷新、6 次 workflow 重用、擋下無 provenance 事實、抓到衝突寫入。B4：0 過期、2 次重算、0 次穩定刷新、6 次重用、兩者都不擋。", "eml_label_zh": "R1 比較表", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_result_type": "MIXED", "eml_metrics": { "aer_recomputations": 3, "b4_recomputations": 2, "aer_only": [ "blocks no-provenance fact", "VersionConflict on stale expected version" ] }, "eml_interpretation": "Tension scheduling paid one proactive refresh that pure event invalidation did not need in an event-rich world; the surviving distinction is mutation authority, not refresh efficiency.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0001/", "json": "/ai/results/RST-2026-0001/index.json" }, { "id": "RST-2026-0002", "kind": "result", "label": "R2 classification matrix", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0002/", "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": "Seven axes CONVERGED or partially converged (four of them LangGraph richer); six axes AER-default-distinct; graph semantics semantically distinct.", "eml_summary_zh": "七個軸收斂或部分收斂（其中四個 LangGraph 更豐富）；六個軸為 AER 預設獨有；圖語義為語義上不同。", "eml_label_zh": "R2 分類矩陣", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_result_type": "MIXED", "eml_metrics": { "converged_or_partial": 7, "langgraph_richer": 4, "aer_default_distinct": 6 }, "eml_interpretation": "Supports the attractor hypothesis for external state, persistence, graph/workflow execution, history and durable recovery; moves the remaining disagreement upward into what state means, who may mutate it and what a mutation requires.", "eml_limitations": [ "Documentary evidence on the LangGraph side; no executable replay." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0002/", "json": "/ai/results/RST-2026-0002/index.json" }, { "id": "RST-2026-0003", "kind": "result", "label": "R3: AER-ECT ≈ centralized application gate", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-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": "On unprovenanced-write blocking, stale-write conflict, automatic audit, dependency binding and single governance site, the centralized application gate and AER-ECT both PASS; the scattered application fails the omission witnesses.", "eml_summary_zh": "在擋無 provenance 寫入、過期寫入衝突、自動 audit、依賴綁定與單一治理站點上，集中式應用 gate 與 AER-ECT 都 PASS；分散式應用在遺漏見證上失敗。", "eml_label_zh": "R3：AER-ECT ≈ 集中式應用 gate", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_result_type": "NEGATIVE", "eml_metrics": { "aer_ect_vs_central_gate": "equal on all tested semantics", "scattered_failures": 3 }, "eml_interpretation": "The most important negative result of the line: what AER-ECT computes can be reproduced by an application; what changes is where the obligation lives.", "eml_limitations": [ "'contradicts' here means the computational-uniqueness reading of ECT; the architectural-elevation reading survives." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0003/", "json": "/ai/results/RST-2026-0003/index.json" }, { "id": "RST-2026-0004", "kind": "result", "label": "R5 ten-scenario tally", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0004/", "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": "5 PREVENTED / 3 OPEN_DETECTED / 1 OPEN_UNDETECTED / 1 SERIALIZED_TO_SEMANTIC_CONFLICT; the undetected case is the coherent full-database forgery.", "eml_summary_zh": "5 PREVENTED／3 OPEN_DETECTED／1 OPEN_UNDETECTED／1 SERIALIZED_TO_SEMANTIC_CONFLICT；未偵測的那一例是連貫的整庫偽造。", "eml_label_zh": "R5 十情境統計", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_result_type": "MIXED", "eml_metrics": { "prevented": 5, "open_detected": 3, "open_undetected": 1, "serialized": 1 }, "eml_interpretation": "No external trust anchor ⇒ no full-DB tamperproof claim — a structural result that defines R6.", "eml_limitations": [ "Retained negative witnesses are part of the verdict, not implementation accidents." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0004/", "json": "/ai/results/RST-2026-0004/index.json" }, { "id": "RST-2026-0005", "kind": "result", "label": "R6: forgery detection flips under an external anchor", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0005/", "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 same coherent full-DB forgery: internal audit OPEN_UNDETECTED, external anchor audit OPEN_DETECTED; prefix truncation: undetected without a trusted head, detected with one.", "eml_summary_zh": "同一個連貫整庫偽造：內部稽核 OPEN_UNDETECTED、外部 anchor 稽核 OPEN_DETECTED；前綴截斷：無可信 head 未偵測、有則偵測。", "eml_label_zh": "R6：外部 anchor 下偽造偵測翻轉", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_result_type": "POSITIVE", "eml_metrics": { "forgery_internal": "OPEN_UNDETECTED", "forgery_external": "OPEN_DETECTED", "truncation_without_head": "OPEN_UNDETECTED", "truncation_with_head": "OPEN_DETECTED" }, "eml_interpretation": "Detection, not prevention; and only under the stated key and head trust assumptions.", "eml_limitations": [ "Not a Certificate Transparency or Rekor implementation; a smaller signed hash chain with an optional head receipt." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0005/", "json": "/ai/results/RST-2026-0005/index.json" }, { "id": "RST-2026-0006", "kind": "result", "label": "v0.1 primary table: Level 3 for N0/N1/N2, two families", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0006/", "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": "Held-out JS 0.000192 (N0/N1) and 0.008053 (N2) uniform; 0.002878 and 0.010109 heterogeneous; shuffled controls ≈ 0.31–0.33; N0↔N1 agreement 1.000, R² 1.000.", "eml_summary_zh": "均勻：held-out JS 0.000192（N0/N1）與 0.008053（N2）；異質：0.002878 與 0.010109；shuffled 控制組 ≈ 0.31–0.33；N0↔N1 一致度 1.000、R² 1.000。", "eml_label_zh": "v0.1 主要表：N0/N1/N2 皆 Level 3，兩個家族", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_result_type": "MIXED", "eml_metrics": { "level": { "N0": 3, "N1": 3, "N2": 3 }, "families": [ [ "N0", "N1" ], [ "N2" ] ] }, "eml_interpretation": "PACC-B/R/D supported as a controlled micro-environment witness; PACC-A not yet supported.", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0006/", "json": "/ai/results/RST-2026-0006/index.json" }, { "id": "RST-2026-0101", "kind": "result", "label": "Scaffolding response on three easy tasks: SSR = 1.0, 3.1× device energy at A5, 7.9–9.3× at A2–A4", "created_at": "2026-09-03", "updated_at": "2026-09-07", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0101/", "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": "Condition means (quality over available trials / wall s / device J): A0 0.5 / 10.21 / 1715.6; A1 0.5 / 9.87 / 1819.0; A2 0.5 / 79.09 / 15143.0; A3 0.6667 / 99.13 / 15921.5; A4 0.6667 / 69.08 / 13546.2; A5 0.5 / 31.91 / 5321.5. Energy ratio vs A0: A1 1.06, A2 8.827, A3 9.281, A4 7.896, A5 3.102. Total measured GPU energy 0.0891 kWh over 29.9 min of trial time; memory residency rises from 72.1 GiB·s (A0) to 714.6 GiB·s (A3).", "eml_summary_zh": "各條件平均（可用試驗的品質／wall 秒／裝置焦耳）：A0 0.5／10.21／1715.6；A1 0.5／9.87／1819.0；A2 0.5／79.09／15143.0；A3 0.6667／99.13／15921.5；A4 0.6667／69.08／13546.2；A5 0.5／31.91／5321.5。能量相對 A0：A1 1.06、A2 8.827、A3 9.281、A4 7.896、A5 3.102。36 次試驗共量得 GPU 能量 0.0891 kWh、試驗時間 29.9 分鐘；記憶體駐留從 A0 的 72.1 GiB·s 升到 A3 的 714.6 GiB·s。", "eml_label_zh": "三個簡單任務上的鷹架響應：SSR = 1.0，A5 的裝置能量 3.1×、A2–A4 7.9–9.3×", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0101", "eml_data_basis": "REAL MODEL", "eml_result_type": "MIXED", "eml_metrics": { "ssr": 1.0, "sdr": 0.0, "scm": { "device_energy_j": 3.1019, "wall_time_s": 3.1264 }, "by_condition": { "A0": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 10.21, "device_energy_j": 1715.6, "energy_ratio_vs_A0": 1.0, "gpu_peak_memory_gib": 7.23, "gpu_memory_residency_gib_s": 72.1, "gpu_utilization_integral_s": 6.57 }, "A1": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 9.87, "device_energy_j": 1819.0, "energy_ratio_vs_A0": 1.06, "gpu_peak_memory_gib": 7.32, "gpu_memory_residency_gib_s": 70.0, "gpu_utilization_integral_s": 6.26 }, "A2": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 79.09, "device_energy_j": 15143.0, "energy_ratio_vs_A0": 8.827, "gpu_peak_memory_gib": 7.28, "gpu_memory_residency_gib_s": 570.0, "gpu_utilization_integral_s": 54.09 }, "A3": { "quality_mean": 0.6667, "quality_n": 3, "success_rate": 0.6667, "wall_time_s": 99.13, "device_energy_j": 15921.5, "energy_ratio_vs_A0": 9.281, "gpu_peak_memory_gib": 7.34, "gpu_memory_residency_gib_s": 714.6, "gpu_utilization_integral_s": 70.02 }, "A4": { "quality_mean": 0.6667, "quality_n": 3, "success_rate": 0.6667, "wall_time_s": 69.08, "device_energy_j": 13546.2, "energy_ratio_vs_A0": 7.896, "gpu_peak_memory_gib": 7.28, "gpu_memory_residency_gib_s": 496.9, "gpu_utilization_integral_s": 46.93 }, "A5": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 31.91, "device_energy_j": 5321.5, "energy_ratio_vs_A0": 3.102, "gpu_peak_memory_gib": 7.24, "gpu_memory_residency_gib_s": 228.7, "gpu_utilization_integral_s": 22.17 } }, "marginal_yield": { "A0->A1": { "allocated_device_time_s": null, "device_energy_j": 0.0, "wall_time_s": null }, "A1->A2": { "allocated_device_time_s": null, "device_energy_j": 0.0, "wall_time_s": 0.0 }, "A2->A3": { "allocated_device_time_s": null, "device_energy_j": 0.00021406648843853404, "wall_time_s": 0.008315919866432606 }, "A3->A4": { "allocated_device_time_s": null, "device_energy_j": null, "wall_time_s": null }, "A4->A5": { "allocated_device_time_s": null, "device_energy_j": null, "wall_time_s": null } } }, "eml_interpretation": "The cost side of the scaffolding response curve is real and steep; the quality side is flat because the tasks were already solved at A0 and because the quality axis was confounded (RST-2026-0102). This is one point on the 'no gap' side of F4 with almost no weight: it neither supports nor refutes the scaffolding-separation hypothesis on non-trivial tasks. The A3/A4 0.667 is not a gain: the aborted CON-003 trials dropped out of the quality denominator and the surviving mean rose.", "eml_limitations": [ "quality_n is 4 (A0–A2, A5) or 3 (A3, A4) per condition because CODE-001 quality is unavailable and three trials aborted — means over 3–4 values.", "Device-measured GPU energy at ~24 % sampling overhead; not marginal energy." ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT) — 2026-09-07 diagnostic", "Splice (Claude Code, Anthropic) — execution and RESULT note" ], "eml_authors": [ "Neo.K (EveMissLab)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0101/", "json": "/ai/results/RST-2026-0101/index.json" }, { "id": "RST-2026-0102", "kind": "result", "label": "Diagnostic: the measured 'quality' was format compliance on 2 of 3 tasks; verifier serialization failed 3/18; the A3/A4 rise is a missingness artifact", "created_at": "2026-09-03", "updated_at": "2026-09-07", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/results/RST-2026-0102/", "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": "Strict output-contract compliance 12/36 (MATH-003 12/12, CODE-001 0/12, CON-003 0/12), but the non-canonical post-hoc check finds every completed selected output correct — math 12/12 canonical correct, code 11/11 selected outputs pass all hidden tests after outer Markdown fence removal, constraint 10/10 selected outputs satisfy all constraints after format-only normalization — 33/33 overall. Verifier-enabled trials 18, verifier-protocol failures 3 (A3 2/6, A4 1/6, A5 0/6), each after eight candidates had been generated. Tool calls 0, retries 0; 24 candidates abandoned on abort are neither selected nor discarded in the schema. Quality availability is reported as 22/36 in the aggregate and 33/36 in protocol_compliance.csv. Telemetry sampling wall fraction 0.244.", "eml_summary_zh": "嚴格輸出契約合規 12/36（MATH-003 12/12、CODE-001 0/12、CON-003 0/12），但非 canonical 的事後檢查發現所有完成的選中輸出都正確——數學 12/12 canonical correct、程式 11/11 selected outputs pass all hidden tests after outer Markdown fence removal、約束 10/10 selected outputs satisfy all constraints after format-only normalization——整體 33/33。啟用驗證器的試驗 18 次，驗證器協定失敗 3 次（A3 2/6、A4 1/6、A5 0/6），每次都在已生成八個候選之後。工具呼叫 0 次、重試 0 次；24 個在中止時被拋棄的候選在 schema 裡既非選中也非丟棄。品質可得率在聚合檔報 22/36、在 protocol_compliance.csv 報 33/36。遙測取樣占 wall time 的 0.244。", "eml_label_zh": "診斷：三題中兩題量到的「品質」是格式服從性；驗證器序列化失敗 3/18；A3/A4 的上升是缺值假象", "eml_primary_domain": "Evaluation", "eml_program_id": "PRG-2026-0101", "eml_data_basis": "REAL MODEL", "eml_result_type": "NEGATIVE", "eml_metrics": { "strict_protocol_compliance": { "count": 12, "total": 36, "rate": 0.3333333333333333 }, "posthoc_semantic_diagnostic": { "canonical": false, "math": "12/12 canonical correct", "code": "11/11 selected outputs pass all hidden tests after outer Markdown fence removal", "constraint": "10/10 selected outputs satisfy all constraints after format-only normalization", "completed_selected_outputs_correct": "33/33" }, "verifier_failure": { "count": 3, "verifier_enabled_trials": 18, "rate": 0.16666666666666666, "by_condition": { "A3": "2/6", "A4": "1/6", "A5": "0/6" } }, "operational_totals": { "model_invocations": 186, "trajectories": 162, "retries": 0, "tool_calls": 0, "verifier_passes": 18, "candidates_created": 162, "candidates_selected": 33, "candidates_discarded": 105, "failure_events": 6, "candidates_abandoned_on_abort": 24 }, "quality_availability_reporting": { "aggregate_analysis": "22/36", "protocol_compliance_csv": "33/36", "inconsistency": true }, "instrumentation": { "mean_sampling_call_wall_fraction": 0.2436, "target_sampling_ms": 250, "observed_cadence_ms": "335–350" }, "instrument_revisions_required_before_XA-07": [ "R1 typed subject/system failure is valid data, separate from instrument failure", "R2 split task_semantic_quality / output_contract_compliance / system_completion_reliability / verifier_protocol_reliability", "R3 failure-aware aggregation (no survivor means)", "R4 abandoned-candidate accounting", "R5 preserve verifier parse diagnostics", "R6 cheaper telemetry (persistent nvidia-smi / NVML)", "R7 tool-trigger tasks" ] }, "eml_interpretation": "Negative for the instrument, informative for the theory. Task semantic quality ≠ protocol/serialization compliance — the model solved everything it completed and was scored 0.5 on average for not obeying a JSON/no-fence contract; same-model verification reduced system reliability rather than raising quality; tool access ≠ tool utilization (enabled, never used). The bundle stays immutable as XA-06 empirical v0.1; the next step is to revise the instrument and re-run a small validation set, not to re-roll failures until they disappear.", "eml_limitations": [ "The post-hoc semantic check is explicitly non-canonical and does not make the strict outputs compliant.", "One model; whether stronger models obey the output contract is unknown." ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT) — 2026-09-07 diagnostic", "Splice (Claude Code, Anthropic) — execution and RESULT note" ], "eml_authors": [ "Neo.K (EveMissLab)" ] }, "canonical_url": "https://evemisslab.com/ai/results/RST-2026-0102/", "json": "/ai/results/RST-2026-0102/index.json" } ], "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 } }