{ "id": "EXP-2026-0002", "kind": "experiment", "label": "R1 — deterministic semantics comparison against four baselines", "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/experiments/EXP-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": "Two facts (one stable, one changing at hours 8 and 16), eight queries over 17 simulated hours. B1 stateless recomputes every query; B2 fixed 6-hour TTL; B3 adds workflow memory; B4 an evented compound agent with event-driven invalidation. AER-0 matches B4 on zero stale answers, zero stable refreshes and workflow reuse, needs one more recomputation (3 vs 2) because its tension policy refreshes proactively, and is alone in blocking a no-provenance fact and catching a conflicting write.", "eml_summary_zh": "兩個事實（一穩定、一在第 8 與 16 小時改變），17 個模擬小時內 8 次查詢。B1 無狀態每次重算；B2 固定 6 小時 TTL；B3 加 workflow 記憶；B4 是帶事件驅動失效的複合 agent。AER-0 在零過期回答、零穩定節點刷新與 workflow 重用上與 B4 打平，因為張力政策主動刷新而多一次重算（3 vs 2），但只有它擋下無 provenance 的事實並抓到衝突寫入。", "eml_label_zh": "R1——對四個基線的決定性語義比較", "eml_primary_domain": "AI Architecture", "eml_domains": [ "Evaluation", "Agent Systems" ], "eml_program_id": "PRG-2026-0001", "eml_hypothesis": "AER's different ownership and update semantics survive into observable runtime behaviour when compared with progressively stronger baselines.", "eml_metrics": { "verdict": "AER_DISTINCT_ON_TESTED_SEMANTICS", "table": { "B1_stateless": { "stale": 0, "recomputation": 8, "stable_refresh": 0, "volatile_refresh": 0, "workflow_reuse": 0, "model_swap_preserves_state": false, "blocks_no_provenance": false, "catches_conflict": false }, "B2_fixed_ttl": { "stale": 2, "recomputation": 4, "stable_refresh": 2, "volatile_refresh": 2, "workflow_reuse": 0, "model_swap_preserves_state": true, "blocks_no_provenance": false, "catches_conflict": false }, "B3_memory_tools": { "stale": 2, "recomputation": 4, "stable_refresh": 2, "volatile_refresh": 2, "workflow_reuse": 6, "model_swap_preserves_state": true, "blocks_no_provenance": false, "catches_conflict": false }, "B4_evented_agent": { "stale": 0, "recomputation": 2, "stable_refresh": 0, "volatile_refresh": 2, "workflow_reuse": 6, "model_swap_preserves_state": true, "blocks_no_provenance": false, "catches_conflict": false }, "AER-0": { "stale": 0, "recomputation": 3, "stable_refresh": 0, "volatile_refresh": 3, "workflow_reuse": 6, "model_swap_preserves_state": true, "blocks_no_provenance": true, "catches_conflict": true } } }, "eml_interpretation": "Not a dominance result. Persistent memory across model swap, workflow reuse and selective event-driven refresh are not unique to AER once the baseline is strengthened; the measured difference collapses to state-mutation semantics (provenance gate, optimistic version conflict, candidate/verify/commit authority).", "eml_limitations": [ "B4 is a reference implementation of event-driven behaviour, not a real production framework (structural closure PARTIAL).", "Says nothing about intelligence, speed, cost in other environments, or whether an attractor exists." ], "eml_controls": [ "B4 deliberately stronger than B3 so ordinary event invalidation and external memory are not attributed to AER." ], "eml_run_count": 1, "eml_result_type": "MIXED", "eml_software_environment": "Python 3.11+, SQLite; no network, no external database, no LLM API required.", "eml_reproduction_instructions": "Extract the round's FINAL bundle; python -m pytest -q; python -m examples.research_assistant_demo; python -m benchmarks.. Checksums in SHA256SUMS.txt.", "eml_completed_at": "2026-09-08", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0002/", "json": "/ai/experiments/EXP-2026-0002/index.json", "relations": [ { "id": "REL-2026-0105", "predicate": "runs_on", "source": "EXP-2026-0002", "target": "SYS-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0106", "predicate": "uses_benchmark", "source": "EXP-2026-0002", "target": "BEN-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0107", "predicate": "tests", "source": "EXP-2026-0002", "target": "THY-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0108", "predicate": "tests", "source": "EXP-2026-0002", "target": "THY-2026-0002", "status": "ACTIVE" }, { "id": "REL-2026-0109", "predicate": "tests", "source": "EXP-2026-0002", "target": "THY-2026-0003", "status": "ACTIVE" }, { "id": "REL-2026-0110", "predicate": "extends", "source": "EXP-2026-0002", "target": "EXP-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0111", "predicate": "produced", "source": "EXP-2026-0002", "target": "ART-2026-0015", "status": "ACTIVE" }, { "id": "REL-2026-0112", "predicate": "produces", "source": "EXP-2026-0002", "target": "RST-2026-0001", "status": "ACTIVE" }, { "id": "REL-2026-0121", "predicate": "extends", "source": "EXP-2026-0003", "target": "EXP-2026-0002", "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 } }