實驗EXP-2026-0002v0.1

R1——對四個基線的決定性語義比較

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。

研究狀態: STABLE 目前的研究結論相對穩定
證據等級: E2 受控實驗
結果: MIXED
資料基礎: DETERMINISTIC RUNTIME 在真實 runtime 裡執行的決定性情境；程式碼與做法都列出，數字是什麼就是什麼。
版本: 0.1
更新: 2026-09-08
建立: 2026-09-08
領域: AI Architecture, Evaluation, Agent Systems
計畫: PRG-2026-0001 自適應世界狀態系統的第一原理框架
作者: Neo.K (EveMissLab)
AI 協作: Sol (GPT-5.6, OpenAI ChatGPT)

假設

hypothesis: AER's different ownership and update semantics survive into observable runtime behaviour when compared with progressively stronger baselines.

設定

software_environment: Python 3.11+, SQLite; no network, no external database, no LLM API required.

執行

run_count

controls

B4 deliberately stronger than B3 so ordinary event invalidation and external memory are not attributed to AER.

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

詮釋

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).

限制

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.

重現

reproduction_instructions: Extract the round's FINAL bundle; python -m pytest -q; python -m examples.research_assistant_demo; python -m benchmarks.<round benchmark>. Checksums in SHA256SUMS.txt.

結果

來源	關係	目標	狀態	ID
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`produces`	`RST-2026-0001` R1 比較表	`ACTIVE`	`REL-2026-0112`

記錄欄位

completed_at: 2026-09-08

關係

來源	關係	目標	狀態	ID
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`runs_on`	`SYS-2026-0001` AER-0——自適應認識 runtime MVP	`ACTIVE`	`REL-2026-0105`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`uses_benchmark`	`BEN-2026-0002` AER-0 架構比較套件（R1–R6）	`ACTIVE`	`REL-2026-0106`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`tests`	`THY-2026-0001` 非對稱時空張力：時間異質的世界知識	`ACTIVE`	`REL-2026-0107`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`tests`	`THY-2026-0002` Canonical 符號狀態與 candidate → verify → commit 權限	`ACTIVE`	`REL-2026-0108`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`tests`	`THY-2026-0003` 智能架構吸引子	`ACTIVE`	`REL-2026-0109`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`extends`	`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`ACTIVE`	`REL-2026-0110`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`produced`	`ART-2026-0015` AER-0 MVP v0.1 Architecture Comparison R1 `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_Architecture_Comparison_R1.zip`	`ACTIVE`	`REL-2026-0111`
`EXP-2026-0002` R1——對四個基線的決定性語義比較	`produces`	`RST-2026-0001` R1 比較表	`ACTIVE`	`REL-2026-0112`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`extends`	`EXP-2026-0002` R1——對四個基線的決定性語義比較	`ACTIVE`	`REL-2026-0121`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0002/

機器可讀

/ai/experiments/EXP-2026-0002/index.json

快照

AI-SNAPSHOT-v0.1-fe85b9694a45

來源歷程

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