實驗EXP-2026-0001v0.1

AER-0 MVP v0.1 收束：不變量能不能被執行？

核准的 Python + SQLite runtime 在 mssp-tdd-apr 下建成，並以行為、結構、判別三類見證收束：candidate gate、provenance 驗證、過期版本衝突、穩定 vs 易變排程、shock 觸發、verifier 拒絕、workflow reuse／adapt／create、模型替換、無模型核心、端到端已驗證 commit。25 個測試；refresh benchmark 在固定 TTL 下選了 2 個節點、在張力排程下只選 1 個易變節點；密封封存包乾淨解壓重播通過後才發布。

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: POSITIVE
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: The scoped MVP invariants (canonical state ownership, candidate gating, provenance, versioned commit, selective refresh, capability/container separation, workflow reuse, model replaceability) can be implemented with positive and falsifying executable witnesses.

設定

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

程序

procedure: TDD under mssp-tdd-apr; full suite, research-assistant demo and refresh benchmark run before packaging; checksum-verified clean extraction replayed after sealing.

執行

run_count

metrics

tests_passed

refresh_benchmark

fixed_6h_ttl_nodes_refreshed: 2
aer_tension_nodes_refreshed: 1

closure

behavioral: PASS
structural: PASS
discriminative: PASS
independent_twin: NotMeasured
production_readiness: NotClaimed
general_ai_superiority: NotMeasured

詮釋

interpretation: A mechanism closure, not a claim of AI superiority: the declared invariants exist in code, are exercised by falsifying witnesses, and survive a fresh-process replay.

限制

limitations: DEGRADED-TWIN: only one live execution context; no simulated independent verdict claimed.
Not measured: performance against production agent frameworks, live research accuracy, distributed semantics, security hardening, real heterogeneous backends, multi-day drift.

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.

記錄欄位

completed_at: 2026-09-08

關係

來源	關係	目標	狀態	ID
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`runs_on`	`SYS-2026-0001` AER-0——自適應認識 runtime MVP	`ACTIVE`	`REL-2026-0099`
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`uses_benchmark`	`BEN-2026-0002` AER-0 架構比較套件（R1–R6）	`ACTIVE`	`REL-2026-0100`
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`tests`	`THY-2026-0002` Canonical 符號狀態與 candidate → verify → commit 權限	`ACTIVE`	`REL-2026-0101`
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`tests`	`THY-2026-0001` 非對稱時空張力：時間異質的世界知識	`ACTIVE`	`REL-2026-0102`
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`tests`	`THY-2026-0007` 能力記憶與載體中立計算：Reuse ≻ Adapt ≻ Create	`ACTIVE`	`REL-2026-0103`
`EXP-2026-0001` AER-0 MVP v0.1 收束：不變量能不能被執行？	`produced`	`ART-2026-0014` AER-0 MVP v0.1 FINAL `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_FINAL.zip`	`ACTIVE`	`REL-2026-0104`
`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`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0001/

機器可讀

/ai/experiments/EXP-2026-0001/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