實驗EXP-2026-0003v0.1

R2——對 LangGraph 1.2.11 的 source-grounded 結構比較

LangGraph 1.2.11（checkpoint 4.2.0、checkpoint-sqlite 3.1.1）裝不起來——對外 PyPI DNS 不可用——因此本輪釘住公開的 release／source 合約，與 AER-0 可執行的不變量比較。runtime 持有的持久狀態、checkpoint 歷史、版本追蹤、長期 store 與 TTL 記憶全部收斂（LangGraph 在 resume、time travel、並行控制與 delta checkpoint 上更豐富）。仍屬 AER 預設獨有的是：candidate → verify → commit、強制 fact provenance、節點層樂觀認識論 commit、任務條件化的張力刷新、capability／container 分離、明示的認識論算子路由，以及「圖」指的是認識論世界表徵而非控制流。

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: Against a real stateful agent runtime, some AER semantics remain distinct beyond 'external state outside the model'.

設定

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

程序

procedure: Pin LangGraph release 1.2.11 at commit 644815f (checkpoint base, PregelProtocol, BaseStore, Agent Protocol docs); classify each axis; keep AER invariants covered by the local suite.

執行

run_count

metrics

verdict

STRONG_CONVERGENCE_WITH_REMAINING_SEMANTIC_CORE

evidence_mode

SOURCE_GROUNDED_STRUCTURAL

executable_langgraph

NOT_RUN

classification

runtime_owned_persistent_state: CONVERGED
checkpoint_history: CONVERGED; LangGraph richer
version_tracking: CONVERGED, different granularity
ttl_memory: PARTIAL_CONVERGENCE
tension_refresh: AER_DEFAULT_DISTINCT
graph_semantics: SEMANTICALLY_DISTINCT
candidate_verify_commit: AER_DEFAULT_DISTINCT
mandatory_provenance: AER_DEFAULT_DISTINCT
pending_write_resume: LANGGRAPH_RICHER
time_travel_fork: LANGGRAPH_RICHER
capability_container_separation: AER_DEFAULT_DISTINCT; not a core LangGraph primitive found
epistemic_router: AER_DEFAULT_DISTINCT

詮釋

interpretation: The candidate AER core after R2 is epistemic world-state semantics + candidate/verify/commit authority + mandatory fact provenance + node-local tension refresh + capability/container separation + explicit epistemic-operator routing — a major compression of the whitepaper. Everything else is a recurring engineering form.

限制

limitations: Cross-runtime performance, trace and operational equivalence NOT MEASURED; AER side executable, LangGraph side documentary.
AER-0 is not a 'more advanced runtime' on the available evidence.

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-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`produces`	`RST-2026-0002` R2 分類矩陣	`ACTIVE`	`REL-2026-0123`

記錄欄位

completed_at: 2026-09-08

關係

來源	關係	目標	狀態	ID
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`runs_on`	`SYS-2026-0001` AER-0——自適應認識 runtime MVP	`ACTIVE`	`REL-2026-0116`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`uses_benchmark`	`BEN-2026-0002` AER-0 架構比較套件（R1–R6）	`ACTIVE`	`REL-2026-0117`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`tests`	`THY-2026-0003` 智能架構吸引子	`ACTIVE`	`REL-2026-0118`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`tests`	`THY-2026-0002` Canonical 符號狀態與 candidate → verify → commit 權限	`ACTIVE`	`REL-2026-0119`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`tests`	`THY-2026-0007` 能力記憶與載體中立計算：Reuse ≻ Adapt ≻ Create	`ACTIVE`	`REL-2026-0120`
`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`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`produced`	`ART-2026-0016` AER-0 MVP v0.1 Architecture Comparison R2 LangGraph `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_Architecture_Comparison_R2_LangGraph.zip`	`ACTIVE`	`REL-2026-0122`
`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`produces`	`RST-2026-0002` R2 分類矩陣	`ACTIVE`	`REL-2026-0123`
`EXP-2026-0004` R3——認識論 commit 交易 vs 分散式與集中式應用 gate	`extends`	`EXP-2026-0003` R2——對 LangGraph 1.2.11 的 source-grounded 結構比較	`ACTIVE`	`REL-2026-0132`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0003/

機器可讀

/ai/experiments/EXP-2026-0003/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