實驗EXP-2026-0013v0.1

PACC-Lab v0.6——階層式組合座標

一個預登記的 95 維組合座標——已驗證任務狀態映射的 held-out 決策商，結合當前關係模式與有界的交互項——在兩種幾何下對四個家族都預測出 Bayesian 共同因座標：組合潛在 JS 0.0034–0.0073，shuffled／constant 為 0.040–0.062，刻意弄壞的組合為 0.040–0.060；反事實 JS 0.0018–0.0047；四個次要 seed 下 direct 通過率 0.0、composed 1.0。

研究狀態: STABLE 目前的研究結論相對穩定
證據等級: E3 重複實驗
結果: POSITIVE
資料基礎: SYNTHETIC 合成數據與理論推理。現在很多人把合成數據當成真的；這個實驗室刻意反過來說——在真正的混合模型出現之前，推論就只是推論，理論上可能不等於實際上可能。
版本: 0.1
更新: 2026-09-09
建立: 2026-09-09
領域: Model Representation, Evaluation, Formal AI
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 latent probability coordinate is compositional relative to the non-probabilistic state: decision quotient + relation pattern, not the raw state, maps to the common-cause posterior.

設定

model_ids: MOD-2026-0001 N0——帶號支持
MOD-2026-0002 N1——序數錦標賽
MOD-2026-0003 N2——帶號圖
MOD-2026-0004 N3——約束競爭
MOD-2026-0005 Bayesian 參考（精確後驗／Beta-Bernoulli／聯合共同因／HMM）
dataset_ids: DAT-2026-0001 PACC 合成證據世界
benchmark_ids: BEN-2026-0001 PACC 微型實驗室協定 v0.1（凍結門檻）
software_environment: Python; deterministic seeded generators; no network, no LLM.

執行

run_count

random_seeds

20260909
4 secondary seeds

controls

shuffled-target mapping
constant prediction
broken composition (v0.6+)
target-local refit (v0.7+)

metrics

verdict

HIERARCHICAL_COMPOSED_COORDINATE_RESCUES_LATENT_DEPENDENCE

direct_robust

0/4

composed_robust

4/4

moderate_N0

composed_latent_js: 0.003603
best_control: 0.061508
broken_composition: 0.058196
counterfactual: 0.00278

high_N0

composed_latent_js: 0.003335
best_control: 0.03973
broken_composition: 0.041238

詮釋

interpretation: Destroying the train alignment between task quotient and relation pattern destroys most of the signal, so the rescue is not a snapshot fit. Reinterprets v0.5: the information was present; adding raw coordinates did not make the latent state a direct coordinate.

限制

limitations: Does not show all non-probabilistic states admit such a composition, that the coordinate transfers between geometries without refitting, or that clusters can be discovered unsupervised.

重現

reproduction_instructions: Extract the version's FINAL bundle; python -m pytest -q; run the version's primary script with the recorded seed; docs/PACC_LAB_v0.N_RESULTS.md and docs/EXPERIMENT_PROTOCOL_v0.N.md are inside the bundle.

結果

來源	關係	目標	狀態	ID
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`produces`	`RST-2026-0009` v0.6：組合座標 4/4、直接映射 0/4	`ACTIVE`	`REL-2026-0228`

記錄欄位

completed_at: 2026-09-09

關係

來源	關係	目標	狀態	ID
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`runs_on`	`SYS-2026-0002` PACC-Lab——收斂猜想的微型實驗室	`ACTIVE`	`REL-2026-0217`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_benchmark`	`BEN-2026-0001` PACC 微型實驗室協定 v0.1（凍結門檻）	`ACTIVE`	`REL-2026-0218`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_dataset`	`DAT-2026-0001` PACC 合成證據世界	`ACTIVE`	`REL-2026-0219`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_model`	`MOD-2026-0001` N0——帶號支持	`ACTIVE`	`REL-2026-0220`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_model`	`MOD-2026-0002` N1——序數錦標賽	`ACTIVE`	`REL-2026-0221`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_model`	`MOD-2026-0003` N2——帶號圖	`ACTIVE`	`REL-2026-0222`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_model`	`MOD-2026-0004` N3——約束競爭	`ACTIVE`	`REL-2026-0223`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`uses_model`	`MOD-2026-0005` Bayesian 參考（精確後驗／Beta-Bernoulli／聯合共同因／HMM）	`ACTIVE`	`REL-2026-0224`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`tests`	`THY-2026-0005` PACC 猜想——四層收斂階梯	`ACTIVE`	`REL-2026-0225`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`extends`	`EXP-2026-0012` PACC-Lab v0.5——更豐富的關係狀態能救回潛在座標嗎？	`ACTIVE`	`REL-2026-0226`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`produced`	`ART-2026-0026` PACC-Lab v0.6 Composed Coordinate FINAL `artifact://evemisslab/adaptive-epistemic-systems/PACC-Lab_v0.6_Composed_Coordinate_FINAL.zip`	`ACTIVE`	`REL-2026-0227`
`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`produces`	`RST-2026-0009` v0.6：組合座標 4/4、直接映射 0/4	`ACTIVE`	`REL-2026-0228`
`EXP-2026-0014` PACC-Lab v0.7——不重新擬合的跨幾何座標轉移	`extends`	`EXP-2026-0013` PACC-Lab v0.6——階層式組合座標	`ACTIVE`	`REL-2026-0239`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0013/

機器可讀

/ai/experiments/EXP-2026-0013/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