實驗EXP-2026-0010v0.1

PACC-Lab v0.3——無 oracle 的來源可靠度學習

雙方都失去來源品質 oracle：Bayesian 參考學 Beta-Bernoulli 來源品質；非概率系統學定性聲譽（信任、摩擦、連勝、熟悉度）。在訓練世界上擬合、在未見過的來源品質排列上評估，聲譽狀態映射到 Beta-Bernoulli 狀態的 JS ≈ 0.00714，shuffled／constant 控制組為 0.017–0.018，回饋更新交換 ≈ 0.00130——跨 seed 穩定 6/6。任務狀態收斂則依架構與 seed 而異：在主要規模下 N0/N1 4/4、N2 3/4、N3 2/4。

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: MIXED
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: Convergence survives when source reliability must be learned from delayed feedback rather than given.

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
6 secondary seeds (smaller)
4 seeds at exact primary scale

controls

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

metrics

verdict

RELIABILITY-STATE CONVERGENCE ROBUST; TASK CONVERGENCE PARTIAL / BASIN-SENSITIVE

primary_scale

20 worlds / 280 episodes / 28 observations

reliability_mapping_js

0.007136

control_js

0.017–0.018

feedback_commutation_js

0.001298

reliability_independent_families

task_pass_at_primary_scale

N0: 4/4
N1: 4/4
N2: 3/4
N3: 2/4

詮釋

interpretation: Calibration-state convergence can be robust while task-state convergence has architecture-dependent basins. A first fixed-quality diagnostic was rejected because Beta means became near-constant and shuffled targets fit almost as well — that redesign is part of the evidence.

限制

limitations: All four wrappers share one NonProbReputationLedger, so reliability convergence counts as one family, not four.
Does not prove Beta-Bernoulli learning and qualitative reputation universally equivalent.

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.

記錄欄位

completed_at: 2026-09-09

關係

來源	關係	目標	狀態	ID
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`runs_on`	`SYS-2026-0002` PACC-Lab——收斂猜想的微型實驗室	`ACTIVE`	`REL-2026-0182`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_benchmark`	`BEN-2026-0001` PACC 微型實驗室協定 v0.1（凍結門檻）	`ACTIVE`	`REL-2026-0183`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_dataset`	`DAT-2026-0001` PACC 合成證據世界	`ACTIVE`	`REL-2026-0184`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_model`	`MOD-2026-0001` N0——帶號支持	`ACTIVE`	`REL-2026-0185`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_model`	`MOD-2026-0002` N1——序數錦標賽	`ACTIVE`	`REL-2026-0186`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_model`	`MOD-2026-0003` N2——帶號圖	`ACTIVE`	`REL-2026-0187`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_model`	`MOD-2026-0004` N3——約束競爭	`ACTIVE`	`REL-2026-0188`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`uses_model`	`MOD-2026-0005` Bayesian 參考（精確後驗／Beta-Bernoulli／聯合共同因／HMM）	`ACTIVE`	`REL-2026-0189`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`tests`	`THY-2026-0005` PACC 猜想——四層收斂階梯	`ACTIVE`	`REL-2026-0190`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`extends`	`EXP-2026-0009` PACC-Lab v0.2——第三個家族（N3）與對抗性證據幾何	`ACTIVE`	`REL-2026-0191`
`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`produced`	`ART-2026-0023` PACC-Lab v0.3 Learned Reliability FINAL `artifact://evemisslab/adaptive-epistemic-systems/PACC-Lab_v0.3_Learned_Reliability_FINAL.zip`	`ACTIVE`	`REL-2026-0192`
`EXP-2026-0011` PACC-Lab v0.4——相關來源與依賴幾何	`extends`	`EXP-2026-0010` PACC-Lab v0.3——無 oracle 的來源可靠度學習	`ACTIVE`	`REL-2026-0202`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0010/

機器可讀

/ai/experiments/EXP-2026-0010/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