理論THY-2026-0007v0.1
能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create
除了事實之外,系統也保存用過的算法、工具、執行契約、成本、版本、適用條件與成敗歷史,並且偏好重用已知求解路徑,勝過調整,再勝過重造。算法與計算容器是不同層:任何能接受可表示輸入、執行有效狀態轉換並回傳可讀輸出的環境都是一個容器,各有自己的成本、延遲、誤差與可用性模型,因此算法/容器成對聯合選擇。
主張
claims- Reuse ≻ Adapt ≻ Create.
- Algorithm ≠ container; a capability/container pair is the unit of selection and of execution trace.
預測
predictions- Planning cost falls with repeated related tasks; ReuseGain grows with task similarity within the applicability range, and constraint mismatch produces measurable false reuse (Paper 11 §83–84).
證偽/失敗條件
falsification_conditions- No planning-cost reduction with experience; negative transfer dominates.
已知限制
known_limitations- R1/R2: persistent workflow memory outside the model is not unique to AER; the capability/container separation was 'AER default distinct' only because no core LangGraph primitive was found, not because it cannot be built there.
證據
| 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? | tests | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0103 |
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 |
關係
| 來源 | 關係 | 目標 | 狀態 | ID |
|---|---|---|---|---|
RES-2026-0001 自適應認識系統的盲推導 | develops | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0017 |
PAP-2026-0005 記憶、算法庫與可重用問題求解路徑——從世界模型到能力模型的累積式智能架構 | formalizes | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0030 |
PAP-2026-0006 載體中立的計算容器理論——從算法選擇到異質計算載體聯合調度 | formalizes | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0033 |
PAP-2026-0013 Adaptive Epistemic AI Runtime——以非對稱時空張力、Canonical State、能力記憶與載體中立計算開發 AI 的技術白皮書 | formalizes | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0056 |
SYS-2026-0001 AER-0——自適應認識 runtime MVP | implements | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0068 |
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-2026-0003 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 |
RST-2026-0002 R2 分類矩陣 | qualifies | THY-2026-0007 能力記憶與載體中立計算:Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0126 |
歷史與來源歷程
- Canonical URL
- https://evemisslab.com/ai/theory/THY-2026-0007/
- 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