TheoryTHY-2026-0007v0.1
Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create
Beyond facts, the system keeps the algorithms, tools, execution contracts, costs, versions, applicability conditions and success/failure history it has used, and prefers reusing a known solution path over adapting one over creating one. Algorithms and compute containers are different layers: any environment that accepts representable input, performs a valid state transition and returns readable output is a container with its own cost, latency, error and availability model, so algorithm/container pairs are selected jointly.
Claims
claims- Reuse ≻ Adapt ≻ Create.
- Algorithm ≠ container; a capability/container pair is the unit of selection and of execution trace.
Predictions
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).
Falsification / failure conditions
falsification_conditions- No planning-cost reduction with experience; negative transfer dominates.
Known limitations
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.
Evidence
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
EXP-2026-0001 AER-0 MVP v0.1 closure: are the invariants executable? | tests | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0103 |
EXP-2026-0003 R2 — source-grounded structural comparison with LangGraph 1.2.11 | tests | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0120 |
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
RES-2026-0001 Blind derivation of an adaptive epistemic architecture | develops | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0017 |
PAP-2026-0005 Paper 05 — Memory, algorithm libraries and reusable solution paths | formalizes | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0030 |
PAP-2026-0006 Paper 06 — Substrate-neutral computational containers | formalizes | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0033 |
PAP-2026-0013 Adaptive Epistemic AI Runtime — technical whitepaper v0.1 | formalizes | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0056 |
SYS-2026-0001 AER-0 — Adaptive Epistemic Runtime MVP | implements | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0068 |
EXP-2026-0001 AER-0 MVP v0.1 closure: are the invariants executable? | tests | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0103 |
EXP-2026-0003 R2 — source-grounded structural comparison with LangGraph 1.2.11 | tests | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0120 |
RST-2026-0002 R2 classification matrix | qualifies | THY-2026-0007 Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create | ACTIVE | REL-2026-0126 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/theory/THY-2026-0007/
- Machine-readable
/ai/theory/THY-2026-0007/index.json- Snapshot
AI-SNAPSHOT-v0.1-fe85b9694a45- Provenance
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