SystemSYS-2026-0102v0.1
XA-04 — A0→A5 model runner and scaffold orchestrator
A policy-driven state machine that runs the same TrialExecutor under immutable condition policies: A0 native single pass, A1 extended single trajectory (2× generation budget), A2 eight samples with exact-majority selection, A3 eight samples plus a typed verifier, A4 verifier plus a bounded deterministic tool loop, A5 a bounded PLAN → ACT → OBSERVE → VERIFY → REVISE loop. XA-02 and XA-03 are external canonical dependencies (declared by hash, not vendored); tool actions under A0–A3 are protocol violations; benchmark scoring happens only after the XA-03 run is finalized so scoring cost is never charged to the system; private references are never read by the task loader; no private chain-of-thought is captured. 29 tests, status CANDIDATE_CLEAN_VERIFIED.
Purpose
purpose- Instantiate Paper 09's controlled ablation ladder so that scaffolding gain and scaffolding physical overhead are measured under identical initial information.
Architecture
architecture- ProviderAdapter (Scripted / LocalCommand / OpenAI-compatible) → ConditionPolicy A0–A5 with a BudgetLedger → candidate model → SameModelVerifier (strict JSON parse of an explicit orchestration message) → tool action envelope → EvaluatorBridge to XA-02 → aggregator for SSR / SDR / SCM / marginal yield; all spans recorded through XA-03.
Repositories and sites
documentation- README.md, SPEC.md (27 sections), IMPLEMENTATION_PLAN.md, validation_report.json inside the package
Recorded fields
tags- EML-IPM-XA-04
- v0.1
- CANDIDATE_CLEAN_VERIFIED
- Policy-Driven State Machine
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | implements | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0452 |
SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | supports | RES-2026-0103 Capability line — how much intelligence remains without the loop, and the unified intelligence event | ACTIVE | REL-2026-0453 |
SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | released_as | ART-2026-0115 EML-IPM-XA-04 v0.1 — A0→A5 model runner and scaffold orchestrator artifact://evemisslab/intelligence-physical-metrology/IPM_v0.2_XA04_Model_Runner_v0.1.zip | ACTIVE | REL-2026-0454 |
EXP-2026-0101 Experiment A — single-pass vs scaffolded controlled measurement (protocol v0.1) | runs_on | SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | ACTIVE | REL-2026-0462 |
EXP-2026-0102 XA-05 — 36-trial end-to-end smoke gate with a scripted provider (synthetic) | runs_on | SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | ACTIVE | REL-2026-0469 |
EXP-2026-0103 XA-06 first real-model pilot — Qwythos-9B-v2 on the A0→A5 ladder (36 trials, 2026-09-03) | runs_on | SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | ACTIVE | REL-2026-0476 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/systems/SYS-2026-0102/
- Machine-readable
/ai/systems/SYS-2026-0102/index.json- Snapshot
AI-SNAPSHOT-v0.1-fe85b9694a45- Provenance
source- EveMissLab research collection: Intelligence Physical Metrology (真本體論13)
extracted_by- Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports
extracted_at- 2026-09-11
generator- tools/extract_all.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