AI Research Laboratory7 records
Systems
Runtimes, tools and experimental systems that formed during research. Ones that matured into their own site are also in the index on the front page.
- SystemSYS-2026-0002PACC-Lab — micro-lab harness for the convergence conjectureFully observable evidence-integration environments, four primitive-level non-probabilistic families (N0–N3), exact Bayesian references, train-only low-complexity mappers, shuffled/constant/broken-composition controls, a design-redundancy diagnostic and frozen preregistered thresholds carried unchanged from v0.1 through v0.13. Each release is a sealed FINAL bundle with its protocol, results and next-experiment preregistration.
- SystemSYS-2026-0003PACC-LLM Hybrid LabAn A/B/C harness — generator only, hard verifier, PACC runtime — over shared candidate pools with equal accounted budgets. v0.1 is a synthetic architecture witness (zero LLM calls); v0.2 adds hand-authored natural-language tasks, a condition-blind judge, literal machine checks independent of the judge, fail-closed behaviour without an API key, and frozen-cache replay for exact reproduction after a live run.
- SystemSYS-2026-0001AER-0 — Adaptive Epistemic Runtime MVPA Python + SQLite reference runtime that owns persistent canonical state; a language model is optional and replaceable. Candidate → verify → versioned commit, mandatory provenance for facts and relations, freshness and confidence as separate state, an asymmetric tension scheduler with shock-triggered refresh, capability/container registries, persisted workflow memory (reuse/adapt/create), and a deterministic/rule/Bayesian/heuristic epistemic router. Grown through six comparison rounds into an epistemic commit transaction with SQLite-level mediation, an Ed25519-signed external anchor and a process-separated writer (79 tests at R6). Developed under mssp-tdd-apr as a DEGRADED-TWIN run — no independent twin verification is claimed.
- SystemSYS-2026-0101XA-03 — telemetry and run logger (physical execution evidence layer)Provider-agnostic logger that records one benchmark run as append-only events plus telemetry and derives a typed summary deterministically: model-invocation, trajectory, tool-call and verifier spans, candidate created/discarded accounting, wall time, device-time, GPU power integrated to device_energy_j (energy type device_measured, never relabelled as marginal), peak memory and memory residency, with unknowns kept null (Unknown ≠ 0) and forbidden conversions (tokens → J, TDP → J, price → J, GPU-hours → J). Golden fixture 450 J / 1.75 util·s / 12 GB peak / 33 GB·s residency verified; 35 passed, 1 skipped in 0.39s; instrumentation burden is calibrated and reported, not subtracted.
- SystemSYS-2026-0102XA-04 — A0→A5 model runner and scaffold orchestratorA 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.
- SystemSYS-2026-0103XA-06 — real-model pilot gatePuts a real model inside the validated XA-01→XA-04 instrument: preflight (one isolated MATH-003/A0 trial through provider, XA-03 and XA-02), the canonical 36-trial matrix (MATH-003, CODE-001, CON-003 × A0…A5 × 2 replicates), gate verification and analysis. Frozen temperature / top-p / seed, the A0/A1 generation-budget multiplier forwarded into the token budget, a calculator tool contract injected only for A4/A5 generator requests, disabled code evaluation treated as quality-unavailable rather than measured zero, and the rule that engineering validation can never be promoted to pilot completion: 'no real model run, no real model claim'. Valid real outcomes explicitly include A0 = A5, A3 < A2, A5 < A0 and SSR = 1. 20 tests; the package itself contains no pilot result (status READY_FOR_REAL_MODEL).
- SystemSYS-2026-0104XA-06L — local real-model execution handoff packThe Windows/local handoff from READY_FOR_REAL_MODEL to a sealed result bundle: configure → preflight → run/resume → verify/analyze → seal. Resume skips a matrix point only if its trial result and XA-03 summary exist, both SHA-256 hashes still match, identity matches and the XA-03 state is COMPLETE; a modified point becomes INVALID and is never overwritten silently. Sealing excludes secret values, redacts absolute paths with provenance, makes run directories bundle-relative and re-hashes everything so the bundle can be re-verified on another machine. Software 29/29 PASS, experiment status in the package: NOT_RUN — the distinction 'READY_FOR_REAL_MODEL ≠ REAL_MODEL_PILOT_COMPLETE' is the package's stated point.