1# Results-to-claim audit report (WP31, 2026-10-30)23* `scripts/verify_manuscript_claims.py`: **AUDIT PASS** — 25 registered claims; every artefact path exists; every run id has a4 manifest (states `completed`, or `stopped-run-used` for the two deliberately stopped runs cited as failures); every numeric5 macro used in the manuscript is generated by `scripts/make_tables.py`; no promotional phrase; no placeholder section.6* Tests: `python -m pytest tests -q` → 23 passed (15 mandated invariants, controller target-freedom with and without the7 residual/entropy features, dense-write ablation, 5 cache-equivalence tests).8* Manuscript: `paper/main.pdf`, 48 pages, latexmk with 0 undefined references/citations (one harmless font-shape warning).9* Pre-registration: `protocol/preregistration.md` frozen v1.0 at 2026-10-30T04:04-0400; `protocol/locked_test_manifest.json`10 unsealed at the same time; test splits were read only afterwards (synthetic test regimes: 5 nodes; FineWeb test: 4 systems).11* Deviations: `protocol/deviations.md` (bootstrap init/scale, controller features, label stream, dense 103M infeasible,12 backbone budget 98.3M instead of 196.6M tokens).13* Not executed: Phase 11 (MLX port), Phase 12 training (459M/1.18B only instantiated on meta), GSM8K/EvalPlus, quantisation, distillation, joint fine-tuning (one degraded attempt), dense editor at 103M14 (collapsed twice), MLX/Metal profiling.15* Checksums of the key artefacts: `reproducibility/checksums.sha256`.16