| { |
| "columns": [ |
| "Date", |
| "Event", |
| "Result / number", |
| "Evidence", |
| "Next action" |
| ], |
| "widths": [ |
| 12, |
| 46, |
| 52, |
| 40, |
| 44 |
| ], |
| "rows": [ |
| [ |
| "2026-09-23", |
| "align consolidated (SFT/DPO/PPO/GRPO, torch-only)", |
| "Dependency firewall test in place", |
| "a4d4d5e", |
| "Hardening" |
| ], |
| [ |
| "2026-10-12", |
| "Strict Lean verifier P1 + OLMoE parity", |
| "Ceiling 177/178 good, 0/61 adversarial accepted", |
| "654c20c", |
| "Goedel SFT build" |
| ], |
| [ |
| "2026-10-13", |
| "Scope narrowed to post-training Goedel-Prover-V2-8B", |
| "OLMoE pretraining / Leanstral-scale out of scope", |
| "align_olmoe_leanstral_roadmap memory", |
| "Baseline" |
| ], |
| [ |
| "2026-10-13", |
| "P2 baseline pass@8 @16k", |
| "78.7% (192/244); 40k identical", |
| "780ce3d", |
| "pass@32 reproduction" |
| ], |
| [ |
| "2026-10-13", |
| "Generation/verification overlap", |
| "Fixed idle-GPU defect (verify was 1.43 h serial)", |
| "7b07b55", |
| "-" |
| ], |
| [ |
| "2026-10-14", |
| "SOTA gate 1: pass@32 @40k", |
| "82.8% (202/244); 30k-equivalent identical", |
| "45f6f99", |
| "300 s timeout re-check" |
| ], |
| [ |
| "2026-10-14", |
| "300 s re-check of 274 timed-out samples", |
| "0 recovered; baseline stays 202", |
| "1cc55e4", |
| "Adopt 300 s / 1,200 s protocol" |
| ], |
| [ |
| "2026-10-14", |
| "miniF2F-valid built", |
| "226 problems", |
| "1c483cc", |
| "Use for all dev decisions" |
| ], |
| [ |
| "2026-10-14", |
| "Pool round 0 started", |
| "2,000 x 8 @16k; 2,963 generated by 14:36 UTC (~600/h)", |
| "align/.tmp/p2/r1/pipe_pool/pipeline.jsonl", |
| "chain5 after completion" |
| ], |
| [ |
| "2026-10-14", |
| "Leanstral lineage research: 6 depth loci done", |
| "RL mostly sharpens; data > RL here; CISPO second-order; FP32 head/averaging not Leanstral", |
| "research/runs/leanstral-recipe-lineage-c14fca/comparisons.md", |
| "Steps 7-16 -> final report" |
| ], |
| [ |
| "2026-10-14", |
| "Open dataset inventory started", |
| "Sonnet discover / Haiku verify / Sonnet critic", |
| "workflow wf_c3f2e9d0-871", |
| "Fill Datasets sheet" |
| ], |
| [ |
| "2026-10-14", |
| "Open dataset inventory complete", |
| "133 entries API-checked (132 exist); 76 candidates, 38 eval-only, 17 need decontamination; 9 gaps -> Data_Gaps", |
| "workflow wf_c3f2e9d0-871; docs/workbook/data/Datasets.json", |
| "Decontaminate (WBS 4.3); build G1/G2 pools" |
| ], |
| [ |
| "2026-10-14", |
| "8B SOTA plan drafted", |
| "Classes A/B/C/D, levers L1-L7, gates G0-G5, ~400-460 box-hours, calendar to Dec 20", |
| "docs/SOTA_PLAN.md", |
| "Finalize after research report; start Phase 0" |
| ], |
| [ |
| "2026-10-14", |
| "Codex independent review applied", |
| "Plan v2: one primary endpoint (~+9 net for significance), K1-K4 controlled contrasts, eval reserved first (~180 GPU-h), budget 520-620 GPU-h; split guard added to EI driver", |
| "docs/evidence/codex_review_2026-10-14.md; docs/SOTA_PLAN.md", |
| "Phase 0 items 1-7" |
| ], |
| [ |
| "2026-10-14", |
| "Codex + Claude code reviews applied", |
| "Codex 3 P1 + 5 P2, Claude 8 findings on build_valid: guard fails closed, protected test sets, per-round recheck, workbook lock, build_valid ceiling test + crash handling, box-hour units", |
| "commit after 9648df1", |
| "WBS 3.6 eval_report registration" |
| ], |
| [ |
| "2026-10-14", |
| "300 s re-check of baseline timeouts complete", |
| "0/274 accepted (195 still time out at 300 s = undecided, 76 compile errors); anchor stays 202/244", |
| ".tmp/p2/r1/baseline/ver_minif2f_c40960.timeouts_unsolved_b300.jsonl", |
| "1,200 s sensitivity on the 195 in Phase 0a" |
| ], |
| [ |
| "2026-10-14", |
| "Deep code verification + fix pass", |
| "12 units, 141 OK invariants; confirmed P1 7 / P2 49 / P3 170; 40 fixed, 15 partial, 1 design decision; 10 deferred (frozen files)", |
| "docs/evidence/deep_verification_2026-10-14.md", |
| "Phase-0a verifier freeze merges the deferred items" |
| ], |
| [ |
| "2026-10-14", |
| "SOTA plan v3", |
| "n=64 unbiased pass@32 + paired sign-flip primary; supply audit; Kimina-Distill-8B contrasts; ETA P50 Nov 27, P90 Dec 8", |
| "docs/SOTA_PLAN.md, docs/IMPLEMENTATION_LANES.md", |
| "Launch lanes V1,V2,S,D,T,B,N; chain6 anchor n=64 queued" |
| ], |
| [ |
| "2026-10-14", |
| "Supply v1 built", |
| "111,016 decontaminated + elaborating statements (Numina 61,136; Pset L4-5 39,576; Nemotron 6,679; FormalMATH 3,625); elab-hash stage caught 10 extra eval duplicates; text-only triage AUC 0.52 (no signal)", |
| ".tmp/p2/supply/supply_v1.jsonl (sha256 b3c505eb...)", |
| "chain7 screening n=4 on a 4,000 stratified sample after Phase-0a merges" |
| ], |
| [ |
| "2026-10-14", |
| "Lanes landed", |
| "merged S, N, T, D, CP; done on branches (merge after chain6): V1 verifier freeze, V2 genharness + temperature/Kimina follow-up, MV math verifier, R RL loop", |
| "docs/IMPLEMENTATION_LANES.md", |
| "chain6 exit -> merge V1, MV, V2, R -> registered ceiling test -> recompute frozen hash -> re-verify anchor -> touch PHASE0A_MERGED" |
| ] |
| ] |
| } |
|
|
