| Age | Commit message (Expand) | Author |
| 21 hours | fix(eval): structured-mode greedy decode capped at in-range layout bound (369... | Void Agent |
| 44 hours | fix(transformer): increase positional embedding and causal mask buffer to 102... | CaptainJack2491 |
| 44 hours | optimize E8: precompute causal mask buffer, add eval early exit, and enable c... | CaptainJack2491 |
| 44 hours | implement Addendum 8: 6-arm token-space recurrence suite (arms A, B, C, D1, D... | CaptainJack2491 |
| 44 hours | refine Addendum 8: expand Arm D into D1 (learned), D2 (frozen), and D3 (dynam... | CaptainJack2491 |
| 44 hours | preregister Addendum 8: 4-arm token-space recurrence & decomposition test (E8) | CaptainJack2491 |
| 45 hours | E7: 20x long-horizon analysis — H-slow rejected (4/4 cells) | Void Agent |
| 7 days | E7 relaunch order: GPU cell first, completed tf-wd01 cell last (idempotent skip) | Void Agent |
| 7 days | eval: strip torch.compile _orig_mod./module. prefixes when loading checkpoint... | Void Agent |
| 10 days | run_sweep: 2 threads for --device cpu jobs (matches Addendum 7 protocol) | Void Agent |
| 10 days | E7 jobs: 4M-step long-horizon, mixed-device (rnn->cpu, transformer->cuda+comp... | Void Agent |
| 11 days | fix(train): enforce epoch permutation without replacement, add max cache OOM ... | CaptainJack2491 |
| 11 days | perf(train): VRAM-resident tensor caching, zero-copy GPU batch sampling, and ... | CaptainJack2491 |
| 11 days | fix(eval): correct sieve-rank indexing + test expectations | Void Agent |
| 11 days | fix(eval): P5/P6 sieve-rank ladder replaces hardcoded FLAGGED_SIEVE_PREDS | Void Agent |
| 13 days | E6 Phase 5: complete 16/16 cells (no O1, all P4, no sieve rank) | Void Agent |
| 14 days | E6 Phase 5: classify 8/16 finished cells (no O1, all P4, no sieve rank) | Void Agent |
| 2026-08-17 | README: blog part 1+2 links, part 3 slot | Void Agent |
| 2026-08-17 | track per-phase summary CSVs (force-added under runs/ ignore) | Void Agent |
| 2026-08-17 | public release prep: full preregistration mirror (addenda 1-6), public README... | Void Agent |
| 2026-08-17 | E6 jobs: 16 cells [2,1000] K=32 cuda AMP (14 primary + 2 batch-128 ablation);... | Void Agent |
| 2026-08-17 | perf(cuda): add AMP fp16 autocast with GradScaler and torch.compile reduce-ov... | CaptainJack2491 |
| 2026-08-17 | feat(gpu): add CUDA support, chunked eval, bisect prime search, and scaling t... | CaptainJack2491 |
| 2026-08-17 | fix D2: integers-mode probe is N/A by construction (OOV probe inputs), functi... | Void Agent |
| 2026-08-16 | Phase 3 diagnostics results + analysis + report phase 4 | Void Agent |
| 2026-08-16 | phase3: task_mode (is_prime), train_frac, lr_decay flags + tests (41 green); ... | Void Agent |
| 2026-08-15 | E2 wd sweep results + analysis + report phase 3 | Void Agent |
| 2026-08-15 | E2 wd sweep: 8 jobs (0.01/0.1/0.3/3.0 x both models, seed 0; 1.0 = existing c... | Void Agent |
| 2026-08-15 | E1 results + analysis + report phase 2 | Void Agent |
| 2026-08-15 | speedup: batched eval (46x, sieve-stub verified), run_sweep orchestrator (2-w... | Void Agent |
| 2026-08-14 | tidy: drop dead --ckpt arg, unused imports/vars; verified report pipeline ad-... | Void Agent |
| 2026-08-14 | report pipeline: build_report.py (self-contained HTML), eval --runs-dir, plot... | Void Agent |
| 2026-08-14 | eval: P1 diagnostic prediction-based (flagged set +209), classifier regressio... | Void Agent |
| 2026-08-14 | fix codex BLOCKERs: global fixed layout invariance, min_steps off-by-one, int... | Void Agent |
| 2026-08-14 | rnn: fully-tied cell (read-in+compute+decode), lambda ramp, ACT regression te... | Void Agent |
| 2026-08-14 | implement Experiment 1: data pipeline, tied-RNN w/ ACT halting, transformer b... | Void Agent |
| 2026-08-14 | scaffold: README, LICENSE, design docs (spec + prereg from research repo 00c6... | Void Agent |