| Age | Commit message (Expand) | Author |
| 2026-07-15 | ERRATUM RESULT 21: original best 3.7117 was @104.8k not @185k — 90k-step wa... | Yuren Hao |
| 2026-07-15 | RESULT 26: C512 ZERO-GAP SEALED — stage1b_cent 1.2334 vs BP 1.2311 (+0.0023... | Yuren Hao |
| 2026-07-15 | External notes: sliding-mode clamping (Stage-0 injection rule), saturated-uni... | Yuren Hao |
| 2026-07-15 | RESULT 25: bias decomposition probe — 100% between-block transmission (TRAN... | Yuren Hao |
| 2026-07-15 | RESULT 23 verdict: gap tracks FIT DEPTH not width — all registered hypothes... | Yuren Hao |
| 2026-07-14 | RESULT 24: fw72m_cent pre-registration (centered crown rerun, bcap-v3 0.9, gr... | Yuren Hao |
| 2026-07-14 | RESULT 22 arms7 verdict (centered@3e-3 wins tail-SNR, momentum refuted) + RES... | Yuren Hao |
| 2026-07-14 | RESULT 21: crown sealed — 72.11M x 1.44B tokens fully BP-free (largest to d... | Yuren Hao |
| 2026-07-14 | RESULT 20: wall-zone verdicts — damping refuted (3 witnesses, monotone spec... | Yuren Hao |
| 2026-07-14 | RESULT 19: wall-2 loop-gain theory, beta window formalism, probe mid-verdicts... | Yuren Hao |
| 2026-07-14 | RESULT 18: wall-2 returns at 72M/FineWeb 195k (drift crossing, beta-stress co... | Yuren Hao |
| 2026-07-13 | fw72m crown run launched (NCCL DDP prod), exact resume (opt state), RESULT 17... | Yuren Hao |
| 2026-07-13 | RESULT 16: FineWeb-Edu pipeline live + smoke passed (CE 10.5->5.8, cos 0.9995... | Yuren Hao |
| 2026-07-12 | stage1b_amp epoch confirm SEALED: 1.2868 vs fp32 1.2808, zero guards, 1.56x held | Yuren Hao |
| 2026-07-12 | RESULT 15 (amp lossless 1.56x) + COST_MODEL v2.1 (sourced July-2026 prices, E... | Yuren Hao |
| 2026-07-12 | E-tier wave-1 ledger (RESULT 14 + HW map rows) + cost model v2 recalibrated o... | Yuren Hao |
| 2026-07-12 | RESULT 13: bsign neutral at 4k (1.7382 vs 1.7314); 42M gap-chasing closed at ... | Yuren Hao |
| 2026-07-11 | RESULT 12: f3e3cont negative (1.2883 vs 1.2808) — residual gap not beta-lif... | Yuren Hao |
| 2026-07-11 | STANDING: looped line abandoned (user directive) — cascade-only default; lo... | Yuren Hao |
| 2026-07-11 | RESULT 11: stage1b sealed (gap 0.050); beta ceiling unfound (3e-3 -> cos 0.99... | Yuren Hao |
| 2026-07-10 | Queue: double-sided nudge after stage1b (0.22 = differential-measurement SNR ... | Yuren Hao |
| 2026-07-10 | RESULT 10: epoch endpoints (BP 1.2509/1.2750 vs EP 1.4802, +0.22 erosion cost... | Yuren Hao |
| 2026-07-10 | cos<0.96: flagship stays as control; bf1e3 continuation from s40000 queued on... | Yuren Hao |
| 2026-07-10 | Sustained dose-response sealed (3e-4/5e-4/1e-3 -> 0.975/0.983/0.990); ship --... | Yuren Hao |
| 2026-07-10 | RESULT 8 sealed (Muon 3v3: BP 1.7098 / EP 1.7314); beta-floor dose-response @... | Yuren Hao |
| 2026-07-10 | Watch: late-epoch cos erosion = intrinsic late-training SNR decline; let it r... | Yuren Hao |
| 2026-07-10 | RESULT 8 final: Muon generic (+0.13 both columns; BP+Muon 1.7020 vs EP+Muon 1... | Yuren Hao |
| 2026-07-10 | RESULT 9: wall-2 ELIMINATED by OLMo2 arch — epoch cleared 10-14k with zero ... | Yuren Hao |
| 2026-07-10 | RESULT 8 prelim: Muon+beta_floor on EP = 1.7316 (-0.098 vs AdamW, n=1, zero s... | Yuren Hao |
| 2026-07-10 | RESULT 7: OLMo2 parity PASS (BP 1.8335 vs EP 1.8643, gap +0.031 within metric... | Yuren Hao |
| 2026-07-10 | RESULT 6 addendum: K8 also blew at 12600 -> wall-2 is true contractivity cros... | Yuren Hao |
| 2026-07-10 | RESULT 6: wall-2 = EP-specific marginal under-convergence at the contractivit... | Yuren Hao |
| 2026-07-10 | AUDIT: retract confounded Muon verdict; tone down parity claims (n=3, best-of... | Yuren Hao |
| 2026-07-10 | Stage-1 epoch blowup @12100: sig story REFUTED (only +8%, cos fine till after... | Yuren Hao |
| 2026-07-10 | RESULT 4: QK-norm validated parity-preserving (EP 1.8868 <= BP 1.9066); qk_no... | Yuren Hao |
| 2026-07-10 | QK-norm: replace nn.MHA with explicit SDPA attn + --qk_norm (OLMo2-style, ana... | Yuren Hao |
| 2026-07-10 | RESULT 3: K4 depth-parity SEALED EP-favorable (EP 1.8907 <= BP 1.9192 @ L12xC... | Yuren Hao |
| 2026-07-10 | CORRECTION: D1a did not die (misread mangled proc scan); originals completed ... | Yuren Hao |
| 2026-07-10 | RESULT 2: beta-floor confirmed as L12 depth fix (3e-4 holds cos=1.0 vs contro... | Yuren Hao |
| 2026-07-10 | K refuted as L12 lever (cos K-invariant K3==K8); BP 3-seed sealed 1.919; mech... | Yuren Hao |
| 2026-07-09 | D1a autopsy + K-ladder diagnostic: parent-death (not nohup'd) killed 4 arms; ... | Yuren Hao |
| 2026-07-09 | notes refresh: plan status stamp (K1-K3 sealed, D-tier in flight), ONBOARDING... | Yuren Hao |
| 2026-07-09 | FINDINGS: 2026-07-11 consolidated hardening entry | Yuren Hao |
| 2026-07-09 | FINDINGS: K3 sealed — matched-tuning parity n=3 (EP 2.0500+-0.015 vs BP 2.0... | Yuren Hao |
| 2026-07-09 | FINDINGS: final C1 verdict — equilibrium fb-EP 2.2949 beats BP 2.3694 (same... | Yuren Hao |
| 2026-07-09 | FINDINGS: cascade pivot one-day arc — bridge, solver saga, fb message-passi... | Yuren Hao |
| 2026-07-09 | cascade: retire zil per user directive (EP route = equilibrium two-phase); pr... | Yuren Hao |
| 2026-07-09 | cascade: zil interleaved scheme = exact gradients at all depths (cos 1.0000 L... | Yuren Hao |
| 2026-07-09 | cascade ablation program: plan doc (5 claims, tiers 0-4), probe v2 (jacobi/gs... | Yuren Hao |
| 2026-07-07 | FLAGSHIP: warm_fast 1.7065 final — beats tuned BP anchor by 0.086, param-ma... | Yuren Hao |