| Age | Commit message (Expand) | Author |
|---|
| 12 hours | Add new experiment scripts, figures, and paper assets; untrack pyc/build arti...HEADmaster | YurenHao0426 |
| 2026-04-26 | d=512 deep scan complete: FA+DFA at L=6,8,12 (10 seeds each) | YurenHao0426 |
| 2026-04-26 | d=256 deep scan: FA+DFA at L=8 and L=12 (5 seeds each) | YurenHao0426 |
| 2026-04-26 | CIFAR-100 per-seed diagnostics complete — full qualifying table | YurenHao0426 |
| 2026-04-26 | CIFAR-100 d=256 L=4: both FA and DFA fail — strongest qualifying setting | YurenHao0426 |
| 2026-04-26 | BP+EP audit for d=512 L=2 qualifying seeds + CIFAR-100 support | YurenHao0426 |
| 2026-04-26 | Find setting where both FA and DFA fail: d=512 L=2 ResMLP | YurenHao0426 |
| 2026-04-22 | Add vanilla FA (Lillicrap 2016) implementation + full experiment suite | YurenHao0426 |
| 2026-04-08 | paper v2.34.1: SB/CB training loss decrease values from 3-seed (were s42) | YurenHao0426 |
| 2026-04-08 | paper v2.33: promote nudging test to §4 main text + correct to 3-seed values | YurenHao0426 |
| 2026-04-08 | paper v2.32: BP+penalty multi-seeded (was single-seed s42) | YurenHao0426 |
| 2026-04-08 | Commit dfa_pen_short lam=1e-4 s123/s456 JSONs (auditable source for §5 ¶2) | YurenHao0426 |
| 2026-04-08 | Save threshold_sensitivity_output.txt for §6 ¶1 + Appendix E audit | YurenHao0426 |
| 2026-04-08 | Save null_calibration_penalized_dfa.json for §6 ¶2 audit | YurenHao0426 |
| 2026-04-08 | paper v2.31.8: Appendix I EP random-target ‖h_L‖ values from saved JSON | YurenHao0426 |
| 2026-04-08 | paper v2.31: matched 30-epoch BP/DFA controls (was unsourced 0.609/0.308) | YurenHao0426 |
| 2026-04-08 | paper v2.30: fix layer-0 cosine numbers + add per-seed appendix M | YurenHao0426 |
| 2026-04-08 | λ sweep on penalty strength: lam ∈ {1e-4, 1e-2, 1e-1} cos + rho results | YurenHao0426 |
| 2026-04-08 | Multi-seed vanilla DFA early-epoch cos: lock-in for round 19 disambiguation | YurenHao0426 |
| 2026-04-08 | BP+penalty control result: mode 2 (intrinsic credit quality) confirmed REAL | YurenHao0426 |
| 2026-04-08 | 3-seed multi-seed verification of penalized DFA deep cos = +0.17 | YurenHao0426 |
| 2026-04-08 | DISAMBIGUATION: vanilla DFA early-epoch checkpoints + cos measurement | YurenHao0426 |
| 2026-04-08 | MAJOR: penalized DFA deep-layer cosine is +0.17, NOT zero | YurenHao0426 |
| 2026-04-08 | Add penalty λ sweep figure: shows λ-dependence of (d) verdict | YurenHao0426 |
| 2026-04-07 | Add CNN third-architecture audit: BN, no terminal LN | YurenHao0426 |
| 2026-04-07 | Add §4 penalty rescue figure: visual two-failure-modes story | YurenHao0426 |
| 2026-04-07 | Add §2/§3 hero figure: 5-method audit horizontal bar chart | YurenHao0426 |
| 2026-04-07 | Add d=512 ResMLP audit table (3 seeds): cross-width validation | YurenHao0426 |
| 2026-04-07 | Add §3 cross-architecture temporal evolution figure | YurenHao0426 |
| 2026-04-07 | Cross-architecture temporal validation: 3 archs x 3 seeds x 2 methods | YurenHao0426 |
| 2026-04-07 | Protocol diagnostic (a): use max per-block growth, not max/min ratio | YurenHao0426 |
| 2026-04-07 | Temporal evolution 3-seed: protocol fires at DFA epoch 3-4 on all seeds | YurenHao0426 |
| 2026-04-07 | Add temporal diagnostic evolution: protocol fires at epoch 4 of DFA | YurenHao0426 |
| 2026-04-07 | Audit table extension to 3 seeds (s42/s123/s456) | YurenHao0426 |
| 2026-04-07 | Add protocol decision-utility ablation table | YurenHao0426 |
| 2026-04-07 | Add audit table example: protocol applied to BP/DFA/SB/CB/EP | YurenHao0426 |
| 2026-04-03 | Add 5 extra seeds to synthetic cross-state distance (now 10 seeds for all met... | YurenHao0426 |
| 2026-04-03 | Recompute all CNN diagnostics with fixed BP gradient flow | YurenHao0426 |
| 2026-04-03 | Complete EP data: 10-seed synthetic + 6-seed CIFAR persample + cross-state | YurenHao0426 |
| 2026-04-03 | EP synthetic 10 seeds complete: 30 JSONs + 30 checkpoints + cross-state distance | YurenHao0426 |
| 2026-04-03 | Add EP cross-state distance for CIFAR + verify CNN summary | YurenHao0426 |
| 2026-04-03 | Add EP synthetic per-seed CSV + synthetic cross-state distance | YurenHao0426 |
| 2026-04-03 | Add EP to BP gradient sparsity analysis | YurenHao0426 |
| 2026-04-03 | Add cross-method hidden state distance vs BP | YurenHao0426 |
| 2026-04-03 | Update all EP results with sign-corrected credit | YurenHao0426 |
| 2026-04-02 | Recompute EP CIFAR d=256 diagnostics with sign fix | YurenHao0426 |
| 2026-04-02 | Add EP synthetic results: 15 JSONs (3α × 5 seeds) | YurenHao0426 |
| 2026-04-02 | Add CNN SB+CB results (5 seeds each), update summary CSV | YurenHao0426 |
| 2026-04-02 | Fix and recompute GELU ablation Gamma from checkpoints | YurenHao0426 |
| 2026-04-02 | Add summary CSVs for EP, GELU ablation, CNN | YurenHao0426 |
