| Age | Commit message (Expand) | Author |
|---|
| 2026-04-03 | Update all EP results with sign-corrected credit | YurenHao0426 |
| 2026-04-03 | Fix EP credit sign in cnn_baseline.py | YurenHao0426 |
| 2026-04-02 | Recompute EP CIFAR d=256 diagnostics with sign fix | YurenHao0426 |
| 2026-04-02 | Fix EP credit sign: negate (h_nudge - h_free)/β to align with BP grad direction | YurenHao0426 |
| 2026-04-02 | Add EP synthetic results: 15 JSONs (3α × 5 seeds) | YurenHao0426 |
| 2026-04-02 | Add --d_hidden arg to ep_baseline.py for d=512 support | YurenHao0426 |
| 2026-04-02 | Fix ep_synthetic: bp dict needs L+1 entries for EP credit comparison | YurenHao0426 |
| 2026-04-02 | Add EP synthetic ladder script | YurenHao0426 |
| 2026-04-02 | Add CNN SB+CB results (5 seeds each), update summary CSV | YurenHao0426 |
| 2026-04-02 | Fix CNN state bridge: use custom CNNStateBridge for variable input dims | YurenHao0426 |
| 2026-04-02 | Add SB and CB methods to cnn_baseline.py | YurenHao0426 |
| 2026-04-02 | Fix and recompute GELU ablation Gamma from checkpoints | YurenHao0426 |
| 2026-04-02 | Fix gelu_ablation.py: compute method-specific Gamma instead of hardcoded 1.0 | YurenHao0426 |
| 2026-04-02 | Add summary CSVs for EP, GELU ablation, CNN | YurenHao0426 |
| 2026-04-02 | Add EP baseline (5 seeds), GELU ablation (20 runs), CNN BP+DFA (10 runs) | YurenHao0426 |
| 2026-04-02 | Add GELU/ReLU ablation script for CIFAR MLP | YurenHao0426 |
| 2026-04-02 | Add CNN baseline: SmallCNN with BP/DFA/EP on CIFAR-10 | YurenHao0426 |
| 2026-04-02 | Add EP baseline implementation (Scellier & Bengio 2017) for CIFAR MLP | YurenHao0426 |
| 2026-04-01 | Add d=512 support sparsity: 20 JSONs + summary CSV | YurenHao0426 |
| 2026-04-01 | Add d512_sparsity.py: support sparsity for d=512 checkpoints | YurenHao0426 |
| 2026-04-01 | Add missing bp_s456.json for CIFAR d=512 (rerun after SIGTERM) | YurenHao0426 |
| 2026-04-01 | Add CIFAR L=4 d=512 confirmatory: 4 methods × 5 seeds with checkpoints | YurenHao0426 |
| 2026-04-01 | Add cifar_d512_confirmatory.py: L=4 d=512 with checkpoint saving | YurenHao0426 |
| 2026-04-01 | Add P3 protocol panel: method ranking across 5 protocol slices | YurenHao0426 |
| 2026-04-01 | Add per-sample gradient stats: 24576 rows (256 samples × 4 layers × 4 metho... | YurenHao0426 |
| 2026-04-01 | Add clean_sparsity_persample.py: per-sample gradient stats | YurenHao0426 |
| 2026-04-01 | Add clean_sparsity_summary.csv: 960 rows aggregated from 168 JSONs | YurenHao0426 |
| 2026-04-01 | Add clean sparsity results: 168 JSONs from independent processes on GPU 1 | YurenHao0426 |
| 2026-04-01 | Add run_clean_sparsity.sh: shell runner for independent-process sparsity | YurenHao0426 |
| 2026-04-01 | Add clean_sparsity_full.py: independent-process full sparsity analysis | YurenHao0426 |
| 2026-04-01 | Add clean gradient check: independent Python process per method, GPU 1 | YurenHao0426 |
| 2026-04-01 | Add element-wise gradient concentration analysis (CPU, from checkpoints) | YurenHao0426 |
| 2026-04-01 | Add confirmatory supplement: T1-T4 from checkpoints (no retraining) | YurenHao0426 |
| 2026-04-01 | Add extended sparsity analysis: A4 per-layer, B1 snapshots, B2 active subset,... | YurenHao0426 |
| 2026-04-01 | Add BP support sparsity analysis: threshold sweep + gradient histograms | YurenHao0426 |
| 2026-04-01 | Recompute BP and DFA Gamma with near-zero gradient filtering | YurenHao0426 |
| 2026-03-31 | Update naive StateErr v3: L2 norm ratio formula, with checkpoints saved | YurenHao0426 |
| 2026-03-31 | Add BP supplement for A2 CIFAR: 10 seeds with acc, Gamma, rho, naive_StateErr | YurenHao0426 |
| 2026-03-31 | Add naive state prediction baseline for A1 and A2 | YurenHao0426 |
| 2026-03-30 | Add confirmatory paper experiments: A1-A4, all 10 seeds complete | YurenHao0426 |
| 2026-03-27 | Add Phase 10A.8C: 3-seed replication — scaffold gains are marginal | YurenHao0426 |
| 2026-03-27 | Add Phase 10A.8: freeze-with-decay confirms stale aux is main freeze failure ... | YurenHao0426 |
| 2026-03-27 | Add Phase 10A.7: minimal aux compression — continuous trainability is essen... | YurenHao0426 |
| 2026-03-26 | Add Phase 10A.6: gain requires trainable depth-aware aux, not semantic credit | YurenHao0426 |
| 2026-03-26 | Add Phase 10A.5: blend gain is implicit regularization, not learned credit | YurenHao0426 |
| 2026-03-26 | Add Phase 10A: no prefit threshold — even random Vec blend beats DFA by +1.3% | YurenHao0426 |
| 2026-03-26 | Add Phase 9B+9C: periodic refit fails, top-down curriculum neutral | YurenHao0426 |
| 2026-03-25 | Full Phase 9A: blend(0.75) outperforms DFA by +1.5% across multiple t0 | YurenHao0426 |
| 2026-03-25 | Add Phase 9A: checkpointed handoff — blend(Vec+DFA) outperforms pure DFA | YurenHao0426 |
| 2026-03-25 | Add Phase 8: schedule timing test — online co-learning is the remaining bot... | YurenHao0426 |
