| Age | Commit message (Expand) | Author |
|---|
| 2026-04-08 | paper v2.31.7: Appendix H vanilla residual DFA endpoint values | YurenHao0426 |
| 2026-04-08 | paper v2.31.6: §3 ¶2 no-residual values use 3-seed means | YurenHao0426 |
| 2026-04-08 | paper v2.31.5: §3 ¶3 ep-4 g_L from 3-seed (was single-seed g_2) | YurenHao0426 |
| 2026-04-08 | paper v2.31.4: §2 ¶3 EP per-block growth 11.6× → 6.6× (3-seed) | YurenHao0426 |
| 2026-04-08 | paper v2.31.3: §2 ¶3 per-block growth values were architecture mix-up | YurenHao0426 |
| 2026-04-08 | paper v2.31.2: depth-scan layer-0 cos range [+0.39,+0.40] → [+0.38,+0.40] | YurenHao0426 |
| 2026-04-08 | paper v2.31.1: deep cos +0.155 → +0.151 (ground-truth re-measurement) | YurenHao0426 |
| 2026-04-08 | paper v2.31: matched 30-epoch BP/DFA controls (was unsourced 0.609/0.308) | YurenHao0426 |
| 2026-04-08 | paper v2.30.2: §3 ¶1 endpoint values use 3-seed means | YurenHao0426 |
| 2026-04-08 | paper v2.30.1: ground-truth ||g_2|| values in §4 ¶1 | YurenHao0426 |
| 2026-04-08 | paper v2.30: fix layer-0 cosine numbers + add per-seed appendix M | YurenHao0426 |
| 2026-04-08 | paper v2.29: add Scellier & Bengio 2017 EP citation | YurenHao0426 |
| 2026-04-08 | §6 polish: clarify Figure 5 (decision_utility) is in Appendix D, not main text | YurenHao0426 |
| 2026-04-08 | Reviewer-concern batch: ρ formula + LN Jacobian derivation + diagnostic (c) ... | YurenHao0426 |
| 2026-04-08 | Intro: add slower FA-first opening paragraph (user feedback) | YurenHao0426 |
| 2026-04-08 | Bib fix: Akrout first name 'Mohamad' -> 'Mohamed' (flagged by user's Semantic... | YurenHao0426 |
| 2026-04-08 | Bib proactive verification: Xiong 2nd author fix + expand 3 'et al.' entries | YurenHao0426 |
| 2026-04-08 | SB/CB probe reframe + compression + Figure 5 to appendix (user-approved) | YurenHao0426 |
| 2026-04-08 | Appendix L: upgrade DFA+pen nudging/drift/trajectory to 3-seed (matches SB/CB) | YurenHao0426 |
| 2026-04-08 | Figures 3 and 4: fix aspect ratio (fig3 was squeezed strip) and key-finding l... | YurenHao0426 |
| 2026-04-08 | Tables 1/2/3: revert to tabular + wrap in resizebox (per user feedback) | YurenHao0426 |
| 2026-04-08 | Polish: tighten §7 conclusion so it fully fits on page 9 (was spilling 2 lin... | YurenHao0426 |
| 2026-04-08 | Polish: convert all 9 tables to tabularx for robust \linewidth fitting | YurenHao0426 |
| 2026-04-08 | Round 41 complete: 3-method cos-vs-acc dissociation with DFA+pen added | YurenHao0426 |
| 2026-04-08 | Round 41 (Appendix L): add 4th piece of cos-vs-acc evidence - trajectory loss... | YurenHao0426 |
| 2026-04-08 | Round 41 (Appendix L): add nudging-test functional evidence for cos-vs-acc di... | YurenHao0426 |
| 2026-04-08 | Round 41 (Appendix L): add per-block drift diagnostic reinforcing cos-vs-acc ... | YurenHao0426 |
| 2026-04-08 | Polish: spell out 'Equilibrium Propagation (EP)' on first discussion in §2 | YurenHao0426 |
| 2026-04-08 | Polish: Appendix L title + intro mention both SB and CB (was SB-only) | YurenHao0426 |
| 2026-04-08 | Polish: remove 5 stale 'TODO: re-render figure' comments | YurenHao0426 |
| 2026-04-08 | Bib fix: Moskovitz + Crafton + Refinetti titles/venues corrected via WebSearc... | YurenHao0426 |
| 2026-04-08 | Bib fix: Akrout 2019 title 'Deep feedback control' -> 'Deep learning without ... | YurenHao0426 |
| 2026-04-08 | Bib fix: correct titles for 3 E&D model papers (Paleka/O'Bray/Jordan) | YurenHao0426 |
| 2026-04-08 | Bib cleanup: fix Xiong 2020 bibitem sort key (fabricated names removed) | YurenHao0426 |
| 2026-04-08 | §3 fix: correctly distinguish DFA/SB/CB local credit vectors | YurenHao0426 |
| 2026-04-08 | Polish: fix §3 typo 'to an meaningful' -> 'to a meaningful' | YurenHao0426 |
| 2026-04-08 | OPTION F polish pass: update abstract, §1 ¶2, §6 ¶3, §7 ¶2 with round 3... | YurenHao0426 |
| 2026-04-08 | Round 40 §4 update: cos-vs-acc 3-part proposition (Observation / Inference /... | YurenHao0426 |
| 2026-04-08 | Round 38 CB+penalty multi-seed: confirm clean cos-vs-acc dissociation across ... | YurenHao0426 |
| 2026-04-08 | Appendix G + J: 3-seed depth scan L=4 validation + SB/CB random_targets 100ep... | YurenHao0426 |
| 2026-04-08 | Appendix J: add EP random_targets full 100ep convergence ||h_L||=2085, acc=0.081 | YurenHao0426 |
| 2026-04-08 | Round 38 paper update: §4 + §5 + new Appendix K with SB+penalty 3-seed result | YurenHao0426 |
| 2026-04-08 | Appendix H: H2 ablation now 3-seed (s42, s123, s456) — multi-seed validates... | YurenHao0426 |
| 2026-04-08 | Fix bibtex citation key: refinetti2023align -> refinetti2023aligning (matches... | YurenHao0426 |
| 2026-04-08 | Fix §3 vanilla DFA comparison: use 100ep audit value 0.306±0.006 (matches t... | YurenHao0426 |
| 2026-04-08 | Fix precision: ||g_L|| = 7.2e-4 (mean), not 7.4e-4 (rounding) | YurenHao0426 |
| 2026-04-08 | Round 37 OPTION C: §3 compression — preserve causal structure, drop per-ro... | YurenHao0426 |
| 2026-04-08 | Round 36: upgrade (b) wording + add EP random-target neg control to §3 | YurenHao0426 |
| 2026-04-08 | Add 100ep trajectory confirmations to Appendix I (H2) and Appendix J (random ... | YurenHao0426 |
| 2026-04-08 | Round 35: SB and CB also show data-agnostic Mode 1 growth on random targets | YurenHao0426 |
