summaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2026-04-08Refresh paper/main.pdf after abstract-update revert experimentYurenHao0426
2026-04-08paper v2.34.1: SB/CB training loss decrease values from 3-seed (were s42)YurenHao0426
2026-04-08paper v2.34: §4 ¶4 mechanism hypothesis adds Mode 2 → Mode 1 causal chainYurenHao0426
2026-04-08paper v2.33: promote nudging test to §4 main text + correct to 3-seed valuesYurenHao0426
2026-04-08Sync EVIDENCE_SUMMARY.md and PAPER_OUTLINE.md with v2.32 valuesYurenHao0426
2026-04-08Sync experiment+protocol scripts with v2.32 corrected control valuesYurenHao0426
2026-04-08protocol/README.md: sync (c) range with v2.31.13 paper updateYurenHao0426
2026-04-08protocol/protocol.py: sync (c) range docstring with v2.31.13 paper updateYurenHao0426
2026-04-08paper v2.32.2: §3 ¶1 "20× below clamp" → "25× below clamp"YurenHao0426
2026-04-08paper v2.32.1: §5 ¶3 BP-to-SB gap 7.7 → 7.9 (cascade from BP+pen 0.530 ...YurenHao0426
2026-04-08paper v2.32: BP+penalty multi-seeded (was single-seed s42)YurenHao0426
2026-04-08paper v2.31.14: §3 ¶1 local-loss formula sign-consistencyYurenHao0426
2026-04-08Commit dfa_pen_short lam=1e-4 s123/s456 JSONs (auditable source for §5 ¶2)YurenHao0426
2026-04-08Refresh paper/main.pdf after v2.31.13 sign-convention experiment revertYurenHao0426
2026-04-08paper v2.31.13: §6 ¶3 (c) ranges replaced with audit-data rangesYurenHao0426
2026-04-08Save threshold_sensitivity_output.txt for §6 ¶1 + Appendix E auditYurenHao0426
2026-04-08paper v2.31.12: §1 ¶2 + §1 ¶3 ‖g_L‖ values consistent with §3 ¶1YurenHao0426
2026-04-08Refresh paper/main.pdf to latest compiled stateYurenHao0426
2026-04-08Save null_calibration_penalized_dfa.json for §6 ¶2 auditYurenHao0426
2026-04-08paper v2.31.11: §3 ¶3 d=512 max-per-block growth uses sourced DFA valueYurenHao0426
2026-04-08paper v2.31.10: Appendix L drift values use 3-seed means (were s42)YurenHao0426
2026-04-08paper v2.31.9: relabel "StudentNet" → "no-terminal-LN ResMLP"YurenHao0426
2026-04-08paper v2.31.8: Appendix I EP random-target ‖h_L‖ values from saved JSONYurenHao0426
2026-04-08paper v2.31.7: Appendix H vanilla residual DFA endpoint valuesYurenHao0426
2026-04-08paper v2.31.6: §3 ¶2 no-residual values use 3-seed meansYurenHao0426
2026-04-08paper v2.31.5: §3 ¶3 ep-4 g_L from 3-seed (was single-seed g_2)YurenHao0426
2026-04-08paper v2.31.4: §2 ¶3 EP per-block growth 11.6× → 6.6× (3-seed)YurenHao0426
2026-04-08paper v2.31.3: §2 ¶3 per-block growth values were architecture mix-upYurenHao0426
2026-04-08paper v2.31.2: depth-scan layer-0 cos range [+0.39,+0.40] → [+0.38,+0.40]YurenHao0426
2026-04-08paper v2.31.1: deep cos +0.155 → +0.151 (ground-truth re-measurement)YurenHao0426
2026-04-08paper v2.31: matched 30-epoch BP/DFA controls (was unsourced 0.609/0.308)YurenHao0426
2026-04-08paper v2.30.2: §3 ¶1 endpoint values use 3-seed meansYurenHao0426
2026-04-08paper v2.30.1: ground-truth ||g_2|| values in §4 ¶1YurenHao0426
2026-04-08paper v2.30: fix layer-0 cosine numbers + add per-seed appendix MYurenHao0426
2026-04-08paper v2.29: add Scellier & Bengio 2017 EP citationYurenHao0426
2026-04-08§6 polish: clarify Figure 5 (decision_utility) is in Appendix D, not main textYurenHao0426
2026-04-08Reviewer-concern batch: ρ formula + LN Jacobian derivation + diagnostic (c) ...YurenHao0426
2026-04-08Intro: add slower FA-first opening paragraph (user feedback)YurenHao0426
2026-04-08Bib fix: Akrout first name 'Mohamad' -> 'Mohamed' (flagged by user's Semantic...YurenHao0426
2026-04-08Bib proactive verification: Xiong 2nd author fix + expand 3 'et al.' entriesYurenHao0426
2026-04-08SB/CB probe reframe + compression + Figure 5 to appendix (user-approved)YurenHao0426
2026-04-08Appendix L: upgrade DFA+pen nudging/drift/trajectory to 3-seed (matches SB/CB)YurenHao0426
2026-04-08Figures 3 and 4: fix aspect ratio (fig3 was squeezed strip) and key-finding l...YurenHao0426
2026-04-08Tables 1/2/3: revert to tabular + wrap in resizebox (per user feedback)YurenHao0426
2026-04-08Polish: tighten §7 conclusion so it fully fits on page 9 (was spilling 2 lin...YurenHao0426
2026-04-08Polish: convert all 9 tables to tabularx for robust \linewidth fittingYurenHao0426
2026-04-08Round 41 complete: 3-method cos-vs-acc dissociation with DFA+pen addedYurenHao0426
2026-04-08Round 41 (Appendix L): add 4th piece of cos-vs-acc evidence - trajectory loss...YurenHao0426
2026-04-08Round 41 (Appendix L): add nudging-test functional evidence for cos-vs-acc di...YurenHao0426
2026-04-08Round 41 (Appendix L): add per-block drift diagnostic reinforcing cos-vs-acc ...YurenHao0426
generated by cgit v1.2.3 (git 2.25.1) at 2026-06-15 03:57:43 +0000