wassname 3cc804b15e results: A3 post-hoc erase rows (weight 0.297 partial, act 0/0 lobotomy) ...

Job 98 (tt_erase_bench on 20260531 vanilla ckpt, n=192): post-hoc erasure cannot
isolate the hack. weight_erase dents hack 0.391->0.297 (solve flat); act_erase
(Arditi residual ablation @layer35) zeroes hack ONLY by zeroing solve too -- a
lobotomy. Contrast: train-time route gets hack 0.000 AND solve 0.625. Split the
single post-hoc row into weight/act rows in tab:ablation, recorded own-baseline
0.391 in provenance. Journal 2026-06-03(c).

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-03 10:50:08 +00:00

..

.gitignore

Merge branch 'probe/distill-cosine' of https://github.com/wassname/projected_grpo into probe/distill-cosine

2026-06-02 07:21:49 +00:00

main.tex

results: A3 post-hoc erase rows (weight 0.297 partial, act 0/0 lobotomy)

2026-06-03 10:50:08 +00:00

nips15submit_e.sty

docs(writeup): NeurIPS-workshop paper skeleton + tectonic compile recipe

2026-06-02 06:59:15 +00:00

refs.bib

paper: address comprehension friction + OpenReview novelty challenge

2026-06-03 02:29:45 +00:00