Pith. sign in

← back to paper

Review history

arxiv: 2601.16398 · 2 revisions

White-Box Sensitivity Auditing with Steering Vectors

  1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
    301708 ms 23417 in 15108 out 2026-08-03T08:37:02.640957+00:00
  2. 2026-05-21 UNVERDICTED LOW v0.9.0 novelty 6.0
    39271 ms 5708 in 1087 out 2026-05-21T16:09:49.301018+00:00