pith. sign in

← back to paper

Review history

arxiv: 2606.25487 · 2 revisions

How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring

  1. 2026-06-26 ACCEPT LOW v0.9.1-grok novelty 7.0
    24605 ms 5878 in 1217 out 2026-06-26T05:25:10.453138+00:00
  2. 2026-06-25 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    23509 ms 5878 in 1180 out 2026-06-25T20:54:43.853039+00:00