← back to paper

Review history

arxiv: 2605.23055 · 2 revisions

Decomposing and Measuring Evaluation Awareness

1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   40187 ms 5820 in 1328 out 2026-06-30T16:41:57.245789+00:00
2. 2026-05-25 UNVERDICTED LOW v0.9.0 novelty 7.0
   26017 ms 5820 in 1423 out 2026-05-25T05:27:03.778227+00:00