← back to paper

Review history

arxiv: 2605.03472 · 3 revisions

Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks

1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   30409 ms 5796 in 1465 out 2026-07-01T00:21:29.679426+00:00
2. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 7.0
   87724 ms 5602 in 1842 out 2026-05-07T16:46:00.218122+00:00
3. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 6.0
   22707 ms 5580 in 1554 out 2026-05-07T01:35:20.829412+00:00