Pith. sign in

← back to paper

Review history

arxiv: 2607.02104 · 2 revisions

When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
    186170 ms 25422 in 19031 out 2026-08-02T09:01:16.733918+00:00
  2. 2026-07-03 UNVERDICTED LOW v0.9.1-grok novelty 6.0
    23369 ms 5878 in 1390 out 2026-07-03T17:16:47.327339+00:00