Pith. sign in

← back to paper

Review history

arxiv: 2607.28587 · 2 revisions

PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

  1. 2026-08-05 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 7.0
    105702 ms 24391 in 10767 out 2026-08-05T04:20:22.679406+00:00
  2. 2026-07-31 CONDITIONAL HIGH v1.2.0-daily-grok45 novelty 6.5
    72734 ms 30587 in 3776 out 2026-07-31T02:58:50.590381+00:00