Pith. sign in

← back to paper

Review history

arxiv: 2607.09328 · 2 revisions

WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 8.0
    168424 ms 20974 in 15956 out 2026-08-02T07:37:12.304665+00:00
  2. 2026-07-13 ACCEPT HIGH v1.1.0-grok45 novelty 7.0
    57218 ms 29550 in 3138 out 2026-07-13T03:50:57.573243+00:00