Pith. sign in

← back to paper

Review history

arxiv: 2605.02395 · 2 revisions

Verifiable Counterfactual Supervision for Process Reward Models

  1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    24440 ms 5667 in 954 out 2026-07-01T00:26:15.689743+00:00
  2. 2026-05-08 UNVERDICTED LOW v0.9.0 novelty 6.0
    48395 ms 5447 in 1257 out 2026-05-08T19:17:57.475971+00:00