Pith. sign in

← back to paper

Review history

arxiv: 2601.14249 · 2 revisions

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

  1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
    141368 ms 33723 in 12774 out 2026-08-03T09:15:14.617070+00:00
  2. 2026-05-16 CONDITIONAL LOW v0.9.0 novelty 6.0
    42843 ms 5561 in 1269 out 2026-05-16T12:19:57.928212+00:00