Pith. sign in

← back to paper

Review history

arxiv: 2605.29007 · 2 revisions

Taxonomy-Targeted Error Generation for Quantitative Reasoning

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
    156957 ms 22117 in 15613 out 2026-08-02T12:52:30.783720+00:00
  2. 2026-06-29 UNVERDICTED LOW v0.9.1-grok novelty 6.0
    58380 ms 5691 in 1020 out 2026-06-29T12:37:48.487126+00:00