Pith. sign in

← back to paper

Review history

arxiv: 2607.11953 · 2 revisions

When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

  1. 2026-08-02 ACCEPT MODERATE v1.3.0-alltime-deepseek novelty 7.0
    187065 ms 16856 in 18891 out 2026-08-02T07:13:34.813074+00:00
  2. 2026-07-15 CONDITIONAL LOW v1.1.0-grok45 novelty 6.0
    24490 ms 6224 in 3116 out 2026-07-15T09:18:04.346466+00:00