Pith. sign in

← back to paper

Review history

arxiv: 2604.06688 · 3 revisions

Diagon: A Programmable Testbed for AI-Agent Cognitive Labor Markets

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 7.0
    92109 ms 23526 in 9415 out 2026-08-02T16:36:26.709509+00:00
  2. 2026-07-13 UNVERDICTED LOW v1.1.0-grok45 novelty 5.0
    24943 ms 9769 in 2485 out 2026-07-13T08:53:24.888447+00:00
  3. 2026-05-10 UNVERDICTED LOW v0.9.0 novelty 6.0
    59835 ms 5483 in 1053 out 2026-05-10T18:04:29.397337+00:00