Pith. sign in

← back to paper

Review history

arxiv: 2607.23424 · 3 revisions

Wrong and More Confident: A Field Experiment on Large Language Models Taking a Graduate Economics Exam

  1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
    267400 ms 29970 in 26202 out 2026-08-03T01:47:58.301207+00:00
  2. 2026-07-31 CONDITIONAL HIGH v1.3.0-alltime-deepseek novelty 6.0
    150058 ms 29970 in 18027 out 2026-07-31T23:36:31.119084+00:00
  3. 2026-07-30 ACCEPT HIGH v1.2.0-grok45-kimik3 novelty 6.5
    75744 ms 33966 in 3682 out 2026-07-30T22:34:27.215155+00:00