Pith. sign in

← back to paper

Review history

arxiv: 2608.00739 · 2 revisions

EduPluginBench: Executable Assurance for AI-Generated Educational Plugins

  1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
    110725 ms 21633 in 14344 out 2026-08-15T15:16:59.819629+00:00
  2. 2026-08-05 CONDITIONAL HIGH v1.3.0-alltime-deepseek novelty 7.0
    143700 ms 217 in 8791 out 2026-08-05T00:22:57.314118+00:00