← back to paper

Review history

arxiv: 2608.06609 · 2 revisions

Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques

1. 2026-08-11 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   99314 ms 14558 in 11911 out 2026-08-11T04:12:48.282305+00:00
2. 2026-08-10 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   109122 ms 14443 in 12962 out 2026-08-10T04:16:22.340887+00:00