Pith. sign in

← back to paper

Review history

arxiv: 2608.03437 · 2 revisions

Dynamically Allocating Evaluation Effort for Model Ranking

  1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
    215491 ms 24429 in 26245 out 2026-08-15T14:51:15.636490+00:00
  2. 2026-08-05 CONDITIONAL HIGH v1.4.0-daily-deepseek-medium novelty 6.0
    147560 ms 24403 in 15573 out 2026-08-05T19:06:19.948526+00:00