Pith. sign in

← back to paper

Review history

arxiv: 2607.27056 · 2 revisions

Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data

  1. 2026-08-04 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 8.0
    303447 ms 29901 in 11291 out 2026-08-04T03:15:08.933617+00:00
  2. 2026-07-30 CONDITIONAL HIGH v1.2.0-daily-grok45 novelty 6.0
    81651 ms 17376 in 3968 out 2026-07-30T12:29:10.633710+00:00