Pith. sign in

← back to paper

Review history

arxiv: 2605.01482 · 3 revisions

Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

  1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 4.0
    27705 ms 5726 in 1197 out 2026-07-01T00:19:00.279250+00:00
  2. 2026-05-11 UNVERDICTED LOW v0.9.0 novelty 5.0
    40608 ms 5504 in 1123 out 2026-05-11T02:12:57.703359+00:00
  3. 2026-05-09 UNVERDICTED LOW v0.9.0 novelty 4.0
    39755 ms 5504 in 1264 out 2026-05-09T14:22:55.347229+00:00