pith. sign in

← back to paper

Review history

arxiv: 2604.18309 · 2 revisions

From Program Slices to Causal Clarity: Evaluating Faithful, Actionable LLM-Generated Failure Explanations via Context Partitioning and LLM-as-a-Judge

  1. 2026-05-21 CONDITIONAL MODERATE v0.9.0 novelty 6.0
    54406 ms 5858 in 1395 out 2026-05-21T08:43:49.173538+00:00
  2. 2026-05-10 UNVERDICTED LOW v0.9.0 novelty 6.0
    37584 ms 5627 in 1406 out 2026-05-10T04:27:26.058727+00:00