Pith. sign in

← back to paper

Review history

arxiv: 2607.03882 · 2 revisions

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language

  1. 2026-07-13 ACCEPT HIGH v1.1.0-grok45 novelty 6.0
    28087 ms 20539 in 3004 out 2026-07-13T07:01:34.368173+00:00
  2. 2026-07-11 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.0
    38296 ms 20573 in 3072 out 2026-07-11T23:16:16.019615+00:00