Integrity report for Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs

A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.

arXiv:2605.23039 · pith:2026:BLOHP6G6PY5AAYF5N2WQLZYFR2

0Critical

0Advisory

6Detectors run

2026-06-05Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

doi_compliance completed v1.0.0 · findings 0 · 2026-06-05 06:07:49.131489+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-06-05 06:06:08.049119+00:00

ai_meta_artifact completed v1.0.0 · findings 0 · 2026-06-01 05:36:58.051244+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-28 16:44:54.369863+00:00

citation_quote_validity completed v0.1.0 · findings 0 · 2026-05-25 23:51:46.432412+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-25 16:25:19.913183+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/BLOHP6G6/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.