Integrity report for On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.
1Critical
0Advisory
6Detectors run
2026-06-05Last checked
Paper page arXiv integrity.json bundle.json
Detector runs
doi_title_agreement
completed
doi_compliance
completed
ai_meta_artifact
completed
claim_evidence
completed
citation_quote_validity
completed
cited_work_retraction
completed
Findings
critical
ai_meta_artifact
certainly_here_is
Verbatim AI-assistant artifact present in paper body: matched pattern 'certainly_here_is'. The matched span is the literal evidence.
Signed record
The machine-readable record for this paper lives at /pith/KX2IWKYPRIHDEITF2Z2YNG6BRU/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.