Integrity report for Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training

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

arXiv:2605.28467 · pith:2026:3DAI3M6PTNBQY6FQJUWNEV6MWI

0Critical

0Advisory

4Detectors run

2026-05-29Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-29 04:05:08.129808+00:00

citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-28 11:50:26.312658+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-28 07:53:53.851151+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-28 02:34:19.122059+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/3DAI3M6P/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.