Integrity report for Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models

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

arXiv:2605.19485 · pith:2026:Y5TN4BOWH53BVJIMHTEFTPDSP7

0Critical

0Advisory

6Detectors run

2026-05-25Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-25 10:32:43.197802+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-25 09:43:46.528914+00:00

doi_compliance completed v1.0.0 · findings 0 · 2026-05-25 07:34:04.756417+00:00

citation_quote_validity completed v0.1.0 · findings 0 · 2026-05-20 17:50:41.662032+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-20 12:52:03.292359+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-20 01:33:29.743874+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/Y5TN4BOW/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.