Integrity report for Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

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

arXiv:2605.20282 · pith:2026:RSECQEF37EU7NQZLXOE24PQZQ7

0Critical

0Advisory

5Detectors run

2026-05-22Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-22 00:22:37.778068+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-21 20:24:44.034956+00:00

doi_compliance completed v1.0.0 · findings 0 · 2026-05-21 08:06:23.632558+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-21 08:01:38.572197+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-21 00:33:41.467240+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/RSECQEF3/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.