Integrity report for Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)

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

arXiv:2605.18629 · pith:2026:5FYGF45JYS4LBAT3QS6KM5ORF7

0Critical

0Advisory

5Detectors run

2026-05-25Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

doi_compliance completed v1.0.0 · findings 0 · 2026-05-25 13:46:59.579908+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-25 12:32:44.675983+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-25 00:43:38.413588+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-20 23:23:40.095439+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-20 00:33:33.329819+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/5FYGF45J/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.