Integrity report for SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

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

arXiv:2605.22658 · pith:2026:VNWXVILVH6SRGJYXD3IOX23Y3A

0Critical

6Advisory

6Detectors run

2026-05-25Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-25 03:43:40.599962+00:00

external_links completed v1.0.0 · findings 1 · 2026-05-24 23:35:16.866068+00:00

citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-24 09:52:24.045283+00:00

shingle_duplication completed v0.1.0 · findings 0 · 2026-05-22 17:50:08.375363+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-22 04:52:58.301449+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-22 02:33:38.023225+00:00

Findings

No public integrity findings for this paper.

Signed record

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