pith. sign in

Integrity report for Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning

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

arXiv:2605.29894 · pith:2026:UKTY3FLO3B6QQ3MYPQEW22MSHK

0Critical
0Advisory
5Detectors run
2026-06-05Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-06-05 03:35:50.452950+00:00
claim_evidence completed v1.0.0 · findings 0 · 2026-06-03 13:48:25.940341+00:00
citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-31 13:50:46.602859+00:00
shingle_duplication skipped v0.1.0 · findings 0 · 2026-05-30 17:50:07.340630+00:00
cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-29 09:54:28.432395+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/UKTY3FLO/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.