pith. sign in

Integrity report for Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory

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

arXiv:2605.12394

0Critical
0Advisory
4Detectors run
2026-05-26Last checked

Paper page arXiv integrity.json

Detector runs

ai_meta_artifact completed v1.0.0 · findings 0 · 2026-05-26 14:40:05.865354+00:00
doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-20 13:31:25.011862+00:00
doi_compliance completed v1.0.0 · findings 0 · 2026-05-20 09:45:43.519827+00:00
claim_evidence completed v1.0.0 · findings 0 · 2026-05-19 22:41:58.212232+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/2605.12394/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.