Integrity report for Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works

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

arXiv:2605.07689

0Critical

0Advisory

4Detectors run

2026-05-20Last checked

Paper page arXiv integrity.json

Detector runs

claim_evidence completed v1.0.0 · findings 0 · 2026-05-20 10:22:02.852596+00:00

ai_meta_artifact completed v1.0.0 · findings 0 · 2026-05-20 05:36:24.293988+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-19 16:01:18.617657+00:00

doi_compliance completed v1.0.0 · findings 0 · 2026-05-19 11:36:18.973203+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/2605.07689/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.