pith. sign in

Integrity report for Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

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

arXiv:2605.20402 · pith:2026:ZOJ2MBIOGIJJFKPZEUK2IIEDNI

0Critical
0Advisory
9Detectors run
2026-06-02Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

ai_meta_artifact completed v1.0.0 · findings 0 · 2026-06-02 23:41:02.937429+00:00
doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-30 00:33:58.290739+00:00
doi_compliance completed v1.0.0 · findings 0 · 2026-05-27 02:05:07.341631+00:00
claim_evidence completed v1.0.0 · findings 0 · 2026-05-27 00:44:18.015590+00:00
doi_compliance completed v1.0.0 · findings 0 · 2026-05-24 08:16:01.051998+00:00
doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-24 08:02:28.101726+00:00
claim_evidence completed v1.0.0 · findings 0 · 2026-05-24 05:23:19.436242+00:00
cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-21 19:24:44.022266+00:00
ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-21 03:33:30.040402+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/ZOJ2MBIOGIJJFKPZEUK2IIEDNI/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.