Integrity report for Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations

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

arXiv:2605.28704 · pith:2026:PCW47THAQCXIIJFHS4DFQYLQLJ

0Critical

0Advisory

6Detectors run

2026-06-04Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-06-04 03:35:38.432725+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-06-02 11:07:43.978633+00:00

external_links completed v1.0.0 · findings 0 · 2026-05-28 23:31:39.999965+00:00

shingle_duplication skipped v0.1.0 · findings 0 · 2026-05-28 13:50:00.315352+00:00

citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-28 05:50:24.901595+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-28 03:53:51.465578+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/PCW47THA/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.