Integrity report for Training ML Models with Predictable Failures

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

arXiv:2605.15134 · pith:2026:TZBVH2UCH57UFKYOX24RCL4VK2

0Critical

1Advisory

10Detectors run

2026-05-28Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

ai_meta_artifact completed v1.0.0 · findings 0 · 2026-05-28 23:44:31.532168+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-24 16:24:12.298121+00:00

doi_compliance completed v1.0.0 · findings 1 · 2026-05-21 20:49:31.407282+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-21 20:31:45.578850+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-21 16:22:30.437345+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-19 14:41:54.368282+00:00

external_links completed v1.0.0 · findings 0 · 2026-05-19 11:34:11.933963+00:00

shingle_duplication skipped v0.1.0 · findings 0 · 2026-05-19 09:50:02.248597+00:00

citation_quote_validity skipped v0.1.0 · findings 0 · 2026-05-19 05:51:07.253963+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-19 05:34:19.505612+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/TZBVH2UCH57UFKYOX24RCL4VK2/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.