Integrity report for SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents

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

arXiv:2605.21384 · pith:2026:462PYM6MLD6BGXPKZRJOQKO3H5

0Critical

0Advisory

8Detectors run

2026-05-21Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

shingle_duplication completed v0.1.0 · findings 0 · 2026-05-21 13:50:26.863511+00:00

external_links completed v1.0.0 · findings 0 · 2026-05-21 11:32:15.847156+00:00

citation_quote_validity completed v0.1.0 · findings 0 · 2026-05-21 05:50:39.998000+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-05-21 03:52:30.264476+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-05-21 03:31:36.625153+00:00

doi_compliance completed v1.0.0 · findings 0 · 2026-05-21 03:13:54.555506+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-05-21 02:33:33.388972+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-05-21 02:22:20.069446+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/462PYM6M/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.