{"as_of":"2026-07-17T22:06:00Z","canonical_paper_id":"OWOLVEFR","canonical_url":"https://pith.science/paper/OWOLVEFR/integrity","context_digest":"sha256:65db195ae4e526a1106d0af6ab7b45942a3fb1336852b2c8e4f8f062793de12d","coverage_summary":[],"findings":[],"findings_empty_copy":"No checks are listed for this paper yet.","findings_observation_state":"no_listed_checks","links":{"arxiv":"https://arxiv.org/abs/2606.07936","bundle_json":"/pith/OWOLVEFRGNJS4LYBYONLAXHEII/bundle.json","citation_record":"/paper/OWOLVEFR/citation-record","evidence":"/evidence","html":"/paper/OWOLVEFR/integrity","integrity_json":"/paper/OWOLVEFR/integrity.json","json":"/paper/OWOLVEFR/integrity.json","legacy_integrity_json":"/pith/OWOLVEFR/integrity.json","paper":"/paper/OWOLVEFR","reference_changes":"/flags?citing=OWOLVEFR"},"paper":{"arxiv_id":"2606.07936","latest_version":2,"primary_cat":"cs.CL","title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation"},"pith_number":"pith:2026:OWOLVEFRGNJS4LYBYONLAXHEII","pith_short":"OWOLVEFRGNJS4LYBYONLAXHEII","record":{"arxiv_id":"2606.07936","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2606.07936. No listed check completed, so this record makes no findings claim.","counts":{"completed":0,"failed":0,"listed":0,"not_collected":0,"not_requested":0,"partial":0,"public_findings_from_completed":0,"skipped":0,"unavailable":0,"withheld":0},"coverage":[],"observed_at":null,"refusal":"This is a record of named checks, not a clean-status claim or a paper verdict.","schema":"pith.integrity.v1"},"schema":"pith.paper-integrity-record.v1","species":"LEDGER"}