{"as_of":"2026-07-17T20:31:00Z","canonical_paper_id":"FZLWJLEP","canonical_url":"https://pith.science/paper/FZLWJLEP/integrity","context_digest":"sha256:02533360a82a9c7bb9d25288d7aa02eaae728054e06ec27f8a96d4c292be4a0b","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/2005.10716","bundle_json":"/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/bundle.json","citation_record":"/paper/FZLWJLEP/citation-record","evidence":"/evidence","html":"/paper/FZLWJLEP/integrity","integrity_json":"/paper/FZLWJLEP/integrity.json","json":"/paper/FZLWJLEP/integrity.json","legacy_integrity_json":"/pith/FZLWJLEP/integrity.json","paper":"/paper/FZLWJLEP","reference_changes":"/flags?citing=FZLWJLEP"},"paper":{"arxiv_id":"2005.10716","latest_version":2,"primary_cat":"cs.CL","title":"Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation"},"pith_number":"pith:2020:FZLWJLEP5HVPZ2MGI6GWYE6NBT","pith_short":"FZLWJLEP5HVPZ2MGI6GWYE6NBT","record":{"arxiv_id":"2005.10716","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2005.10716. 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"}