{"as_of":"2026-07-22T03:05:00Z","canonical_paper_id":"2305.01633","canonical_url":"https://pith.science/paper/2305.01633/integrity","context_digest":"sha256:12b1dfc4cf3f6c63ca17103ecdc1bf8870822f80a2b55b8c5cbb888f16640848","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/2305.01633","bundle_json":"/pith/I2GELOUXOQAWKN3ZU6C2GFG2KW/bundle.json","citation_record":"/paper/2305.01633/citation-record","evidence":"/evidence","html":"/paper/2305.01633/integrity","integrity_json":"/paper/2305.01633/integrity.json","json":"/paper/2305.01633/integrity.json","legacy_integrity_json":"/pith/2305.01633/integrity.json","paper":"/paper/2305.01633","reference_changes":"/flags?citing=2305.01633"},"paper":{"arxiv_id":"2305.01633","latest_version":2,"primary_cat":"cs.CL","title":"Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP"},"pith_number":"pith:2023:I2GELOUXOQAWKN3ZU6C2GFG2KW","pith_short":"I2GELOUXOQAWKN3ZU6C2GFG2KW","record":{"arxiv_id":"2305.01633","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2305.01633. 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"}