{"as_of":"2026-07-16T21:12:00Z","canonical_paper_id":"2104.02145","canonical_url":"https://pith.science/paper/2104.02145/integrity","context_digest":"sha256:948316c9b1006d35b24668071f49e45f77d2adfa93ba6f0072d1b5ef3e52ec89","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/2104.02145","bundle_json":"/pith/5LZPZHSVHXBKWI5FWWZXGXCA7O/bundle.json","citation_record":"/paper/2104.02145/citation-record","evidence":"/evidence","html":"/paper/2104.02145/integrity","integrity_json":"/paper/2104.02145/integrity.json","json":"/paper/2104.02145/integrity.json","legacy_integrity_json":"/pith/2104.02145/integrity.json","paper":"/paper/2104.02145","reference_changes":"/flags?citing=2104.02145"},"paper":{"arxiv_id":"2104.02145","latest_version":3,"primary_cat":"cs.CL","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?"},"pith_number":"pith:2021:5LZPZHSVHXBKWI5FWWZXGXCA7O","pith_short":"5LZPZHSVHXBKWI5FWWZXGXCA7O","record":{"arxiv_id":"2104.02145","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2104.02145. 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"}