{"as_of":"2026-07-14T02:10:00Z","canonical_paper_id":"2003.11080","canonical_url":"https://pith.science/paper/2003.11080/integrity","context_digest":"sha256:c6a6318c755aaf8186cda17b06fd3223b6cdd670c1f3270d7df361c55d39930e","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/2003.11080","bundle_json":"/pith/B5H55RVHOTIGBKVVJCW47SFFUY/bundle.json","citation_record":"/paper/2003.11080/citation-record","evidence":"/evidence","html":"/paper/2003.11080/integrity","integrity_json":"/paper/2003.11080/integrity.json","json":"/paper/2003.11080/integrity.json","legacy_integrity_json":"/pith/2003.11080/integrity.json","paper":"/paper/2003.11080","reference_changes":"/flags?citing=2003.11080"},"paper":{"arxiv_id":"2003.11080","latest_version":5,"primary_cat":"cs.CL","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization"},"pith_number":"pith:2020:B5H55RVHOTIGBKVVJCW47SFFUY","pith_short":"B5H55RVHOTIGBKVVJCW47SFFUY","record":{"arxiv_id":"2003.11080","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2003.11080. 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"}