{"as_of":"2026-07-17T21:47:00Z","canonical_paper_id":"2FLK2MWJ","canonical_url":"https://pith.science/paper/2FLK2MWJ/integrity","context_digest":"sha256:9f2a4cb44f728f8e2965be826bbc855ebe310954fb990fd9bb990d8c82a2ca45","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/2310.11324","bundle_json":"/pith/2FLK2MWJLATJAVAZTWKFIVMEEF/bundle.json","citation_record":"/paper/2FLK2MWJ/citation-record","evidence":"/evidence","html":"/paper/2FLK2MWJ/integrity","integrity_json":"/paper/2FLK2MWJ/integrity.json","json":"/paper/2FLK2MWJ/integrity.json","legacy_integrity_json":"/pith/2FLK2MWJ/integrity.json","paper":"/paper/2FLK2MWJ","reference_changes":"/flags?citing=2FLK2MWJ"},"paper":{"arxiv_id":"2310.11324","latest_version":2,"primary_cat":"cs.CL","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting"},"pith_number":"pith:2023:2FLK2MWJLATJAVAZTWKFIVMEEF","pith_short":"2FLK2MWJLATJAVAZTWKFIVMEEF","record":{"arxiv_id":"2310.11324","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2310.11324. 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"}