{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V6XHVFUNIWTWZAZ6VJRZY4Y7VA","short_pith_number":"pith:V6XHVFUN","schema_version":"1.0","canonical_sha256":"afae7a968d45a76c833eaa639c731fa83f1682dfaf914d84ce70a7726612b557","source":{"kind":"arxiv","id":"2410.22473","version":2},"attestation_state":"computed","paper":{"title":"The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Christoph Becker, Ciara Zogheib, Eshta Bhardwaj, Harshit Gujral, Siyi Wu, Tegan Maharaj","submitted_at":"2024-10-29T19:07:50Z","abstract_excerpt":"Data curation is a field with origins in librarianship and archives, whose scholarship and thinking on data issues go back centuries, if not millennia. The field of machine learning is increasingly observing the importance of data curation to the advancement of both applications and fundamental understanding of machine learning models - evidenced not least by the creation of the Datasets and Benchmarks track itself. This work provides an analysis of dataset development practices at NeurIPS through the lens of data curation. We present an evaluation framework for dataset documentation, consisti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.22473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-29T19:07:50Z","cross_cats_sorted":[],"title_canon_sha256":"47f8b0accd49f42f96befa1e5362940f4d32fb414d07ac513078c9510e3cc8ec","abstract_canon_sha256":"510e2c7194a9b5583278ac2ce8832c996cf68c0c8f1bbc49cfc7d3f5c8d351f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:37.603520Z","signature_b64":"T705dTjYiznh9rw7Cq0tZsJwZhQTAQk7F8zxCAJcvsloZwN1Q0JP+RKJ7ov0Zq86uZBs1jy3A0gyXodlTp4UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afae7a968d45a76c833eaa639c731fa83f1682dfaf914d84ce70a7726612b557","last_reissued_at":"2026-07-05T09:56:37.602952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:37.602952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Christoph Becker, Ciara Zogheib, Eshta Bhardwaj, Harshit Gujral, Siyi Wu, Tegan Maharaj","submitted_at":"2024-10-29T19:07:50Z","abstract_excerpt":"Data curation is a field with origins in librarianship and archives, whose scholarship and thinking on data issues go back centuries, if not millennia. The field of machine learning is increasingly observing the importance of data curation to the advancement of both applications and fundamental understanding of machine learning models - evidenced not least by the creation of the Datasets and Benchmarks track itself. This work provides an analysis of dataset development practices at NeurIPS through the lens of data curation. We present an evaluation framework for dataset documentation, consisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22473","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.22473/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.22473","created_at":"2026-07-05T09:56:37.603011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22473v2","created_at":"2026-07-05T09:56:37.603011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22473","created_at":"2026-07-05T09:56:37.603011+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6XHVFUNIWTW","created_at":"2026-07-05T09:56:37.603011+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6XHVFUNIWTWZAZ6","created_at":"2026-07-05T09:56:37.603011+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6XHVFUN","created_at":"2026-07-05T09:56:37.603011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA","json":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA.json","graph_json":"https://pith.science/api/pith-number/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/graph.json","events_json":"https://pith.science/api/pith-number/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/events.json","paper":"https://pith.science/paper/V6XHVFUN"},"agent_actions":{"view_html":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA","download_json":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA.json","view_paper":"https://pith.science/paper/V6XHVFUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22473&json=true","fetch_graph":"https://pith.science/api/pith-number/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/graph.json","fetch_events":"https://pith.science/api/pith-number/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/action/storage_attestation","attest_author":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/action/author_attestation","sign_citation":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/action/citation_signature","submit_replication":"https://pith.science/pith/V6XHVFUNIWTWZAZ6VJRZY4Y7VA/action/replication_record"}},"created_at":"2026-07-05T09:56:37.603011+00:00","updated_at":"2026-07-05T09:56:37.603011+00:00"}