{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DXNG34DL5UE7DVQGDIOPJIDURZ","short_pith_number":"pith:DXNG34DL","schema_version":"1.0","canonical_sha256":"1dda6df06bed09f1d6061a1cf4a0748e7b99c95af12c65742363149819c32394","source":{"kind":"arxiv","id":"2204.01075","version":1},"attestation_state":"computed","paper":{"title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.HC","authors_text":"Andrew Zaldivar (1), Mahima Pushkarna (1), Oddur Kjartansson (1) ((1) Google Research)","submitted_at":"2022-04-03T13:49:36Z","abstract_excerpt":"As research and industry moves towards large-scale models capable of numerous downstream tasks, the complexity of understanding multi-modal datasets that give nuance to models rapidly increases. A clear and thorough understanding of a dataset's origins, development, intent, ethical considerations and evolution becomes a necessary step for the responsible and informed deployment of models, especially those in people-facing contexts and high-risk domains. However, the burden of this understanding often falls on the intelligibility, conciseness, and comprehensiveness of the documentation. It requ"},"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":"2204.01075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-04-03T13:49:36Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"77a8f58a3e4e4751e577ffd8150ca0882f419ef6ed9b2a88975b4fea1017b562","abstract_canon_sha256":"2ebfdadd3e9b6446b4bca3d5e2e721ad6cbe495fafd3bcecc17e0c3d7367fc77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:15.134312Z","signature_b64":"Sf2c8Net9M1qM10bxxg8pyBLkSigTBJxDTIdnAgxJlt3p/qS0EXZrySiV7L//7i9o4cZ1+0IOAs8HTC68aTaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dda6df06bed09f1d6061a1cf4a0748e7b99c95af12c65742363149819c32394","last_reissued_at":"2026-07-05T04:11:15.133935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:15.133935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.HC","authors_text":"Andrew Zaldivar (1), Mahima Pushkarna (1), Oddur Kjartansson (1) ((1) Google Research)","submitted_at":"2022-04-03T13:49:36Z","abstract_excerpt":"As research and industry moves towards large-scale models capable of numerous downstream tasks, the complexity of understanding multi-modal datasets that give nuance to models rapidly increases. A clear and thorough understanding of a dataset's origins, development, intent, ethical considerations and evolution becomes a necessary step for the responsible and informed deployment of models, especially those in people-facing contexts and high-risk domains. However, the burden of this understanding often falls on the intelligibility, conciseness, and comprehensiveness of the documentation. It requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01075","kind":"arxiv","version":1},"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/2204.01075/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":"2204.01075","created_at":"2026-07-05T04:11:15.133990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01075v1","created_at":"2026-07-05T04:11:15.133990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01075","created_at":"2026-07-05T04:11:15.133990+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXNG34DL5UE7","created_at":"2026-07-05T04:11:15.133990+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXNG34DL5UE7DVQG","created_at":"2026-07-05T04:11:15.133990+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXNG34DL","created_at":"2026-07-05T04:11:15.133990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12433","citing_title":"Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ","json":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ.json","graph_json":"https://pith.science/api/pith-number/DXNG34DL5UE7DVQGDIOPJIDURZ/graph.json","events_json":"https://pith.science/api/pith-number/DXNG34DL5UE7DVQGDIOPJIDURZ/events.json","paper":"https://pith.science/paper/DXNG34DL"},"agent_actions":{"view_html":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ","download_json":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ.json","view_paper":"https://pith.science/paper/DXNG34DL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01075&json=true","fetch_graph":"https://pith.science/api/pith-number/DXNG34DL5UE7DVQGDIOPJIDURZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DXNG34DL5UE7DVQGDIOPJIDURZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ/action/storage_attestation","attest_author":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ/action/author_attestation","sign_citation":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ/action/citation_signature","submit_replication":"https://pith.science/pith/DXNG34DL5UE7DVQGDIOPJIDURZ/action/replication_record"}},"created_at":"2026-07-05T04:11:15.133990+00:00","updated_at":"2026-07-05T04:11:15.133990+00:00"}