{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXIRRI7EDZZKY6MOGKSCVV2ZYJ","short_pith_number":"pith:JXIRRI7E","schema_version":"1.0","canonical_sha256":"4dd118a3e41e72ac798e32a42ad759c277b705d900804e215f4d25c042e842bf","source":{"kind":"arxiv","id":"2402.05160","version":1},"attestation_state":"computed","paper":{"title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Daniel Scott Smith, Eric Wu, Ezinwanne Ozoani, James Zou, Nazneen Rajani, Weixin Liang, Xinyu Yang, Yiqun Chen","submitted_at":"2024-02-07T18:04:32Z","abstract_excerpt":"The rapid proliferation of AI models has underscored the importance of thorough documentation, as it enables users to understand, trust, and effectively utilize these models in various applications. Although developers are encouraged to produce model cards, it's not clear how much information or what information these cards contain. In this study, we conduct a comprehensive analysis of 32,111 AI model documentations on Hugging Face, a leading platform for distributing and deploying AI models. Our investigation sheds light on the prevailing model card documentation practices. Most of the AI mod"},"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":"2402.05160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-07T18:04:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d45d9786b877fe33adfdb5abb853b6dd4ce4ed7118c0bca53ee56bfe1500fa2f","abstract_canon_sha256":"8189c2e62f2be3ccf8e396380fd3213a647640dd338dd15812c7d3db15a71fb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:45.645300Z","signature_b64":"ZUpyC5MG7g3rofHGB2irpaGvWOgLFVxvt8aMAPfwRhPhywa8QtISaW0Og+FLVMT80fmSbcwBatjdBkeQpYVKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dd118a3e41e72ac798e32a42ad759c277b705d900804e215f4d25c042e842bf","last_reissued_at":"2026-07-05T07:42:45.644801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:45.644801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Daniel Scott Smith, Eric Wu, Ezinwanne Ozoani, James Zou, Nazneen Rajani, Weixin Liang, Xinyu Yang, Yiqun Chen","submitted_at":"2024-02-07T18:04:32Z","abstract_excerpt":"The rapid proliferation of AI models has underscored the importance of thorough documentation, as it enables users to understand, trust, and effectively utilize these models in various applications. Although developers are encouraged to produce model cards, it's not clear how much information or what information these cards contain. In this study, we conduct a comprehensive analysis of 32,111 AI model documentations on Hugging Face, a leading platform for distributing and deploying AI models. Our investigation sheds light on the prevailing model card documentation practices. Most of the AI mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05160","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/2402.05160/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":"2402.05160","created_at":"2026-07-05T07:42:45.644858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05160v1","created_at":"2026-07-05T07:42:45.644858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05160","created_at":"2026-07-05T07:42:45.644858+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXIRRI7EDZZK","created_at":"2026-07-05T07:42:45.644858+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXIRRI7EDZZKY6MO","created_at":"2026-07-05T07:42:45.644858+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXIRRI7E","created_at":"2026-07-05T07:42:45.644858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10911","citing_title":"Ethical and Technical Limits of Deepfake Speech Datasets","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22766","citing_title":"Diversed Model Discovery via Structured Table Discovery","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17104","citing_title":"TStore: Rethinking AI Model Hub with Tensor-Centric Compression","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17104","citing_title":"TStore: Rethinking AI Model Hub with Tensor-Centric Compression","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ","json":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ.json","graph_json":"https://pith.science/api/pith-number/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/graph.json","events_json":"https://pith.science/api/pith-number/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/events.json","paper":"https://pith.science/paper/JXIRRI7E"},"agent_actions":{"view_html":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ","download_json":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ.json","view_paper":"https://pith.science/paper/JXIRRI7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05160&json=true","fetch_graph":"https://pith.science/api/pith-number/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/action/storage_attestation","attest_author":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/action/author_attestation","sign_citation":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/action/citation_signature","submit_replication":"https://pith.science/pith/JXIRRI7EDZZKY6MOGKSCVV2ZYJ/action/replication_record"}},"created_at":"2026-07-05T07:42:45.644858+00:00","updated_at":"2026-07-05T07:42:45.644858+00:00"}