{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ONZAVRSJFFNJDXDOB5XGK4GURB","short_pith_number":"pith:ONZAVRSJ","schema_version":"1.0","canonical_sha256":"73720ac649295a91dc6e0f6e6570d48844fe450f693320f40debba7bb63c7c15","source":{"kind":"arxiv","id":"2407.16883","version":1},"attestation_state":"computed","paper":{"title":"A Standardized Machine-readable Dataset Documentation Format for Responsible AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.DB","cs.LG"],"primary_cat":"cs.IR","authors_text":"Costanza Conforti, Elena Simperl, Joan Giner-Miguelez, Joaquin Vanschoren, Lora Aroyo, Luis Oala, Manil Maskey, Michael Kuchnik, Michalis Karamousadakis, Mubashara Akhtar, Nitisha Jain, Omar Benjelloun, Pierre Marcenac, Rajat Shinde, Steffen Vogler, Sujata Goswami, Tim Santos, Yuhan Rao","submitted_at":"2024-06-04T16:40:14Z","abstract_excerpt":"Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croissant-RAI, a machine-readable metadata format designed to enhance the discoverability, interoperability, and trustworthiness of AI datasets. Croissant-RAI extends the Croissant metadata format and builds upon existing responsible AI (RAI) documentation frameworks, offering a standardized set of attributes and practices to facilitate community-wide ad"},"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":"2407.16883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-04T16:40:14Z","cross_cats_sorted":["cs.AI","cs.CY","cs.DB","cs.LG"],"title_canon_sha256":"8790b541742a8114cd0d9739e014042b1b0e0f4f0ef202b05d1f91d937f5c5f3","abstract_canon_sha256":"89f0c8d88127051b7f3b24d0f60e69ea525573395ed21daf94b53213a696c35d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:58.054285Z","signature_b64":"LVQwmgv7ysSHempoHotNaQMFd7JdGQXDxCWb0IIb7aL3Yk+8X6RdplfP35VNptGPd4atQbCzSyu8reCuMP4KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73720ac649295a91dc6e0f6e6570d48844fe450f693320f40debba7bb63c7c15","last_reissued_at":"2026-07-05T08:47:58.053825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:58.053825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Standardized Machine-readable Dataset Documentation Format for Responsible AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.DB","cs.LG"],"primary_cat":"cs.IR","authors_text":"Costanza Conforti, Elena Simperl, Joan Giner-Miguelez, Joaquin Vanschoren, Lora Aroyo, Luis Oala, Manil Maskey, Michael Kuchnik, Michalis Karamousadakis, Mubashara Akhtar, Nitisha Jain, Omar Benjelloun, Pierre Marcenac, Rajat Shinde, Steffen Vogler, Sujata Goswami, Tim Santos, Yuhan Rao","submitted_at":"2024-06-04T16:40:14Z","abstract_excerpt":"Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croissant-RAI, a machine-readable metadata format designed to enhance the discoverability, interoperability, and trustworthiness of AI datasets. Croissant-RAI extends the Croissant metadata format and builds upon existing responsible AI (RAI) documentation frameworks, offering a standardized set of attributes and practices to facilitate community-wide ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16883","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/2407.16883/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":"2407.16883","created_at":"2026-07-05T08:47:58.053884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16883v1","created_at":"2026-07-05T08:47:58.053884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16883","created_at":"2026-07-05T08:47:58.053884+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONZAVRSJFFNJ","created_at":"2026-07-05T08:47:58.053884+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONZAVRSJFFNJDXDO","created_at":"2026-07-05T08:47:58.053884+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONZAVRSJ","created_at":"2026-07-05T08:47:58.053884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21831","citing_title":"RAIDS: Rethinking Data Systems as Responsible Intelligent Infrastructure","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB","json":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB.json","graph_json":"https://pith.science/api/pith-number/ONZAVRSJFFNJDXDOB5XGK4GURB/graph.json","events_json":"https://pith.science/api/pith-number/ONZAVRSJFFNJDXDOB5XGK4GURB/events.json","paper":"https://pith.science/paper/ONZAVRSJ"},"agent_actions":{"view_html":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB","download_json":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB.json","view_paper":"https://pith.science/paper/ONZAVRSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16883&json=true","fetch_graph":"https://pith.science/api/pith-number/ONZAVRSJFFNJDXDOB5XGK4GURB/graph.json","fetch_events":"https://pith.science/api/pith-number/ONZAVRSJFFNJDXDOB5XGK4GURB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB/action/storage_attestation","attest_author":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB/action/author_attestation","sign_citation":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB/action/citation_signature","submit_replication":"https://pith.science/pith/ONZAVRSJFFNJDXDOB5XGK4GURB/action/replication_record"}},"created_at":"2026-07-05T08:47:58.053884+00:00","updated_at":"2026-07-05T08:47:58.053884+00:00"}