{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DBEICEM2UFKLFCGW2K5EZ6OC3T","short_pith_number":"pith:DBEICEM2","schema_version":"1.0","canonical_sha256":"184881119aa154b288d6d2ba4cf9c2dce2941bb9b71fbd34c8f5bc04b7fdfdc6","source":{"kind":"arxiv","id":"2506.02071","version":1},"attestation_state":"computed","paper":{"title":"AI Data Development: A Scorecard for the System Card Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Haileleol Tibebu, Ioannis A. Kakadiaris, Tadesse K. Bahiru","submitted_at":"2025-06-02T06:35:45Z","abstract_excerpt":"Artificial intelligence has transformed numerous industries, from healthcare to finance, enhancing decision-making through automated systems. However, the reliability of these systems is mainly dependent on the quality of the underlying datasets, raising ongoing concerns about transparency, accountability, and potential biases. This paper introduces a scorecard designed to evaluate the development of AI datasets, focusing on five key areas from the system card framework data development life cycle: data dictionary, collection process, composition, motivation, and pre-processing. The method fol"},"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":"2506.02071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-06-02T06:35:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5d893f6feacafbb77e1e1021486bf360426b36a19732fc82ecc17dbfa5df34ef","abstract_canon_sha256":"15a3fdfa1c320f8c897e6d08866c191685059712d5b934ec9068517191df2669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:31.849220Z","signature_b64":"KdRF3Z9HCEDu0TjglBctKaAeFchbQV6zjIPE2FDBl4A5rbtMrB1fxWa0wC16LQMaPMr3ej0bbmiGlgOJS1OzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184881119aa154b288d6d2ba4cf9c2dce2941bb9b71fbd34c8f5bc04b7fdfdc6","last_reissued_at":"2026-07-05T11:14:31.848834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:31.848834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Data Development: A Scorecard for the System Card Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Haileleol Tibebu, Ioannis A. Kakadiaris, Tadesse K. Bahiru","submitted_at":"2025-06-02T06:35:45Z","abstract_excerpt":"Artificial intelligence has transformed numerous industries, from healthcare to finance, enhancing decision-making through automated systems. However, the reliability of these systems is mainly dependent on the quality of the underlying datasets, raising ongoing concerns about transparency, accountability, and potential biases. This paper introduces a scorecard designed to evaluate the development of AI datasets, focusing on five key areas from the system card framework data development life cycle: data dictionary, collection process, composition, motivation, and pre-processing. The method fol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02071","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/2506.02071/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":"2506.02071","created_at":"2026-07-05T11:14:31.848889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02071v1","created_at":"2026-07-05T11:14:31.848889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02071","created_at":"2026-07-05T11:14:31.848889+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBEICEM2UFKL","created_at":"2026-07-05T11:14:31.848889+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBEICEM2UFKLFCGW","created_at":"2026-07-05T11:14:31.848889+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBEICEM2","created_at":"2026-07-05T11:14:31.848889+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/DBEICEM2UFKLFCGW2K5EZ6OC3T","json":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T.json","graph_json":"https://pith.science/api/pith-number/DBEICEM2UFKLFCGW2K5EZ6OC3T/graph.json","events_json":"https://pith.science/api/pith-number/DBEICEM2UFKLFCGW2K5EZ6OC3T/events.json","paper":"https://pith.science/paper/DBEICEM2"},"agent_actions":{"view_html":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T","download_json":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T.json","view_paper":"https://pith.science/paper/DBEICEM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02071&json=true","fetch_graph":"https://pith.science/api/pith-number/DBEICEM2UFKLFCGW2K5EZ6OC3T/graph.json","fetch_events":"https://pith.science/api/pith-number/DBEICEM2UFKLFCGW2K5EZ6OC3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T/action/storage_attestation","attest_author":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T/action/author_attestation","sign_citation":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T/action/citation_signature","submit_replication":"https://pith.science/pith/DBEICEM2UFKLFCGW2K5EZ6OC3T/action/replication_record"}},"created_at":"2026-07-05T11:14:31.848889+00:00","updated_at":"2026-07-05T11:14:31.848889+00:00"}