{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HRYFARTCHAJINCEUMTE44AF3LR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a271aada0ad58ab48735863c593d8d6cf96cd5cee0d42bdf76d6410b2b9692f0","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T17:44:56Z","title_canon_sha256":"4ee02bce81b0df439ff132df3552673b1ec2a80a97082ad445a26c195f22748e"},"schema_version":"1.0","source":{"id":"2303.10158","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.10158","created_at":"2026-07-05T06:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2303.10158v3","created_at":"2026-07-05T06:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10158","created_at":"2026-07-05T06:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"HRYFARTCHAJI","created_at":"2026-07-05T06:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"HRYFARTCHAJINCEU","created_at":"2026-07-05T06:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"HRYFARTC","created_at":"2026-07-05T06:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:d7f947ba7ed8fc5a641d15e7d67ae2ef1c667cf6ac661cc1f88bf21ad94c20a9","target":"graph","created_at":"2026-07-05T06:19:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.10158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler of its great success is the availability of abundant and high-quality data for building machine learning models. Recently, the role of data in AI has been significantly magnified, giving rise to the emerging concept of data-centric AI. The attention of researchers and practitioners has gradually shifted from advancing model design to enhancing the quality and quantity of the data. In this survey, we discuss the necessity of data-centric AI, followed by a holistic view of three general data-centric ","authors_text":"Daochen Zha, Fan Yang, Kwei-Herng Lai, Shaochen Zhong, Xia Hu, Zaid Pervaiz Bhat, Zhimeng Jiang","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T17:44:56Z","title":"Data-centric Artificial Intelligence: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10158","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74ed0024d1c5e68624f3eb174dc6b13963403b2f30a7ad78e6094622efa8debe","target":"record","created_at":"2026-07-05T06:19:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a271aada0ad58ab48735863c593d8d6cf96cd5cee0d42bdf76d6410b2b9692f0","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T17:44:56Z","title_canon_sha256":"4ee02bce81b0df439ff132df3552673b1ec2a80a97082ad445a26c195f22748e"},"schema_version":"1.0","source":{"id":"2303.10158","kind":"arxiv","version":3}},"canonical_sha256":"3c70504662381286889464c9ce00bb5c63ea6b2b34aade1a46bbfa1a5cd9b4ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c70504662381286889464c9ce00bb5c63ea6b2b34aade1a46bbfa1a5cd9b4ea","first_computed_at":"2026-07-05T06:19:19.130574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:19.130574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sh80fNUUljirMhpYJigpXMappmRVE7abTMpY/x+NCvV7zHt8llw6WPgMMeBN45GE1Q+wHBpV1ak3vOVcgnyhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:19.131118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.10158","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74ed0024d1c5e68624f3eb174dc6b13963403b2f30a7ad78e6094622efa8debe","sha256:d7f947ba7ed8fc5a641d15e7d67ae2ef1c667cf6ac661cc1f88bf21ad94c20a9"],"state_sha256":"dcda61ec89c78c08dfc48d332965ad6862f65a155d980f01b0488e7688e0d787"}