{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HRYFARTCHAJINCEUMTE44AF3LR","short_pith_number":"pith:HRYFARTC","schema_version":"1.0","canonical_sha256":"3c70504662381286889464c9ce00bb5c63ea6b2b34aade1a46bbfa1a5cd9b4ea","source":{"kind":"arxiv","id":"2303.10158","version":3},"attestation_state":"computed","paper":{"title":"Data-centric Artificial Intelligence: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Daochen Zha, Fan Yang, Kwei-Herng Lai, Shaochen Zhong, Xia Hu, Zaid Pervaiz Bhat, Zhimeng Jiang","submitted_at":"2023-03-17T17:44:56Z","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 "},"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":"2303.10158","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T17:44:56Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"4ee02bce81b0df439ff132df3552673b1ec2a80a97082ad445a26c195f22748e","abstract_canon_sha256":"a271aada0ad58ab48735863c593d8d6cf96cd5cee0d42bdf76d6410b2b9692f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:19.131118Z","signature_b64":"Sh80fNUUljirMhpYJigpXMappmRVE7abTMpY/x+NCvV7zHt8llw6WPgMMeBN45GE1Q+wHBpV1ak3vOVcgnyhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c70504662381286889464c9ce00bb5c63ea6b2b34aade1a46bbfa1a5cd9b4ea","last_reissued_at":"2026-07-05T06:19:19.130574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:19.130574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-centric Artificial Intelligence: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Daochen Zha, Fan Yang, Kwei-Herng Lai, Shaochen Zhong, Xia Hu, Zaid Pervaiz Bhat, Zhimeng Jiang","submitted_at":"2023-03-17T17:44:56Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10158","kind":"arxiv","version":3},"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/2303.10158/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":"2303.10158","created_at":"2026-07-05T06:19:19.130633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10158v3","created_at":"2026-07-05T06:19:19.130633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10158","created_at":"2026-07-05T06:19:19.130633+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRYFARTCHAJI","created_at":"2026-07-05T06:19:19.130633+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRYFARTCHAJINCEU","created_at":"2026-07-05T06:19:19.130633+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRYFARTC","created_at":"2026-07-05T06:19:19.130633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21337","citing_title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17915","citing_title":"Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10136","citing_title":"iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01185","citing_title":"\"Skill Issues'': Data-Centric Optimization of Lakehouse Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2405.01557","citing_title":"An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06621","citing_title":"Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05930","citing_title":"Can We Predict Before Executing Machine Learning Agents?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16364","citing_title":"Clinical Note Bloat Reduction for Efficient LLM Use","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25154","citing_title":"Prior-Aligned Data Cleaning for Tabular Foundation Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09791","citing_title":"Pioneer Agent: Continual Improvement of Small Language Models in Production","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR","json":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR.json","graph_json":"https://pith.science/api/pith-number/HRYFARTCHAJINCEUMTE44AF3LR/graph.json","events_json":"https://pith.science/api/pith-number/HRYFARTCHAJINCEUMTE44AF3LR/events.json","paper":"https://pith.science/paper/HRYFARTC"},"agent_actions":{"view_html":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR","download_json":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR.json","view_paper":"https://pith.science/paper/HRYFARTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10158&json=true","fetch_graph":"https://pith.science/api/pith-number/HRYFARTCHAJINCEUMTE44AF3LR/graph.json","fetch_events":"https://pith.science/api/pith-number/HRYFARTCHAJINCEUMTE44AF3LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR/action/storage_attestation","attest_author":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR/action/author_attestation","sign_citation":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR/action/citation_signature","submit_replication":"https://pith.science/pith/HRYFARTCHAJINCEUMTE44AF3LR/action/replication_record"}},"created_at":"2026-07-05T06:19:19.130633+00:00","updated_at":"2026-07-05T06:19:19.130633+00:00"}