{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3DFQNTUMIHYBJWPEZLTMLUVP6J","short_pith_number":"pith:3DFQNTUM","schema_version":"1.0","canonical_sha256":"d8cb06ce8c41f014d9e4cae6c5d2aff24ae4737b5b7b5c931d24100666fa5f65","source":{"kind":"arxiv","id":"2310.00749","version":3},"attestation_state":"computed","paper":{"title":"SEED: Domain-Specific Data Curation With Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Chunwei Liu, Ju Fan, Lei Cao, Michael Cafarella, Nan Tang, Sam Madden, Tim Kraska, Zeyuan Shang, Zihui Gu, Zui Chen","submitted_at":"2023-10-01T17:59:20Z","abstract_excerpt":"Data curation tasks that prepare data for analytics are critical for turning data into actionable insights. However, due to the diverse requirements of applications in different domains, generic off-the-shelf tools are typically insufficient. As a result, data scientists often have to develop domain-specific solutions tailored to both the dataset and the task, e.g. writing domain-specific code or training machine learning models on a sufficient number of annotated examples. This process is notoriously difficult and time-consuming. We present SEED, an LLM-as-compiler approach that automatically"},"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":"2310.00749","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-01T17:59:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff9dbbaadaee6c21962e474951a987aef6855a2755c3d84067cd43886cf00168","abstract_canon_sha256":"5ad322f0f394f002aa622cbfa196d0e822b777064816a25d6ede5648a393b065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:39.792827Z","signature_b64":"jmLmF3nMTw2XotZVBFum1DF2UrDlPqpiX8SKetmIdMuGZ9pvB25/4oOi6KTHzWElk6RBS8Rb8M8vmM31BdUQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8cb06ce8c41f014d9e4cae6c5d2aff24ae4737b5b7b5c931d24100666fa5f65","last_reissued_at":"2026-07-05T08:11:39.792340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:39.792340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEED: Domain-Specific Data Curation With Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Chunwei Liu, Ju Fan, Lei Cao, Michael Cafarella, Nan Tang, Sam Madden, Tim Kraska, Zeyuan Shang, Zihui Gu, Zui Chen","submitted_at":"2023-10-01T17:59:20Z","abstract_excerpt":"Data curation tasks that prepare data for analytics are critical for turning data into actionable insights. However, due to the diverse requirements of applications in different domains, generic off-the-shelf tools are typically insufficient. As a result, data scientists often have to develop domain-specific solutions tailored to both the dataset and the task, e.g. writing domain-specific code or training machine learning models on a sufficient number of annotated examples. This process is notoriously difficult and time-consuming. We present SEED, an LLM-as-compiler approach that automatically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00749","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/2310.00749/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":"2310.00749","created_at":"2026-07-05T08:11:39.792400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00749v3","created_at":"2026-07-05T08:11:39.792400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00749","created_at":"2026-07-05T08:11:39.792400+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DFQNTUMIHYB","created_at":"2026-07-05T08:11:39.792400+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DFQNTUMIHYBJWPE","created_at":"2026-07-05T08:11:39.792400+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DFQNTUM","created_at":"2026-07-05T08:11:39.792400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16616","citing_title":"LDI: Localized Data Imputation for Text-Rich Tables","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08687","citing_title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J","json":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J.json","graph_json":"https://pith.science/api/pith-number/3DFQNTUMIHYBJWPEZLTMLUVP6J/graph.json","events_json":"https://pith.science/api/pith-number/3DFQNTUMIHYBJWPEZLTMLUVP6J/events.json","paper":"https://pith.science/paper/3DFQNTUM"},"agent_actions":{"view_html":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J","download_json":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J.json","view_paper":"https://pith.science/paper/3DFQNTUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00749&json=true","fetch_graph":"https://pith.science/api/pith-number/3DFQNTUMIHYBJWPEZLTMLUVP6J/graph.json","fetch_events":"https://pith.science/api/pith-number/3DFQNTUMIHYBJWPEZLTMLUVP6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J/action/storage_attestation","attest_author":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J/action/author_attestation","sign_citation":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J/action/citation_signature","submit_replication":"https://pith.science/pith/3DFQNTUMIHYBJWPEZLTMLUVP6J/action/replication_record"}},"created_at":"2026-07-05T08:11:39.792400+00:00","updated_at":"2026-07-05T08:11:39.792400+00:00"}