{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3DFQNTUMIHYBJWPEZLTMLUVP6J","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":"5ad322f0f394f002aa622cbfa196d0e822b777064816a25d6ede5648a393b065","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-01T17:59:20Z","title_canon_sha256":"ff9dbbaadaee6c21962e474951a987aef6855a2755c3d84067cd43886cf00168"},"schema_version":"1.0","source":{"id":"2310.00749","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00749","created_at":"2026-07-05T08:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00749v3","created_at":"2026-07-05T08:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00749","created_at":"2026-07-05T08:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"3DFQNTUMIHYB","created_at":"2026-07-05T08:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"3DFQNTUMIHYBJWPE","created_at":"2026-07-05T08:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"3DFQNTUM","created_at":"2026-07-05T08:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:db54aad28f51f2316aebbf63e0398d82f7de6d26f9ff16b44bcf1d665f5806af","target":"graph","created_at":"2026-07-05T08:11:39Z","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/2310.00749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunwei Liu, Ju Fan, Lei Cao, Michael Cafarella, Nan Tang, Sam Madden, Tim Kraska, Zeyuan Shang, Zihui Gu, Zui Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-01T17:59:20Z","title":"SEED: Domain-Specific Data Curation With Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00749","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":"sha256:21c33ce598a9dd88fdd0c10a7c2fd4756c1637f363214a9a676d58a29ad415d2","target":"record","created_at":"2026-07-05T08:11:39Z","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":"5ad322f0f394f002aa622cbfa196d0e822b777064816a25d6ede5648a393b065","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-10-01T17:59:20Z","title_canon_sha256":"ff9dbbaadaee6c21962e474951a987aef6855a2755c3d84067cd43886cf00168"},"schema_version":"1.0","source":{"id":"2310.00749","kind":"arxiv","version":3}},"canonical_sha256":"d8cb06ce8c41f014d9e4cae6c5d2aff24ae4737b5b7b5c931d24100666fa5f65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8cb06ce8c41f014d9e4cae6c5d2aff24ae4737b5b7b5c931d24100666fa5f65","first_computed_at":"2026-07-05T08:11:39.792340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:39.792340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jmLmF3nMTw2XotZVBFum1DF2UrDlPqpiX8SKetmIdMuGZ9pvB25/4oOi6KTHzWElk6RBS8Rb8M8vmM31BdUQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:39.792827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00749","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21c33ce598a9dd88fdd0c10a7c2fd4756c1637f363214a9a676d58a29ad415d2","sha256:db54aad28f51f2316aebbf63e0398d82f7de6d26f9ff16b44bcf1d665f5806af"],"state_sha256":"2702dc4da6c68f0f5d8aa649c6a26a60323dd724b69eb0d9c8dd083b0fd008f3"}