{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NQ2SYCIZSXSHAJUM3IG74F3VT5","short_pith_number":"pith:NQ2SYCIZ","schema_version":"1.0","canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","source":{"kind":"arxiv","id":"2406.16349","version":1},"attestation_state":"computed","paper":{"title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilias Fountalis, Jin Tian, Nikolaos Vasiloglou, Yaojie Hu","submitted_at":"2024-06-24T06:44:14Z","abstract_excerpt":"Tabular data is ubiquitous in real-world applications and abundant on the web, yet its annotation has traditionally required human labor, posing a significant scalability bottleneck for tabular machine learning. Our methodology can successfully annotate a large amount of tabular data and can be flexibly steered to generate various types of annotations based on specific research objectives, as we demonstrate with SQL annotation and input-target column annotation as examples. As a result, we release AnnotatedTables, a collection of 32,119 databases with LLM-generated annotations. The dataset inc"},"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":"2406.16349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"2c922961c959351b927a9ca54fbb7951c32f20c1c9b0642f8b8bc5ef33025cd5","abstract_canon_sha256":"21a1fadee44a0f29edfc9f57e690d633664fcc43b797bc7260d9103b526134b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:57.125034Z","signature_b64":"pWnE+YoeaHUayZRCalxPsJ0xR2NMOsTw23rcxEa6mSk9OxLysjemB03YzE8JwxU1XGza6kdrWUu2rdoEsVuxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","last_reissued_at":"2026-07-05T08:35:57.124548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:57.124548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilias Fountalis, Jin Tian, Nikolaos Vasiloglou, Yaojie Hu","submitted_at":"2024-06-24T06:44:14Z","abstract_excerpt":"Tabular data is ubiquitous in real-world applications and abundant on the web, yet its annotation has traditionally required human labor, posing a significant scalability bottleneck for tabular machine learning. Our methodology can successfully annotate a large amount of tabular data and can be flexibly steered to generate various types of annotations based on specific research objectives, as we demonstrate with SQL annotation and input-target column annotation as examples. As a result, we release AnnotatedTables, a collection of 32,119 databases with LLM-generated annotations. The dataset inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16349","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/2406.16349/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":"2406.16349","created_at":"2026-07-05T08:35:57.124610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16349v1","created_at":"2026-07-05T08:35:57.124610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16349","created_at":"2026-07-05T08:35:57.124610+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQ2SYCIZSXSH","created_at":"2026-07-05T08:35:57.124610+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQ2SYCIZSXSHAJUM","created_at":"2026-07-05T08:35:57.124610+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQ2SYCIZ","created_at":"2026-07-05T08:35:57.124610+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/NQ2SYCIZSXSHAJUM3IG74F3VT5","json":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5.json","graph_json":"https://pith.science/api/pith-number/NQ2SYCIZSXSHAJUM3IG74F3VT5/graph.json","events_json":"https://pith.science/api/pith-number/NQ2SYCIZSXSHAJUM3IG74F3VT5/events.json","paper":"https://pith.science/paper/NQ2SYCIZ"},"agent_actions":{"view_html":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5","download_json":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5.json","view_paper":"https://pith.science/paper/NQ2SYCIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16349&json=true","fetch_graph":"https://pith.science/api/pith-number/NQ2SYCIZSXSHAJUM3IG74F3VT5/graph.json","fetch_events":"https://pith.science/api/pith-number/NQ2SYCIZSXSHAJUM3IG74F3VT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/action/storage_attestation","attest_author":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/action/author_attestation","sign_citation":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/action/citation_signature","submit_replication":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/action/replication_record"}},"created_at":"2026-07-05T08:35:57.124610+00:00","updated_at":"2026-07-05T08:35:57.124610+00:00"}