{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POZY6KWQCXXLAPMRISICWQRPMC","short_pith_number":"pith:POZY6KWQ","schema_version":"1.0","canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","source":{"kind":"arxiv","id":"2310.07875","version":1},"attestation_state":"computed","paper":{"title":"TabLib: A Dataset of 627M Tables with Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gus Eggert, Justin Waugh, Kevin Huo, Mike Biven","submitted_at":"2023-10-11T20:34:42Z","abstract_excerpt":"It is well-established that large, diverse datasets play a pivotal role in the performance of modern AI systems for text and image modalities. However, there are no datasets for tabular data of comparable size and diversity to those available for text and images. Thus we present \"TabLib'', a compilation of 627 million tables totaling 69 TiB, along with 867B tokens of context. TabLib was extracted from numerous file formats, including CSV, HTML, SQLite, PDF, Excel, and others, sourced from GitHub and Common Crawl. The size and diversity of TabLib offer considerable promise in the table modality"},"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":"2310.07875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T20:34:42Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"3d241c4baa3f8338d0d1cac3fda3a03d0305047c774c0c84a7756e9e451a260c","abstract_canon_sha256":"b4fffd127a29ccad47072ba629722a083ebd6a89ea69d6098b1a44577e791043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:57.760988Z","signature_b64":"3Tw68Va08qdTDOX+r7umcQLLq9DigpcwIVxf0RRN60BAj3ThzTSOmoiJo+oi8s1BG5dk/4jgLJ7TOlpwYv0uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","last_reissued_at":"2026-07-05T06:59:57.760490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:57.760490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabLib: A Dataset of 627M Tables with Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gus Eggert, Justin Waugh, Kevin Huo, Mike Biven","submitted_at":"2023-10-11T20:34:42Z","abstract_excerpt":"It is well-established that large, diverse datasets play a pivotal role in the performance of modern AI systems for text and image modalities. However, there are no datasets for tabular data of comparable size and diversity to those available for text and images. Thus we present \"TabLib'', a compilation of 627 million tables totaling 69 TiB, along with 867B tokens of context. TabLib was extracted from numerous file formats, including CSV, HTML, SQLite, PDF, Excel, and others, sourced from GitHub and Common Crawl. The size and diversity of TabLib offer considerable promise in the table modality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07875","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/2310.07875/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":"2310.07875","created_at":"2026-07-05T06:59:57.760552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07875v1","created_at":"2026-07-05T06:59:57.760552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07875","created_at":"2026-07-05T06:59:57.760552+00:00"},{"alias_kind":"pith_short_12","alias_value":"POZY6KWQCXXL","created_at":"2026-07-05T06:59:57.760552+00:00"},{"alias_kind":"pith_short_16","alias_value":"POZY6KWQCXXLAPMR","created_at":"2026-07-05T06:59:57.760552+00:00"},{"alias_kind":"pith_short_8","alias_value":"POZY6KWQ","created_at":"2026-07-05T06:59:57.760552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23595","citing_title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23595","citing_title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09329","citing_title":"MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10616","citing_title":"MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06343","citing_title":"Mind the Gap? A Distributional Comparison of Real and Synthetic Priors for Tabular Foundation Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04962","citing_title":"TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC","json":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC.json","graph_json":"https://pith.science/api/pith-number/POZY6KWQCXXLAPMRISICWQRPMC/graph.json","events_json":"https://pith.science/api/pith-number/POZY6KWQCXXLAPMRISICWQRPMC/events.json","paper":"https://pith.science/paper/POZY6KWQ"},"agent_actions":{"view_html":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC","download_json":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC.json","view_paper":"https://pith.science/paper/POZY6KWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07875&json=true","fetch_graph":"https://pith.science/api/pith-number/POZY6KWQCXXLAPMRISICWQRPMC/graph.json","fetch_events":"https://pith.science/api/pith-number/POZY6KWQCXXLAPMRISICWQRPMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/action/storage_attestation","attest_author":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/action/author_attestation","sign_citation":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/action/citation_signature","submit_replication":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/action/replication_record"}},"created_at":"2026-07-05T06:59:57.760552+00:00","updated_at":"2026-07-05T06:59:57.760552+00:00"}