{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:POZY6KWQCXXLAPMRISICWQRPMC","short_pith_number":"pith:POZY6KWQ","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"},"canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","source":{"kind":"arxiv","id":"2310.07875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07875","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07875v1","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07875","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"POZY6KWQCXXL","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"POZY6KWQCXXLAPMR","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"POZY6KWQ","created_at":"2026-07-05T06:59:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:POZY6KWQCXXLAPMRISICWQRPMC","target":"record","payload":{"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"},"canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","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"},"source_kind":"arxiv","source_id":"2310.07875","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o703ULeZJkE0uzMOyWrDZoOHmoEZhp4cbFLKtthScEEdwn5uCn9g21l5rAbzR98Je6N2ldgOkoUSlOfFSFM2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:28.043222Z"},"content_sha256":"76216ea1b8ba629e28d3a7fa934589df1636c7a3969f79646d8362c7ebacd1f6","schema_version":"1.0","event_id":"sha256:76216ea1b8ba629e28d3a7fa934589df1636c7a3969f79646d8362c7ebacd1f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:POZY6KWQCXXLAPMRISICWQRPMC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wl5sJF5QWU3cpleNSTlFlex3hOXi3+SvhrkU8s8kFsyxotjmXVBs8rzeDISwJglERCXtt3+xPM4od2Ul9mosBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:28.044215Z"},"content_sha256":"accec649cc47de795c8a3e891d8e50258041af528dc5c658d03a4d8b4cf64653","schema_version":"1.0","event_id":"sha256:accec649cc47de795c8a3e891d8e50258041af528dc5c658d03a4d8b4cf64653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/bundle.json","state_url":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POZY6KWQCXXLAPMRISICWQRPMC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T12:18:28Z","links":{"resolver":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC","bundle":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/bundle.json","state":"https://pith.science/pith/POZY6KWQCXXLAPMRISICWQRPMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POZY6KWQCXXLAPMRISICWQRPMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:POZY6KWQCXXLAPMRISICWQRPMC","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":"b4fffd127a29ccad47072ba629722a083ebd6a89ea69d6098b1a44577e791043","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T20:34:42Z","title_canon_sha256":"3d241c4baa3f8338d0d1cac3fda3a03d0305047c774c0c84a7756e9e451a260c"},"schema_version":"1.0","source":{"id":"2310.07875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07875","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07875v1","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07875","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"POZY6KWQCXXL","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"POZY6KWQCXXLAPMR","created_at":"2026-07-05T06:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"POZY6KWQ","created_at":"2026-07-05T06:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:accec649cc47de795c8a3e891d8e50258041af528dc5c658d03a4d8b4cf64653","target":"graph","created_at":"2026-07-05T06:59:57Z","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/2310.07875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gus Eggert, Justin Waugh, Kevin Huo, Mike Biven","cross_cats":["cs.AI","cs.DB","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T20:34:42Z","title":"TabLib: A Dataset of 627M Tables with Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07875","kind":"arxiv","version":1},"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":"sha256:76216ea1b8ba629e28d3a7fa934589df1636c7a3969f79646d8362c7ebacd1f6","target":"record","created_at":"2026-07-05T06:59:57Z","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":"b4fffd127a29ccad47072ba629722a083ebd6a89ea69d6098b1a44577e791043","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T20:34:42Z","title_canon_sha256":"3d241c4baa3f8338d0d1cac3fda3a03d0305047c774c0c84a7756e9e451a260c"},"schema_version":"1.0","source":{"id":"2310.07875","kind":"arxiv","version":1}},"canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bb38f2ad015eeb03d9144902b422f60b2d0213f9cebba401b8a9f12476b1f54","first_computed_at":"2026-07-05T06:59:57.760490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:57.760490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Tw68Va08qdTDOX+r7umcQLLq9DigpcwIVxf0RRN60BAj3ThzTSOmoiJo+oi8s1BG5dk/4jgLJ7TOlpwYv0uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:57.760988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76216ea1b8ba629e28d3a7fa934589df1636c7a3969f79646d8362c7ebacd1f6","sha256:accec649cc47de795c8a3e891d8e50258041af528dc5c658d03a4d8b4cf64653"],"state_sha256":"6ba949128a04903faebce58c6edef1ace15b526625d4c7ca1aea6b9566b45c63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PkL3tts7xPs6nSHtnxZTRXr18BBPzChJkRXrvMs/zPkWKkVn4rc2m7a+VWJrgZ6ZiXupS6PqzJ+JUl+zxf5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:18:28.049545Z","bundle_sha256":"c59838d35d85d2d6e100e6d2d7635aceb6f8f9556ea83c50cbc223a471db81eb"}}