{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7XSJ2CHZR7MOQVHQVBSWVZCMLD","short_pith_number":"pith:7XSJ2CHZ","canonical_record":{"source":{"id":"2406.12031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T18:58:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66f1467228386fb7eec4dd4f98aa466ba7f300f4f175bf2f74cea6b5560593fe","abstract_canon_sha256":"3234e066eced14e42b817f93b929c3d9c52270a5d5b222972a52b1737e489498"},"schema_version":"1.0"},"canonical_sha256":"fde49d08f98fd8e854f0a8656ae44c58fa3804713c8dde1c04d6d0ce55d6c173","source":{"kind":"arxiv","id":"2406.12031","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12031","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12031v2","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12031","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_12","alias_value":"7XSJ2CHZR7MO","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_16","alias_value":"7XSJ2CHZR7MOQVHQ","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_8","alias_value":"7XSJ2CHZ","created_at":"2026-07-05T09:38:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7XSJ2CHZR7MOQVHQVBSWVZCMLD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T18:58:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66f1467228386fb7eec4dd4f98aa466ba7f300f4f175bf2f74cea6b5560593fe","abstract_canon_sha256":"3234e066eced14e42b817f93b929c3d9c52270a5d5b222972a52b1737e489498"},"schema_version":"1.0"},"canonical_sha256":"fde49d08f98fd8e854f0a8656ae44c58fa3804713c8dde1c04d6d0ce55d6c173","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:27.356777Z","signature_b64":"GzS+nIpeUBVy0KNZ7V5kBJGpfL/wUn+USdNOuG4UsWn36OIxmPM/hzMoIO9B5c48upkc3uyplHMWz+AOsAyKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde49d08f98fd8e854f0a8656ae44c58fa3804713c8dde1c04d6d0ce55d6c173","last_reissued_at":"2026-07-05T09:38:27.356120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:27.356120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12031","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MkbhW4SMgzQEuXWq6Zze4SyI+SNTZoL76MJu5Rrz5OiqkkEAgzx9U6lFn4cwHC71udpCQsndTmN9rOTdKbibBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:17:52.187830Z"},"content_sha256":"507a077bd63f4bdf6d8d5fa89f31eeb54d6c46676af91cc2f6621dce6dc3def4","schema_version":"1.0","event_id":"sha256:507a077bd63f4bdf6d8d5fa89f31eeb54d6c46676af91cc2f6621dce6dc3def4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7XSJ2CHZR7MOQVHQVBSWVZCMLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Josh Gardner, Juan C. Perdomo, Ludwig Schmidt","submitted_at":"2024-06-17T18:58:20Z","abstract_excerpt":"Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TabuLa-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12031","kind":"arxiv","version":2},"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/2406.12031/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":"2026-07-05T09:38:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3vuDeAcrWNkOQ5lUc9s9/MpHcUWU/MfgmgaAp+0B3M6sLj2iGvUVLzWw6J3+qArZTBb8RKzz4CzdCcwao+f6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:17:52.188335Z"},"content_sha256":"5b00f0ff78b6c751d26331d639b44e51325bc8c60809820fbb783094988f9d6b","schema_version":"1.0","event_id":"sha256:5b00f0ff78b6c751d26331d639b44e51325bc8c60809820fbb783094988f9d6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/bundle.json","state_url":"https://pith.science/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/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":"2026-08-10T05:17:52Z","links":{"resolver":"https://pith.science/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD","bundle":"https://pith.science/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/bundle.json","state":"https://pith.science/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XSJ2CHZR7MOQVHQVBSWVZCMLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7XSJ2CHZR7MOQVHQVBSWVZCMLD","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":"3234e066eced14e42b817f93b929c3d9c52270a5d5b222972a52b1737e489498","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T18:58:20Z","title_canon_sha256":"66f1467228386fb7eec4dd4f98aa466ba7f300f4f175bf2f74cea6b5560593fe"},"schema_version":"1.0","source":{"id":"2406.12031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12031","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12031v2","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12031","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_12","alias_value":"7XSJ2CHZR7MO","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_16","alias_value":"7XSJ2CHZR7MOQVHQ","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_8","alias_value":"7XSJ2CHZ","created_at":"2026-07-05T09:38:27Z"}],"graph_snapshots":[{"event_id":"sha256:5b00f0ff78b6c751d26331d639b44e51325bc8c60809820fbb783094988f9d6b","target":"graph","created_at":"2026-07-05T09:38:27Z","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/2406.12031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TabuLa-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, pro","authors_text":"Josh Gardner, Juan C. Perdomo, Ludwig Schmidt","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T18:58:20Z","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12031","kind":"arxiv","version":2},"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":"sha256:507a077bd63f4bdf6d8d5fa89f31eeb54d6c46676af91cc2f6621dce6dc3def4","target":"record","created_at":"2026-07-05T09:38:27Z","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":"3234e066eced14e42b817f93b929c3d9c52270a5d5b222972a52b1737e489498","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T18:58:20Z","title_canon_sha256":"66f1467228386fb7eec4dd4f98aa466ba7f300f4f175bf2f74cea6b5560593fe"},"schema_version":"1.0","source":{"id":"2406.12031","kind":"arxiv","version":2}},"canonical_sha256":"fde49d08f98fd8e854f0a8656ae44c58fa3804713c8dde1c04d6d0ce55d6c173","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fde49d08f98fd8e854f0a8656ae44c58fa3804713c8dde1c04d6d0ce55d6c173","first_computed_at":"2026-07-05T09:38:27.356120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:27.356120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzS+nIpeUBVy0KNZ7V5kBJGpfL/wUn+USdNOuG4UsWn36OIxmPM/hzMoIO9B5c48upkc3uyplHMWz+AOsAyKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:27.356777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:507a077bd63f4bdf6d8d5fa89f31eeb54d6c46676af91cc2f6621dce6dc3def4","sha256:5b00f0ff78b6c751d26331d639b44e51325bc8c60809820fbb783094988f9d6b"],"state_sha256":"1861a84b6e066704753446ad60f885c725e0c4f96dfe18ae731eb66518873d13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgzCGoH3tdzxA9k8Eotef9RcTK6FZpbsG9UlM11BlYrwsblkagKwX65SAnaRQfOe8z+1nXgjs4apjSMEAA7FAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:17:52.192497Z","bundle_sha256":"91ab912be311f707a35ca573bb517cd4d8ee89f533085487eb35ce2af4abbc51"}}