{"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"}