{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IACSBKZ64MEWIVPUSGJJWOHTQK","short_pith_number":"pith:IACSBKZ6","schema_version":"1.0","canonical_sha256":"400520ab3ee3096455f491929b38f38287620f41ccc282e8f9ea2f7f48324c57","source":{"kind":"arxiv","id":"2406.17673","version":1},"attestation_state":"computed","paper":{"title":"LaTable: Towards Large Tabular Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Jonathan Crabb\\'e, Mihaela van der Schaar, Rob Davis","submitted_at":"2024-06-25T16:03:50Z","abstract_excerpt":"Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of different tabular datasets, tabular metadata (e.g. dataset description and feature headers), and tables lacking prior knowledge (e.g. feature order). In this work we propose LaTable: a novel tabular diffusion model that addresses these challenges and can be trained across different datasets. Through extensive experiments we find that LaTable outperforms "},"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":"2406.17673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T16:03:50Z","cross_cats_sorted":[],"title_canon_sha256":"29964df2728610428dea83bdbdd7036e171729458b85c062d74478d0f7a74d5e","abstract_canon_sha256":"36df414103e64bb03c865b47bd5b93920597195470c9d65b1aa3e7cbb9857ce3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:38.512698Z","signature_b64":"OUV7SCbVZDaf4O4CbWOkiraptPhCNXOwLd+FFYIMYtOAegNCIaHUYe1XC3IO0aT28AFnB4GKHB1SG2K+pcjOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"400520ab3ee3096455f491929b38f38287620f41ccc282e8f9ea2f7f48324c57","last_reissued_at":"2026-07-05T08:36:38.512151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:38.512151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaTable: Towards Large Tabular Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Jonathan Crabb\\'e, Mihaela van der Schaar, Rob Davis","submitted_at":"2024-06-25T16:03:50Z","abstract_excerpt":"Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of different tabular datasets, tabular metadata (e.g. dataset description and feature headers), and tables lacking prior knowledge (e.g. feature order). In this work we propose LaTable: a novel tabular diffusion model that addresses these challenges and can be trained across different datasets. Through extensive experiments we find that LaTable outperforms "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17673","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/2406.17673/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":"2406.17673","created_at":"2026-07-05T08:36:38.512210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17673v1","created_at":"2026-07-05T08:36:38.512210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17673","created_at":"2026-07-05T08:36:38.512210+00:00"},{"alias_kind":"pith_short_12","alias_value":"IACSBKZ64MEW","created_at":"2026-07-05T08:36:38.512210+00:00"},{"alias_kind":"pith_short_16","alias_value":"IACSBKZ64MEWIVPU","created_at":"2026-07-05T08:36:38.512210+00:00"},{"alias_kind":"pith_short_8","alias_value":"IACSBKZ6","created_at":"2026-07-05T08:36:38.512210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.02161","citing_title":"LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK","json":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK.json","graph_json":"https://pith.science/api/pith-number/IACSBKZ64MEWIVPUSGJJWOHTQK/graph.json","events_json":"https://pith.science/api/pith-number/IACSBKZ64MEWIVPUSGJJWOHTQK/events.json","paper":"https://pith.science/paper/IACSBKZ6"},"agent_actions":{"view_html":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK","download_json":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK.json","view_paper":"https://pith.science/paper/IACSBKZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17673&json=true","fetch_graph":"https://pith.science/api/pith-number/IACSBKZ64MEWIVPUSGJJWOHTQK/graph.json","fetch_events":"https://pith.science/api/pith-number/IACSBKZ64MEWIVPUSGJJWOHTQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK/action/storage_attestation","attest_author":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK/action/author_attestation","sign_citation":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK/action/citation_signature","submit_replication":"https://pith.science/pith/IACSBKZ64MEWIVPUSGJJWOHTQK/action/replication_record"}},"created_at":"2026-07-05T08:36:38.512210+00:00","updated_at":"2026-07-05T08:36:38.512210+00:00"}