{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JK6GD2DZKARFACAB5UW7NVFDFF","short_pith_number":"pith:JK6GD2DZ","schema_version":"1.0","canonical_sha256":"4abc61e8795022500801ed2df6d4a329581c9691f71aaf2b6ed019fee9d009ab","source":{"kind":"arxiv","id":"2406.09837","version":2},"attestation_state":"computed","paper":{"title":"TabularFM: An Open Framework For Tabular Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dzung Phan, Hoang Thanh Lam, Lam M. Nguyen, Quan M. Tran, Suong N. Hoang","submitted_at":"2024-06-14T08:46:33Z","abstract_excerpt":"Foundational models (FMs), pretrained on extensive datasets using self-supervised techniques, are capable of learning generalized patterns from large amounts of data. This reduces the need for extensive labeled datasets for each new task, saving both time and resources by leveraging the broad knowledge base established during pretraining. Most research on FMs has primarily focused on unstructured data, such as text and images, or semi-structured data, like time-series. However, there has been limited attention to structured data, such as tabular data, which, despite its prevalence, remains und"},"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":"2406.09837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T08:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"6e633b299a6367355775101f35faf164e7c74280b81ec09bfb1f527dd807dd6d","abstract_canon_sha256":"7c8eb6db812bd1afb0372f80ab6dc3c7c7637e445d840f02352f990bdd1d591c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:41.074796Z","signature_b64":"2g+48WAJT4Lg+VkXB/UR0PrFH0/Aa4GPT8FCucRxwvPX9Uhw5l0Nf+uTjCiN3oHiOHLqSiY6hDVJ+V1tng0OAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4abc61e8795022500801ed2df6d4a329581c9691f71aaf2b6ed019fee9d009ab","last_reissued_at":"2026-07-05T08:33:41.074345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:41.074345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabularFM: An Open Framework For Tabular Foundational Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dzung Phan, Hoang Thanh Lam, Lam M. Nguyen, Quan M. Tran, Suong N. Hoang","submitted_at":"2024-06-14T08:46:33Z","abstract_excerpt":"Foundational models (FMs), pretrained on extensive datasets using self-supervised techniques, are capable of learning generalized patterns from large amounts of data. This reduces the need for extensive labeled datasets for each new task, saving both time and resources by leveraging the broad knowledge base established during pretraining. Most research on FMs has primarily focused on unstructured data, such as text and images, or semi-structured data, like time-series. However, there has been limited attention to structured data, such as tabular data, which, despite its prevalence, remains und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09837","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/2406.09837/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":"2406.09837","created_at":"2026-07-05T08:33:41.074402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09837v2","created_at":"2026-07-05T08:33:41.074402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09837","created_at":"2026-07-05T08:33:41.074402+00:00"},{"alias_kind":"pith_short_12","alias_value":"JK6GD2DZKARF","created_at":"2026-07-05T08:33:41.074402+00:00"},{"alias_kind":"pith_short_16","alias_value":"JK6GD2DZKARFACAB","created_at":"2026-07-05T08:33:41.074402+00:00"},{"alias_kind":"pith_short_8","alias_value":"JK6GD2DZ","created_at":"2026-07-05T08:33:41.074402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03971","citing_title":"Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF","json":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF.json","graph_json":"https://pith.science/api/pith-number/JK6GD2DZKARFACAB5UW7NVFDFF/graph.json","events_json":"https://pith.science/api/pith-number/JK6GD2DZKARFACAB5UW7NVFDFF/events.json","paper":"https://pith.science/paper/JK6GD2DZ"},"agent_actions":{"view_html":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF","download_json":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF.json","view_paper":"https://pith.science/paper/JK6GD2DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09837&json=true","fetch_graph":"https://pith.science/api/pith-number/JK6GD2DZKARFACAB5UW7NVFDFF/graph.json","fetch_events":"https://pith.science/api/pith-number/JK6GD2DZKARFACAB5UW7NVFDFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF/action/storage_attestation","attest_author":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF/action/author_attestation","sign_citation":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF/action/citation_signature","submit_replication":"https://pith.science/pith/JK6GD2DZKARFACAB5UW7NVFDFF/action/replication_record"}},"created_at":"2026-07-05T08:33:41.074402+00:00","updated_at":"2026-07-05T08:33:41.074402+00:00"}