{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EQ2FYVSKUPINUCBVAES3MF42BX","short_pith_number":"pith:EQ2FYVSK","schema_version":"1.0","canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","source":{"kind":"arxiv","id":"2410.20626","version":3},"attestation_state":"computed","paper":{"title":"TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harper Hua, Hengrui Zhang, Juntong Shi, Jure Leskovec, Minkai Xu, Stefano Ermon","submitted_at":"2024-10-27T22:58:47Z","abstract_excerpt":"Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its inherent heterogeneous data types, complex inter-correlations, and intricate column-wise distributions. In this paper, we introduce TabDiff, a joint diffusion framework that models all mixed-type distributions of tabular data in one model. Our key innovation is the development of a joint continuous-time diffusion process for numerical and categorical data, whe"},"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":"2410.20626","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-27T22:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"de2d7a1a8add1fd4082a12f7b0a9d1bafee877e3c17d2b5d39b10a29f6706e7f","abstract_canon_sha256":"fa3c4f79cf313c181fe9d3c29d237b62cdf5f07bad10aaa7ceeec8de441d8291"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:47.262067Z","signature_b64":"yd8AJ4QmtgOMyKBaNwQLW8DwBnpgfHkjjqjZbrxhx8EMH2tbNrVLzp4fPldMiOQcaaDzq7u7G1btweHHsxMFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","last_reissued_at":"2026-07-05T10:14:47.261572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:47.261572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harper Hua, Hengrui Zhang, Juntong Shi, Jure Leskovec, Minkai Xu, Stefano Ermon","submitted_at":"2024-10-27T22:58:47Z","abstract_excerpt":"Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its inherent heterogeneous data types, complex inter-correlations, and intricate column-wise distributions. In this paper, we introduce TabDiff, a joint diffusion framework that models all mixed-type distributions of tabular data in one model. Our key innovation is the development of a joint continuous-time diffusion process for numerical and categorical data, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20626","kind":"arxiv","version":3},"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/2410.20626/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":"2410.20626","created_at":"2026-07-05T10:14:47.261631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20626v3","created_at":"2026-07-05T10:14:47.261631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20626","created_at":"2026-07-05T10:14:47.261631+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQ2FYVSKUPIN","created_at":"2026-07-05T10:14:47.261631+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQ2FYVSKUPINUCBV","created_at":"2026-07-05T10:14:47.261631+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQ2FYVSK","created_at":"2026-07-05T10:14:47.261631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06990","citing_title":"Accelerating Reproducible Research in Synthetic EHR Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02607","citing_title":"Geometry-Aware Tabular Diffusion","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16527","citing_title":"Joint Relational Database Generation via Graph-Conditional Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01666","citing_title":"Synthesis of discrete-continuous quantum circuits with multimodal diffusion models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11527","citing_title":"FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06261","citing_title":"Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04911","citing_title":"Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX","json":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX.json","graph_json":"https://pith.science/api/pith-number/EQ2FYVSKUPINUCBVAES3MF42BX/graph.json","events_json":"https://pith.science/api/pith-number/EQ2FYVSKUPINUCBVAES3MF42BX/events.json","paper":"https://pith.science/paper/EQ2FYVSK"},"agent_actions":{"view_html":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX","download_json":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX.json","view_paper":"https://pith.science/paper/EQ2FYVSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20626&json=true","fetch_graph":"https://pith.science/api/pith-number/EQ2FYVSKUPINUCBVAES3MF42BX/graph.json","fetch_events":"https://pith.science/api/pith-number/EQ2FYVSKUPINUCBVAES3MF42BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/action/storage_attestation","attest_author":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/action/author_attestation","sign_citation":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/action/citation_signature","submit_replication":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/action/replication_record"}},"created_at":"2026-07-05T10:14:47.261631+00:00","updated_at":"2026-07-05T10:14:47.261631+00:00"}