{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J5OGJAPX25W3RAHDVNXXCEDLQO","short_pith_number":"pith:J5OGJAPX","schema_version":"1.0","canonical_sha256":"4f5c6481f7d76db880e3ab6f71106b83967ca07115af30fbd0cf6fea11344331","source":{"kind":"arxiv","id":"2310.09656","version":3},"attestation_state":"computed","paper":{"title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Christos Faloutsos, George Karypis, Hengrui Zhang, Huzefa Rangwala, Jiani Zhang, Xiao Qin, Zhengyuan Shen","submitted_at":"2023-10-14T19:59:03Z","abstract_excerpt":"Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces Tabsyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capture i"},"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":"2310.09656","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-14T19:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"f5d8be205050a99ce25cd3668430aa9b7ae2c37ab3116a1f4533da2c4d9d00e3","abstract_canon_sha256":"e96451af2efada3968549a5ef9604c2b86ddd1730befd739806268d0bc4ce6a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:00.945475Z","signature_b64":"FXVDlF/B7yj39BO4B+veDsb1dYiDe6/hhUR98CuShVXrPOG7pPu7oPdWQQM3uAhFGYkJ1zorPz/qye5JK1+EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5c6481f7d76db880e3ab6f71106b83967ca07115af30fbd0cf6fea11344331","last_reissued_at":"2026-07-05T08:18:00.945011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:00.945011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balasubramaniam Srinivasan, Christos Faloutsos, George Karypis, Hengrui Zhang, Huzefa Rangwala, Jiani Zhang, Xiao Qin, Zhengyuan Shen","submitted_at":"2023-10-14T19:59:03Z","abstract_excerpt":"Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces Tabsyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capture i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09656","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/2310.09656/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":"2310.09656","created_at":"2026-07-05T08:18:00.945064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09656v3","created_at":"2026-07-05T08:18:00.945064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09656","created_at":"2026-07-05T08:18:00.945064+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5OGJAPX25W3","created_at":"2026-07-05T08:18:00.945064+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5OGJAPX25W3RAHD","created_at":"2026-07-05T08:18:00.945064+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5OGJAPX","created_at":"2026-07-05T08:18:00.945064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06990","citing_title":"Accelerating Reproducible Research in Synthetic EHR Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04055","citing_title":"Evaluating Inter-Column Logical Relationships in Synthetic Tabular Data Generation","ref_index":20,"is_internal_anchor":false},{"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16527","citing_title":"Joint Relational Database Generation via Graph-Conditional Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19185","citing_title":"MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11527","citing_title":"FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06261","citing_title":"Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05257","citing_title":"Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16817","citing_title":"Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration","ref_index":4,"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":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO","json":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO.json","graph_json":"https://pith.science/api/pith-number/J5OGJAPX25W3RAHDVNXXCEDLQO/graph.json","events_json":"https://pith.science/api/pith-number/J5OGJAPX25W3RAHDVNXXCEDLQO/events.json","paper":"https://pith.science/paper/J5OGJAPX"},"agent_actions":{"view_html":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO","download_json":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO.json","view_paper":"https://pith.science/paper/J5OGJAPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09656&json=true","fetch_graph":"https://pith.science/api/pith-number/J5OGJAPX25W3RAHDVNXXCEDLQO/graph.json","fetch_events":"https://pith.science/api/pith-number/J5OGJAPX25W3RAHDVNXXCEDLQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO/action/storage_attestation","attest_author":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO/action/author_attestation","sign_citation":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO/action/citation_signature","submit_replication":"https://pith.science/pith/J5OGJAPX25W3RAHDVNXXCEDLQO/action/replication_record"}},"created_at":"2026-07-05T08:18:00.945064+00:00","updated_at":"2026-07-05T08:18:00.945064+00:00"}