{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E4EKQLULZH2GY5TOKN2ZMN33JX","short_pith_number":"pith:E4EKQLUL","schema_version":"1.0","canonical_sha256":"2708a82e8bc9f46c766e537596377b4de766286984ee418f5ffa79e4927ce6e1","source":{"kind":"arxiv","id":"2605.17642","version":1},"attestation_state":"computed","paper":{"title":"TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chin-Chia Michael Yeh, Jeff M. Phillips, Junpeng Wang, Meysam Alishahi, Yan Zheng","submitted_at":"2026-05-17T20:21:56Z","abstract_excerpt":"Tabular data generation considers a large table with multiple columns -- each column comprised of numerical, categorical, or sometimes ordinal values. The goal is to produce new rows for the table that replicate the distribution of rows from the original data -- without just copying those initial rows. The last 4 years have seen enormous progress on this problem, mostly using computational expensive methods that employ one-hot encoding, VAEs, and diffusion.\n  This paper describes a new approach to the problem of tabular data generation. By employing copula transformations and modeling the dist"},"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":"2605.17642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T20:21:56Z","cross_cats_sorted":[],"title_canon_sha256":"41ba2af0718c628df5473b007589ee9434077273e64b598193cb754b483ec0e7","abstract_canon_sha256":"eb2642bd4784e411b54d3dd6922e317f4c5c82e5d46e85f29b759edbb821233d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:50.253814Z","signature_b64":"Jw+UnZocVqobPloowruSFLik0uIWFF262l0hwVc9k/xClucM88rQ8L10WzXv2+pTsGDZliHZ49E1CoikR47CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2708a82e8bc9f46c766e537596377b4de766286984ee418f5ffa79e4927ce6e1","last_reissued_at":"2026-05-20T00:04:50.253027Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:50.253027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chin-Chia Michael Yeh, Jeff M. Phillips, Junpeng Wang, Meysam Alishahi, Yan Zheng","submitted_at":"2026-05-17T20:21:56Z","abstract_excerpt":"Tabular data generation considers a large table with multiple columns -- each column comprised of numerical, categorical, or sometimes ordinal values. The goal is to produce new rows for the table that replicate the distribution of rows from the original data -- without just copying those initial rows. The last 4 years have seen enormous progress on this problem, mostly using computational expensive methods that employ one-hot encoding, VAEs, and diffusion.\n  This paper describes a new approach to the problem of tabular data generation. By employing copula transformations and modeling the dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17642","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/2605.17642/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T22:22:49.390781Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.551857Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.472836Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"492c834ff958069c2476af5af67702318a574e83f6a0a3cf9510f5737d7880e1"},"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":"2605.17642","created_at":"2026-05-20T00:04:50.253166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17642v1","created_at":"2026-05-20T00:04:50.253166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17642","created_at":"2026-05-20T00:04:50.253166+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4EKQLULZH2G","created_at":"2026-05-20T00:04:50.253166+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4EKQLULZH2GY5TO","created_at":"2026-05-20T00:04:50.253166+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4EKQLUL","created_at":"2026-05-20T00:04:50.253166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX","json":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX.json","graph_json":"https://pith.science/api/pith-number/E4EKQLULZH2GY5TOKN2ZMN33JX/graph.json","events_json":"https://pith.science/api/pith-number/E4EKQLULZH2GY5TOKN2ZMN33JX/events.json","paper":"https://pith.science/paper/E4EKQLUL"},"agent_actions":{"view_html":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX","download_json":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX.json","view_paper":"https://pith.science/paper/E4EKQLUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17642&json=true","fetch_graph":"https://pith.science/api/pith-number/E4EKQLULZH2GY5TOKN2ZMN33JX/graph.json","fetch_events":"https://pith.science/api/pith-number/E4EKQLULZH2GY5TOKN2ZMN33JX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX/action/storage_attestation","attest_author":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX/action/author_attestation","sign_citation":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX/action/citation_signature","submit_replication":"https://pith.science/pith/E4EKQLULZH2GY5TOKN2ZMN33JX/action/replication_record"}},"created_at":"2026-05-20T00:04:50.253166+00:00","updated_at":"2026-05-20T00:04:50.253166+00:00"}