{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JDAOC6KGURAHOHTPXKT3RTPNY","short_pith_number":"pith:3JDAOC6K","schema_version":"1.0","canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","source":{"kind":"arxiv","id":"2405.20602","version":2},"attestation_state":"computed","paper":{"title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Changhyun Kim, Gyeongdong Woo, Jaesung Lim, Jong-June Jeon, Seunghwan An, Sungchul Hong","submitted_at":"2024-05-31T03:26:42Z","abstract_excerpt":"In this paper, our goal is to generate synthetic data for heterogeneous (mixed-type) tabular datasets with high machine learning utility (MLu). Since the MLu performance depends on accurately approximating the conditional distributions, we focus on devising a synthetic data generation method based on conditional distribution estimation. We introduce MaCoDE by redefining the consecutive multi-class classification task of Masked Language Modeling (MLM) as histogram-based non-parametric conditional density estimation. Our approach enables the estimation of conditional densities across arbitrary c"},"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":"2405.20602","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T03:26:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b0307307619ae0c0d6eda37c4bc5f0a68694c161f287fb9b7375bb6385989e30","abstract_canon_sha256":"f23a8cb3098a7694234db45cef81c3875d7a288237c88a9cdf83e8610361e514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:21.384167Z","signature_b64":"uTLVvoz8SOXOF/h6LCU3CJZo3tmppl909SQnbxjZIMSe9/erakpHN51GC17qH4X8jpaT3A2dBUInpaXfw8+CDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","last_reissued_at":"2026-07-05T08:56:21.383693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:21.383693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Changhyun Kim, Gyeongdong Woo, Jaesung Lim, Jong-June Jeon, Seunghwan An, Sungchul Hong","submitted_at":"2024-05-31T03:26:42Z","abstract_excerpt":"In this paper, our goal is to generate synthetic data for heterogeneous (mixed-type) tabular datasets with high machine learning utility (MLu). Since the MLu performance depends on accurately approximating the conditional distributions, we focus on devising a synthetic data generation method based on conditional distribution estimation. We introduce MaCoDE by redefining the consecutive multi-class classification task of Masked Language Modeling (MLM) as histogram-based non-parametric conditional density estimation. Our approach enables the estimation of conditional densities across arbitrary c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20602","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/2405.20602/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":"2405.20602","created_at":"2026-07-05T08:56:21.383750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20602v2","created_at":"2026-07-05T08:56:21.383750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20602","created_at":"2026-07-05T08:56:21.383750+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JDAOC6KGURA","created_at":"2026-07-05T08:56:21.383750+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JDAOC6KGURAHOHT","created_at":"2026-07-05T08:56:21.383750+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JDAOC6K","created_at":"2026-07-05T08:56:21.383750+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/3JDAOC6KGURAHOHTPXKT3RTPNY","json":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY.json","graph_json":"https://pith.science/api/pith-number/3JDAOC6KGURAHOHTPXKT3RTPNY/graph.json","events_json":"https://pith.science/api/pith-number/3JDAOC6KGURAHOHTPXKT3RTPNY/events.json","paper":"https://pith.science/paper/3JDAOC6K"},"agent_actions":{"view_html":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY","download_json":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY.json","view_paper":"https://pith.science/paper/3JDAOC6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20602&json=true","fetch_graph":"https://pith.science/api/pith-number/3JDAOC6KGURAHOHTPXKT3RTPNY/graph.json","fetch_events":"https://pith.science/api/pith-number/3JDAOC6KGURAHOHTPXKT3RTPNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/action/storage_attestation","attest_author":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/action/author_attestation","sign_citation":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/action/citation_signature","submit_replication":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/action/replication_record"}},"created_at":"2026-07-05T08:56:21.383750+00:00","updated_at":"2026-07-05T08:56:21.383750+00:00"}