{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3JDAOC6KGURAHOHTPXKT3RTPNY","short_pith_number":"pith:3JDAOC6K","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"},"canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","source":{"kind":"arxiv","id":"2405.20602","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20602","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20602v2","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20602","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"3JDAOC6KGURA","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"3JDAOC6KGURAHOHT","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"3JDAOC6K","created_at":"2026-07-05T08:56:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3JDAOC6KGURAHOHTPXKT3RTPNY","target":"record","payload":{"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"},"canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","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"},"source_kind":"arxiv","source_id":"2405.20602","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLcPD+GJjkwpmSU46ywXiaLVPtX9oHzqdcZbj7tkgv6xnQs8xyu/w6Am7k1rLE65VBORnzt7Owng8G77/EzlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:48:32.423489Z"},"content_sha256":"07235ef49538e43efa0cb067f7a7bfd630146e3c7e426cd5881865c53ff80e13","schema_version":"1.0","event_id":"sha256:07235ef49538e43efa0cb067f7a7bfd630146e3c7e426cd5881865c53ff80e13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3JDAOC6KGURAHOHTPXKT3RTPNY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z3QprL+eGMNGvpzCag5nPx9+nWijem+tX4+mBm3OWLbbn5qTylI+Eh9+0I83rvmZeC2Egn/T6bMSAjpnwuz6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:48:32.423869Z"},"content_sha256":"34d4537380512c29a6d1248cdebca3bbaf519b30b2af2f863ebe7a13e2b498be","schema_version":"1.0","event_id":"sha256:34d4537380512c29a6d1248cdebca3bbaf519b30b2af2f863ebe7a13e2b498be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/bundle.json","state_url":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T01:48:32Z","links":{"resolver":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY","bundle":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/bundle.json","state":"https://pith.science/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JDAOC6KGURAHOHTPXKT3RTPNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3JDAOC6KGURAHOHTPXKT3RTPNY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f23a8cb3098a7694234db45cef81c3875d7a288237c88a9cdf83e8610361e514","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T03:26:42Z","title_canon_sha256":"b0307307619ae0c0d6eda37c4bc5f0a68694c161f287fb9b7375bb6385989e30"},"schema_version":"1.0","source":{"id":"2405.20602","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20602","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20602v2","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20602","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"3JDAOC6KGURA","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"3JDAOC6KGURAHOHT","created_at":"2026-07-05T08:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"3JDAOC6K","created_at":"2026-07-05T08:56:21Z"}],"graph_snapshots":[{"event_id":"sha256:34d4537380512c29a6d1248cdebca3bbaf519b30b2af2f863ebe7a13e2b498be","target":"graph","created_at":"2026-07-05T08:56:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.20602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changhyun Kim, Gyeongdong Woo, Jaesung Lim, Jong-June Jeon, Seunghwan An, Sungchul Hong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T03:26:42Z","title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20602","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:07235ef49538e43efa0cb067f7a7bfd630146e3c7e426cd5881865c53ff80e13","target":"record","created_at":"2026-07-05T08:56:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f23a8cb3098a7694234db45cef81c3875d7a288237c88a9cdf83e8610361e514","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T03:26:42Z","title_canon_sha256":"b0307307619ae0c0d6eda37c4bc5f0a68694c161f287fb9b7375bb6385989e30"},"schema_version":"1.0","source":{"id":"2405.20602","kind":"arxiv","version":2}},"canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da46070bca352203b8f37dd53dc66f6e1f500a896b7031f9fc94a3f659aba23f","first_computed_at":"2026-07-05T08:56:21.383693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:21.383693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTLVvoz8SOXOF/h6LCU3CJZo3tmppl909SQnbxjZIMSe9/erakpHN51GC17qH4X8jpaT3A2dBUInpaXfw8+CDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:21.384167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20602","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07235ef49538e43efa0cb067f7a7bfd630146e3c7e426cd5881865c53ff80e13","sha256:34d4537380512c29a6d1248cdebca3bbaf519b30b2af2f863ebe7a13e2b498be"],"state_sha256":"d64854d30080f1b1d9c112a0f47471cd82cd7027f55e724a051ba7dead241171"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvSWxMi/LbaTqKO23rn6c0jIhizqGsV/si7s1l5STz39lqTJ3VGPTMf/+j0vDIPzBbK8uErPj53MaO82JHw1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:48:32.425934Z","bundle_sha256":"954ea35025c9bedf14553dc3d3c82184a39d708d664f8e57095c155ffc360ac7"}}