{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EQ2FYVSKUPINUCBVAES3MF42BX","short_pith_number":"pith:EQ2FYVSK","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"},"canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","source":{"kind":"arxiv","id":"2410.20626","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20626","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20626v3","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20626","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"EQ2FYVSKUPIN","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"EQ2FYVSKUPINUCBV","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"EQ2FYVSK","created_at":"2026-07-05T10:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EQ2FYVSKUPINUCBVAES3MF42BX","target":"record","payload":{"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"},"canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","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"},"source_kind":"arxiv","source_id":"2410.20626","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3GYGQY+gKifjHbbWny15s6Agplk/wR+QXJqWpDz7nAEkJlWAyUd2kpgeClcTxbiKf9S7ruTs1DVwuWD1mZ+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:55:25.676898Z"},"content_sha256":"16f32623db79c99bd7c6d3a5a62252027b6521dd8709edaeadb7df4f9be37582","schema_version":"1.0","event_id":"sha256:16f32623db79c99bd7c6d3a5a62252027b6521dd8709edaeadb7df4f9be37582"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EQ2FYVSKUPINUCBVAES3MF42BX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjL1U67kQ8XY6I33Xr2XsKIGnE6R+411cK8dvlfVDD3+LrYIoZQtwFKsKy/d7ztw+JoDYFUf3HYxAaZNM8+hAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:55:25.677412Z"},"content_sha256":"2e5bb030b66f9e5704d7d4d61b432b3b40fe048f535488edf8dafb4e93f13b78","schema_version":"1.0","event_id":"sha256:2e5bb030b66f9e5704d7d4d61b432b3b40fe048f535488edf8dafb4e93f13b78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/bundle.json","state_url":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQ2FYVSKUPINUCBVAES3MF42BX/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":"2026-08-10T10:55:25Z","links":{"resolver":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX","bundle":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/bundle.json","state":"https://pith.science/pith/EQ2FYVSKUPINUCBVAES3MF42BX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQ2FYVSKUPINUCBVAES3MF42BX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EQ2FYVSKUPINUCBVAES3MF42BX","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":"fa3c4f79cf313c181fe9d3c29d237b62cdf5f07bad10aaa7ceeec8de441d8291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-27T22:58:47Z","title_canon_sha256":"de2d7a1a8add1fd4082a12f7b0a9d1bafee877e3c17d2b5d39b10a29f6706e7f"},"schema_version":"1.0","source":{"id":"2410.20626","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20626","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20626v3","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20626","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"EQ2FYVSKUPIN","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"EQ2FYVSKUPINUCBV","created_at":"2026-07-05T10:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"EQ2FYVSK","created_at":"2026-07-05T10:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:2e5bb030b66f9e5704d7d4d61b432b3b40fe048f535488edf8dafb4e93f13b78","target":"graph","created_at":"2026-07-05T10:14:47Z","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/2410.20626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Harper Hua, Hengrui Zhang, Juntong Shi, Jure Leskovec, Minkai Xu, Stefano Ermon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-27T22:58:47Z","title":"TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20626","kind":"arxiv","version":3},"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":"sha256:16f32623db79c99bd7c6d3a5a62252027b6521dd8709edaeadb7df4f9be37582","target":"record","created_at":"2026-07-05T10:14:47Z","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":"fa3c4f79cf313c181fe9d3c29d237b62cdf5f07bad10aaa7ceeec8de441d8291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-27T22:58:47Z","title_canon_sha256":"de2d7a1a8add1fd4082a12f7b0a9d1bafee877e3c17d2b5d39b10a29f6706e7f"},"schema_version":"1.0","source":{"id":"2410.20626","kind":"arxiv","version":3}},"canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24345c564aa3d0da08350125b6179a0ddee5e60713b406a9e8efd982501c03ba","first_computed_at":"2026-07-05T10:14:47.261572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:47.261572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yd8AJ4QmtgOMyKBaNwQLW8DwBnpgfHkjjqjZbrxhx8EMH2tbNrVLzp4fPldMiOQcaaDzq7u7G1btweHHsxMFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:47.262067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20626","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16f32623db79c99bd7c6d3a5a62252027b6521dd8709edaeadb7df4f9be37582","sha256:2e5bb030b66f9e5704d7d4d61b432b3b40fe048f535488edf8dafb4e93f13b78"],"state_sha256":"c049cfb3834e9c3a8416e9e3e6f5da3b825bf9a2f3323b57b4f272f1896f6eb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iC/9nT6/L+P8QLK6yXaB5mGXT3oe/2lfjyFLpT/eSuRXTzr3VEVRQ+gYtOOgBbJ+FgDiLHllzZA5zUsmgKMWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:55:25.682539Z","bundle_sha256":"ce2a558be91ecec863f52d518132406c9a259a49a8dd4ae9c6406285d26f8d1d"}}