{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TZRP7B6WCZWBEPEZIJDHJUTV75","short_pith_number":"pith:TZRP7B6W","canonical_record":{"source":{"id":"2507.19700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T22:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"708e03e8f572d44d819934cd3882f72e49b2b142fc430c818c971286c2d41980","abstract_canon_sha256":"48a07970c227fb0dc4548c0eeba454bedaf12fe5c48bf8235bfd8fd971c06499"},"schema_version":"1.0"},"canonical_sha256":"9e62ff87d6166c123c99424674d275ff77a1abde3815f77c7b0112714d51c1d8","source":{"kind":"arxiv","id":"2507.19700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19700","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19700v2","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19700","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"TZRP7B6WCZWB","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"TZRP7B6WCZWBEPEZ","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"TZRP7B6W","created_at":"2026-06-09T02:07:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TZRP7B6WCZWBEPEZIJDHJUTV75","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T22:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"708e03e8f572d44d819934cd3882f72e49b2b142fc430c818c971286c2d41980","abstract_canon_sha256":"48a07970c227fb0dc4548c0eeba454bedaf12fe5c48bf8235bfd8fd971c06499"},"schema_version":"1.0"},"canonical_sha256":"9e62ff87d6166c123c99424674d275ff77a1abde3815f77c7b0112714d51c1d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:06.085382Z","signature_b64":"J4to5S9lgOH7IlF5HDDORCMTP2lQZTriPQCZCOj7k0Pb4At9dSH7pgBwwsXD93r3HSb2NARX0iup9s6bDeypDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e62ff87d6166c123c99424674d275ff77a1abde3815f77c7b0112714d51c1d8","last_reissued_at":"2026-06-09T02:07:06.084469Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:06.084469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19700","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":"2026-06-09T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fDdBVpF0CsE0eK+msHqCDwLJs8uh2ql/yORjAlnbGxEUm/6vJMy8/Ln3lnCWix0XKyMSleh0Y6XrDxxUuy68BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:11:16.515364Z"},"content_sha256":"ee02a1d6346cff27b2b281c38b0a1927e3b8fd4ea17745ee6b92d3c3db472fce","schema_version":"1.0","event_id":"sha256:ee02a1d6346cff27b2b281c38b0a1927e3b8fd4ea17745ee6b92d3c3db472fce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TZRP7B6WCZWBEPEZIJDHJUTV75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disjoint Generation of Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton Danholt Lautrup, Arthur Zimek, Muhammad Rajabinasab, Peter Schneider-Kamp, Tobias Hyrup","submitted_at":"2025-07-25T22:38:06Z","abstract_excerpt":"We propose a new framework for generating tabular synthetic datasets via disjoint generative models. In this paradigm, a dataset is partitioned into disjoint subsets that are supplied to separate instances of generative models. The results are then combined post hoc by a joining operation that works in the absence of common variables/identifiers. The success of the framework is demonstrated through several case studies and examples on tabular data that help illuminate some of the design choices that one may make. The advantages achieved by the disjoint generation include: i) An observed increa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19700","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/2507.19700/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":"2026-06-09T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gcnRVLVnzypTTPM96Zao7x7dBPkqipB3HUf6i2cFb1AFRmTX9JRsW4lQUW+MkMseIVmDgDmKapjS02telMc6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:11:16.515769Z"},"content_sha256":"870bc86c0daa95305f16292853e1d4a5b2b70a9c4805b6927fe74ff25e0f17d3","schema_version":"1.0","event_id":"sha256:870bc86c0daa95305f16292853e1d4a5b2b70a9c4805b6927fe74ff25e0f17d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/bundle.json","state_url":"https://pith.science/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/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":"2026-06-28T11:11:16Z","links":{"resolver":"https://pith.science/pith/TZRP7B6WCZWBEPEZIJDHJUTV75","bundle":"https://pith.science/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/bundle.json","state":"https://pith.science/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TZRP7B6WCZWBEPEZIJDHJUTV75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TZRP7B6WCZWBEPEZIJDHJUTV75","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":"48a07970c227fb0dc4548c0eeba454bedaf12fe5c48bf8235bfd8fd971c06499","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T22:38:06Z","title_canon_sha256":"708e03e8f572d44d819934cd3882f72e49b2b142fc430c818c971286c2d41980"},"schema_version":"1.0","source":{"id":"2507.19700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19700","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19700v2","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19700","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"TZRP7B6WCZWB","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"TZRP7B6WCZWBEPEZ","created_at":"2026-06-09T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"TZRP7B6W","created_at":"2026-06-09T02:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:870bc86c0daa95305f16292853e1d4a5b2b70a9c4805b6927fe74ff25e0f17d3","target":"graph","created_at":"2026-06-09T02:07:06Z","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/2507.19700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new framework for generating tabular synthetic datasets via disjoint generative models. In this paradigm, a dataset is partitioned into disjoint subsets that are supplied to separate instances of generative models. The results are then combined post hoc by a joining operation that works in the absence of common variables/identifiers. The success of the framework is demonstrated through several case studies and examples on tabular data that help illuminate some of the design choices that one may make. The advantages achieved by the disjoint generation include: i) An observed increa","authors_text":"Anton Danholt Lautrup, Arthur Zimek, Muhammad Rajabinasab, Peter Schneider-Kamp, Tobias Hyrup","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T22:38:06Z","title":"Disjoint Generation of Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19700","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:ee02a1d6346cff27b2b281c38b0a1927e3b8fd4ea17745ee6b92d3c3db472fce","target":"record","created_at":"2026-06-09T02:07:06Z","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":"48a07970c227fb0dc4548c0eeba454bedaf12fe5c48bf8235bfd8fd971c06499","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T22:38:06Z","title_canon_sha256":"708e03e8f572d44d819934cd3882f72e49b2b142fc430c818c971286c2d41980"},"schema_version":"1.0","source":{"id":"2507.19700","kind":"arxiv","version":2}},"canonical_sha256":"9e62ff87d6166c123c99424674d275ff77a1abde3815f77c7b0112714d51c1d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e62ff87d6166c123c99424674d275ff77a1abde3815f77c7b0112714d51c1d8","first_computed_at":"2026-06-09T02:07:06.084469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:06.084469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J4to5S9lgOH7IlF5HDDORCMTP2lQZTriPQCZCOj7k0Pb4At9dSH7pgBwwsXD93r3HSb2NARX0iup9s6bDeypDA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:06.085382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee02a1d6346cff27b2b281c38b0a1927e3b8fd4ea17745ee6b92d3c3db472fce","sha256:870bc86c0daa95305f16292853e1d4a5b2b70a9c4805b6927fe74ff25e0f17d3"],"state_sha256":"9f5a5352631f55efd2d976142f50e4a476429d4d6a5950404d432c11f79d3fa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNPdOeSnCy97cRgxF6gqBy0Z/ezWbehjdv4AA01xyyx6Uee+JUHbEMnMdxodrr8eeens/TP+qrsfLWB46fbIAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:11:16.517938Z","bundle_sha256":"6f322cd94debd2b7797106254839f924c5f9d74eb896ee5eabf3e2215e22fdff"}}