{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7HPBJHZBEIARK424ZMQDEPVZVF","short_pith_number":"pith:7HPBJHZB","schema_version":"1.0","canonical_sha256":"f9de149f21220115735ccb20323eb9a964dae1e07825e2888a38ef2862dfd07d","source":{"kind":"arxiv","id":"2506.00710","version":1},"attestation_state":"computed","paper":{"title":"RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik \\v{S}trumbelj, Juntong Shi, Jure Leskovec, Lovro \\v{S}ubelj, Minkai Xu, Stefano Ermon, Valter Hudovernik","submitted_at":"2025-05-31T21:01:02Z","abstract_excerpt":"Real-world databases are predominantly relational, comprising multiple interlinked tables that contain complex structural and statistical dependencies. Learning generative models on relational data has shown great promise in generating synthetic data and imputing missing values. However, existing methods often struggle to capture this complexity, typically reducing relational data to conditionally generated flat tables and imposing limiting structural assumptions. To address these limitations, we introduce RelDiff, a novel diffusion generative model that synthesizes complete relational databas"},"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":"2506.00710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T21:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"87ed9719ce29d7af771abf5bb7704769463fb34eac8592b2c98283cfecfa6f1c","abstract_canon_sha256":"e4ec36c1f5280e61b0bbe20e23eb995411423d934f5309556d0d3f9545369e34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.148679Z","signature_b64":"wGvrB3U5G+9bKdSmNpbQcOj0IbdZpwNExxrUNJa8uwBASJhOPijpRGV37X1p2MlyoZzIgOZOqpX9VO8iJHUhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9de149f21220115735ccb20323eb9a964dae1e07825e2888a38ef2862dfd07d","last_reissued_at":"2026-07-05T11:13:39.148215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.148215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik \\v{S}trumbelj, Juntong Shi, Jure Leskovec, Lovro \\v{S}ubelj, Minkai Xu, Stefano Ermon, Valter Hudovernik","submitted_at":"2025-05-31T21:01:02Z","abstract_excerpt":"Real-world databases are predominantly relational, comprising multiple interlinked tables that contain complex structural and statistical dependencies. Learning generative models on relational data has shown great promise in generating synthetic data and imputing missing values. However, existing methods often struggle to capture this complexity, typically reducing relational data to conditionally generated flat tables and imposing limiting structural assumptions. To address these limitations, we introduce RelDiff, a novel diffusion generative model that synthesizes complete relational databas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00710","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/2506.00710/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":"2506.00710","created_at":"2026-07-05T11:13:39.148271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00710v1","created_at":"2026-07-05T11:13:39.148271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00710","created_at":"2026-07-05T11:13:39.148271+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HPBJHZBEIAR","created_at":"2026-07-05T11:13:39.148271+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HPBJHZBEIARK424","created_at":"2026-07-05T11:13:39.148271+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HPBJHZB","created_at":"2026-07-05T11:13:39.148271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08736","citing_title":"Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31904","citing_title":"Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12606","citing_title":"RelBench v2: A Large-Scale Benchmark and Repository for Relational Data","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF","json":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF.json","graph_json":"https://pith.science/api/pith-number/7HPBJHZBEIARK424ZMQDEPVZVF/graph.json","events_json":"https://pith.science/api/pith-number/7HPBJHZBEIARK424ZMQDEPVZVF/events.json","paper":"https://pith.science/paper/7HPBJHZB"},"agent_actions":{"view_html":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF","download_json":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF.json","view_paper":"https://pith.science/paper/7HPBJHZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00710&json=true","fetch_graph":"https://pith.science/api/pith-number/7HPBJHZBEIARK424ZMQDEPVZVF/graph.json","fetch_events":"https://pith.science/api/pith-number/7HPBJHZBEIARK424ZMQDEPVZVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF/action/storage_attestation","attest_author":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF/action/author_attestation","sign_citation":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF/action/citation_signature","submit_replication":"https://pith.science/pith/7HPBJHZBEIARK424ZMQDEPVZVF/action/replication_record"}},"created_at":"2026-07-05T11:13:39.148271+00:00","updated_at":"2026-07-05T11:13:39.148271+00:00"}