{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IGKQRWABMEG7R53OGLMBUNTIOQ","short_pith_number":"pith:IGKQRWAB","schema_version":"1.0","canonical_sha256":"419508d801610df8f76e32d81a36687423903a5b2e860383d831796a09bdde3a","source":{"kind":"arxiv","id":"2405.17724","version":2},"attestation_state":"computed","paper":{"title":"ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lucy Liu, Masoumeh Shafieinejad, Stephanie Hazlewood, Wei Pang, Xi He","submitted_at":"2024-05-28T00:42:18Z","abstract_excerpt":"Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational (multi-table) data fall short in two key aspects: scalability for larger datasets and capturing long-range dependencies, such as correlations between attributes spread across different tables. Inspired by the success of diffusion models in tabular data modeling, we introduce\n  $\\textbf{C}luster$ $\\textbf{La}tent$ $\\textbf{Va}riable$ $guided$ $\\textbf{D}enoising$ $\\t"},"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":"2405.17724","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T00:42:18Z","cross_cats_sorted":[],"title_canon_sha256":"020753eea92cb1ae306ee9d3ea90ec8301b6e2d09d5b003c259048bd563d042a","abstract_canon_sha256":"0a07794297858911b90d908055f861e80fb768aa3e8b4785c600aa844c7cde1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:10.181398Z","signature_b64":"jz4IWL+cUnGFBS8IqfA1sdzvMR61q3CwLv5qRuo6wr2dPoJLcaothG6a4nU0Y5zriUcphoDK+OmaoWzV2rKfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"419508d801610df8f76e32d81a36687423903a5b2e860383d831796a09bdde3a","last_reissued_at":"2026-07-05T09:35:10.180965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:10.180965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lucy Liu, Masoumeh Shafieinejad, Stephanie Hazlewood, Wei Pang, Xi He","submitted_at":"2024-05-28T00:42:18Z","abstract_excerpt":"Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational (multi-table) data fall short in two key aspects: scalability for larger datasets and capturing long-range dependencies, such as correlations between attributes spread across different tables. Inspired by the success of diffusion models in tabular data modeling, we introduce\n  $\\textbf{C}luster$ $\\textbf{La}tent$ $\\textbf{Va}riable$ $guided$ $\\textbf{D}enoising$ $\\t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17724","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/2405.17724/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":"2405.17724","created_at":"2026-07-05T09:35:10.181017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17724v2","created_at":"2026-07-05T09:35:10.181017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17724","created_at":"2026-07-05T09:35:10.181017+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGKQRWABMEG7","created_at":"2026-07-05T09:35:10.181017+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGKQRWABMEG7R53O","created_at":"2026-07-05T09:35:10.181017+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGKQRWAB","created_at":"2026-07-05T09:35:10.181017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31904","citing_title":"Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19185","citing_title":"MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ","json":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ.json","graph_json":"https://pith.science/api/pith-number/IGKQRWABMEG7R53OGLMBUNTIOQ/graph.json","events_json":"https://pith.science/api/pith-number/IGKQRWABMEG7R53OGLMBUNTIOQ/events.json","paper":"https://pith.science/paper/IGKQRWAB"},"agent_actions":{"view_html":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ","download_json":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ.json","view_paper":"https://pith.science/paper/IGKQRWAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17724&json=true","fetch_graph":"https://pith.science/api/pith-number/IGKQRWABMEG7R53OGLMBUNTIOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IGKQRWABMEG7R53OGLMBUNTIOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ/action/storage_attestation","attest_author":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ/action/author_attestation","sign_citation":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ/action/citation_signature","submit_replication":"https://pith.science/pith/IGKQRWABMEG7R53OGLMBUNTIOQ/action/replication_record"}},"created_at":"2026-07-05T09:35:10.181017+00:00","updated_at":"2026-07-05T09:35:10.181017+00:00"}