{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCMMOYUQIA2N7IV4EDCIMBDLNT","short_pith_number":"pith:GCMMOYUQ","schema_version":"1.0","canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","source":{"kind":"arxiv","id":"2507.19334","version":1},"attestation_state":"computed","paper":{"title":"Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bardh Prenkaj, Gjergji Kasneci, Shuo Yang, Zheyu Zhang","submitted_at":"2025-07-25T14:43:50Z","abstract_excerpt":"Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major limitations: (1) dense dependency modeling among tabular features that can introduce bias, and (2) high computational overhead in sampling. To address these issues, we propose SPADA for SPArse Dependency-driven Augmentation, a lightweight generative framework that explicitly captures sparse dependencies via an LLM-induced graph. We treat each feature"},"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":"2507.19334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T14:43:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d505e7228ea54651e55779ed6cf7e0a147ff55e24d215e3a127b6be7d1f44e","abstract_canon_sha256":"cb1267618794ccbba9738214900a120310db42b373d6b1cf50ce1b85fcd553b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:23.658284Z","signature_b64":"wZ2qfLefGC/uvgFSeTKm57HepFC4OHUJN3TEfr8F6Zmq1nbU6elGUuLmTjn8qYkFL1Ocrk2hreudI0gkul8WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3098c762904034dfa2bc20c486046b6cd9378aa953a2d66a585c97b98abe49d1","last_reissued_at":"2026-07-05T11:43:23.657686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:23.657686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bardh Prenkaj, Gjergji Kasneci, Shuo Yang, Zheyu Zhang","submitted_at":"2025-07-25T14:43:50Z","abstract_excerpt":"Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major limitations: (1) dense dependency modeling among tabular features that can introduce bias, and (2) high computational overhead in sampling. To address these issues, we propose SPADA for SPArse Dependency-driven Augmentation, a lightweight generative framework that explicitly captures sparse dependencies via an LLM-induced graph. We treat each feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19334","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/2507.19334/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":"2507.19334","created_at":"2026-07-05T11:43:23.657747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19334v1","created_at":"2026-07-05T11:43:23.657747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19334","created_at":"2026-07-05T11:43:23.657747+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCMMOYUQIA2N","created_at":"2026-07-05T11:43:23.657747+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCMMOYUQIA2N7IV4","created_at":"2026-07-05T11:43:23.657747+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCMMOYUQ","created_at":"2026-07-05T11:43:23.657747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02040","citing_title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT","json":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT.json","graph_json":"https://pith.science/api/pith-number/GCMMOYUQIA2N7IV4EDCIMBDLNT/graph.json","events_json":"https://pith.science/api/pith-number/GCMMOYUQIA2N7IV4EDCIMBDLNT/events.json","paper":"https://pith.science/paper/GCMMOYUQ"},"agent_actions":{"view_html":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT","download_json":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT.json","view_paper":"https://pith.science/paper/GCMMOYUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19334&json=true","fetch_graph":"https://pith.science/api/pith-number/GCMMOYUQIA2N7IV4EDCIMBDLNT/graph.json","fetch_events":"https://pith.science/api/pith-number/GCMMOYUQIA2N7IV4EDCIMBDLNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/action/storage_attestation","attest_author":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/action/author_attestation","sign_citation":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/action/citation_signature","submit_replication":"https://pith.science/pith/GCMMOYUQIA2N7IV4EDCIMBDLNT/action/replication_record"}},"created_at":"2026-07-05T11:43:23.657747+00:00","updated_at":"2026-07-05T11:43:23.657747+00:00"}