{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MJ4RGLWNEASWIWSC5AT2F544XQ","short_pith_number":"pith:MJ4RGLWN","schema_version":"1.0","canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","source":{"kind":"arxiv","id":"2302.02041","version":1},"attestation_state":"computed","paper":{"title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aivin V. Solatorio, Olivier Dupriez","submitted_at":"2023-02-04T00:32:50Z","abstract_excerpt":"Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a \"parent\" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent"},"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":"2302.02041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T00:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"1642978b84f3656a06b31f7f30eaa1bd8cc5c036a7ec38a14df38e0a7a4de0b6","abstract_canon_sha256":"acaafe3509c4ebf5c1c5f669d9fe900b80ca93fea38654bcb8d4859f75095a07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:48.066586Z","signature_b64":"s68gxAgP0P4aitHRgw0c01boG070ZZBas/Q8kFFdD0box41keIwGd1JS6VlkDGhYPtkh1Mvseec5ekeJBh79CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6279132ecd2025645a42e827a2f79cbc1ae7680e3043d4c43d38cdc124f361f7","last_reissued_at":"2026-07-05T05:38:48.066013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:48.066013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aivin V. Solatorio, Olivier Dupriez","submitted_at":"2023-02-04T00:32:50Z","abstract_excerpt":"Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a \"parent\" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02041","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/2302.02041/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":"2302.02041","created_at":"2026-07-05T05:38:48.066073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02041v1","created_at":"2026-07-05T05:38:48.066073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02041","created_at":"2026-07-05T05:38:48.066073+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJ4RGLWNEASW","created_at":"2026-07-05T05:38:48.066073+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJ4RGLWNEASWIWSC","created_at":"2026-07-05T05:38:48.066073+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJ4RGLWN","created_at":"2026-07-05T05:38:48.066073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18518","citing_title":"PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11961","citing_title":"Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31904","citing_title":"Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30473","citing_title":"Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02161","citing_title":"LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23964","citing_title":"Making Logic a First-Class Citizen in Generative ML for Networking","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11742","citing_title":"Cross-Flow Correlations Survive Synthesis: Measuring Source-Level Privacy Leakage in Synthetic Network Traces","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07126","citing_title":"Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Setting","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09855","citing_title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10536","citing_title":"HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00445","citing_title":"The Power of Order: Fooling LLMs with Adversarial Table Permutations","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16817","citing_title":"Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ","json":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ.json","graph_json":"https://pith.science/api/pith-number/MJ4RGLWNEASWIWSC5AT2F544XQ/graph.json","events_json":"https://pith.science/api/pith-number/MJ4RGLWNEASWIWSC5AT2F544XQ/events.json","paper":"https://pith.science/paper/MJ4RGLWN"},"agent_actions":{"view_html":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ","download_json":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ.json","view_paper":"https://pith.science/paper/MJ4RGLWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02041&json=true","fetch_graph":"https://pith.science/api/pith-number/MJ4RGLWNEASWIWSC5AT2F544XQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MJ4RGLWNEASWIWSC5AT2F544XQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/action/storage_attestation","attest_author":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/action/author_attestation","sign_citation":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/action/citation_signature","submit_replication":"https://pith.science/pith/MJ4RGLWNEASWIWSC5AT2F544XQ/action/replication_record"}},"created_at":"2026-07-05T05:38:48.066073+00:00","updated_at":"2026-07-05T05:38:48.066073+00:00"}