{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3RSVITZGPVCHGDUUALRPBVX3CG","short_pith_number":"pith:3RSVITZG","schema_version":"1.0","canonical_sha256":"dc65544f267d44730e9402e2f0d6fb11b2c4f0fa7048b9ce87c5a07057fd2354","source":{"kind":"arxiv","id":"2302.04062","version":10},"attestation_state":"computed","paper":{"title":"Machine Learning for Synthetic Data Generation: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Capucine Van Rechem, Huazheng Wang, Lulu Chen, Minjie Shen, Tianfan Fu, Wenqi Wei, Xiao Wang, Yingzhou Lu, Yuanyuan Zhang","submitted_at":"2023-02-08T13:59:31Z","abstract_excerpt":"Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to under-fitting of machine learning models, and difficulties in data access due to concerns surrounding privacy, safety, and regulations. In light of these challenges, the concept of synthetic data generation emerges as a promising alternative that allows for data sharing and utilization in ways that real-world data cannot facilitate. This paper presents a comprehensive systematic review of existing studies that "},"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":"2302.04062","kind":"arxiv","version":10},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T13:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"f640b34801ac09a15de9ecb6fa698d813a4826abf25f0bb4c285d35e8bd4c6cb","abstract_canon_sha256":"e6da4ab6a509ab71f058bdae7c9d7428067878809c157d853ae2a59527385fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:12.150162Z","signature_b64":"aCqQH7JkxQlJVBHWYuVlmlahh51FTfJKLq3LBkBRN/LALNqEHIMTsiArFY+7VpdOSk4DVgpJPNRdqc45bkiCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc65544f267d44730e9402e2f0d6fb11b2c4f0fa7048b9ce87c5a07057fd2354","last_reissued_at":"2026-07-05T10:44:12.149761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:12.149761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning for Synthetic Data Generation: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Capucine Van Rechem, Huazheng Wang, Lulu Chen, Minjie Shen, Tianfan Fu, Wenqi Wei, Xiao Wang, Yingzhou Lu, Yuanyuan Zhang","submitted_at":"2023-02-08T13:59:31Z","abstract_excerpt":"Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to under-fitting of machine learning models, and difficulties in data access due to concerns surrounding privacy, safety, and regulations. In light of these challenges, the concept of synthetic data generation emerges as a promising alternative that allows for data sharing and utilization in ways that real-world data cannot facilitate. This paper presents a comprehensive systematic review of existing studies that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04062","kind":"arxiv","version":10},"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/2302.04062/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":"2302.04062","created_at":"2026-07-05T10:44:12.149818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04062v10","created_at":"2026-07-05T10:44:12.149818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04062","created_at":"2026-07-05T10:44:12.149818+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RSVITZGPVCH","created_at":"2026-07-05T10:44:12.149818+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RSVITZGPVCHGDUU","created_at":"2026-07-05T10:44:12.149818+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RSVITZG","created_at":"2026-07-05T10:44:12.149818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26053","citing_title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01785","citing_title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15087","citing_title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22467","citing_title":"SADGE: Structure and Appearance Domain Gap Estimation of Synthetic and Real Data","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17889","citing_title":"CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19289","citing_title":"What Makes Synthetic Data Effective in Image Segmentation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20151","citing_title":"When Does Model Collapse Occur in Structured Interactive Learning?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17558","citing_title":"Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07876","citing_title":"Stochastic dynamics learning with state-space systems","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08826","citing_title":"Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05752","citing_title":"Generative AI-Based Monte Carlo Simulation for Method Evaluation Using Synthetic Multilevel Data","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG","json":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG.json","graph_json":"https://pith.science/api/pith-number/3RSVITZGPVCHGDUUALRPBVX3CG/graph.json","events_json":"https://pith.science/api/pith-number/3RSVITZGPVCHGDUUALRPBVX3CG/events.json","paper":"https://pith.science/paper/3RSVITZG"},"agent_actions":{"view_html":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG","download_json":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG.json","view_paper":"https://pith.science/paper/3RSVITZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04062&json=true","fetch_graph":"https://pith.science/api/pith-number/3RSVITZGPVCHGDUUALRPBVX3CG/graph.json","fetch_events":"https://pith.science/api/pith-number/3RSVITZGPVCHGDUUALRPBVX3CG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG/action/storage_attestation","attest_author":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG/action/author_attestation","sign_citation":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG/action/citation_signature","submit_replication":"https://pith.science/pith/3RSVITZGPVCHGDUUALRPBVX3CG/action/replication_record"}},"created_at":"2026-07-05T10:44:12.149818+00:00","updated_at":"2026-07-05T10:44:12.149818+00:00"}