{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ACRGCXYRB7D2C34GFMCR7DY7UI","short_pith_number":"pith:ACRGCXYR","schema_version":"1.0","canonical_sha256":"00a2615f110fc7a16f862b051f8f1fa2308378d69cfb099284f8953bbe995519","source":{"kind":"arxiv","id":"2205.03257","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Data -- what, why and how?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Carsten Maple, Florimond Houssiau, Giovanni Cherubin, James Jordon, Lukasz Szpruch, Mirko Bottarelli, Samuel N. Cohen","submitted_at":"2022-05-06T14:27:45Z","abstract_excerpt":"This explainer document aims to provide an overview of the current state of the rapidly expanding work on synthetic data technologies, with a particular focus on privacy. The article is intended for a non-technical audience, though some formal definitions have been given to provide clarity to specialists. This article is intended to enable the reader to quickly become familiar with the notion of synthetic data, as well as understand some of the subtle intricacies that come with it. We do believe that synthetic data is a very useful tool, and our hope is that this report highlights that, while "},"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":"2205.03257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-06T14:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"15f7fc414550470edcb8ddc7695a1c5cd949833c6c9271abc4712181c3bc301c","abstract_canon_sha256":"7c02e317a2f2ce483cfa42dcc41a7faa91feb933301c2c2c2a490f9ec6d90144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:57.809494Z","signature_b64":"g/w91OVfypZLpkrVa2zMLUmJ42Fs+E7z1cXMl8CbhEfWXxmG+tgHGTC2txoQu96anRrDp7FvKOxza0iG47SIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a2615f110fc7a16f862b051f8f1fa2308378d69cfb099284f8953bbe995519","last_reissued_at":"2026-07-05T04:20:57.808967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:57.808967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data -- what, why and how?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Carsten Maple, Florimond Houssiau, Giovanni Cherubin, James Jordon, Lukasz Szpruch, Mirko Bottarelli, Samuel N. Cohen","submitted_at":"2022-05-06T14:27:45Z","abstract_excerpt":"This explainer document aims to provide an overview of the current state of the rapidly expanding work on synthetic data technologies, with a particular focus on privacy. The article is intended for a non-technical audience, though some formal definitions have been given to provide clarity to specialists. This article is intended to enable the reader to quickly become familiar with the notion of synthetic data, as well as understand some of the subtle intricacies that come with it. We do believe that synthetic data is a very useful tool, and our hope is that this report highlights that, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03257","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/2205.03257/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":"2205.03257","created_at":"2026-07-05T04:20:57.809026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03257v1","created_at":"2026-07-05T04:20:57.809026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03257","created_at":"2026-07-05T04:20:57.809026+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACRGCXYRB7D2","created_at":"2026-07-05T04:20:57.809026+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACRGCXYRB7D2C34G","created_at":"2026-07-05T04:20:57.809026+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACRGCXYR","created_at":"2026-07-05T04:20:57.809026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"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":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08372","citing_title":"SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14686","citing_title":"ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24703","citing_title":"TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27113","citing_title":"High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00282","citing_title":"Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31489","citing_title":"Context-Conditioned Generative Models Enable Subnational Refinement of Sparse Humanitarian Surveys","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23492","citing_title":"Continuous Hidden Markov Models for Equity Returns: Heavy-Tail Emission Families and Regime-Conditional Value-at-Risk","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01793","citing_title":"Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation","ref_index":23,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17528","citing_title":"CasualSynth: Generating Structurally Sound Synthetic Data","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03294","citing_title":"A Comprehensive Guide to Differential Privacy: From Theory to User Expectations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17421","citing_title":"Diffusion Models as Dataset Distillation Priors","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01444","citing_title":"Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18352","citing_title":"Tight Auditing of Differential Privacy in MST and AIM","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI","json":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI.json","graph_json":"https://pith.science/api/pith-number/ACRGCXYRB7D2C34GFMCR7DY7UI/graph.json","events_json":"https://pith.science/api/pith-number/ACRGCXYRB7D2C34GFMCR7DY7UI/events.json","paper":"https://pith.science/paper/ACRGCXYR"},"agent_actions":{"view_html":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI","download_json":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI.json","view_paper":"https://pith.science/paper/ACRGCXYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03257&json=true","fetch_graph":"https://pith.science/api/pith-number/ACRGCXYRB7D2C34GFMCR7DY7UI/graph.json","fetch_events":"https://pith.science/api/pith-number/ACRGCXYRB7D2C34GFMCR7DY7UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI/action/storage_attestation","attest_author":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI/action/author_attestation","sign_citation":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI/action/citation_signature","submit_replication":"https://pith.science/pith/ACRGCXYRB7D2C34GFMCR7DY7UI/action/replication_record"}},"created_at":"2026-07-05T04:20:57.809026+00:00","updated_at":"2026-07-05T04:20:57.809026+00:00"}