{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KPLV5II2GFDIJGEMR2IC24TXJJ","short_pith_number":"pith:KPLV5II2","schema_version":"1.0","canonical_sha256":"53d75ea11a314684988c8e902d72774a5c034a50acf5704bae40947706a80718","source":{"kind":"arxiv","id":"2301.07573","version":1},"attestation_state":"computed","paper":{"title":"Synthcity: facilitating innovative use cases of synthetic data in different data modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bogdan-Constantin Cebere, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-01-18T14:49:54Z","abstract_excerpt":"Synthcity is an open-source software package for innovative use cases of synthetic data in ML fairness, privacy and augmentation across diverse tabular data modalities, including static data, regular and irregular time series, data with censoring, multi-source data, composite data, and more. Synthcity provides the practitioners with a single access point to cutting edge research and tools in synthetic data. It also offers the community a playground for rapid experimentation and prototyping, a one-stop-shop for SOTA benchmarks, and an opportunity for extending research impact. The library can b"},"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":"2301.07573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T14:49:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e57024e7cc1104b61905299bd3ad1a9f5d482234191e604f32914bcf29b44bb","abstract_canon_sha256":"c79e4c1e9b4ea5bab1adee358396d8656ae68d368012e089cb631d97da47b431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:10.618414Z","signature_b64":"GBEzrMioeuOn5jYa/9cD/fmmJT4MDHkmCgYlY0XJpD0qCyfPEq8yzFiZhcMU9ZSEhmWjuSpwRBDbr35eVQGQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53d75ea11a314684988c8e902d72774a5c034a50acf5704bae40947706a80718","last_reissued_at":"2026-07-05T05:34:10.617928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:10.617928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthcity: facilitating innovative use cases of synthetic data in different data modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bogdan-Constantin Cebere, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-01-18T14:49:54Z","abstract_excerpt":"Synthcity is an open-source software package for innovative use cases of synthetic data in ML fairness, privacy and augmentation across diverse tabular data modalities, including static data, regular and irregular time series, data with censoring, multi-source data, composite data, and more. Synthcity provides the practitioners with a single access point to cutting edge research and tools in synthetic data. It also offers the community a playground for rapid experimentation and prototyping, a one-stop-shop for SOTA benchmarks, and an opportunity for extending research impact. The library can b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07573","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/2301.07573/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":"2301.07573","created_at":"2026-07-05T05:34:10.617987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07573v1","created_at":"2026-07-05T05:34:10.617987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07573","created_at":"2026-07-05T05:34:10.617987+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPLV5II2GFDI","created_at":"2026-07-05T05:34:10.617987+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPLV5II2GFDIJGEM","created_at":"2026-07-05T05:34:10.617987+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPLV5II2","created_at":"2026-07-05T05:34:10.617987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14686","citing_title":"ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators","ref_index":39,"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":47,"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":44,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02947","citing_title":"Quality Degradation Attack in Synthetic Data","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17804","citing_title":"GenTS: A Comprehensive Benchmark Library for Generative Time Series Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08875","citing_title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ","json":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ.json","graph_json":"https://pith.science/api/pith-number/KPLV5II2GFDIJGEMR2IC24TXJJ/graph.json","events_json":"https://pith.science/api/pith-number/KPLV5II2GFDIJGEMR2IC24TXJJ/events.json","paper":"https://pith.science/paper/KPLV5II2"},"agent_actions":{"view_html":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ","download_json":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ.json","view_paper":"https://pith.science/paper/KPLV5II2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07573&json=true","fetch_graph":"https://pith.science/api/pith-number/KPLV5II2GFDIJGEMR2IC24TXJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KPLV5II2GFDIJGEMR2IC24TXJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ/action/storage_attestation","attest_author":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ/action/author_attestation","sign_citation":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ/action/citation_signature","submit_replication":"https://pith.science/pith/KPLV5II2GFDIJGEMR2IC24TXJJ/action/replication_record"}},"created_at":"2026-07-05T05:34:10.617987+00:00","updated_at":"2026-07-05T05:34:10.617987+00:00"}