{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HPLXTHVOV5VTHDJU52NBAYM7S5","short_pith_number":"pith:HPLXTHVO","schema_version":"1.0","canonical_sha256":"3bd7799eaeaf6b338d34ee9a10619f976bc772a551e59fc66a15b548f9de28b5","source":{"kind":"arxiv","id":"2011.07018","version":6},"attestation_state":"computed","paper":{"title":"Synthetic Data -- Anonymisation Groundhog Day","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bristena Oprisanu, Carmela Troncoso, Theresa Stadler","submitted_at":"2020-11-13T16:58:42Z","abstract_excerpt":"Synthetic data has been advertised as a silver-bullet solution to privacy-preserving data publishing that addresses the shortcomings of traditional anonymisation techniques. The promise is that synthetic data drawn from generative models preserves the statistical properties of the original dataset but, at the same time, provides perfect protection against privacy attacks. In this work, we present the first quantitative evaluation of the privacy gain of synthetic data publishing and compare it to that of previous anonymisation techniques.\n  Our evaluation of a wide range of state-of-the-art gen"},"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":"2011.07018","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T16:58:42Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"41f3793f2e065a1cc553fb89f238ee74df62b84f0ee804a0e44064dc87274e54","abstract_canon_sha256":"ab494bc0d31dcc6100406860869ea3e2ca123a41b1eddeb3604e08e81b91693f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:46.945126Z","signature_b64":"Gzp/KwUwhOLU0EP3spCtO256LEgcZh8bhlii4cvjdyFpbsGemATBCL6UMsTh+ZRbMkCJdACd3Qgp0eZKV+A5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd7799eaeaf6b338d34ee9a10619f976bc772a551e59fc66a15b548f9de28b5","last_reissued_at":"2026-07-05T03:50:46.944744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:46.944744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data -- Anonymisation Groundhog Day","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Bristena Oprisanu, Carmela Troncoso, Theresa Stadler","submitted_at":"2020-11-13T16:58:42Z","abstract_excerpt":"Synthetic data has been advertised as a silver-bullet solution to privacy-preserving data publishing that addresses the shortcomings of traditional anonymisation techniques. The promise is that synthetic data drawn from generative models preserves the statistical properties of the original dataset but, at the same time, provides perfect protection against privacy attacks. In this work, we present the first quantitative evaluation of the privacy gain of synthetic data publishing and compare it to that of previous anonymisation techniques.\n  Our evaluation of a wide range of state-of-the-art gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07018","kind":"arxiv","version":6},"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/2011.07018/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":"2011.07018","created_at":"2026-07-05T03:50:46.944799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07018v6","created_at":"2026-07-05T03:50:46.944799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07018","created_at":"2026-07-05T03:50:46.944799+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPLXTHVOV5VT","created_at":"2026-07-05T03:50:46.944799+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPLXTHVOV5VTHDJU","created_at":"2026-07-05T03:50:46.944799+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPLXTHVO","created_at":"2026-07-05T03:50:46.944799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.14205","citing_title":"Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5","json":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5.json","graph_json":"https://pith.science/api/pith-number/HPLXTHVOV5VTHDJU52NBAYM7S5/graph.json","events_json":"https://pith.science/api/pith-number/HPLXTHVOV5VTHDJU52NBAYM7S5/events.json","paper":"https://pith.science/paper/HPLXTHVO"},"agent_actions":{"view_html":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5","download_json":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5.json","view_paper":"https://pith.science/paper/HPLXTHVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07018&json=true","fetch_graph":"https://pith.science/api/pith-number/HPLXTHVOV5VTHDJU52NBAYM7S5/graph.json","fetch_events":"https://pith.science/api/pith-number/HPLXTHVOV5VTHDJU52NBAYM7S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5/action/storage_attestation","attest_author":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5/action/author_attestation","sign_citation":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5/action/citation_signature","submit_replication":"https://pith.science/pith/HPLXTHVOV5VTHDJU52NBAYM7S5/action/replication_record"}},"created_at":"2026-07-05T03:50:46.944799+00:00","updated_at":"2026-07-05T03:50:46.944799+00:00"}