{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HN3PCF3DRAO4FB52VPAI6UIVPC","short_pith_number":"pith:HN3PCF3D","schema_version":"1.0","canonical_sha256":"3b76f11763881dc287baabc08f511578859a79b0e43383c1bf6a33ba4712fd73","source":{"kind":"arxiv","id":"2411.12451","version":1},"attestation_state":"computed","paper":{"title":"Empirical Privacy Evaluations of Generative and Predictive Machine Learning Models -- A review and challenges for practice","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Sun, Flavio Hafner","submitted_at":"2024-11-19T12:19:28Z","abstract_excerpt":"Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to empirically assess the privacy risks associated with the generated synthetic data before deploying generative technologies. This paper outlines the key concepts and assumptions underlying empirical privacy evaluation in machine learning-based generative and predictive models. Then, this paper explores the practical challenges for privacy evaluations of genera"},"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":"2411.12451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T12:19:28Z","cross_cats_sorted":[],"title_canon_sha256":"fb7afec9fa812e7f193449b73e1c826c482d20e0e87ca6a4729fed6175a90f3e","abstract_canon_sha256":"1bf33a9fa96a5c8d794eb4e4b3a4ad92d7110a3f18e078ea92696d3db5aa370d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:21.967248Z","signature_b64":"7wnar+bL+uf7OQnT9L7dXNZZg07MooGAR34wOwSA28igxHsJpj6vr1sMkZxxD38Ipm2MsBJZ0oCIleGhwsslDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b76f11763881dc287baabc08f511578859a79b0e43383c1bf6a33ba4712fd73","last_reissued_at":"2026-07-05T09:37:21.966768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:21.966768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Privacy Evaluations of Generative and Predictive Machine Learning Models -- A review and challenges for practice","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Sun, Flavio Hafner","submitted_at":"2024-11-19T12:19:28Z","abstract_excerpt":"Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to empirically assess the privacy risks associated with the generated synthetic data before deploying generative technologies. This paper outlines the key concepts and assumptions underlying empirical privacy evaluation in machine learning-based generative and predictive models. Then, this paper explores the practical challenges for privacy evaluations of genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12451","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/2411.12451/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":"2411.12451","created_at":"2026-07-05T09:37:21.966833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12451v1","created_at":"2026-07-05T09:37:21.966833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12451","created_at":"2026-07-05T09:37:21.966833+00:00"},{"alias_kind":"pith_short_12","alias_value":"HN3PCF3DRAO4","created_at":"2026-07-05T09:37:21.966833+00:00"},{"alias_kind":"pith_short_16","alias_value":"HN3PCF3DRAO4FB52","created_at":"2026-07-05T09:37:21.966833+00:00"},{"alias_kind":"pith_short_8","alias_value":"HN3PCF3D","created_at":"2026-07-05T09:37:21.966833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09809","citing_title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC","json":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC.json","graph_json":"https://pith.science/api/pith-number/HN3PCF3DRAO4FB52VPAI6UIVPC/graph.json","events_json":"https://pith.science/api/pith-number/HN3PCF3DRAO4FB52VPAI6UIVPC/events.json","paper":"https://pith.science/paper/HN3PCF3D"},"agent_actions":{"view_html":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC","download_json":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC.json","view_paper":"https://pith.science/paper/HN3PCF3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12451&json=true","fetch_graph":"https://pith.science/api/pith-number/HN3PCF3DRAO4FB52VPAI6UIVPC/graph.json","fetch_events":"https://pith.science/api/pith-number/HN3PCF3DRAO4FB52VPAI6UIVPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC/action/storage_attestation","attest_author":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC/action/author_attestation","sign_citation":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC/action/citation_signature","submit_replication":"https://pith.science/pith/HN3PCF3DRAO4FB52VPAI6UIVPC/action/replication_record"}},"created_at":"2026-07-05T09:37:21.966833+00:00","updated_at":"2026-07-05T09:37:21.966833+00:00"}