{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SJ3XNJUL4VZBHZFGX74ZFU5PFD","short_pith_number":"pith:SJ3XNJUL","schema_version":"1.0","canonical_sha256":"927776a68be57213e4a6bff992d3af28fb82c9f4f228e1112cc5d03e264801f2","source":{"kind":"arxiv","id":"2505.01524","version":1},"attestation_state":"computed","paper":{"title":"The DCR Delusion: Measuring the Privacy Risk of Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Georgi Ganev, Nata\\v{s}a Kr\\v{c}o, Yves-Alexandre de Montjoye, Zexi Yao","submitted_at":"2025-05-02T18:21:14Z","abstract_excerpt":"Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks (MIAs) are widely considered the gold standard for empirically assessing the privacy of a synthetic dataset, practitioners and researchers often rely on simpler proxy metrics such as Distance to Closest Record (DCR). These metrics estimate privacy by measuring the similarity between the training data and generated synthetic data. This similarity is also compared against that between the training data and a disjoint holdout set of real records to const"},"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":"2505.01524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-02T18:21:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ffaca729ddfcb2618ba11ffc3fa0101ac4fc8724fd4d7b8ed4566aee65c33276","abstract_canon_sha256":"8af5ceb1323986be9c635cbfbe1bfd3a775aec87e0d7474e1a63de486d12ffa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:59.429991Z","signature_b64":"mPiXWYQKNAwpQhyGyoeYUiczkKHL5Kt2zyjR0Dhr5Mn7GzHpADToj6q2hPhaZ1o01sZ5DtvQYdWsJQbGNynUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"927776a68be57213e4a6bff992d3af28fb82c9f4f228e1112cc5d03e264801f2","last_reissued_at":"2026-07-05T10:57:59.429496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:59.429496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DCR Delusion: Measuring the Privacy Risk of Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Georgi Ganev, Nata\\v{s}a Kr\\v{c}o, Yves-Alexandre de Montjoye, Zexi Yao","submitted_at":"2025-05-02T18:21:14Z","abstract_excerpt":"Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks (MIAs) are widely considered the gold standard for empirically assessing the privacy of a synthetic dataset, practitioners and researchers often rely on simpler proxy metrics such as Distance to Closest Record (DCR). These metrics estimate privacy by measuring the similarity between the training data and generated synthetic data. This similarity is also compared against that between the training data and a disjoint holdout set of real records to const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01524","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/2505.01524/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":"2505.01524","created_at":"2026-07-05T10:57:59.429557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01524v1","created_at":"2026-07-05T10:57:59.429557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01524","created_at":"2026-07-05T10:57:59.429557+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJ3XNJUL4VZB","created_at":"2026-07-05T10:57:59.429557+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJ3XNJUL4VZBHZFG","created_at":"2026-07-05T10:57:59.429557+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJ3XNJUL","created_at":"2026-07-05T10:57:59.429557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08736","citing_title":"Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19653","citing_title":"A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD","json":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD.json","graph_json":"https://pith.science/api/pith-number/SJ3XNJUL4VZBHZFGX74ZFU5PFD/graph.json","events_json":"https://pith.science/api/pith-number/SJ3XNJUL4VZBHZFGX74ZFU5PFD/events.json","paper":"https://pith.science/paper/SJ3XNJUL"},"agent_actions":{"view_html":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD","download_json":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD.json","view_paper":"https://pith.science/paper/SJ3XNJUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01524&json=true","fetch_graph":"https://pith.science/api/pith-number/SJ3XNJUL4VZBHZFGX74ZFU5PFD/graph.json","fetch_events":"https://pith.science/api/pith-number/SJ3XNJUL4VZBHZFGX74ZFU5PFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD/action/storage_attestation","attest_author":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD/action/author_attestation","sign_citation":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD/action/citation_signature","submit_replication":"https://pith.science/pith/SJ3XNJUL4VZBHZFGX74ZFU5PFD/action/replication_record"}},"created_at":"2026-07-05T10:57:59.429557+00:00","updated_at":"2026-07-05T10:57:59.429557+00:00"}