{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R4UO3L5XJOP7MSYMJNNLSKOA4F","short_pith_number":"pith:R4UO3L5X","schema_version":"1.0","canonical_sha256":"8f28edafb74b9ff64b0c4b5ab929c0e14b8a5bce4e3f6490cba38ad1116ee1d9","source":{"kind":"arxiv","id":"2606.16952","version":2},"attestation_state":"computed","paper":{"title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.AP","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adel Javanmard, Alessandro Epasto, Dennis Kraft, Kareem Amin, M\\'onica Ribero, Rudrajit Das, Sergei Vassilvitskii","submitted_at":"2026-06-15T16:54:02Z","abstract_excerpt":"The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information from the training corpus. In this work, we present a customizable empirical auditing framework designed to detect and explain such data disclosures. Our framework introduces a mechanism to distinguish between \"true disclosures\"-where the system directly reproduces a user's information-and \"phantom "},"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":"2606.16952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T16:54:02Z","cross_cats_sorted":["cs.AI","stat.AP","stat.ME","stat.ML"],"title_canon_sha256":"4f5559cb17b326ce6cb910488e0fc33f2ca777161cb6cb39c9d274cbdc745944","abstract_canon_sha256":"0464d4919679f28952a27ebd96d2db121173b0c771153893e69daa0334062944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:35.830165Z","signature_b64":"i5MGwM6nOiQdmHlyovqxzPobhnbraGnctqjMr4ark9SCMzkGP4MHsVRR3qiOYyIyR3skakgy6W37tRT9T/evBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f28edafb74b9ff64b0c4b5ab929c0e14b8a5bce4e3f6490cba38ad1116ee1d9","last_reissued_at":"2026-07-22T00:22:35.829277Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:35.829277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.AP","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adel Javanmard, Alessandro Epasto, Dennis Kraft, Kareem Amin, M\\'onica Ribero, Rudrajit Das, Sergei Vassilvitskii","submitted_at":"2026-06-15T16:54:02Z","abstract_excerpt":"The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information from the training corpus. In this work, we present a customizable empirical auditing framework designed to detect and explain such data disclosures. Our framework introduces a mechanism to distinguish between \"true disclosures\"-where the system directly reproduces a user's information-and \"phantom "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16952","kind":"arxiv","version":2},"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/2606.16952/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":"2606.16952","created_at":"2026-07-22T00:22:35.829718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.16952v2","created_at":"2026-07-22T00:22:35.829718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16952","created_at":"2026-07-22T00:22:35.829718+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4UO3L5XJOP7","created_at":"2026-07-22T00:22:35.829718+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4UO3L5XJOP7MSYM","created_at":"2026-07-22T00:22:35.829718+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4UO3L5X","created_at":"2026-07-22T00:22:35.829718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F","json":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F.json","graph_json":"https://pith.science/api/pith-number/R4UO3L5XJOP7MSYMJNNLSKOA4F/graph.json","events_json":"https://pith.science/api/pith-number/R4UO3L5XJOP7MSYMJNNLSKOA4F/events.json","paper":"https://pith.science/paper/R4UO3L5X"},"agent_actions":{"view_html":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F","download_json":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F.json","view_paper":"https://pith.science/paper/R4UO3L5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.16952&json=true","fetch_graph":"https://pith.science/api/pith-number/R4UO3L5XJOP7MSYMJNNLSKOA4F/graph.json","fetch_events":"https://pith.science/api/pith-number/R4UO3L5XJOP7MSYMJNNLSKOA4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F/action/storage_attestation","attest_author":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F/action/author_attestation","sign_citation":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F/action/citation_signature","submit_replication":"https://pith.science/pith/R4UO3L5XJOP7MSYMJNNLSKOA4F/action/replication_record"}},"created_at":"2026-07-22T00:22:35.829718+00:00","updated_at":"2026-07-22T00:22:35.829718+00:00"}