{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HOTAUMWGE5I6SHX46TVR4QR4SH","short_pith_number":"pith:HOTAUMWG","schema_version":"1.0","canonical_sha256":"3ba60a32c62751e91efcf4eb1e423c91c8a5c32812395476c583f90bfe262d04","source":{"kind":"arxiv","id":"2606.09582","version":1},"attestation_state":"computed","paper":{"title":"On Choosing the $\\mu$ Parameter in Gaussian Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antti Honkela, Bogdan Kulynych","submitted_at":"2026-06-08T14:56:07Z","abstract_excerpt":"Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide principled mappings from pure-DP $\\varepsilon$ to GDP $\\mu$ by matching the worst-case success of a strong-adversary membership inference attack in terms of three metrics: multiplicative advantage at fixed FPR, precision at fixed recall, and the standard privacy profile. We tabulate $\\mu$ values across a useful range of parameters and recommend $\\mu \\approx \\varepsilon/5$ as a conservative general-purpose conversion."},"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":"2606.09582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T14:56:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"95c9edd839f1635646eac1e70be6fcabd465b2fb070e3d02660c335b035c2f6c","abstract_canon_sha256":"5b79580ca815a9072803820d74a5adad594ae9efab34d72e2ea71e771b00b5cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:57.314281Z","signature_b64":"GSIYjGq+VIoWsABUvfOyBHKjTBcKU5/yTq2tRJ8lBUNyRQM12R8Mxa9QfL4pnT9+anREXkteyNIzuhpDimawDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba60a32c62751e91efcf4eb1e423c91c8a5c32812395476c583f90bfe262d04","last_reissued_at":"2026-06-09T02:08:57.313416Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:57.313416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Choosing the $\\mu$ Parameter in Gaussian Differential Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antti Honkela, Bogdan Kulynych","submitted_at":"2026-06-08T14:56:07Z","abstract_excerpt":"Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide principled mappings from pure-DP $\\varepsilon$ to GDP $\\mu$ by matching the worst-case success of a strong-adversary membership inference attack in terms of three metrics: multiplicative advantage at fixed FPR, precision at fixed recall, and the standard privacy profile. We tabulate $\\mu$ values across a useful range of parameters and recommend $\\mu \\approx \\varepsilon/5$ as a conservative general-purpose conversion."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09582","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/2606.09582/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":"2606.09582","created_at":"2026-06-09T02:08:57.313568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09582v1","created_at":"2026-06-09T02:08:57.313568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09582","created_at":"2026-06-09T02:08:57.313568+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOTAUMWGE5I6","created_at":"2026-06-09T02:08:57.313568+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOTAUMWGE5I6SHX4","created_at":"2026-06-09T02:08:57.313568+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOTAUMWG","created_at":"2026-06-09T02:08:57.313568+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/HOTAUMWGE5I6SHX46TVR4QR4SH","json":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH.json","graph_json":"https://pith.science/api/pith-number/HOTAUMWGE5I6SHX46TVR4QR4SH/graph.json","events_json":"https://pith.science/api/pith-number/HOTAUMWGE5I6SHX46TVR4QR4SH/events.json","paper":"https://pith.science/paper/HOTAUMWG"},"agent_actions":{"view_html":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH","download_json":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH.json","view_paper":"https://pith.science/paper/HOTAUMWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09582&json=true","fetch_graph":"https://pith.science/api/pith-number/HOTAUMWGE5I6SHX46TVR4QR4SH/graph.json","fetch_events":"https://pith.science/api/pith-number/HOTAUMWGE5I6SHX46TVR4QR4SH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH/action/storage_attestation","attest_author":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH/action/author_attestation","sign_citation":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH/action/citation_signature","submit_replication":"https://pith.science/pith/HOTAUMWGE5I6SHX46TVR4QR4SH/action/replication_record"}},"created_at":"2026-06-09T02:08:57.313568+00:00","updated_at":"2026-06-09T02:08:57.313568+00:00"}