{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2009:YRYIC6A36RNAGKPYKZHXNVHHOF","short_pith_number":"pith:YRYIC6A3","canonical_record":{"source":{"id":"0912.0071","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-01T04:35:44Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DB"],"title_canon_sha256":"48eddf809786ac5081370a946ed32c46b9c40ff16f96409631be7060978165df","abstract_canon_sha256":"cf8df58e9d2a735d75424e525fa68344c7bc8357e6fcc62044a92469be3a787a"},"schema_version":"1.0"},"canonical_sha256":"c47081781bf45a0329f8564f76d4e77165a5304bbbb77fb02e349505f6a981bc","source":{"kind":"arxiv","id":"0912.0071","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0912.0071","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"0912.0071v5","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0912.0071","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"YRYIC6A36RNA","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_16","alias_value":"YRYIC6A36RNAGKPY","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_8","alias_value":"YRYIC6A3","created_at":"2026-05-18T12:26:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2009:YRYIC6A36RNAGKPYKZHXNVHHOF","target":"record","payload":{"canonical_record":{"source":{"id":"0912.0071","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-01T04:35:44Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DB"],"title_canon_sha256":"48eddf809786ac5081370a946ed32c46b9c40ff16f96409631be7060978165df","abstract_canon_sha256":"cf8df58e9d2a735d75424e525fa68344c7bc8357e6fcc62044a92469be3a787a"},"schema_version":"1.0"},"canonical_sha256":"c47081781bf45a0329f8564f76d4e77165a5304bbbb77fb02e349505f6a981bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:28:30.072189Z","signature_b64":"wKMoscd6id6gNT3xCt2ZPu25DoiMOi9yi+woc2YkTEvqvSUFEzZ51pn1YA52Hh4NtGmkZ2vqJo3UdPNKHJ8pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c47081781bf45a0329f8564f76d4e77165a5304bbbb77fb02e349505f6a981bc","last_reissued_at":"2026-05-18T04:28:30.071757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:28:30.071757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"0912.0071","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Plc2qcpgDmVHO8KU7htC01xRwWEvOI+Kl6UYCCCkiPZs93xOKJehdyWe+PBg8j2pGY780QZEx6h3GF1QeeScCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:26:50.967538Z"},"content_sha256":"bba00db689a4588942a2d8de0ef99a2fffd13c6a5dd08e5d07ba56d34a902f40","schema_version":"1.0","event_id":"sha256:bba00db689a4588942a2d8de0ef99a2fffd13c6a5dd08e5d07ba56d34a902f40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2009:YRYIC6A36RNAGKPYKZHXNVHHOF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentially Private Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DB"],"primary_cat":"cs.LG","authors_text":"Anand D. Sarwate, Claire Monteleoni, Kamalika Chaudhuri","submitted_at":"2009-12-01T04:35:44Z","abstract_excerpt":"Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the $\\epsilon$-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0912.0071","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOrHyi2BQHqWHTwBWgz2GugUqnyG65Ko9Q3ziTsP+DG8n6sAImXhDr0a15VLzODghhswMvlrFhUmxMaHrLNXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:26:50.967898Z"},"content_sha256":"90ba263ff0ecea34175077b56ef827b8d134feaa27c293bd8bb43df84ff1a60f","schema_version":"1.0","event_id":"sha256:90ba263ff0ecea34175077b56ef827b8d134feaa27c293bd8bb43df84ff1a60f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/bundle.json","state_url":"https://pith.science/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:26:50Z","links":{"resolver":"https://pith.science/pith/YRYIC6A36RNAGKPYKZHXNVHHOF","bundle":"https://pith.science/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/bundle.json","state":"https://pith.science/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRYIC6A36RNAGKPYKZHXNVHHOF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:YRYIC6A36RNAGKPYKZHXNVHHOF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cf8df58e9d2a735d75424e525fa68344c7bc8357e6fcc62044a92469be3a787a","cross_cats_sorted":["cs.AI","cs.CR","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-01T04:35:44Z","title_canon_sha256":"48eddf809786ac5081370a946ed32c46b9c40ff16f96409631be7060978165df"},"schema_version":"1.0","source":{"id":"0912.0071","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0912.0071","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"0912.0071v5","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0912.0071","created_at":"2026-05-18T04:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"YRYIC6A36RNA","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_16","alias_value":"YRYIC6A36RNAGKPY","created_at":"2026-05-18T12:26:02Z"},{"alias_kind":"pith_short_8","alias_value":"YRYIC6A3","created_at":"2026-05-18T12:26:02Z"}],"graph_snapshots":[{"event_id":"sha256:90ba263ff0ecea34175077b56ef827b8d134feaa27c293bd8bb43df84ff1a60f","target":"graph","created_at":"2026-05-18T04:28:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the $\\epsilon$-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving","authors_text":"Anand D. Sarwate, Claire Monteleoni, Kamalika Chaudhuri","cross_cats":["cs.AI","cs.CR","cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-01T04:35:44Z","title":"Differentially Private Empirical Risk Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0912.0071","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bba00db689a4588942a2d8de0ef99a2fffd13c6a5dd08e5d07ba56d34a902f40","target":"record","created_at":"2026-05-18T04:28:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cf8df58e9d2a735d75424e525fa68344c7bc8357e6fcc62044a92469be3a787a","cross_cats_sorted":["cs.AI","cs.CR","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-12-01T04:35:44Z","title_canon_sha256":"48eddf809786ac5081370a946ed32c46b9c40ff16f96409631be7060978165df"},"schema_version":"1.0","source":{"id":"0912.0071","kind":"arxiv","version":5}},"canonical_sha256":"c47081781bf45a0329f8564f76d4e77165a5304bbbb77fb02e349505f6a981bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c47081781bf45a0329f8564f76d4e77165a5304bbbb77fb02e349505f6a981bc","first_computed_at":"2026-05-18T04:28:30.071757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:28:30.071757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wKMoscd6id6gNT3xCt2ZPu25DoiMOi9yi+woc2YkTEvqvSUFEzZ51pn1YA52Hh4NtGmkZ2vqJo3UdPNKHJ8pAA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:28:30.072189Z","signed_message":"canonical_sha256_bytes"},"source_id":"0912.0071","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bba00db689a4588942a2d8de0ef99a2fffd13c6a5dd08e5d07ba56d34a902f40","sha256:90ba263ff0ecea34175077b56ef827b8d134feaa27c293bd8bb43df84ff1a60f"],"state_sha256":"9b01f968a4aad76cf5b57397301116a7a55e202623ee5e65176ce75e5aed3ca4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sl3Xk70m+0Klg1DNTw0DOU0OHz+owxhqqSfCFE9kI5Q6jGtn+e9LcBzhZBffDGaSL9xKIebHQHJ7RmDE2pVACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:26:50.970299Z","bundle_sha256":"fcf671b4b2eb0acaffad4c3c96dbeae1091e416df773826a7b2fbe4ecf1c708c"}}