{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WABINFF2GBRKAEDBMLALGJBME4","short_pith_number":"pith:WABINFF2","canonical_record":{"source":{"id":"1812.06210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T00:32:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"33b281ec263557859152ff2041fbb913c11af04a31f93bfc38822376f6398585","abstract_canon_sha256":"50271303064ad55bae22a65974090e146365a14d054917d2fbadd77d56dc2d94"},"schema_version":"1.0"},"canonical_sha256":"b0028694ba3062a0106162c0b3242c27348acf43e7a934f4f9c31a07d3a8525d","source":{"kind":"arxiv","id":"1812.06210","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06210","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06210v2","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06210","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"WABINFF2GBRK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WABINFF2GBRKAEDB","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WABINFF2","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WABINFF2GBRKAEDBMLALGJBME4","target":"record","payload":{"canonical_record":{"source":{"id":"1812.06210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T00:32:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"33b281ec263557859152ff2041fbb913c11af04a31f93bfc38822376f6398585","abstract_canon_sha256":"50271303064ad55bae22a65974090e146365a14d054917d2fbadd77d56dc2d94"},"schema_version":"1.0"},"canonical_sha256":"b0028694ba3062a0106162c0b3242c27348acf43e7a934f4f9c31a07d3a8525d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:09.263375Z","signature_b64":"OpJcXN0ftEwLdfa42C8bDJSuMhg0jL5jCkwyYcRwTY0RgC29Hgq6AWmkQitdc7i4W6mY+rDtRNcKl5OzFM2UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0028694ba3062a0106162c0b3242c27348acf43e7a934f4f9c31a07d3a8525d","last_reissued_at":"2026-05-17T23:52:09.262894Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:09.262894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.06210","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NV06ieQ2eb3+tzGTmr2UWmP34o/liA8F5tg/5Ld3Sc1NkFAKKaZ7xMDVk45LTo3kpL8dD2WRg0s5/ddB0+VBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:03:37.064270Z"},"content_sha256":"e04b8609baee1aeabac4cfa2b6c49a8582d55acfbd3c2b5ed23d0fe903e0efa4","schema_version":"1.0","event_id":"sha256:e04b8609baee1aeabac4cfa2b6c49a8582d55acfbd3c2b5ed23d0fe903e0efa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WABINFF2GBRKAEDBMLALGJBME4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A General Approach to Adding Differential Privacy to Iterative Training Procedures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Galen Andrew, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Peter Kairouz, Steve Chien, Ulfar Erlingsson","submitted_at":"2018-12-15T00:32:09Z","abstract_excerpt":"In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration strategies for the privacy mechanism, and then isolates and simplifies the critical logic that computes the final privacy guarantees. A key challenge is that training algorithms often require estimating many different quantities (vectors) from the same set of examples --- for example, gradients of different layers in a deep learning architecture, as well as metrics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06210","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":""},"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":"2026-05-17T23:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9kZ2FDKE48DuRrnbg6HpNkXZTNngDPRI+WX0JS/KADfCx1VRPaEJBmWWkHsPJ0neT6a0D8Qz6+w8D2j90pmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:03:37.064757Z"},"content_sha256":"5e71a3b907ac657a1088c5961fc5149113305257e374b7433c20dfe44fac27e7","schema_version":"1.0","event_id":"sha256:5e71a3b907ac657a1088c5961fc5149113305257e374b7433c20dfe44fac27e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WABINFF2GBRKAEDBMLALGJBME4/bundle.json","state_url":"https://pith.science/pith/WABINFF2GBRKAEDBMLALGJBME4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WABINFF2GBRKAEDBMLALGJBME4/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":"2026-05-26T18:03:37Z","links":{"resolver":"https://pith.science/pith/WABINFF2GBRKAEDBMLALGJBME4","bundle":"https://pith.science/pith/WABINFF2GBRKAEDBMLALGJBME4/bundle.json","state":"https://pith.science/pith/WABINFF2GBRKAEDBMLALGJBME4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WABINFF2GBRKAEDBMLALGJBME4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WABINFF2GBRKAEDBMLALGJBME4","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":"50271303064ad55bae22a65974090e146365a14d054917d2fbadd77d56dc2d94","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T00:32:09Z","title_canon_sha256":"33b281ec263557859152ff2041fbb913c11af04a31f93bfc38822376f6398585"},"schema_version":"1.0","source":{"id":"1812.06210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06210","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06210v2","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06210","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"WABINFF2GBRK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WABINFF2GBRKAEDB","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WABINFF2","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:5e71a3b907ac657a1088c5961fc5149113305257e374b7433c20dfe44fac27e7","target":"graph","created_at":"2026-05-17T23:52:09Z","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":"In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration strategies for the privacy mechanism, and then isolates and simplifies the critical logic that computes the final privacy guarantees. A key challenge is that training algorithms often require estimating many different quantities (vectors) from the same set of examples --- for example, gradients of different layers in a deep learning architecture, as well as metrics ","authors_text":"Galen Andrew, H. Brendan McMahan, Ilya Mironov, Nicolas Papernot, Peter Kairouz, Steve Chien, Ulfar Erlingsson","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T00:32:09Z","title":"A General Approach to Adding Differential Privacy to Iterative Training Procedures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06210","kind":"arxiv","version":2},"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:e04b8609baee1aeabac4cfa2b6c49a8582d55acfbd3c2b5ed23d0fe903e0efa4","target":"record","created_at":"2026-05-17T23:52:09Z","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":"50271303064ad55bae22a65974090e146365a14d054917d2fbadd77d56dc2d94","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T00:32:09Z","title_canon_sha256":"33b281ec263557859152ff2041fbb913c11af04a31f93bfc38822376f6398585"},"schema_version":"1.0","source":{"id":"1812.06210","kind":"arxiv","version":2}},"canonical_sha256":"b0028694ba3062a0106162c0b3242c27348acf43e7a934f4f9c31a07d3a8525d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0028694ba3062a0106162c0b3242c27348acf43e7a934f4f9c31a07d3a8525d","first_computed_at":"2026-05-17T23:52:09.262894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:09.262894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OpJcXN0ftEwLdfa42C8bDJSuMhg0jL5jCkwyYcRwTY0RgC29Hgq6AWmkQitdc7i4W6mY+rDtRNcKl5OzFM2UDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:09.263375Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.06210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e04b8609baee1aeabac4cfa2b6c49a8582d55acfbd3c2b5ed23d0fe903e0efa4","sha256:5e71a3b907ac657a1088c5961fc5149113305257e374b7433c20dfe44fac27e7"],"state_sha256":"d7129c27a75f2394d48efdcdf2df221eea60ccad6e5f645d63e5af34ed590bef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+zLYRyL0iFZ2I4VeHcGRTgQn4fPeYdfbABTroBQiNqWBeLNsCx50rE6thitcGLis/5DsPqKSmtBpY+iRI1/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:03:37.067771Z","bundle_sha256":"ccefa958890404932143d8c09d46aabb476c4924e75000bb77a1dbfc8f2f64cd"}}