{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UCLKJZOC7EOCG3N26Y3KT46IYR","short_pith_number":"pith:UCLKJZOC","canonical_record":{"source":{"id":"1805.00216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-05-01T07:20:46Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"2114e0420f4cbd6721dd03afe150437413e260a5a2ca096a6560dd15988f40af","abstract_canon_sha256":"4f7ea033a98ef194e7699236534df22992ee762aaa951b3472ce0bf3aa435ade"},"schema_version":"1.0"},"canonical_sha256":"a096a4e5c2f91c236dbaf636a9f3c8c452251d290cc96a21805937c920eb8067","source":{"kind":"arxiv","id":"1805.00216","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00216","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00216v3","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00216","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"UCLKJZOC7EOC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UCLKJZOC7EOCG3N2","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UCLKJZOC","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UCLKJZOC7EOCG3N26Y3KT46IYR","target":"record","payload":{"canonical_record":{"source":{"id":"1805.00216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-05-01T07:20:46Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"2114e0420f4cbd6721dd03afe150437413e260a5a2ca096a6560dd15988f40af","abstract_canon_sha256":"4f7ea033a98ef194e7699236534df22992ee762aaa951b3472ce0bf3aa435ade"},"schema_version":"1.0"},"canonical_sha256":"a096a4e5c2f91c236dbaf636a9f3c8c452251d290cc96a21805937c920eb8067","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:43.319841Z","signature_b64":"MdHWYncN6cBOS37vkcZHdLSnZ7Wg1VJaUKjm5TC5j/joYEdZ3sigJJOArTkTJACQj7kGv2+9j4ULPahBtPzIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a096a4e5c2f91c236dbaf636a9f3c8c452251d290cc96a21805937c920eb8067","last_reissued_at":"2026-05-17T23:44:43.319345Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:43.319345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.00216","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwCyKoYpnJ1glV+QEpJB1r2P0H7Q4erbBpzA5KMNFpOvj6xsMJyJ/ZCNHRigeAEnO85DWILDIEldAjriJIvpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:59:12.987401Z"},"content_sha256":"74a5ce904c7812776d04bde6e78e8c4c32cf6428b89ad80b11c60c0a41693e96","schema_version":"1.0","event_id":"sha256:74a5ce904c7812776d04bde6e78e8c4c32cf6428b89ad80b11c60c0a41693e96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UCLKJZOC7EOCG3N26Y3KT46IYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Privately Learning High-Dimensional Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Gautam Kamath, Jerry Li, Jonathan Ullman, Vikrant Singhal","submitted_at":"2018-05-01T07:20:46Z","abstract_excerpt":"We present novel, computationally efficient, and differentially private algorithms for two fundamental high-dimensional learning problems: learning a multivariate Gaussian and learning a product distribution over the Boolean hypercube in total variation distance. The sample complexity of our algorithms nearly matches the sample complexity of the optimal non-private learners for these tasks in a wide range of parameters, showing that privacy comes essentially for free for these problems. In particular, in contrast to previous approaches, our algorithm for learning Gaussians does not require str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00216","kind":"arxiv","version":3},"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":"2026-05-17T23:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZQpbD/3uvMb+XWJwDJRMp/bd6Jy/MWFsf7HHpOIL5ZYzQL+BemmVrXDeXxo4s2Rsuurez/AdQIxMmD46u3TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:59:12.988064Z"},"content_sha256":"23ac9282bb575acab2c306f47309ef2b88a4ae711b8372cdbe9c39f44675de2b","schema_version":"1.0","event_id":"sha256:23ac9282bb575acab2c306f47309ef2b88a4ae711b8372cdbe9c39f44675de2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/bundle.json","state_url":"https://pith.science/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/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":"2026-05-26T09:59:12Z","links":{"resolver":"https://pith.science/pith/UCLKJZOC7EOCG3N26Y3KT46IYR","bundle":"https://pith.science/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/bundle.json","state":"https://pith.science/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UCLKJZOC7EOCG3N26Y3KT46IYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UCLKJZOC7EOCG3N26Y3KT46IYR","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":"4f7ea033a98ef194e7699236534df22992ee762aaa951b3472ce0bf3aa435ade","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-05-01T07:20:46Z","title_canon_sha256":"2114e0420f4cbd6721dd03afe150437413e260a5a2ca096a6560dd15988f40af"},"schema_version":"1.0","source":{"id":"1805.00216","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00216","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00216v3","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00216","created_at":"2026-05-17T23:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"UCLKJZOC7EOC","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UCLKJZOC7EOCG3N2","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UCLKJZOC","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:23ac9282bb575acab2c306f47309ef2b88a4ae711b8372cdbe9c39f44675de2b","target":"graph","created_at":"2026-05-17T23:44:43Z","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":"We present novel, computationally efficient, and differentially private algorithms for two fundamental high-dimensional learning problems: learning a multivariate Gaussian and learning a product distribution over the Boolean hypercube in total variation distance. The sample complexity of our algorithms nearly matches the sample complexity of the optimal non-private learners for these tasks in a wide range of parameters, showing that privacy comes essentially for free for these problems. In particular, in contrast to previous approaches, our algorithm for learning Gaussians does not require str","authors_text":"Gautam Kamath, Jerry Li, Jonathan Ullman, Vikrant Singhal","cross_cats":["cs.CR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-05-01T07:20:46Z","title":"Privately Learning High-Dimensional Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00216","kind":"arxiv","version":3},"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":"sha256:74a5ce904c7812776d04bde6e78e8c4c32cf6428b89ad80b11c60c0a41693e96","target":"record","created_at":"2026-05-17T23:44:43Z","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":"4f7ea033a98ef194e7699236534df22992ee762aaa951b3472ce0bf3aa435ade","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-05-01T07:20:46Z","title_canon_sha256":"2114e0420f4cbd6721dd03afe150437413e260a5a2ca096a6560dd15988f40af"},"schema_version":"1.0","source":{"id":"1805.00216","kind":"arxiv","version":3}},"canonical_sha256":"a096a4e5c2f91c236dbaf636a9f3c8c452251d290cc96a21805937c920eb8067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a096a4e5c2f91c236dbaf636a9f3c8c452251d290cc96a21805937c920eb8067","first_computed_at":"2026-05-17T23:44:43.319345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:43.319345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MdHWYncN6cBOS37vkcZHdLSnZ7Wg1VJaUKjm5TC5j/joYEdZ3sigJJOArTkTJACQj7kGv2+9j4ULPahBtPzIAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:43.319841Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.00216","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74a5ce904c7812776d04bde6e78e8c4c32cf6428b89ad80b11c60c0a41693e96","sha256:23ac9282bb575acab2c306f47309ef2b88a4ae711b8372cdbe9c39f44675de2b"],"state_sha256":"e63f6b0a3e230b6847521af6289bf8cf5a19361179490a04e740663b6967007f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jcN0KYUN5NAXVSobbDzW3foiR1gF2vTA0wWi4HAR0xw6FTHbkC8st31oG1o/MH+T5EbCG5ImfFPAQ6ZTBPUkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T09:59:12.991675Z","bundle_sha256":"02c1239e9ae3d974fafde9516c84e0ae00de1fe76f8602c508ca96d90669bfc3"}}