{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:W63OAPRXLM4MTCTQI2NIHRWOTD","short_pith_number":"pith:W63OAPRX","schema_version":"1.0","canonical_sha256":"b7b6e03e375b38c98a70469a83c6ce98fd0e1406f4bce94a3774a4f992183117","source":{"kind":"arxiv","id":"1911.06679","version":2},"attestation_state":"computed","paper":{"title":"Generative Models for Effective ML on Private, Decentralized Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Blaise Aguera y Arcas, Daniel Ramage, H. Brendan McMahan, Mingqing Chen, Peter Kairouz, Rajiv Mathews, Sean Augenstein, Swaroop Ramaswamy","submitted_at":"2019-11-15T14:56:44Z","abstract_excerpt":"To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of misclassifications - is an essential tool in a) identifying and fixing problems in the data, b) generating new modeling hypotheses, and c) assigning or refining human-provided labels. However, manual data inspection is problematic for privacy sensitive datasets, such as those representing the behavior of real-world individuals. Furthermore, manual data inspection is"},"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":"1911.06679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-15T14:56:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d7eb4362db44a2361716c9d8a9733980439b8d8e383c3235240efcf3173ccc39","abstract_canon_sha256":"76ca9b61a0187ad205e4c6ce09da261c8e9f79d6a7fea6a2eba9a15bd51e5004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:34.823525Z","signature_b64":"iUSQAPlAyhhRjpSivqanbRzKbAWas1Zyf3Rphay7ZawmW/SzsOFJ10Ykm+6OgUmb4b4/2MuCyuT3SNnEqY2xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7b6e03e375b38c98a70469a83c6ce98fd0e1406f4bce94a3774a4f992183117","last_reissued_at":"2026-07-05T00:38:34.822987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:34.822987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Models for Effective ML on Private, Decentralized Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Blaise Aguera y Arcas, Daniel Ramage, H. Brendan McMahan, Mingqing Chen, Peter Kairouz, Rajiv Mathews, Sean Augenstein, Swaroop Ramaswamy","submitted_at":"2019-11-15T14:56:44Z","abstract_excerpt":"To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of misclassifications - is an essential tool in a) identifying and fixing problems in the data, b) generating new modeling hypotheses, and c) assigning or refining human-provided labels. However, manual data inspection is problematic for privacy sensitive datasets, such as those representing the behavior of real-world individuals. Furthermore, manual data inspection is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06679","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/1911.06679/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":"1911.06679","created_at":"2026-07-05T00:38:34.823050+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06679v2","created_at":"2026-07-05T00:38:34.823050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06679","created_at":"2026-07-05T00:38:34.823050+00:00"},{"alias_kind":"pith_short_12","alias_value":"W63OAPRXLM4M","created_at":"2026-07-05T00:38:34.823050+00:00"},{"alias_kind":"pith_short_16","alias_value":"W63OAPRXLM4MTCTQ","created_at":"2026-07-05T00:38:34.823050+00:00"},{"alias_kind":"pith_short_8","alias_value":"W63OAPRX","created_at":"2026-07-05T00:38:34.823050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.11563","citing_title":"A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD","json":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD.json","graph_json":"https://pith.science/api/pith-number/W63OAPRXLM4MTCTQI2NIHRWOTD/graph.json","events_json":"https://pith.science/api/pith-number/W63OAPRXLM4MTCTQI2NIHRWOTD/events.json","paper":"https://pith.science/paper/W63OAPRX"},"agent_actions":{"view_html":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD","download_json":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD.json","view_paper":"https://pith.science/paper/W63OAPRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06679&json=true","fetch_graph":"https://pith.science/api/pith-number/W63OAPRXLM4MTCTQI2NIHRWOTD/graph.json","fetch_events":"https://pith.science/api/pith-number/W63OAPRXLM4MTCTQI2NIHRWOTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD/action/storage_attestation","attest_author":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD/action/author_attestation","sign_citation":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD/action/citation_signature","submit_replication":"https://pith.science/pith/W63OAPRXLM4MTCTQI2NIHRWOTD/action/replication_record"}},"created_at":"2026-07-05T00:38:34.823050+00:00","updated_at":"2026-07-05T00:38:34.823050+00:00"}