{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MI67GDQ3PL7GNKGB4NTLXTU6O3","short_pith_number":"pith:MI67GDQ3","schema_version":"1.0","canonical_sha256":"623df30e1b7afe66a8c1e366bbce9e76dad2712edeb728a6a0ebfbdeb673e2f4","source":{"kind":"arxiv","id":"1906.01167","version":3},"attestation_state":"computed","paper":{"title":"Towards Fair and Privacy-Preserving Federated Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Han Yu, Jiangshan Yu, Jiong Jin, Karthik Nandakumar, Kee Siong Ng, Lingjuan Lyu, Xingjun Ma, Yitong Li","submitted_at":"2019-06-04T02:43:42Z","abstract_excerpt":"The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of parti"},"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":"1906.01167","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2019-06-04T02:43:42Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"4968da6e1907f43a0343a91fa561a00833719582896476db260fc8df3ffb399e","abstract_canon_sha256":"a46fd8b01986e22990f1bc876dece63da14868416c4fad35746244caadad4926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:39.839970Z","signature_b64":"bSZHKbk8SF1bg8Dr2PGzaA9S0mnbRltsTMbTxsSkvRU88u+Nt9AKujNawVjPZQWUhQg/CymAmCeS64ItWKiRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623df30e1b7afe66a8c1e366bbce9e76dad2712edeb728a6a0ebfbdeb673e2f4","last_reissued_at":"2026-07-05T01:03:39.839486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:39.839486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fair and Privacy-Preserving Federated Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Han Yu, Jiangshan Yu, Jiong Jin, Karthik Nandakumar, Kee Siong Ng, Lingjuan Lyu, Xingjun Ma, Yitong Li","submitted_at":"2019-06-04T02:43:42Z","abstract_excerpt":"The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01167","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.01167/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":"1906.01167","created_at":"2026-07-05T01:03:39.839544+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01167v3","created_at":"2026-07-05T01:03:39.839544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01167","created_at":"2026-07-05T01:03:39.839544+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI67GDQ3PL7G","created_at":"2026-07-05T01:03:39.839544+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI67GDQ3PL7GNKGB","created_at":"2026-07-05T01:03:39.839544+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI67GDQ3","created_at":"2026-07-05T01:03:39.839544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07138","citing_title":"Strategic Incentivization for Locally Differentially Private Federated Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3","json":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3.json","graph_json":"https://pith.science/api/pith-number/MI67GDQ3PL7GNKGB4NTLXTU6O3/graph.json","events_json":"https://pith.science/api/pith-number/MI67GDQ3PL7GNKGB4NTLXTU6O3/events.json","paper":"https://pith.science/paper/MI67GDQ3"},"agent_actions":{"view_html":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3","download_json":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3.json","view_paper":"https://pith.science/paper/MI67GDQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01167&json=true","fetch_graph":"https://pith.science/api/pith-number/MI67GDQ3PL7GNKGB4NTLXTU6O3/graph.json","fetch_events":"https://pith.science/api/pith-number/MI67GDQ3PL7GNKGB4NTLXTU6O3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3/action/storage_attestation","attest_author":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3/action/author_attestation","sign_citation":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3/action/citation_signature","submit_replication":"https://pith.science/pith/MI67GDQ3PL7GNKGB4NTLXTU6O3/action/replication_record"}},"created_at":"2026-07-05T01:03:39.839544+00:00","updated_at":"2026-07-05T01:03:39.839544+00:00"}