{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2HT67ACCL57Y6MD4SBV4HQIJ6K","short_pith_number":"pith:2HT67ACC","schema_version":"1.0","canonical_sha256":"d1e7ef80425f7f8f307c906bc3c109f2896cf6a75b1fcaee2b18e9b3474bc9b1","source":{"kind":"arxiv","id":"2112.00818","version":3},"attestation_state":"computed","paper":{"title":"Models of fairness in federated learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.GT","cs.LG"],"primary_cat":"cs.CY","authors_text":"Jon Kleinberg, Kate Donahue","submitted_at":"2021-12-01T20:34:27Z","abstract_excerpt":"In many real-world situations, data is distributed across multiple self-interested agents. These agents can collaborate to build a machine learning model based on data from multiple agents, potentially reducing the error each experiences. However, sharing models in this way raises questions of fairness: to what extent can the error experienced by one agent be significantly lower than the error experienced by another agent in the same coalition? In this work, we consider two notions of fairness that each may be appropriate in different circumstances: \"egalitarian fairness\" (which aims to bound "},"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":"2112.00818","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-12-01T20:34:27Z","cross_cats_sorted":["cs.DC","cs.GT","cs.LG"],"title_canon_sha256":"65e52f1d225b45545a0b52c218a53986eee75032d4a4eb74f6cc654fae6a1e7d","abstract_canon_sha256":"a1d9e37fd13c693f95993aa10207e257059a54016b9d999607a065f76856c138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:25.816281Z","signature_b64":"sVTcjshPDRr86fwz5KabgepAXd8TOiOslXO4GuE7ga+KHG6GVmShbi78PBJyFr0vATa7tqA/p6tszMa9LS/ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e7ef80425f7f8f307c906bc3c109f2896cf6a75b1fcaee2b18e9b3474bc9b1","last_reissued_at":"2026-07-05T05:45:25.815872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:25.815872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Models of fairness in federated learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.GT","cs.LG"],"primary_cat":"cs.CY","authors_text":"Jon Kleinberg, Kate Donahue","submitted_at":"2021-12-01T20:34:27Z","abstract_excerpt":"In many real-world situations, data is distributed across multiple self-interested agents. These agents can collaborate to build a machine learning model based on data from multiple agents, potentially reducing the error each experiences. However, sharing models in this way raises questions of fairness: to what extent can the error experienced by one agent be significantly lower than the error experienced by another agent in the same coalition? In this work, we consider two notions of fairness that each may be appropriate in different circumstances: \"egalitarian fairness\" (which aims to bound "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00818","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/2112.00818/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":"2112.00818","created_at":"2026-07-05T05:45:25.815931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00818v3","created_at":"2026-07-05T05:45:25.815931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00818","created_at":"2026-07-05T05:45:25.815931+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HT67ACCL57Y","created_at":"2026-07-05T05:45:25.815931+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HT67ACCL57Y6MD4","created_at":"2026-07-05T05:45:25.815931+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HT67ACC","created_at":"2026-07-05T05:45:25.815931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21584","citing_title":"Fairness in Federated Learning: Fairness for Whom?","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K","json":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K.json","graph_json":"https://pith.science/api/pith-number/2HT67ACCL57Y6MD4SBV4HQIJ6K/graph.json","events_json":"https://pith.science/api/pith-number/2HT67ACCL57Y6MD4SBV4HQIJ6K/events.json","paper":"https://pith.science/paper/2HT67ACC"},"agent_actions":{"view_html":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K","download_json":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K.json","view_paper":"https://pith.science/paper/2HT67ACC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00818&json=true","fetch_graph":"https://pith.science/api/pith-number/2HT67ACCL57Y6MD4SBV4HQIJ6K/graph.json","fetch_events":"https://pith.science/api/pith-number/2HT67ACCL57Y6MD4SBV4HQIJ6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K/action/storage_attestation","attest_author":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K/action/author_attestation","sign_citation":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K/action/citation_signature","submit_replication":"https://pith.science/pith/2HT67ACCL57Y6MD4SBV4HQIJ6K/action/replication_record"}},"created_at":"2026-07-05T05:45:25.815931+00:00","updated_at":"2026-07-05T05:45:25.815931+00:00"}