{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VPPCF37ZGIZZO7EMTO7IPPM45B","short_pith_number":"pith:VPPCF37Z","schema_version":"1.0","canonical_sha256":"abde22eff93233977c8c9bbe87bd9ce850ca6cc21f949d124fdf836556719df1","source":{"kind":"arxiv","id":"2109.08604","version":2},"attestation_state":"computed","paper":{"title":"Enforcing fairness in private federated learning via the modified method of differential multipliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Rodr\\'iguez-G\\'alvez, Filip Granqvist, Matt Seigel, Rogier Van Dalen","submitted_at":"2021-09-17T15:28:47Z","abstract_excerpt":"Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance of the models on under-represented groups, as these parts of the distribution are difficult to learn in the presence of noise. Existing approaches for enforcing fairness in machine learning models have considered the centralized setting, in which the algorithm has access to the users' data. This paper introduces an algorithm to enforce group fairness in priv"},"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":"2109.08604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-17T15:28:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f5d75a5f08babbcd0f87d4c7d4e25b4ef26d64fedc467095bcaeced05dba0f1a","abstract_canon_sha256":"c2d1e1c5d54e5398239667192e9f49e4fe6b2e16bd287e8891d5d106ad2a67e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:59.474105Z","signature_b64":"Fi2d3IRuXXEwdX3dHImnPPXs8zhOO6XrwVUz2jMqhDPZp2+W/hprsNAjtvaQpRtTh6lYB1H2rDZf/c0AqaOvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abde22eff93233977c8c9bbe87bd9ce850ca6cc21f949d124fdf836556719df1","last_reissued_at":"2026-07-05T04:14:59.473661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:59.473661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enforcing fairness in private federated learning via the modified method of differential multipliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Borja Rodr\\'iguez-G\\'alvez, Filip Granqvist, Matt Seigel, Rogier Van Dalen","submitted_at":"2021-09-17T15:28:47Z","abstract_excerpt":"Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance of the models on under-represented groups, as these parts of the distribution are difficult to learn in the presence of noise. Existing approaches for enforcing fairness in machine learning models have considered the centralized setting, in which the algorithm has access to the users' data. This paper introduces an algorithm to enforce group fairness in priv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08604","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/2109.08604/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":"2109.08604","created_at":"2026-07-05T04:14:59.473720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08604v2","created_at":"2026-07-05T04:14:59.473720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08604","created_at":"2026-07-05T04:14:59.473720+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPPCF37ZGIZZ","created_at":"2026-07-05T04:14:59.473720+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPPCF37ZGIZZO7EM","created_at":"2026-07-05T04:14:59.473720+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPPCF37Z","created_at":"2026-07-05T04:14:59.473720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.16251","citing_title":"RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B","json":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B.json","graph_json":"https://pith.science/api/pith-number/VPPCF37ZGIZZO7EMTO7IPPM45B/graph.json","events_json":"https://pith.science/api/pith-number/VPPCF37ZGIZZO7EMTO7IPPM45B/events.json","paper":"https://pith.science/paper/VPPCF37Z"},"agent_actions":{"view_html":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B","download_json":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B.json","view_paper":"https://pith.science/paper/VPPCF37Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08604&json=true","fetch_graph":"https://pith.science/api/pith-number/VPPCF37ZGIZZO7EMTO7IPPM45B/graph.json","fetch_events":"https://pith.science/api/pith-number/VPPCF37ZGIZZO7EMTO7IPPM45B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B/action/storage_attestation","attest_author":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B/action/author_attestation","sign_citation":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B/action/citation_signature","submit_replication":"https://pith.science/pith/VPPCF37ZGIZZO7EMTO7IPPM45B/action/replication_record"}},"created_at":"2026-07-05T04:14:59.473720+00:00","updated_at":"2026-07-05T04:14:59.473720+00:00"}