{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BQRHSARVFRPBUB2MBYZUVFCYBP","short_pith_number":"pith:BQRHSARV","schema_version":"1.0","canonical_sha256":"0c227902352c5e1a074c0e334a94580bcec9bdd0402244f3f4305a926c27f82a","source":{"kind":"arxiv","id":"2508.12042","version":2},"attestation_state":"computed","paper":{"title":"FAIRVAR: Fair Federated Learning via Variance Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Dadras, Tommy L\\\"ofstedt, Zahra Kharaghani","submitted_at":"2025-08-16T13:32:41Z","abstract_excerpt":"Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the global model, leading to disparities in their performance. Fairness, understood as reducing these disparities, is therefore a crucial concern in FL and has been addressed in various ways. We studied performance equitable fairness in FL, where the goal is to minimize performance disparities across clients. We evaluated several existing fairness-aware methods and introduce he"},"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":"2508.12042","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-16T13:32:41Z","cross_cats_sorted":[],"title_canon_sha256":"1d4d71039cb1bf3297917ab2bbeea9a2346eb4a619363fd63503a77f181de174","abstract_canon_sha256":"f5c191af9555934d5f5eb23c50004fadd94765c1a91883cc808e495ab2365ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:46.801863Z","signature_b64":"hySKLEgYZMTCjZvA3kdKufZmJVie5/b9xah+r+MLkxGD4zB1JmnChTAO+iWM0anmBI1tsG3X2w/KSsgJ/93cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c227902352c5e1a074c0e334a94580bcec9bdd0402244f3f4305a926c27f82a","last_reissued_at":"2026-06-23T03:13:46.801382Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:46.801382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAIRVAR: Fair Federated Learning via Variance Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Dadras, Tommy L\\\"ofstedt, Zahra Kharaghani","submitted_at":"2025-08-16T13:32:41Z","abstract_excerpt":"Federated learning (FL) allows collaborative training of machine learning models across multiple parties without sharing raw data. However, heterogeneous data can cause some clients to have disproportionate influence on the global model, leading to disparities in their performance. Fairness, understood as reducing these disparities, is therefore a crucial concern in FL and has been addressed in various ways. We studied performance equitable fairness in FL, where the goal is to minimize performance disparities across clients. We evaluated several existing fairness-aware methods and introduce he"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12042","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/2508.12042/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":"2508.12042","created_at":"2026-06-23T03:13:46.801441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12042v2","created_at":"2026-06-23T03:13:46.801441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12042","created_at":"2026-06-23T03:13:46.801441+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQRHSARVFRPB","created_at":"2026-06-23T03:13:46.801441+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQRHSARVFRPBUB2M","created_at":"2026-06-23T03:13:46.801441+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQRHSARV","created_at":"2026-06-23T03:13:46.801441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP","json":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP.json","graph_json":"https://pith.science/api/pith-number/BQRHSARVFRPBUB2MBYZUVFCYBP/graph.json","events_json":"https://pith.science/api/pith-number/BQRHSARVFRPBUB2MBYZUVFCYBP/events.json","paper":"https://pith.science/paper/BQRHSARV"},"agent_actions":{"view_html":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP","download_json":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP.json","view_paper":"https://pith.science/paper/BQRHSARV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12042&json=true","fetch_graph":"https://pith.science/api/pith-number/BQRHSARVFRPBUB2MBYZUVFCYBP/graph.json","fetch_events":"https://pith.science/api/pith-number/BQRHSARVFRPBUB2MBYZUVFCYBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP/action/storage_attestation","attest_author":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP/action/author_attestation","sign_citation":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP/action/citation_signature","submit_replication":"https://pith.science/pith/BQRHSARVFRPBUB2MBYZUVFCYBP/action/replication_record"}},"created_at":"2026-06-23T03:13:46.801441+00:00","updated_at":"2026-06-23T03:13:46.801441+00:00"}