{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R4ZUSXX66CLR2V2B4O3AAULJSY","short_pith_number":"pith:R4ZUSXX6","schema_version":"1.0","canonical_sha256":"8f33495efef0971d5741e3b60051699638697961d923371d982d154b0263ca0c","source":{"kind":"arxiv","id":"2309.07085","version":2},"attestation_state":"computed","paper":{"title":"Mitigating Group Bias in Federated Learning for Heterogeneous Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Fatima M. Anwar, Khotso Selialia, Yasra Chandio","submitted_at":"2023-09-13T16:53:48Z","abstract_excerpt":"Federated Learning is emerging as a privacy-preserving model training approach in distributed edge applications. As such, most edge deployments are heterogeneous in nature i.e., their sensing capabilities and environments vary across deployments. This edge heterogeneity violates the independence and identical distribution (IID) property of local data across clients and produces biased global models i.e. models that contribute to unfair decision-making and discrimination against a particular community or a group. Existing bias mitigation techniques only focus on bias generated from label hetero"},"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":"2309.07085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-13T16:53:48Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8c0f13bc0212a1e63ea7ec3f45af267e6b3dc19b3b2470cd682e33a587cd2dff","abstract_canon_sha256":"2b18272264030b5419432c2cb873a36398a0c2633e9bde669f316964bee0eedb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:53.047261Z","signature_b64":"ILE6mxRYzCxwM+H6obF1sU72T8W3+kpl/4OtRGl/NGstpsntEJ7cJbt82FWL+4AQuwXjJko8meTQnLN31J95BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f33495efef0971d5741e3b60051699638697961d923371d982d154b0263ca0c","last_reissued_at":"2026-07-05T08:42:53.046882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:53.046882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Group Bias in Federated Learning for Heterogeneous Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Fatima M. Anwar, Khotso Selialia, Yasra Chandio","submitted_at":"2023-09-13T16:53:48Z","abstract_excerpt":"Federated Learning is emerging as a privacy-preserving model training approach in distributed edge applications. As such, most edge deployments are heterogeneous in nature i.e., their sensing capabilities and environments vary across deployments. This edge heterogeneity violates the independence and identical distribution (IID) property of local data across clients and produces biased global models i.e. models that contribute to unfair decision-making and discrimination against a particular community or a group. Existing bias mitigation techniques only focus on bias generated from label hetero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07085","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/2309.07085/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":"2309.07085","created_at":"2026-07-05T08:42:53.046939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07085v2","created_at":"2026-07-05T08:42:53.046939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07085","created_at":"2026-07-05T08:42:53.046939+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4ZUSXX66CLR","created_at":"2026-07-05T08:42:53.046939+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4ZUSXX66CLR2V2B","created_at":"2026-07-05T08:42:53.046939+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4ZUSXX6","created_at":"2026-07-05T08:42:53.046939+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":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY","json":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY.json","graph_json":"https://pith.science/api/pith-number/R4ZUSXX66CLR2V2B4O3AAULJSY/graph.json","events_json":"https://pith.science/api/pith-number/R4ZUSXX66CLR2V2B4O3AAULJSY/events.json","paper":"https://pith.science/paper/R4ZUSXX6"},"agent_actions":{"view_html":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY","download_json":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY.json","view_paper":"https://pith.science/paper/R4ZUSXX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07085&json=true","fetch_graph":"https://pith.science/api/pith-number/R4ZUSXX66CLR2V2B4O3AAULJSY/graph.json","fetch_events":"https://pith.science/api/pith-number/R4ZUSXX66CLR2V2B4O3AAULJSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY/action/storage_attestation","attest_author":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY/action/author_attestation","sign_citation":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY/action/citation_signature","submit_replication":"https://pith.science/pith/R4ZUSXX66CLR2V2B4O3AAULJSY/action/replication_record"}},"created_at":"2026-07-05T08:42:53.046939+00:00","updated_at":"2026-07-05T08:42:53.046939+00:00"}