{"id":"W4415195241","doi":"10.1609/aies.v8i3.36730","title":"Fairness in Federated Learning: Fairness for Whom?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Sociotechnical system; Conflation; Stakeholder; Upstream (networking); Through-the-lens metering; Psychological intervention; Harm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00325599,0.000146329,0.0002445749,0.0000475565,0.001927907,0.0004516921,0.0007832873,0.0004649419,0.00001339723],"category_scores_gemma":[0.00668405,0.0001210235,0.0001193135,0.000474229,0.0006645262,0.0002965973,0.0004484859,0.001341216,9.515315e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008665431,"about_ca_system_score_gemma":0.0005891692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00126609,"about_ca_topic_score_gemma":0.0004462177,"domain_scores_codex":[0.9986638,0.00007988432,0.0002524727,0.0003443893,0.0003564836,0.0003030068],"domain_scores_gemma":[0.9983692,0.0004152539,0.0001732038,0.0001299828,0.0008563618,0.00005598307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007022062,0.00009946751,0.01136687,0.0004575054,0.00003591428,6.112951e-8,0.05631923,0.000001789962,0.001866595,0.9218215,0.005041357,0.00291951],"study_design_scores_gemma":[0.001954609,0.0002114237,0.01119953,0.001110575,0.00006701808,8.773387e-7,0.1091974,0.005453222,0.005703161,0.8203353,0.04420035,0.0005665725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.769455,0.0002104927,0.001901682,0.1879771,0.0008437948,0.002151571,0.00003317383,0.000174071,0.03725307],"genre_scores_gemma":[0.9961324,0.0008871744,0.0002551792,0.001044176,0.00005968131,0.0000697771,0.000003158309,0.00000798307,0.001540493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2266773,"threshold_uncertainty_score":0.9993715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06930457143493446,"score_gpt":0.3633415513586792,"score_spread":0.2940369799237447,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}