{"id":"W4414359142","doi":"10.24963/ijcai.2025/1240","title":"Ensuring Reliable and Transparent Algorithmic Fairness Through Optimal Transport and Uncertainty Quantification","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transparency (behavior); Trustworthiness; Calibration; Uncertainty quantification; Attribution; Measurement uncertainty","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003007444,0.0001471001,0.0001878371,0.00007059168,0.0002306654,0.00008957087,0.0003050092,0.00006958531,0.000007728166],"category_scores_gemma":[0.0000146262,0.0001362678,0.00002808477,0.0002906205,0.0000793592,0.0005341775,0.00007380617,0.0001796389,0.000001512097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000306679,"about_ca_system_score_gemma":0.00004864331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004341572,"about_ca_topic_score_gemma":0.00002853369,"domain_scores_codex":[0.9988434,0.00003408106,0.0002398212,0.0005091185,0.0001541308,0.0002194274],"domain_scores_gemma":[0.9994808,0.00007590095,0.00004817075,0.0003055506,0.00004673013,0.0000428377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004278991,0.00007485183,0.01698163,0.0002137679,0.00006343241,0.00001920037,0.003860763,0.5022104,0.0007614216,0.4260394,0.00008766894,0.04964465],"study_design_scores_gemma":[0.0006659311,0.00003174576,0.02367767,0.00007635311,0.00002539156,0.000009552549,0.0002462814,0.9683977,0.0009550392,0.003472577,0.00219324,0.0002484672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05498614,0.0002144657,0.9412039,0.001298073,0.0002345443,0.00016986,9.564551e-7,0.000186491,0.001705572],"genre_scores_gemma":[0.867857,0.00008353301,0.131467,0.00008859389,0.00001831492,0.00001341171,0.000004137085,0.000006194097,0.0004617348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8128709,"threshold_uncertainty_score":0.5556839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02078479655882227,"score_gpt":0.2822741808919831,"score_spread":0.2614893843331609,"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."}}