{"id":"W4307421239","doi":"10.5281/zenodo.7255934","title":"Can Ensembling Pre-processing Algorithms Lead to Better Machine Learning Fairness?","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal; Concordia University","funders":"","keywords":"Lead (geology); Computer science; Artificial intelligence; Machine learning","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":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001216451,0.000174143,0.0001607317,0.0004194093,0.006037412,0.001641673,0.002548372,0.00003372657,0.002614569],"category_scores_gemma":[0.0004422957,0.0002026275,0.00005186652,0.001641385,0.00006552742,0.0005556022,0.004449703,0.0006011036,0.001977617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003096355,"about_ca_system_score_gemma":0.00001075327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001333198,"about_ca_topic_score_gemma":0.000001963434,"domain_scores_codex":[0.997137,0.0005436895,0.0003108718,0.0006961109,0.0007060665,0.0006062936],"domain_scores_gemma":[0.9986629,0.00003553618,0.0001204781,0.0005511191,0.0004151463,0.0002147472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003748347,0.0001349037,0.00001924687,0.0000415282,0.00002100798,0.00008644229,0.01439476,0.01699195,0.0114215,0.005743517,0.01126748,0.9398402],"study_design_scores_gemma":[0.0001555779,0.0004022554,0.00008146266,0.00001973441,0.000005471773,0.0001501208,0.001112425,0.1818687,0.004867131,0.0008093112,0.8101931,0.0003347693],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04566993,0.0001810639,0.91906,0.01042493,0.0003367586,0.0007251118,0.00006280368,0.002771531,0.0207679],"genre_scores_gemma":[0.9895335,0.000009712687,0.006654921,0.0009693161,0.0001439316,3.54811e-7,0.000217866,0.0007951461,0.00167527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9438636,"threshold_uncertainty_score":0.9993947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04433373836655441,"score_gpt":0.2657895283475195,"score_spread":0.2214557899809651,"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."}}