{"id":"W4402130453","doi":"10.1080/0960085x.2024.2395531","title":"Reducing the incidence of biased algorithmic decisions through feature importance transparency: an empirical study","year":2024,"lang":"en","type":"article","venue":"European Journal of Information Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; McMaster University; University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Transparency (behavior); Computer science; Strategic information system; Empirical research; Feature (linguistics); Data science; Information system; Management information systems; Computer security; Statistics; Mathematics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.004670457,0.0001481699,0.0002498748,0.0002406594,0.0001873438,0.0007016852,0.001544852,0.00002716246,0.000005194451],"category_scores_gemma":[0.0003324001,0.00009249856,0.0001142104,0.001059799,0.00005425638,0.005842748,0.00007734742,0.0004089836,0.00006783157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007176003,"about_ca_system_score_gemma":0.000237001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002883182,"about_ca_topic_score_gemma":0.000005122474,"domain_scores_codex":[0.9964968,0.0007704039,0.001553709,0.0001464908,0.000834629,0.0001979811],"domain_scores_gemma":[0.9976818,0.0003306044,0.0007355415,0.000574147,0.0005789547,0.00009896155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001285175,0.0004832114,0.004796237,0.0002919546,0.0003491981,0.001460514,0.6854564,0.1131821,0.00167297,0.01502762,0.02267292,0.1544784],"study_design_scores_gemma":[0.001227399,0.005698993,0.02836288,0.00490882,0.0001657414,0.004463652,0.1276701,0.7391558,0.004523274,0.001181567,0.08146551,0.001176265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1965514,0.0008105377,0.7984072,0.0006962792,0.00150955,0.0003600426,0.000005474465,0.0000652199,0.001594315],"genre_scores_gemma":[0.9937848,0.0000426047,0.005825852,0.0001089845,0.0001963169,0.000002833947,0.00000132021,0.000009896126,0.00002742131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7972333,"threshold_uncertainty_score":0.6766367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517048671140001,"score_gpt":0.3321928754086463,"score_spread":0.2670223886972463,"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."}}