{"id":"W4395109821","doi":"10.2139/ssrn.4805663","title":"Human Performance Effects of Combining Counterfactual Explanations with Normative and Contrastive Explanations in Supervised Machine Learning for Automated Decision Assistance","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Normative; Artificial intelligence; Computer science; Machine learning; Contrastive analysis; Psychology; Cognitive psychology; Natural language processing; Social psychology; Epistemology; Linguistics; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01052105,0.001436473,0.0006521623,0.0006226826,0.0003764417,0.003303514,0.001110853,0.00264134,0.007434039],"category_scores_gemma":[0.1454813,0.0009339182,0.0006218872,0.0003691884,0.00120427,0.003590162,0.001689674,0.002627487,0.0009028466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006287217,"about_ca_system_score_gemma":0.0006765857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009836728,"about_ca_topic_score_gemma":0.0008281908,"domain_scores_codex":[0.9935684,0.004199034,0.0004900692,0.000941664,0.0006194077,0.0001813019],"domain_scores_gemma":[0.6736863,0.3098233,0.006941538,0.006358436,0.001946371,0.001243993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.09114084,0.01133126,0.1055894,0.003650854,0.00367292,0.001437749,0.01394474,0.1874904,0.1202188,0.02268789,0.008732334,0.4301026],"study_design_scores_gemma":[0.005465566,0.01085186,0.09636707,0.0004448161,0.003715518,0.001259612,0.001854584,0.7199205,0.05155073,0.1016967,0.006318762,0.0005543412],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9776954,0.0004774565,0.0137121,0.0009152053,0.0001754787,0.0001016821,0.0002259129,0.0003433416,0.00635335],"genre_scores_gemma":[0.9882918,0.0001571001,0.009752437,0.0001723333,0.0001068455,0.00006922112,0.0003054208,0.0001307799,0.001014058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01052105,"threshold_uncertainty_score":0.05564123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01138504757478094,"score_gpt":0.2713207258632177,"score_spread":0.2599356782884368,"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."}}