{"id":"W4380365974","doi":"10.1145/3593013.3594087","title":"Towards a Science of Human-AI Decision Making: An Overview of Design Space in Empirical Human-Subject Studies","year":2023,"lang":"en","type":"article","venue":"","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Subject (documents); Space (punctuation); Computer science; Empirical research; Data science; Management science; Artificial intelligence; Engineering; Mathematics; World Wide Web; Statistics","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":[0.00911236,0.0001113083,0.0003904338,0.0003753348,0.0006981876,0.00009708227,0.0005904181,0.0001343753,0.00005912461],"category_scores_gemma":[0.004465954,0.00009435354,0.00008103681,0.002626679,0.001845193,0.0006662528,0.0002165436,0.0001936524,0.000005469726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590256,"about_ca_system_score_gemma":0.0008320421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003224741,"about_ca_topic_score_gemma":0.009509778,"domain_scores_codex":[0.9973093,0.0003617962,0.0004001529,0.0002925897,0.00121437,0.0004218383],"domain_scores_gemma":[0.9980284,0.0007050982,0.0001486341,0.0002336653,0.0007779485,0.0001062774],"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":[0.00003086713,0.0002842279,0.008561981,0.00009838371,0.00002988265,0.00001536219,0.1966032,0.0001143653,0.009092849,0.7764362,0.002487628,0.006245021],"study_design_scores_gemma":[0.0004148955,0.0007041476,0.1149934,0.0005489619,0.0000197771,2.172046e-7,0.05841613,0.0001155769,0.003242945,0.8210393,0.0002035378,0.0003010853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730908,0.0004744457,0.0001362275,0.002843216,0.000143596,0.0003004652,0.000002038183,0.00007205911,0.0229371],"genre_scores_gemma":[0.9973894,0.0008123601,0.001291944,0.0002517991,0.0000498273,0.000004671735,3.021389e-7,0.000008383588,0.000191292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1381871,"threshold_uncertainty_score":0.6798691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.575512177150944,"score_gpt":0.6125726880057574,"score_spread":0.03706051085481332,"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."}}