{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2568512,0.002893564,0.004091535,0.01939548,0.004806761,0.02811026,0.006271694,0.006209773,0.007094571],"category_scores_gemma":[0.2907382,0.002795978,0.004100977,0.01737315,0.03830482,0.02572049,0.01019985,0.008843726,0.001754634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01369144,"about_ca_system_score_gemma":0.01765558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004205044,"about_ca_topic_score_gemma":0.003777861,"domain_scores_codex":[0.6246209,0.3235855,0.0171627,0.01243029,0.02042316,0.001777518],"domain_scores_gemma":[0.3859736,0.5558164,0.01169144,0.02404107,0.0204412,0.002036377],"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":[0.00020645,0.0002529833,0.008245346,0.01562045,0.0004618174,0.0001584407,0.01651193,0.00451005,0.0006660647,0.7313488,0.004697646,0.2173201],"study_design_scores_gemma":[0.000168944,0.0003766782,0.004730369,0.01864983,0.0002701126,0.0002927342,0.01184644,0.009087088,0.001045933,0.8714126,0.08198392,0.0001353701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01282414,0.1873983,0.7248726,0.04773114,0.001071055,0.002526515,0.0007579162,0.0005734235,0.02224501],"genre_scores_gemma":[0.1939359,0.07733959,0.7039351,0.005995062,0.0009637018,0.01445172,0.0008492716,0.0005333179,0.001996282],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.2568512,"threshold_uncertainty_score":0.9164348,"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."}}