{"id":"W4308409996","doi":"10.1007/s10339-022-01113-1","title":"The uncertain advisor: trust, accuracy, and self-correction in an automated decision support system","year":2022,"lang":"en","type":"article","venue":"Cognitive Processing","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Operationalization; Computer science; Automation; Scope (computer science); Decision support system; Human error; Artificial intelligence; Human–computer interaction; Machine learning; Risk analysis (engineering); 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":[0.0007929651,0.0001359014,0.0001486416,0.0001901587,0.001138387,0.0001687012,0.00012579,0.00005594204,0.0006084365],"category_scores_gemma":[0.000183416,0.0001161239,0.00002982213,0.0003758998,0.00004697651,0.0003471177,0.00006921547,0.0003368212,0.0000643981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000217091,"about_ca_system_score_gemma":0.0001013603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003642673,"about_ca_topic_score_gemma":0.00007201942,"domain_scores_codex":[0.998309,0.0004830035,0.0003927872,0.0003542886,0.0002232149,0.0002376767],"domain_scores_gemma":[0.9988892,0.0005157987,0.0002318395,0.0001199189,0.0001801745,0.00006306519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006489359,0.0003498537,0.009855952,0.00004902694,0.00003383226,0.0000590606,0.03113333,0.00009369678,0.00004422728,0.0003255104,0.002161291,0.9552453],"study_design_scores_gemma":[0.002870345,0.0005769228,0.2096426,0.0002686249,0.00005856531,0.0006794507,0.178221,0.5870158,0.00006093214,0.0001611663,0.02002094,0.0004237007],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9735743,0.0002479324,0.002342306,0.0001670017,0.002112483,0.000551616,0.00001838416,0.001208746,0.01977718],"genre_scores_gemma":[0.9986677,0.000004348522,0.0000747033,0.0002056842,0.00006124739,0.0002915233,0.00003957804,0.00002269718,0.0006325589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9548216,"threshold_uncertainty_score":0.8755665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02614069226572752,"score_gpt":0.386308240141407,"score_spread":0.3601675478756795,"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."}}