{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004411353,0.0003712671,0.0004142699,0.0005857549,0.0008413129,0.002995234,0.000648384,0.001245208,0.002171531],"category_scores_gemma":[0.07269344,0.0003524719,0.0002707552,0.0005010396,0.00115446,0.003448818,0.00107809,0.001618153,0.0002361189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00088108,"about_ca_system_score_gemma":0.001337307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006726907,"about_ca_topic_score_gemma":0.005064881,"domain_scores_codex":[0.9970939,0.001480463,0.0001852696,0.0003120672,0.000750977,0.0001772978],"domain_scores_gemma":[0.9501505,0.03585612,0.007226681,0.002593443,0.002829144,0.001344076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008391116,0.001704213,0.5243468,0.000367846,0.0005931387,0.001380908,0.01708216,0.07801196,0.01773623,0.02961578,0.003614459,0.3171553],"study_design_scores_gemma":[0.0001884842,0.001685325,0.2133265,0.0001306303,0.0003720608,0.0008748133,0.005167279,0.6981835,0.01078167,0.06624509,0.002779164,0.0002655594],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9722268,0.0001959215,0.02101547,0.0009492853,0.00004828391,0.00002586917,0.00004062258,0.00008925908,0.005408475],"genre_scores_gemma":[0.9975991,0.00002551846,0.00201082,0.00003756791,0.000008348085,0.00000328159,0.00001035717,0.00000918738,0.0002958873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006726907,"threshold_uncertainty_score":0.02332973,"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."}}