{"id":"W4377030819","doi":"10.1016/j.artint.2023.103945","title":"Human performance consequences of normative and contrastive explanations: An experiment in machine learning for reliability maintenance","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Mitacs","keywords":"Normative; Computer science; Artificial intelligence; Workload; Task (project management); Reliability (semiconductor); Machine learning; Automation; Advice (programming); Contrast (vision); Baseline (sea); Human–computer interaction; Psychology; 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":[0.007652932,0.0009538512,0.000595593,0.0003618426,0.0007293104,0.001797398,0.001767495,0.00299933,0.008187596],"category_scores_gemma":[0.08338857,0.0006624458,0.0003958326,0.0002551562,0.001279476,0.002507738,0.0008910792,0.002745624,0.0008851396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006163089,"about_ca_system_score_gemma":0.0007788382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336681,"about_ca_topic_score_gemma":0.001018113,"domain_scores_codex":[0.9969354,0.001724225,0.0002672918,0.0005735292,0.0003670815,0.0001324797],"domain_scores_gemma":[0.8003916,0.1837606,0.003849821,0.008790311,0.00170956,0.001498112],"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":[0.1270255,0.07923002,0.08060361,0.003454009,0.002107455,0.003058082,0.04142727,0.1476922,0.1247987,0.03616461,0.02479139,0.3296472],"study_design_scores_gemma":[0.02977771,0.07222683,0.1080386,0.0004856806,0.001567588,0.001800636,0.004440935,0.5719845,0.05769808,0.1291821,0.02198096,0.0008163336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920031,0.0001272312,0.004105843,0.0004978865,0.00008821087,0.0001463111,0.0001832014,0.0001274466,0.002720847],"genre_scores_gemma":[0.9936952,0.00005286763,0.004437183,0.0001878053,0.00003869528,0.0001225345,0.0002032946,0.00004388427,0.001218493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008187596,"threshold_uncertainty_score":0.0404731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07485535456500177,"score_gpt":0.3397358529433857,"score_spread":0.264880498378384,"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."}}