{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603341,0.000212317,0.0003246484,0.0003276139,0.0003506011,0.0001056516,0.0006509213,0.00007938953,0.00001572653],"category_scores_gemma":[0.0007008815,0.0002081653,0.00005214572,0.001011302,0.0005457703,0.001188153,0.0001701841,0.0002163595,0.00002967092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009048202,"about_ca_system_score_gemma":0.00008453376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006662033,"about_ca_topic_score_gemma":0.0005219117,"domain_scores_codex":[0.9975792,0.0001936829,0.0008374507,0.0006077954,0.0002798093,0.000502128],"domain_scores_gemma":[0.9983057,0.0005820574,0.0002573781,0.0003828371,0.0003635134,0.0001085098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001627441,0.0004092431,0.006768768,0.0001559073,0.00002656067,0.00002251059,0.03515092,0.07155619,0.07721231,0.7240959,0.00003761756,0.08440127],"study_design_scores_gemma":[0.000042292,0.0005107464,0.001099028,0.00007331778,0.000003024918,0.000003179786,0.005259036,0.5349899,0.3945294,0.06321469,0.00006155797,0.0002138323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7481307,0.00008633875,0.2498761,0.0006043201,0.0001686117,0.0007141696,0.00001171461,0.0001639643,0.0002440721],"genre_scores_gemma":[0.9939868,0.00009665569,0.005532967,0.00005755764,0.00002121837,0.0002241815,0.00001218961,0.00001211315,0.00005627633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6608813,"threshold_uncertainty_score":0.8488735,"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."}}