{"id":"W4405166943","doi":"10.1016/j.engappai.2024.109678","title":"Quantifying the trustworthiness of explainable artificial intelligence outputs in uncertain decision-making scenarios","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Trustworthiness; Artificial intelligence; Machine learning; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.01485314,0.0009177497,0.0009631807,0.002839496,0.0006437196,0.002977756,0.001032037,0.002053437,0.001245842],"category_scores_gemma":[0.1436826,0.0005369756,0.001126298,0.001164247,0.002019592,0.004234257,0.002324656,0.001821317,0.0001496074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001617415,"about_ca_system_score_gemma":0.001110758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002069981,"about_ca_topic_score_gemma":0.001620209,"domain_scores_codex":[0.9899306,0.004554835,0.0008711899,0.001207053,0.002908405,0.0005278756],"domain_scores_gemma":[0.8190919,0.1488305,0.01658952,0.007614023,0.006423435,0.001450543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001019488,0.0001497404,0.08906545,0.0005332113,0.001167635,0.001053829,0.001168832,0.7878448,0.003092675,0.08043759,0.0007454715,0.03372129],"study_design_scores_gemma":[0.00004244237,0.0002126168,0.01405865,0.0001110968,0.0001232883,0.0002096036,0.0002922885,0.8548597,0.001740599,0.1278625,0.0004305909,0.00005679265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6795,0.0008172647,0.3103146,0.001714529,0.0000906065,0.0001480734,0.0005084055,0.0002250605,0.006681408],"genre_scores_gemma":[0.9906632,0.0001212589,0.008837509,0.00003462741,0.00003418217,0.00002468661,0.0001449089,0.00001545423,0.0001242778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01485314,"threshold_uncertainty_score":0.07855183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04832276726054405,"score_gpt":0.3265637760144577,"score_spread":0.2782410087539136,"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."}}