{"id":"W4363678929","doi":"10.1109/mc.2022.3233806","title":"A Trustworthy View on Explainable Artificial Intelligence Method Evaluation","year":2023,"lang":"en","type":"article","venue":"Computer","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Trustworthiness; Consistency (knowledge bases); Computer science; Process (computing); Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003308841,0.0003052282,0.0003250194,0.0005063887,0.0003774036,0.0004639463,0.001502551,0.0001236998,0.000219945],"category_scores_gemma":[0.0001435772,0.0002957699,0.0001589599,0.002550322,0.00005829379,0.0007391464,0.000559486,0.0002804619,0.008777548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690993,"about_ca_system_score_gemma":0.0001582641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003946341,"about_ca_topic_score_gemma":0.00001970381,"domain_scores_codex":[0.9961727,0.0005248354,0.0005976653,0.0009939958,0.0009351396,0.000775679],"domain_scores_gemma":[0.9974417,0.000634579,0.0001498247,0.00121299,0.0003761511,0.0001847598],"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":[0.000009580733,0.00007246117,0.000006824637,0.00001749985,0.00001445315,0.00004784274,0.0009912009,0.04511251,0.0001389435,0.213267,0.003595829,0.7367259],"study_design_scores_gemma":[0.0000373773,0.0002140159,0.00008407177,0.0000645122,0.000009364485,0.00001129719,0.000106691,0.8453072,0.01511233,0.1274729,0.01127459,0.0003056271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003746297,0.00007461691,0.98804,0.002042297,0.001681499,0.0006416425,0.00000150008,0.0008428849,0.002929224],"genre_scores_gemma":[0.5411443,0.0001173779,0.4501028,0.004492088,0.001995467,0.0006388875,0.00004643525,0.0001066623,0.001355959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8001947,"threshold_uncertainty_score":0.9999495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1278275846633145,"score_gpt":0.3804678654842235,"score_spread":0.2526402808209089,"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."}}