{"id":"W4388976300","doi":"10.21203/rs.3.rs-3528413/v1","title":"Improving Explainable AI Interpretability: Mathematical Models for Evaluating Explanation Methods.","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Transparency (behavior); Computer science; Accountability; Artificial intelligence; Correctness; Management science; Machine learning; Algorithm; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03852816,0.001666619,0.001043827,0.006103454,0.0008972376,0.005730597,0.002433844,0.003058398,0.004384484],"category_scores_gemma":[0.300734,0.0007642272,0.002165434,0.003035479,0.004191614,0.009956408,0.003946638,0.003808667,0.000482998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006220785,"about_ca_system_score_gemma":0.002574359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003513533,"about_ca_topic_score_gemma":0.002537482,"domain_scores_codex":[0.9690006,0.02025919,0.002243852,0.001748753,0.006237904,0.0005097014],"domain_scores_gemma":[0.6377876,0.321192,0.01789192,0.00904585,0.01274087,0.001341836],"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":[0.0003249871,0.0002448607,0.01036829,0.001208658,0.0004851906,0.0001414151,0.001275085,0.356784,0.001907417,0.3968332,0.004923197,0.2255038],"study_design_scores_gemma":[0.00002559059,0.0001387671,0.001397163,0.0003169308,0.00006306868,0.00006199315,0.0001141629,0.8345585,0.00145203,0.159811,0.002011479,0.00004937903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01297776,0.001829991,0.9789637,0.00198742,0.0001138956,0.0002752007,0.0002253982,0.0003626121,0.003264101],"genre_scores_gemma":[0.3318798,0.001341618,0.6623603,0.0005064101,0.0002229719,0.001348707,0.0005675839,0.0002713484,0.001501236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03852816,"threshold_uncertainty_score":0.2037588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3921491170560181,"score_gpt":0.5530217707892984,"score_spread":0.1608726537332803,"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."}}