{"id":"W4304097640","doi":"10.36227/techrxiv.21262041.v1","title":"Analyzing XAI Metrics: Summary of the Literature Review","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Multidisciplinary approach; Field (mathematics); Point (geometry); Computer science; Management science; Artificial intelligence; Operations research; Sociology; Economics; Engineering; Social science; Mathematics","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00158493,0.0002701913,0.0005143177,0.0003386994,0.0001833159,0.0002540023,0.005331596,0.0001409807,0.0003355299],"category_scores_gemma":[0.0005724519,0.0001864515,0.0004766185,0.003916236,0.00005431379,0.0002921562,0.008684846,0.001192785,0.000019703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001444614,"about_ca_system_score_gemma":0.0002790637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001517256,"about_ca_topic_score_gemma":0.00002399628,"domain_scores_codex":[0.99713,0.0004404296,0.0006963229,0.0007386521,0.0006823653,0.000312221],"domain_scores_gemma":[0.996035,0.000268768,0.0004871048,0.002793816,0.000344973,0.00007036397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001066923,0.0004864399,0.0033819,0.02249802,0.0005050415,0.0002581302,0.00510432,0.006613094,0.0004176464,0.5387194,0.2034163,0.218589],"study_design_scores_gemma":[0.0002051408,0.0002958371,0.001034186,0.06356559,0.0005570269,0.00010574,0.0006943772,0.07159977,0.04287535,0.1971578,0.618041,0.003868223],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005231609,0.6702857,0.2422277,0.01518711,0.005186549,0.002269856,0.00005890855,0.0004203829,0.06384061],"genre_scores_gemma":[0.08244748,0.6766774,0.1601624,0.02395209,0.0008745229,0.0008094168,0.0001644627,0.0001844008,0.05472787],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4146247,"threshold_uncertainty_score":0.9993327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03535584859169921,"score_gpt":0.3053836625846889,"score_spread":0.2700278139929897,"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."}}