{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02373629,0.002274098,0.003415154,0.03890929,0.001313336,0.008666247,0.003132375,0.002396666,0.005517722],"category_scores_gemma":[0.1206423,0.001276174,0.003052168,0.04003591,0.002631481,0.01236164,0.002589741,0.002832841,0.001998179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006691222,"about_ca_system_score_gemma":0.009811591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006352356,"about_ca_topic_score_gemma":0.006283554,"domain_scores_codex":[0.9809403,0.006339617,0.003434249,0.002003374,0.006798196,0.0004843534],"domain_scores_gemma":[0.7890579,0.1526893,0.01613661,0.004170765,0.0365937,0.001351789],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001181157,0.0001035823,0.005146605,0.086621,0.0009111482,0.00009869687,0.0007539416,0.00194181,0.0003554668,0.02907447,0.03478956,0.8400856],"study_design_scores_gemma":[0.000039747,0.0003391595,0.02155235,0.2657996,0.003084897,0.001055703,0.003454384,0.003633795,0.001915861,0.04570577,0.6531411,0.0002777884],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009116796,0.9899008,0.002732162,0.002765569,0.0003077469,0.00005875166,0.0003076072,0.00005628559,0.002959456],"genre_scores_gemma":[0.01507709,0.9746839,0.007393036,0.0008007149,0.0005828448,0.0001514468,0.0007150698,0.00007294831,0.0005229923],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9762637,"threshold_uncertainty_score":0.125531,"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."}}