{"id":"W3000965188","doi":"10.1007/s13218-020-00636-z","title":"Measuring the Quality of Explanations: The System Causability Scale (SCS)","year":2020,"lang":"en","type":"article","venue":"KI - Künstliche Intelligenz","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":386,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital","funders":"Karl-Franzens-Universität Graz; Medizinische Universität Graz; Austrian Science Fund","keywords":"Computer science; Variety (cybernetics); Relevance (law); Artificial intelligence; Transparency (behavior); Scale (ratio); Quality (philosophy); Domain (mathematical analysis); Usability; Traceability; Data science; Machine learning; Human–computer interaction; Software engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.006445002,0.000565849,0.0005403349,0.005067068,0.0005108643,0.002299495,0.0007839455,0.001410086,0.004185329],"category_scores_gemma":[0.0744951,0.0002237011,0.0008001636,0.00250751,0.001220798,0.002821773,0.002058824,0.0008812614,0.000623837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009356096,"about_ca_system_score_gemma":0.0007240481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002196312,"about_ca_topic_score_gemma":0.001691372,"domain_scores_codex":[0.9919466,0.002933248,0.0008462446,0.0009338264,0.003121935,0.000218215],"domain_scores_gemma":[0.9291462,0.05119849,0.006391274,0.003558698,0.008472519,0.001232939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001601919,0.0006197675,0.4981181,0.001946396,0.001023809,0.0003203485,0.006055498,0.02770644,0.02335168,0.02141434,0.01330419,0.4045375],"study_design_scores_gemma":[0.0002874902,0.002097872,0.4897416,0.0005485261,0.0007758505,0.0005626278,0.003133403,0.3992614,0.02607578,0.05494366,0.0220826,0.000489159],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7628422,0.001653876,0.2009608,0.001617051,0.0001986971,0.001048103,0.004337282,0.004861574,0.02248041],"genre_scores_gemma":[0.9529912,0.0001106439,0.04490865,0.00007996013,0.00003404326,0.0002426142,0.001156799,0.0000759039,0.0004002697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006445002,"threshold_uncertainty_score":0.03408486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1665657092871626,"score_gpt":0.3220066411088041,"score_spread":0.1554409318216415,"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."}}