{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003230297,0.0002735342,0.0003975425,0.00006136102,0.0005589419,0.000246363,0.003336032,0.0001117022,0.00004251482],"category_scores_gemma":[0.001327459,0.0001697141,0.0002496861,0.001295224,0.0003745005,0.0006140546,0.0006139884,0.0004435809,0.0003926704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710621,"about_ca_system_score_gemma":0.0001720252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001144853,"about_ca_topic_score_gemma":0.0005459733,"domain_scores_codex":[0.9959581,0.0008141426,0.001147464,0.0006586618,0.0009327299,0.0004889008],"domain_scores_gemma":[0.9957101,0.001448929,0.000406105,0.001729269,0.0005227862,0.0001827857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008677775,0.0002904645,0.008520423,0.0005902613,0.0002216484,0.00001840057,0.0501617,0.008339814,0.01591022,0.8729082,0.00266817,0.04028395],"study_design_scores_gemma":[0.000182267,0.0002202462,0.004096488,0.0001666718,0.00006212161,0.00004021449,0.02890957,0.1585536,0.7814516,0.008146344,0.0173109,0.0008599282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1944198,0.000883113,0.7683439,0.02281101,0.0008141864,0.001357597,0.0000221003,0.0006069086,0.01074141],"genre_scores_gemma":[0.996641,0.00003553267,0.002005281,0.0009480364,0.000193836,0.00008729989,0.000001917706,0.00001928828,0.0000678265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8647618,"threshold_uncertainty_score":0.6920739,"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."}}