{"id":"W4387592307","doi":"10.1017/9781316718636.021","title":"Evaluating Models","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Figuring; Harm; Computer science; Psychology; Social psychology; Physics","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":[0.01001013,0.002233752,0.001138903,0.003167145,0.001103198,0.006117334,0.002555521,0.002014475,0.02554396],"category_scores_gemma":[0.06762981,0.0006180097,0.001709125,0.001911874,0.001079581,0.00724486,0.002987891,0.002089976,0.004043606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0026244,"about_ca_system_score_gemma":0.002063798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004296798,"about_ca_topic_score_gemma":0.008222757,"domain_scores_codex":[0.9898346,0.004817186,0.0004170322,0.001027172,0.003565122,0.0003388604],"domain_scores_gemma":[0.9612257,0.02742956,0.001174188,0.005512873,0.003879412,0.0007782716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000464893,0.0004107915,0.01118498,0.0009608159,0.0006614075,0.000239394,0.0007032621,0.2239245,0.002869052,0.3135911,0.04497462,0.4000153],"study_design_scores_gemma":[0.000103514,0.0004709906,0.001662547,0.0006414572,0.0003757278,0.0001870896,0.0007743096,0.4394372,0.005415981,0.4871921,0.06363267,0.000106402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.06062628,0.005286919,0.780461,0.0073225,0.001135857,0.001119743,0.003767032,0.003730666,0.13655],"genre_scores_gemma":[0.4164798,0.003307964,0.5476285,0.001162006,0.0003386731,0.0008587039,0.006453421,0.001002484,0.02276852],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02554396,"threshold_uncertainty_score":0.08545303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1564211363363931,"score_gpt":0.2838641209800691,"score_spread":0.1274429846436761,"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."}}