{"id":"W2487975284","doi":"10.1093/med:psych/9780195310641.003.0001","title":"Developing Criteria for Evidence-Based Assessment","year":2008,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Ottawa","funders":"","keywords":"Computer science","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":[0.1744049,0.003893372,0.009431401,0.03439423,0.003069097,0.02038827,0.007657532,0.00724638,0.009523619],"category_scores_gemma":[0.3317376,0.003609645,0.00475388,0.01693046,0.007810932,0.01261082,0.01030073,0.01122816,0.003299539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01055686,"about_ca_system_score_gemma":0.02583753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00453287,"about_ca_topic_score_gemma":0.007105428,"domain_scores_codex":[0.8143327,0.08824158,0.05147834,0.003118973,0.04121298,0.001615411],"domain_scores_gemma":[0.6601056,0.272444,0.01243511,0.007744839,0.04445583,0.002814615],"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":[0.0001142666,0.000119445,0.0009833017,0.01683507,0.0008773074,0.0002522714,0.002008547,0.005468257,0.0005516153,0.3720624,0.04787567,0.5528518],"study_design_scores_gemma":[0.0001529743,0.0001708727,0.0007761581,0.03410609,0.0008715094,0.0004206567,0.001681191,0.01046905,0.001243772,0.8194125,0.130506,0.0001892893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001900786,0.06451339,0.8602238,0.01929986,0.002693944,0.006706994,0.001362482,0.0007341971,0.04256464],"genre_scores_gemma":[0.01072081,0.01164314,0.9712138,0.0009028837,0.0002923454,0.002925485,0.0005813893,0.0001160738,0.001603893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1744049,"threshold_uncertainty_score":0.9223523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4388937843731766,"score_gpt":0.4515329646806724,"score_spread":0.01263918030749578,"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."}}