{"id":"W2009348101","doi":"10.1075/intp.7.1.06cli","title":"Putting the exam to the test","year":2005,"lang":"en","type":"article","venue":"Interpreting International Journal of Research and Practice in Interpreting","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpreter; Certification; Test (biology); Computer science; Quality (philosophy); Psychology; Quality assessment; Natural language processing; Evaluation methods; Epistemology; Programming language; Political science; Reliability engineering; Engineering","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":[0.01164883,0.0009940474,0.001498971,0.003524016,0.003272262,0.008018716,0.002217228,0.004400286,0.02914403],"category_scores_gemma":[0.1087347,0.0006452426,0.001161065,0.001169364,0.008124528,0.012434,0.006715794,0.01054629,0.02260952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002076732,"about_ca_system_score_gemma":0.005548538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003768682,"about_ca_topic_score_gemma":0.00310647,"domain_scores_codex":[0.9880057,0.005561712,0.001195502,0.0007676113,0.003615475,0.0008540675],"domain_scores_gemma":[0.9655604,0.01164681,0.001556998,0.003068847,0.01376797,0.00439891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002152113,0.0002118946,0.007750297,0.0004033823,0.00005266396,0.001185753,0.002633217,0.0005424916,0.001286777,0.143695,0.3195432,0.5224801],"study_design_scores_gemma":[0.00005650886,0.0005529805,0.005882499,0.001917651,0.00004083431,0.001745008,0.004741794,0.0007674172,0.002417358,0.1593138,0.8224032,0.000160914],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.0238951,0.01298953,0.1725718,0.3877336,0.04820875,0.0007669784,0.001835949,0.005591121,0.3464073],"genre_scores_gemma":[0.3293646,0.01534921,0.3301858,0.1206527,0.01587764,0.00137091,0.003180945,0.004551668,0.1794666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02914403,"threshold_uncertainty_score":0.09749645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1439068949241577,"score_gpt":0.5866487712491207,"score_spread":0.4427418763249631,"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."}}