{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03387533,0.000196357,0.0002728135,0.0005868415,0.001122492,0.0002911981,0.002563821,0.0001527234,0.0002031432],"category_scores_gemma":[0.1922433,0.0001208566,0.0001027699,0.0005271989,0.0002846094,0.0006472782,0.00138256,0.005043154,0.0001694695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006118771,"about_ca_system_score_gemma":0.0004229834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006737973,"about_ca_topic_score_gemma":0.0005768157,"domain_scores_codex":[0.9902732,0.005454439,0.001799068,0.0003057784,0.00140432,0.0007631537],"domain_scores_gemma":[0.8570135,0.1360339,0.001224613,0.0006262538,0.00486799,0.0002337524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003734467,0.0004898,0.1321896,0.0001475215,0.0003628466,0.0001627924,0.3472804,0.0008566375,0.002031616,0.005966674,0.06713299,0.4396447],"study_design_scores_gemma":[0.0008826136,0.0009668584,0.004208705,0.01256389,0.00002422522,0.001146392,0.170179,0.006467389,0.0002035884,0.002866775,0.8002101,0.0002804143],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1949412,0.002711883,0.001487897,0.6941549,0.003449461,0.001126118,0.00001802459,0.0000626772,0.1020479],"genre_scores_gemma":[0.979393,0.0005227748,0.00645194,0.01116786,0.001810565,0.00009411287,0.000001103328,0.00003410655,0.0005245145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7844518,"threshold_uncertainty_score":0.9972522,"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."}}