{"id":"W2337150116","doi":"10.1177/0265532214559115","title":"Design in four diagnostic language assessments","year":2015,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Language assessment; Language proficiency; Psychology; Educational assessment; Process (computing); Intervention (counseling); Educational research; Mathematics education; Management science; Computer science; Pedagogy","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":[0.04240267,0.0009022532,0.0007321286,0.004225131,0.002880648,0.006577973,0.003126456,0.002231469,0.007169635],"category_scores_gemma":[0.09704426,0.0009262599,0.0009327391,0.002483279,0.004181888,0.003782096,0.008320687,0.002305858,0.002214636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006543671,"about_ca_system_score_gemma":0.01134942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001704589,"about_ca_topic_score_gemma":0.002881874,"domain_scores_codex":[0.9487635,0.03257975,0.006099351,0.004137253,0.00663344,0.001786844],"domain_scores_gemma":[0.9171156,0.04341727,0.006101175,0.01032144,0.01940824,0.003636196],"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":[0.002408999,0.002323169,0.05155953,0.003210473,0.0001330811,0.0008577225,0.0805931,0.003390515,0.008093774,0.1151241,0.01237813,0.7199275],"study_design_scores_gemma":[0.002325702,0.005836597,0.05971565,0.004425993,0.0006106213,0.002487499,0.0804157,0.01607157,0.0347132,0.1686709,0.6241461,0.0005804698],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.394625,0.003220085,0.4009633,0.006334351,0.001475645,0.03884285,0.001441421,0.002413718,0.1506836],"genre_scores_gemma":[0.4884155,0.0007269115,0.4682192,0.001840254,0.00008664049,0.02273213,0.0007693658,0.000248319,0.01696162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04240267,"threshold_uncertainty_score":0.2242494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2169898390405153,"score_gpt":0.4566473782595891,"score_spread":0.2396575392190738,"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."}}