{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007257408,0.0001494996,0.0001647942,0.00009358831,0.00003452504,0.0000345979,0.000237739,0.00008543235,0.0007884694],"category_scores_gemma":[0.001703368,0.0001292658,0.00002396037,0.0004209597,0.00002648387,0.00008381988,0.00004606538,0.0002456873,0.0007392911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007258174,"about_ca_system_score_gemma":0.00005724497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007418139,"about_ca_topic_score_gemma":0.00002382573,"domain_scores_codex":[0.9985015,0.0003299797,0.0002512382,0.0003275388,0.0002141629,0.0003756204],"domain_scores_gemma":[0.9971808,0.002264897,0.00009315529,0.0002619827,0.0000477164,0.0001514326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006337519,0.0009274896,0.8644369,0.00001936628,0.00005099646,0.002507317,0.02806913,0.0002056492,0.001733516,0.0009175239,0.006765139,0.0943036],"study_design_scores_gemma":[0.002171991,0.0004366001,0.9734071,0.0001243053,0.00002388082,0.0001648063,0.01967905,0.0003269118,0.00008796591,0.002760428,0.0003349666,0.0004819754],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9064298,0.0006309916,0.002269101,0.0001852939,0.0006810406,0.0002722091,0.000005234132,0.0001438678,0.08938245],"genre_scores_gemma":[0.9737221,5.469306e-7,0.02211025,0.0007883082,0.0002640341,0.0001202889,0.00001667827,0.00002136328,0.002956407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1089702,"threshold_uncertainty_score":0.9502338,"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."}}