{"id":"W4290958425","doi":"10.1080/15434303.2022.2073886","title":"Developing a Scenario-Based English Language Assessment in an Asian University","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Language assessment; Linguistics; Language proficiency; Psychology; Mathematics education; Sociology; 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":[0.008776259,0.0007051748,0.0003047969,0.0008761144,0.002114645,0.003702386,0.001946215,0.001386028,0.002719635],"category_scores_gemma":[0.0125861,0.0004562959,0.0004948117,0.0005220273,0.001191946,0.003479391,0.003036566,0.001426995,0.0006677856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003035573,"about_ca_system_score_gemma":0.005583114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003319,"about_ca_topic_score_gemma":0.008437269,"domain_scores_codex":[0.9928288,0.005554812,0.0003157376,0.0002988654,0.0005905689,0.0004112198],"domain_scores_gemma":[0.992303,0.002902016,0.000468829,0.0004499121,0.002093159,0.001783057],"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":[0.0009217536,0.02187661,0.1026526,0.0009320241,0.0001818091,0.01087938,0.2411086,0.09661947,0.04734749,0.05089191,0.02132377,0.4052646],"study_design_scores_gemma":[0.0005159819,0.01243172,0.05518021,0.001197118,0.0001660292,0.005988545,0.3904881,0.2635636,0.05645583,0.03027283,0.1827128,0.001027317],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8692669,0.00007200305,0.09608491,0.001870965,0.00009420318,0.00344583,0.0001961708,0.0005951173,0.02837387],"genre_scores_gemma":[0.8168699,0.000127254,0.177422,0.0001718322,0.00001388182,0.001024783,0.0002472946,0.00004176223,0.004081364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008776259,"threshold_uncertainty_score":0.04641384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01712562869737202,"score_gpt":0.2795077938743099,"score_spread":0.2623821651769379,"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."}}