{"id":"W4388532635","doi":"10.32038/ltrq.2023.37.13","title":"Mixed Methods Investigation into Test Score Users’ Perspectives about IELTS Reading Skill Profiles","year":2023,"lang":"en","type":"article","venue":"Language Teaching Research Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Test (biology); Coursework; Reading (process); Test score; Psychology; Language assessment; Computer science; Standardized test; Mathematics education; Linguistics","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":[0.05947059,0.000640886,0.0008510444,0.002365334,0.00168485,0.003044221,0.001000389,0.001144741,0.002941084],"category_scores_gemma":[0.09896194,0.0005794366,0.001236771,0.001827502,0.001405059,0.001531885,0.002428398,0.001220637,0.0005218593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234575,"about_ca_system_score_gemma":0.001323917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001421603,"about_ca_topic_score_gemma":0.002063608,"domain_scores_codex":[0.9463373,0.03975172,0.0045749,0.002583638,0.005449423,0.001303135],"domain_scores_gemma":[0.8544099,0.1182797,0.01081198,0.006825143,0.008979612,0.0006937222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.003617359,0.003926795,0.5355099,0.001137749,0.0005662531,0.0006350192,0.2874739,0.0007942953,0.01004206,0.003597987,0.001150997,0.1515476],"study_design_scores_gemma":[0.0006676648,0.02820114,0.6514938,0.0009674968,0.0007397362,0.00134281,0.2556896,0.01556427,0.02391757,0.005786318,0.01522188,0.0004077],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9878725,0.0001319073,0.008578839,0.000117062,0.00001965037,0.001711063,0.0002850391,0.00003099506,0.001253063],"genre_scores_gemma":[0.9707135,0.0001501269,0.0167355,0.0003347806,0.00003010886,0.01029985,0.0003335442,0.00003487027,0.001367749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05947059,"threshold_uncertainty_score":0.3145142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09945545217034842,"score_gpt":0.4139256863294651,"score_spread":0.3144702341591167,"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."}}