{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01043701,0.0002984334,0.0003382269,0.0009683665,0.002613368,0.001132159,0.0005489426,0.0001211149,0.000383012],"category_scores_gemma":[0.005069287,0.0002621981,0.0001257225,0.0003423867,0.0005749802,0.0006877228,0.0001037879,0.002482077,0.0005760544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002090042,"about_ca_system_score_gemma":0.0001137735,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008343825,"about_ca_topic_score_gemma":0.0015904,"domain_scores_codex":[0.993868,0.003293795,0.0004017893,0.0007011281,0.0008040605,0.0009312556],"domain_scores_gemma":[0.9957315,0.00307422,0.0001345701,0.0005840662,0.0002358327,0.0002398449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001130267,0.00005889296,0.001425845,0.0001182038,0.00003981546,0.0000543101,0.8530013,0.000004613481,0.01104375,0.04244025,0.005038012,0.08676369],"study_design_scores_gemma":[0.0003628225,0.0007350596,0.004917433,0.000545275,0.00001958886,0.0000073434,0.9760738,0.001686985,0.0005764157,0.005083475,0.009547707,0.0004440926],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810556,0.0004916327,0.0002283775,0.001282638,0.0003556329,0.0004055933,0.0000175629,0.001204212,0.01495881],"genre_scores_gemma":[0.9679547,0.000009482081,0.005118533,0.00006567862,0.001463794,0.0001048159,0.0001342883,0.00009715535,0.02505153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1230725,"threshold_uncertainty_score":0.999983,"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."}}