{"id":"W4403746254","doi":"10.5539/elt.v17n11p81","title":"What Are the Effective Tests for Measuring English Proficiency in a Japanese Project-Based English Program? A Comparison of the Test of English for International Communication, Global Test of English Communication, and CNN Global English Test Service","year":2024,"lang":"en","type":"article","venue":"English Language Teaching","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Test (biology); Test of English as a Foreign Language; Language assessment; International communication; Language proficiency; English language; Mathematics education; Communication","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01490573,0.0007166048,0.0005610551,0.003338979,0.0005743944,0.001755045,0.0009632325,0.0008039855,0.001089016],"category_scores_gemma":[0.04302561,0.0002623043,0.0008671176,0.002119279,0.001107784,0.002600562,0.001108864,0.000728083,0.0003594358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001182496,"about_ca_system_score_gemma":0.001910906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008377723,"about_ca_topic_score_gemma":0.02129473,"domain_scores_codex":[0.9899871,0.004199447,0.001231249,0.0009117043,0.003251521,0.0004189167],"domain_scores_gemma":[0.9674373,0.01264167,0.006651229,0.00171152,0.008954466,0.002603788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003088247,0.0002386105,0.9218051,0.0001792292,0.0001992229,0.00005425811,0.0008605947,0.0001850509,0.0007242768,0.0001884363,0.0005505178,0.07470582],"study_design_scores_gemma":[0.00002103775,0.0004254434,0.9957592,0.00006451355,0.0001589056,0.00006237888,0.001290007,0.0007905485,0.0005037784,0.0001330534,0.0007735552,0.00001753892],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985595,0.001647608,0.00286962,0.0003887135,0.00008951975,0.0001431147,0.0003876091,0.00004462201,0.008834175],"genre_scores_gemma":[0.9955592,0.0003971745,0.003149981,0.00007923198,0.00002745967,0.0001100584,0.0002841406,0.00001373042,0.0003790061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01490573,"threshold_uncertainty_score":0.07883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02628894309734106,"score_gpt":0.3188600427328047,"score_spread":0.2925710996354637,"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."}}