{"id":"W3178523571","doi":"10.5539/elt.v14n7p95","title":"The Development of STEP, the CEFR-Based English Proficiency Test","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Active listening; Reliability (semiconductor); Construct validity; Content validity; Language proficiency; Language assessment; Test validity; Validity; Mathematics education; Natural language processing; Computer science; Psychometrics; 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":[0.008009762,0.0005033615,0.0006755534,0.002632895,0.0004603937,0.001448665,0.001442527,0.0008543619,0.003036481],"category_scores_gemma":[0.02541367,0.0002530015,0.0006665111,0.0009550419,0.0006491001,0.002015629,0.002161509,0.001340465,0.001609417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009837553,"about_ca_system_score_gemma":0.004504243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002262098,"about_ca_topic_score_gemma":0.005110128,"domain_scores_codex":[0.9944159,0.002435817,0.0006308801,0.0004588671,0.001815187,0.00024342],"domain_scores_gemma":[0.9896186,0.0033197,0.0006185062,0.0005855983,0.005212059,0.0006454316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000578856,0.001608218,0.1793388,0.0009621272,0.0001021824,0.0005784338,0.003794333,0.002430221,0.008989349,0.01402668,0.01361943,0.7739714],"study_design_scores_gemma":[0.0004461515,0.01030812,0.7102784,0.002541014,0.0003470834,0.005087369,0.009273141,0.0266447,0.04198546,0.01677301,0.175901,0.0004145121],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6833267,0.002308717,0.1920859,0.002162276,0.001046427,0.01724883,0.007081653,0.002081055,0.09265855],"genre_scores_gemma":[0.5739101,0.001417869,0.3834685,0.0009473737,0.0001129131,0.01226147,0.008451964,0.000203957,0.01922594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008009762,"threshold_uncertainty_score":0.04236019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110321991743183,"score_gpt":0.292937380573598,"score_spread":0.2818341606561662,"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."}}