{"id":"W2290866021","doi":"10.18806/tesl.v32i0.1217","title":"The Relationship Between Lexical Frequency Profiling Measures and Rater Judgements of Spoken and Written General English Language Proficiency on the CELPIP-General Test","year":2016,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Vocabulary; Test (biology); Linguistics; Profiling (computer programming); Lexical density; Standardized test; Language proficiency; Lexical item; Cognitive psychology; Computer science; Mathematics education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009450993,0.0001174288,0.0001259203,0.00005201159,0.0004636404,0.00006751318,0.0001784953,0.0000564401,0.006127803],"category_scores_gemma":[0.001050166,0.00005581902,0.00002904445,0.0000802672,0.0001202714,0.0000658278,0.00002681375,0.0003486722,0.000002787447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006065726,"about_ca_system_score_gemma":0.0001485743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003773518,"about_ca_topic_score_gemma":0.001152845,"domain_scores_codex":[0.9986435,0.0003162439,0.0002973276,0.0001611044,0.0003015121,0.0002803179],"domain_scores_gemma":[0.99831,0.001135635,0.0001636979,0.000184707,0.00009375688,0.0001121636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007317096,0.00004821644,0.9349139,0.00001507214,0.0001433812,0.0001415927,0.006382713,0.000002073631,0.009219049,0.01546932,0.02018804,0.01340342],"study_design_scores_gemma":[0.0009173689,0.0001694507,0.9897224,0.000052901,0.00003537185,0.00008188302,0.004466712,0.000006175854,0.001152066,0.0005105822,0.002711072,0.0001739835],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869841,0.008559351,0.0000263109,0.002255159,0.0002516111,0.0001432963,0.00002984691,0.0000111703,0.001739194],"genre_scores_gemma":[0.991212,0.000005839966,0.00007336521,0.006446433,0.000634148,0.000008671813,0.000003009319,0.00001415959,0.001602408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05480848,"threshold_uncertainty_score":0.9947807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03343393740597254,"score_gpt":0.2879289499966267,"score_spread":0.2544950125906541,"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."}}