{"id":"W2082767250","doi":"10.1177/0265532208101010","title":"An investigation into native and non-native teachers' judgments of oral English performance: A mixed methods approach","year":2009,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":137,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Pronunciation; Rasch model; Consistency (knowledge bases); Grammar; Mathematics education; First language; Internal consistency; Multimethodology; Linguistics; Psychometrics; Developmental psychology; Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0417037,0.0006480066,0.0008543473,0.00311591,0.002603126,0.002956682,0.001306123,0.0006082811,0.001026302],"category_scores_gemma":[0.05004807,0.0006764524,0.0005815889,0.001619973,0.001699835,0.00136684,0.00185989,0.0005619381,0.0002681937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001627646,"about_ca_system_score_gemma":0.002254832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004566922,"about_ca_topic_score_gemma":0.01536712,"domain_scores_codex":[0.9665099,0.02428945,0.00224711,0.001928286,0.004367743,0.0006575187],"domain_scores_gemma":[0.9390922,0.04464059,0.004326257,0.003399726,0.007683879,0.0008573094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001390271,0.003530941,0.3214507,0.000972909,0.0003686852,0.0008487219,0.4738581,0.0004838374,0.01729441,0.001584493,0.0002813131,0.1779356],"study_design_scores_gemma":[0.0004271279,0.01309273,0.3884966,0.0005438776,0.0004753736,0.001454717,0.5517167,0.005656139,0.02621405,0.002588756,0.009041518,0.0002924264],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879448,0.0001672156,0.009387945,0.00007053011,0.00001920398,0.0009306056,0.00007954667,0.00001685538,0.001383254],"genre_scores_gemma":[0.9609865,0.0002290241,0.0337419,0.0001724302,0.00002291856,0.003398923,0.0001208821,0.00002155667,0.001305829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0417037,"threshold_uncertainty_score":0.2205529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04154220340015909,"score_gpt":0.3200407438186342,"score_spread":0.2784985404184751,"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."}}