{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001155387,0.0001420475,0.0001992127,0.0001099408,0.0003225747,0.0000983085,0.0001067728,0.00004438387,0.00002396408],"category_scores_gemma":[0.0007698403,0.0001239099,0.00002288274,0.00007973056,0.000142393,0.0004091733,0.0000250243,0.0003415127,7.06702e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002950846,"about_ca_system_score_gemma":0.00002206755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007746941,"about_ca_topic_score_gemma":0.00003919139,"domain_scores_codex":[0.9989463,0.0003177896,0.0002082213,0.0002180045,0.0001390702,0.0001706197],"domain_scores_gemma":[0.9993135,0.0001982529,0.0001766146,0.0001218346,0.0001271684,0.00006257673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000005036533,0.00004507543,0.004986664,0.00004149772,0.00001603269,0.000001039187,0.8422319,0.00007775443,0.003015193,0.0007998537,0.00002082888,0.1487592],"study_design_scores_gemma":[0.001566952,0.00156339,0.0506083,0.0005329209,0.0001354867,0.000006502383,0.8271337,0.106333,0.009431276,0.001483698,0.0003798519,0.0008249379],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9757374,0.000114781,0.0005273069,0.00001392735,0.00007283677,0.0001209268,0.000001913189,0.0001330943,0.02327783],"genre_scores_gemma":[0.9013217,6.711829e-7,0.09794325,0.00009590042,0.0002086236,0.000006673522,0.0000247728,0.00001338915,0.00038504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1479342,"threshold_uncertainty_score":0.50529,"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."}}