{"id":"W3096173211","doi":"10.37213/cjal.2020.30436","title":"Examining Rater Performance on the CELBAN Speaking: A Many-Facets Rasch Measurement Analysis","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Queen's University","keywords":"Rasch model; Psychology; Licensure; Language proficiency; Language assessment; Grammar; Rating scale; Inter-rater reliability; Reliability (semiconductor); Test (biology); Context (archaeology); Item response theory; Psychometrics; Applied psychology; Scale (ratio); Judgement; Medical education; Clinical psychology; Mathematics education; Medicine; Developmental psychology; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.001847743,0.0001490864,0.0003189267,0.0002050809,0.001066793,0.00003378232,0.0006036573,0.0001150483,0.0004794443],"category_scores_gemma":[0.002698504,0.00010935,0.00008470537,0.0004341608,0.00006270748,0.000008194698,0.00003394954,0.001435062,0.000137832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004031729,"about_ca_system_score_gemma":0.001810831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006381616,"about_ca_topic_score_gemma":0.002007659,"domain_scores_codex":[0.9979577,0.000272678,0.0008042105,0.0001454779,0.0003887053,0.0004312324],"domain_scores_gemma":[0.9968357,0.0004039633,0.0006076794,0.0004082866,0.001154545,0.0005898158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001370084,0.0001014487,0.3175415,0.001600857,0.003717959,0.0001939785,0.3209937,0.02111097,0.0005830218,0.2063497,0.1176505,0.008786285],"study_design_scores_gemma":[0.001119793,0.0005810815,0.02545079,0.001390665,0.0009314413,0.00000371472,0.03966058,0.01172206,0.0005382761,0.0005059392,0.9174647,0.0006309886],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5476241,0.0003410451,0.001083479,0.01036828,0.002591469,0.000794591,0.00003657713,0.00004740621,0.4371131],"genre_scores_gemma":[0.9904751,0.00001832271,0.0004752963,0.007716674,0.001220729,0.00001327364,0.00000370616,0.00002357528,0.00005335925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7998142,"threshold_uncertainty_score":0.8205013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1965768547620296,"score_gpt":0.3578816742305013,"score_spread":0.1613048194684717,"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."}}