{"id":"W2889522036","doi":"10.5539/ies.v11n9p12","title":"Interrater Scoring of Public Speaking Performances in English Language Teacher Education Program","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Inter-rater reliability; Mathematics education; Curriculum; Rating scale; Qualitative research; Qualitative property; Empowerment; Pedagogy; Teacher education; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005498487,0.00007889622,0.0001092871,0.0002700774,0.0001304596,0.00009531466,0.0002631994,0.00003259757,0.0003515275],"category_scores_gemma":[0.0007476577,0.00007369325,0.00003387368,0.0002841119,0.0002592956,0.0006005514,0.00007195206,0.00007701695,0.00002322309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002404816,"about_ca_system_score_gemma":0.0004233549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006688636,"about_ca_topic_score_gemma":0.002399691,"domain_scores_codex":[0.9990399,0.00006773672,0.0002509726,0.0001583551,0.0003281297,0.0001549322],"domain_scores_gemma":[0.9982087,0.00004464665,0.0001503412,0.00008023837,0.001485963,0.00003010595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000006765903,0.0007322814,0.5499142,0.00001319047,0.00005693782,7.729913e-8,0.2523673,1.982636e-7,0.00004652951,0.004385395,0.002513754,0.1899634],"study_design_scores_gemma":[0.0001660882,0.00004857935,0.1743899,0.0001757368,0.00001005516,2.686452e-7,0.6507661,0.00001945794,0.0001878891,0.0003469666,0.1737519,0.0001370413],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8529606,0.000602692,0.000007495549,0.001041693,0.007095044,0.0002296566,5.428442e-7,0.00004571331,0.1380166],"genre_scores_gemma":[0.9906074,0.0001969957,0.0008553122,0.0000815655,0.002142695,0.000188644,0.000008820151,0.000006114904,0.005912444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3983988,"threshold_uncertainty_score":0.384898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08813912167534482,"score_gpt":0.4762929714795188,"score_spread":0.3881538498041739,"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."}}