{"id":"W2993353296","doi":"10.5539/elt.v13n1p18","title":"Comparison of Automatic and Expert Teachers’ Rating of Computerized English Listening-Speaking Test","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Active listening; Rasch model; Test (biology); Reliability (semiconductor); Inter-rater reliability; Rating scale; Mathematics education; Applied psychology; Developmental psychology; Communication","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":[0.0007681214,0.0001517519,0.0003875147,0.0001456926,0.00009073317,0.0000634411,0.0005850863,0.00009109677,0.00001739784],"category_scores_gemma":[0.0009663026,0.0001449669,0.0000556203,0.0001560721,0.00005858308,0.0004176142,0.0003152833,0.0004356393,0.000001050654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003453425,"about_ca_system_score_gemma":0.00004609619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006668107,"about_ca_topic_score_gemma":0.000003201441,"domain_scores_codex":[0.9986616,0.0001483564,0.0004458255,0.000303199,0.000240101,0.0002008629],"domain_scores_gemma":[0.9982549,0.00081087,0.0003616324,0.0004530601,0.00007526834,0.0000442647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000001659045,0.0003020931,0.08847149,0.0001235089,0.00004293382,0.000003159339,0.8146486,0.00006187933,0.02907907,0.01164227,0.0001097413,0.05551364],"study_design_scores_gemma":[0.003969603,0.0009877828,0.0340896,0.002646093,0.00006267906,0.00002733034,0.5185774,0.3488244,0.08648559,0.0004558581,0.002386232,0.001487422],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768179,0.0005316848,0.01829157,0.00007498626,0.0004945654,0.0001737024,0.000001906193,0.0003173898,0.003296318],"genre_scores_gemma":[0.8682559,0.000001302346,0.1315317,0.00004023491,0.0001040122,0.000006467325,0.000004687159,0.00001024589,0.00004545424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3487625,"threshold_uncertainty_score":0.5911579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0112248277917318,"score_gpt":0.3145122398373942,"score_spread":0.3032874120456624,"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."}}