{"id":"W2469956075","doi":"10.5539/ijel.v6n4p12","title":"Validating an Academic Group Tutorial Discussion Speaking Test","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Psychology; Grading (engineering); Active listening; Cronbach's alpha; Test (biology); Construct validity; Face validity; Applied psychology; Mathematics education; Social psychology; Clinical psychology; Psychometrics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01580286,0.0006589473,0.0006226455,0.001485057,0.0009397993,0.001348308,0.001384947,0.0006124968,0.003523441],"category_scores_gemma":[0.02721319,0.00023175,0.0007397851,0.0005618714,0.0006562043,0.001024602,0.001685041,0.0006730597,0.002493593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001164359,"about_ca_system_score_gemma":0.002519864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003334068,"about_ca_topic_score_gemma":0.005092882,"domain_scores_codex":[0.9938212,0.002425932,0.0008028985,0.0006189875,0.001873612,0.0004573452],"domain_scores_gemma":[0.9700717,0.007053733,0.002513703,0.002439761,0.01493399,0.002987092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001495348,0.005258805,0.5402923,0.0005881461,0.0001944072,0.0009872228,0.02286277,0.002474594,0.02438955,0.001423848,0.007721124,0.3923118],"study_design_scores_gemma":[0.0002645685,0.01429241,0.8917314,0.0002498593,0.0001552155,0.001062737,0.01936956,0.01321363,0.03355948,0.0006971768,0.02525112,0.0001529423],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807623,0.00007703465,0.007165743,0.0001546911,0.0001260773,0.001392403,0.0003190307,0.0002246103,0.009778148],"genre_scores_gemma":[0.9712012,0.00009710214,0.01733959,0.0001482374,0.00004933848,0.001214044,0.00108984,0.00005484649,0.008805769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01580286,"threshold_uncertainty_score":0.08357453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04612066075859254,"score_gpt":0.3314109014771126,"score_spread":0.28529024071852,"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."}}