{"id":"W4292582621","doi":"10.5539/elt.v15n9p69","title":"The Influence of Partners’ L2 Proficiency on Test-Takers’ Performance in Paired Oral Assessment","year":2022,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Anhui Provincial Department of Education","keywords":"Psychology; Test (biology); Zone of proximal development; Ceiling effect; Mathematics education; Social psychology","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":[0.004374928,0.0005637788,0.0003468207,0.000879703,0.0006541004,0.002179936,0.000574185,0.0005071114,0.003787265],"category_scores_gemma":[0.03464885,0.0002548893,0.0004661399,0.0004586481,0.0009425464,0.0008376365,0.002156116,0.0007182029,0.0009655516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004245302,"about_ca_system_score_gemma":0.0005494784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004318209,"about_ca_topic_score_gemma":0.003675307,"domain_scores_codex":[0.9919583,0.004116497,0.0005416788,0.0009871983,0.001794003,0.0006023829],"domain_scores_gemma":[0.9748526,0.01294293,0.004245364,0.00186445,0.002136172,0.003958602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004100668,0.0004485817,0.9578272,0.00004279478,0.0001395113,0.0008808929,0.008692251,0.0002776954,0.00469438,0.0001224747,0.0001847902,0.02627952],"study_design_scores_gemma":[0.000007798056,0.0005494697,0.9920635,0.00001391581,0.00003575118,0.0003060547,0.004605863,0.0005516206,0.001367793,0.000110607,0.0003584563,0.00002920307],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977125,0.00004677169,0.0002401545,0.00003328082,0.000005407482,0.00001060088,0.00002713573,0.000009011305,0.001915217],"genre_scores_gemma":[0.9991323,0.00002272258,0.0001665497,0.000009301019,0.000002962691,0.00001163709,0.00002620816,0.000004469331,0.0006239319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004374928,"threshold_uncertainty_score":0.02313709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02720714462329934,"score_gpt":0.381316186096742,"score_spread":0.3541090414734427,"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."}}