{"id":"W2024115163","doi":"10.1111/j.1944-9720.2007.tb02882.x","title":"Rethinking Description in the Russian SOPI: Shortcomings of the Simulated Oral Proficiency Interview","year":2007,"lang":"en","type":"article","venue":"Foreign Language Annals","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"American Council on The Teaching of Foreign Languages","keywords":"Conceptualization; Language proficiency; Psychology; Test (biology); Linguistics; Field (mathematics); Foreign language; Language assessment; Mathematics education","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1145171,0.0005479886,0.0006746295,0.001860876,0.001628495,0.004761618,0.002156024,0.001061058,0.001287675],"category_scores_gemma":[0.2157803,0.000589238,0.0005779455,0.001525867,0.006029943,0.00479078,0.008157807,0.002337093,0.0007884529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003808375,"about_ca_system_score_gemma":0.004951386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004540716,"about_ca_topic_score_gemma":0.006053277,"domain_scores_codex":[0.7711301,0.2059407,0.008190498,0.002545039,0.01087251,0.001321132],"domain_scores_gemma":[0.7847637,0.1711042,0.009923799,0.01286446,0.01997562,0.0013682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0009391346,0.0002607368,0.05951331,0.002209194,0.0001222494,0.0008603616,0.4521163,0.004607396,0.01516941,0.09322842,0.006466345,0.3645071],"study_design_scores_gemma":[0.0002774638,0.002030164,0.0865434,0.003878468,0.0001451568,0.002500438,0.5604545,0.03215832,0.0340911,0.06866615,0.2085452,0.0007096428],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6432457,0.0009776558,0.291655,0.01157579,0.001176156,0.002003896,0.0005422814,0.0005353884,0.0482882],"genre_scores_gemma":[0.930784,0.000680046,0.06132581,0.001347387,0.0001077343,0.002786326,0.0003108717,0.0001264542,0.002531349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1145171,"threshold_uncertainty_score":0.6056317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1200010285193464,"score_gpt":0.3189502230694571,"score_spread":0.1989491945501107,"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."}}