{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003149597,0.0001105661,0.0001529559,0.00008914553,0.000268127,0.0001034215,0.0003436116,0.00004757102,0.0003555015],"category_scores_gemma":[0.0001203119,0.00005853516,0.000114547,0.000101954,0.0001234794,0.0001550461,0.00004477828,0.0003950646,0.00000834658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001411215,"about_ca_system_score_gemma":0.00001324362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000702597,"about_ca_topic_score_gemma":0.001097156,"domain_scores_codex":[0.998778,0.0002797553,0.0003265392,0.000131364,0.0002274348,0.0002568764],"domain_scores_gemma":[0.9994527,0.000104892,0.0001515341,0.0002428454,0.00002935135,0.00001864642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001792309,0.00007533687,0.003651164,0.00007025285,0.00001655274,0.00002278726,0.7045236,0.00005997505,0.000219637,0.279721,0.0003412793,0.0112806],"study_design_scores_gemma":[0.00198359,0.001040746,0.09783723,0.004555697,0.0002179214,0.00007498192,0.6314937,0.006274582,0.00535277,0.1368453,0.1127218,0.00160172],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9093957,0.000700975,0.0001447534,0.0005660188,0.0001121187,0.0002290983,0.000003538956,0.0000427311,0.08880504],"genre_scores_gemma":[0.996778,0.000003526392,0.00003542408,0.001403925,0.0001574186,0.000002508852,0.000008126435,0.00001303323,0.001598108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1428757,"threshold_uncertainty_score":0.3892492,"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."}}