{"id":"W2109863812","doi":"10.1191/0265532204lt278oa","title":"A teacher-verification study of speaking and writing prototype tasks for a new TOEFL","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Test of English as a Foreign Language; Active listening; Psychology; Formative assessment; Mathematics education; Test (biology); CLARITY; Reading (process); Second language writing; Language proficiency; Presentation (obstetrics); Language assessment; Pedagogy; Computer science; Second language; Linguistics; Communication","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":[0.0003661521,0.00009192758,0.0001368742,0.0000523529,0.0003030353,0.0001014493,0.00006773145,0.0000200847,0.00003361943],"category_scores_gemma":[0.0006213356,0.00008420099,0.00002038952,0.00003605224,0.00002575096,0.0001085483,0.00002259408,0.0001523259,0.000001878259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001741643,"about_ca_system_score_gemma":0.00002548229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005348182,"about_ca_topic_score_gemma":0.001010677,"domain_scores_codex":[0.9993507,0.0000351501,0.000204487,0.0001713831,0.00008817248,0.0001501598],"domain_scores_gemma":[0.9994986,0.0001594528,0.0001471806,0.0001163153,0.00004610915,0.00003231229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002501725,0.000193915,0.008487372,0.0001722214,0.00002646607,0.00000701509,0.8562801,0.0001795212,0.003525621,0.004053048,0.00001679919,0.1270329],"study_design_scores_gemma":[0.005402894,0.003165028,0.01077141,0.001543824,0.0001963589,0.00003030716,0.9680936,0.002798713,0.0006503473,0.001676873,0.004861932,0.0008086776],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929972,0.0001994275,0.0004205132,0.00004932929,0.00003359448,0.000639434,0.000002000766,0.0001431058,0.005515357],"genre_scores_gemma":[0.9936404,1.625203e-7,0.005305791,0.00003040754,0.0005671749,0.00003456566,0.000005429826,0.00002172561,0.0003943319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1262242,"threshold_uncertainty_score":0.8084887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08046825576428888,"score_gpt":0.3114058708120012,"score_spread":0.2309376150477123,"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."}}