{"id":"W1964735878","doi":"10.1002/j.2333-8504.2005.tb01990.x","title":"ANALYSIS OF DISCOURSE FEATURES AND VERIFICATION OF SCORING LEVELS FOR INDEPENDENT AND INTEGRATED PROTOTYPE WRITTEN TASKS FOR THE NEW TOEFL®","year":2005,"lang":"en","type":"article","venue":"ETS Research Report Series","topic":"Software Engineering Research","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Test of English as a Foreign Language; Computer science; Natural language processing; Psychology; Artificial intelligence; Mathematics education; Language assessment","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":[0.002325503,0.00009337194,0.0002290504,0.000387119,0.0001441025,0.0001349958,0.0004175851,0.00005773546,0.000003968843],"category_scores_gemma":[0.002871457,0.00006504294,0.00005791264,0.0009244829,0.0002176304,0.000404753,0.0002159826,0.0001896613,1.189946e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004085656,"about_ca_system_score_gemma":0.0003229892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002624266,"about_ca_topic_score_gemma":0.0002016873,"domain_scores_codex":[0.9984255,0.00005007491,0.000300699,0.0003434134,0.000604879,0.0002754164],"domain_scores_gemma":[0.9974728,0.001101339,0.0001050182,0.0005986843,0.0006315527,0.00009067286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00145126,0.0003381527,0.120562,0.001509829,0.003612379,0.00005676824,0.01757843,0.005264806,0.06851996,0.03216276,0.004518662,0.7444251],"study_design_scores_gemma":[0.0006414898,0.0008266608,0.8658916,0.0001377187,0.0001261196,0.00009286679,0.0008664462,0.02441253,0.09696329,0.001284616,0.008498325,0.0002583765],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5566862,0.001961216,0.4309771,0.006573038,0.00008805842,0.003559347,0.00004442733,0.00007461809,0.00003601002],"genre_scores_gemma":[0.9746764,0.00007626827,0.02381977,0.000003237956,0.00004705236,0.0003226921,0.00001110969,0.00001068321,0.001032779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7453296,"threshold_uncertainty_score":0.343761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.075963810214805,"score_gpt":0.3964993958148846,"score_spread":0.3205355856000797,"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."}}