{"id":"W2090334593","doi":"10.1016/j.asw.2005.02.001","title":"Differences in written discourse in independent and integrated prototype tasks for next generation TOEFL","year":2005,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":334,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of Toronto","funders":"Educational Testing Service","keywords":"Test of English as a Foreign Language; Linguistics; Argument (complex analysis); Active listening; Computer science; Natural language processing; Reading (process); Test (biology); Psychology; Artificial intelligence; Language assessment; 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":[0.0003954075,0.0001064652,0.0001556516,0.00009970579,0.00009618766,0.0002573163,0.0000805923,0.00009569255,0.00003675069],"category_scores_gemma":[0.00007364514,0.00009445318,0.00001824016,0.0001217413,0.00005337272,0.0003594414,0.00001929694,0.000171726,0.000002741024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018889,"about_ca_system_score_gemma":0.00006711254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007042761,"about_ca_topic_score_gemma":0.001147179,"domain_scores_codex":[0.9990327,0.00009001746,0.0003016795,0.0002579448,0.00007422698,0.0002434806],"domain_scores_gemma":[0.9995784,0.0001839842,0.0000865825,0.00008692632,0.00003826413,0.00002591217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004330896,0.0002616324,0.85646,0.00005062997,0.00001747634,0.000009072796,0.00356892,0.00003345188,0.004233526,0.01598503,0.0002639577,0.119073],"study_design_scores_gemma":[0.0006145108,0.0000835945,0.95081,0.0001578242,0.000006570002,0.00001350745,0.04377053,0.003185637,0.0001169144,0.0008477411,0.0002003464,0.0001928541],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940862,0.0004012033,0.0004426052,0.002274428,0.0001570361,0.0003994959,0.000003530338,0.00002283258,0.002212668],"genre_scores_gemma":[0.995907,0.00001193017,0.003185071,0.0001149189,0.0002981085,0.0003145734,0.00003904289,0.00001051018,0.0001188571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1188801,"threshold_uncertainty_score":0.3851689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1472476809860803,"score_gpt":0.4120701150341848,"score_spread":0.2648224340481045,"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."}}