{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006644728,0.00057732,0.0005394156,0.001394986,0.0006484786,0.003283902,0.0009095906,0.001432443,0.006379295],"category_scores_gemma":[0.1263865,0.0003952712,0.0003763816,0.0005136477,0.0006866336,0.002799569,0.00235374,0.001285241,0.001526256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005614921,"about_ca_system_score_gemma":0.0006073504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001198022,"about_ca_topic_score_gemma":0.0014125,"domain_scores_codex":[0.9956612,0.001869545,0.0006208459,0.0006632548,0.0009295165,0.0002556882],"domain_scores_gemma":[0.8512352,0.130911,0.004027478,0.004804761,0.007278851,0.001742723],"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":[0.01472364,0.00507491,0.1609657,0.001478212,0.0003370864,0.001561137,0.2193298,0.004006798,0.1758124,0.003128404,0.003406787,0.4101751],"study_design_scores_gemma":[0.00119602,0.01187467,0.8056464,0.0006283011,0.0004372782,0.002710273,0.05703959,0.02426172,0.07898418,0.006342663,0.01035611,0.0005227879],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976241,0.00003241656,0.0007184687,0.00001828776,0.00001090581,0.00004913749,0.00006972805,0.00004286138,0.001434064],"genre_scores_gemma":[0.9931191,0.00003073208,0.00292788,0.00006175579,0.000009933069,0.000192241,0.0003754334,0.00008713389,0.003195851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006644728,"threshold_uncertainty_score":0.03514111,"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."}}