{"id":"W1504933570","doi":"10.1002/ets2.12050","title":"Test Takers' Writing Activities During the<i><scp>TOEFL iBT</scp><sup>®</sup></i>Writing Tasks: A Stimulated Recall Study","year":2015,"lang":"en","type":"article","venue":"ETS Research Report Series","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Test of English as a Foreign Language; Test (biology); Task (project management); Psychology; Second language writing; Mathematics education; Recall; English language; Cognitive psychology; Linguistics; Second language","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":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02048649,0.0003190058,0.000445477,0.0003681246,0.004881889,0.00168364,0.0007284533,0.0002223905,0.00004990469],"category_scores_gemma":[0.0403089,0.0002890061,0.0001204186,0.001517614,0.00122298,0.001313814,0.0004046568,0.001345979,0.00007762029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005457953,"about_ca_system_score_gemma":0.001774438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005776494,"about_ca_topic_score_gemma":0.002016699,"domain_scores_codex":[0.9915826,0.002073101,0.0009412749,0.0008497308,0.002905735,0.00164751],"domain_scores_gemma":[0.9920149,0.004593248,0.0003726342,0.0008143476,0.001642799,0.0005620204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009618516,0.001585794,0.470497,0.000312267,0.0002344677,0.00278136,0.4987831,0.0006751416,0.001664592,0.001383823,0.01668504,0.005301282],"study_design_scores_gemma":[0.0006766269,0.0004154456,0.02034014,0.0003757244,0.00002777424,0.0002966138,0.9442359,0.0001601757,0.0006693769,0.001278314,0.03130058,0.0002233955],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9291077,0.0003646374,0.000004474733,0.003074386,0.0002167611,0.001105557,0.00001302504,0.0004951194,0.06561836],"genre_scores_gemma":[0.969063,0.0001077817,0.0002619346,0.00003683464,0.001924188,0.0002608782,0.00002559253,0.00006938612,0.02825037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4501569,"threshold_uncertainty_score":0.9999562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1097165021020219,"score_gpt":0.4172894513180939,"score_spread":0.3075729492160719,"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."}}