{"id":"W2568968076","doi":"10.1177/1362168816684366","title":"Developing the assessment literacy of teachers in Chinese language classrooms: A focus on assessment task design","year":2017,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Task (project management); Literacy; Psychology; Mathematics education; Professional development; Pedagogy; Task analysis; Authentic assessment; Quality (philosophy); Faculty development; Language assessment; Curriculum","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.02126425,0.000227872,0.0003526236,0.0003606108,0.002429437,0.0008925637,0.002118654,0.0001435179,0.0001711353],"category_scores_gemma":[0.002310554,0.0001575261,0.0001153194,0.0003458471,0.0005158896,0.0005049199,0.0005113065,0.001920951,0.00002352158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008858742,"about_ca_system_score_gemma":0.0007146316,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01782575,"about_ca_topic_score_gemma":0.004326982,"domain_scores_codex":[0.9919218,0.00428806,0.0004108639,0.0004671501,0.002017332,0.0008947812],"domain_scores_gemma":[0.9961212,0.0023686,0.0002550959,0.001021855,0.0001110479,0.0001222096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00004449388,0.0004513084,0.2916088,0.00003612549,0.00008668657,0.0001694214,0.5341461,0.00002153481,0.003746394,0.03750178,0.0004977845,0.1316896],"study_design_scores_gemma":[0.001633005,0.0002692696,0.773909,0.0004784393,0.00001773734,0.000001517785,0.2169586,0.0006885606,0.0001542788,0.003502205,0.001938801,0.0004485746],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8886061,0.0002053623,0.002660341,0.007043086,0.0002066929,0.001064317,0.000005694693,0.00006248024,0.100146],"genre_scores_gemma":[0.9879083,0.00005905707,0.008476843,0.00007240548,0.000361044,0.0001211893,0.000006750198,0.00003148512,0.002962906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4823001,"threshold_uncertainty_score":0.9988692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09606259991720532,"score_gpt":0.5312202756607064,"score_spread":0.4351576757435011,"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."}}