{"id":"W1531240630","doi":"10.58680/rte201424579","title":"A Framework for Using Consequential Validity Evidence in Evaluating Large-Scale Writing Assessments: A Canadian Study","year":2014,"lang":"en","type":"article","venue":"Research in the Teaching of English","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Lethbridge","funders":"","keywords":"Scale (ratio); Psychology; Test validity; Mathematics education; Pedagogy; Psychometrics; Developmental psychology; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09818516,0.0001100602,0.0002529053,0.0004060734,0.001275876,0.0003355237,0.0009909467,0.0001123354,0.00002251352],"category_scores_gemma":[0.04033357,0.0001000796,0.00006591832,0.0007065354,0.0002001451,0.0004006039,0.000144098,0.001249003,9.895568e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006607172,"about_ca_system_score_gemma":0.0008422278,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2240594,"about_ca_topic_score_gemma":0.2969534,"domain_scores_codex":[0.9866157,0.009847878,0.0004545437,0.0003594405,0.001692304,0.001030103],"domain_scores_gemma":[0.9882947,0.01060233,0.0001180357,0.0003202111,0.0005391919,0.0001255185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003949275,0.0003986191,0.740841,0.00004651309,0.00001437247,0.000004708913,0.227613,0.000082531,0.00002426313,0.02958147,0.00009654798,0.001257435],"study_design_scores_gemma":[0.001602492,0.0007088039,0.07853465,0.001718257,0.00003617374,2.701991e-7,0.8781093,0.01565048,0.000007424291,0.02225236,0.001058437,0.0003213334],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988718,0.00003881172,0.001463908,0.0003430134,0.0003595508,0.001653931,0.000004834013,0.00001734121,0.007400565],"genre_scores_gemma":[0.9908051,0.000005257129,0.008126366,0.00004146618,0.0008755132,0.0001120022,0.000001744599,0.00001382571,0.00001874594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6623064,"threshold_uncertainty_score":0.9813137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.50791354546036,"score_gpt":0.5991396042643354,"score_spread":0.09122605880397539,"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."}}