{"id":"W1984249886","doi":"10.1016/j.asw.2008.10.002","title":"How accurate are ESL students’ holistic writing scores on large-scale assessments?—A generalizability theory approach","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Alberta; Francis Crick Institute","keywords":"Generalizability theory; Reliability (semiconductor); Variance components; Psychology; Variance (accounting); Rating scale; Scale (ratio); Mathematics education; Variation (astronomy); Statistics; Mathematics; Developmental psychology; Accounting; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07491568,0.0009850069,0.001346943,0.004878155,0.001323996,0.003331717,0.001763703,0.002292308,0.002257773],"category_scores_gemma":[0.3230976,0.000627691,0.002213534,0.003282735,0.003310747,0.006852057,0.004198493,0.002313567,0.001011489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225684,"about_ca_system_score_gemma":0.001003914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002196302,"about_ca_topic_score_gemma":0.002325264,"domain_scores_codex":[0.9527761,0.0218336,0.005887711,0.007067039,0.01174684,0.0006886002],"domain_scores_gemma":[0.5202525,0.3436615,0.03345395,0.04898734,0.05128389,0.002360898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004496962,0.0004538807,0.8886583,0.0003324671,0.001566965,0.0001611449,0.007573518,0.001790644,0.001888764,0.002412092,0.001652682,0.09305978],"study_design_scores_gemma":[0.0001711512,0.001811277,0.953873,0.000399056,0.0009864885,0.0004750154,0.007027504,0.01320052,0.006367338,0.01163011,0.003950687,0.0001078612],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.921491,0.001016708,0.04975529,0.001578108,0.0003783091,0.0008213346,0.0006705493,0.0004459756,0.02384277],"genre_scores_gemma":[0.9903183,0.0001545296,0.007600429,0.0002925286,0.00008169505,0.0003797926,0.0004306793,0.00006664768,0.0006754977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07491568,"threshold_uncertainty_score":0.3961967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1330202938737769,"score_gpt":0.3594221099872191,"score_spread":0.2264018161134423,"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."}}