{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1783687,0.0008130009,0.001010267,0.006722518,0.00523628,0.009038216,0.004826706,0.002168444,0.002485752],"category_scores_gemma":[0.5317957,0.0006734873,0.001641216,0.006111457,0.01809934,0.004133444,0.008799448,0.002775795,0.000191719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04590621,"about_ca_system_score_gemma":0.04270188,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4577401,"about_ca_topic_score_gemma":0.4440976,"domain_scores_codex":[0.8053914,0.131009,0.007624681,0.004572826,0.04813973,0.003262399],"domain_scores_gemma":[0.3516014,0.5002401,0.06280159,0.01280341,0.07066703,0.001886627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001097542,0.0003335537,0.6406736,0.002815852,0.0009401556,0.0008947505,0.1903153,0.002683178,0.0007447829,0.0645788,0.006554093,0.08836835],"study_design_scores_gemma":[0.0003664152,0.0009282005,0.7094768,0.0114942,0.001389317,0.0001902798,0.1912088,0.01114879,0.004854373,0.03023581,0.0384125,0.0002943715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8734542,0.006931508,0.01446214,0.0334613,0.0005854814,0.0012063,0.001570117,0.00006345061,0.06826553],"genre_scores_gemma":[0.992042,0.0004945359,0.004812666,0.000926743,0.00004284059,0.0005099642,0.0002940349,0.00001919496,0.0008579599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5422599,"threshold_uncertainty_score":0.9433153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646036534847547,"score_gpt":0.3890332495887422,"score_spread":0.3725728842402667,"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."}}