{"id":"W2596511830","doi":"","title":"The Rights and Responsibility of Test Takers when Large-Scale Testing Is Used for Classroom Assessment","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Test (biology); Expectancy theory; Scale (ratio); Psychology; Mathematics education; Descriptive statistics; Social psychology; Pedagogy; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.1311193,0.0003868745,0.0006265446,0.003024913,0.004016599,0.007480425,0.002582392,0.001845691,0.001858292],"category_scores_gemma":[0.4266312,0.0005983223,0.0005049634,0.001505258,0.01078442,0.005979145,0.005660612,0.004669178,0.0005866717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003926796,"about_ca_system_score_gemma":0.009155406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006007923,"about_ca_topic_score_gemma":0.006293837,"domain_scores_codex":[0.7331327,0.1791482,0.01640205,0.009528444,0.05266867,0.009119859],"domain_scores_gemma":[0.4312956,0.3541849,0.1108908,0.04569225,0.04474275,0.01319371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003161574,0.000412699,0.4660224,0.0002162295,0.0001087802,0.001399042,0.303561,0.000651936,0.006941606,0.03922872,0.003733113,0.1774083],"study_design_scores_gemma":[0.00008684048,0.0007926796,0.5205863,0.001217875,0.0001074501,0.004666153,0.3149022,0.005284072,0.01648898,0.05991155,0.07547682,0.0004790652],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9235629,0.0006222748,0.02652109,0.01271066,0.0001778642,0.0002022447,0.00008943659,0.00008935783,0.03602418],"genre_scores_gemma":[0.9948444,0.00008139374,0.002883767,0.0005576141,0.00003905538,0.0001007093,0.00002452772,0.0000221204,0.001446424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1311193,"threshold_uncertainty_score":0.6934333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1375582813637777,"score_gpt":0.4016476764237638,"score_spread":0.2640893950599861,"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."}}