{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.007682689,0.0001389913,0.0002554773,0.0003668555,0.001529106,0.0006484516,0.0009002761,0.0000762175,0.00008033603],"category_scores_gemma":[0.01553923,0.0001083389,0.00009975125,0.0002067778,0.0002015091,0.0005884041,0.00002054016,0.0001828233,0.000001770754],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001610142,"about_ca_system_score_gemma":0.01574362,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01648419,"about_ca_topic_score_gemma":0.5584232,"domain_scores_codex":[0.9978857,0.0001594258,0.000944354,0.0002992447,0.0002547973,0.0004564579],"domain_scores_gemma":[0.9906848,0.002795806,0.001818514,0.0008312869,0.003019733,0.0008498781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002840644,0.0002509051,0.7748674,0.00006083416,0.00006537395,0.000001363833,0.04944462,0.00001171493,0.001443704,0.01279311,0.1245859,0.03644675],"study_design_scores_gemma":[0.0003533638,0.0002249329,0.6677608,0.0001136405,0.00005335877,0.00003234479,0.0254628,0.0005559906,0.0002732246,0.1757746,0.1292402,0.00015466],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9562144,0.0001387083,0.0007374766,0.03833965,0.003168095,0.000403008,0.0001084775,0.000001732926,0.0008884384],"genre_scores_gemma":[0.9865854,0.000004164476,0.007886434,0.0003163365,0.0004359862,0.00003848647,0.000009646706,0.000011291,0.004712187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.541939,"threshold_uncertainty_score":0.9997708,"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."}}