{"id":"W3025093973","doi":"10.1007/s10833-020-09380-5","title":"Large-scale assessments and their effects: The case of mid-stakes tests in Ontario","year":2020,"lang":"en","type":"article","venue":"Journal of Educational Change","topic":"Global Educational Reforms and Inequalities","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Accountability; Excellence; Incentive; Equity (law); Transparency (behavior); Psychology; Standardized test; Scale (ratio); Pace; Test (biology); Literacy; Political science; Pedagogy; Economics; Mathematics education; Law; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005601894,0.00006139284,0.0001326757,0.00004782473,0.0001225274,0.00003093561,0.0001257514,0.00003245126,0.0002227854],"category_scores_gemma":[0.0005115227,0.00003687329,0.00004219178,0.0001840351,0.00007797175,0.000306911,0.00001775611,0.0001445591,0.000001389937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001664573,"about_ca_system_score_gemma":0.0009694073,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03282294,"about_ca_topic_score_gemma":0.2145908,"domain_scores_codex":[0.999303,0.00009077752,0.0002414443,0.00006224423,0.0001794955,0.0001230206],"domain_scores_gemma":[0.9988786,0.0004877042,0.0002254836,0.00004183513,0.0002582933,0.000108078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00005207693,0.0005514233,0.3088042,0.00008203444,0.00005560379,0.00001529263,0.639823,0.000003199103,0.00008772838,0.04439776,0.004151827,0.001975825],"study_design_scores_gemma":[0.000465022,0.0002605144,0.6892452,0.0001314481,0.00001995367,0.00008875792,0.2463995,0.00001153012,0.00006228763,0.01333155,0.04986847,0.0001158161],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9696029,0.000743774,0.000003006827,0.02703855,0.0003726579,0.0001153169,0.00001215167,8.906991e-7,0.002110797],"genre_scores_gemma":[0.997979,0.00006187443,0.0001478849,0.001031672,0.0005637772,0.000009378678,0.000002599079,0.000003082916,0.0002007064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3934236,"threshold_uncertainty_score":0.9736176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0907132103583014,"score_gpt":0.3791114910045938,"score_spread":0.2883982806462925,"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."}}