{"id":"W1214597323","doi":"10.26481/dis.20150617dc","title":"Teacher-based reactivity to provincial large-scale assessment in Canada","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Accountability; Test (biology); Mathematics education; Psychology; Medical education; Pedagogy; Political science; Geography; Medicine; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004728948,0.0001935687,0.0003437897,0.00113903,0.0051735,0.002251617,0.001226281,0.0005337694,0.004463033],"category_scores_gemma":[0.02905725,0.0003406831,0.0002363221,0.002620991,0.001220024,0.0004689769,0.002367705,0.0011598,0.0007043557],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.06446281,"about_ca_system_score_gemma":0.0644879,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9833582,"about_ca_topic_score_gemma":0.9921415,"domain_scores_codex":[0.992959,0.001580423,0.0002942205,0.0007016046,0.003088076,0.001376652],"domain_scores_gemma":[0.968349,0.004493931,0.002888493,0.001107143,0.01801086,0.005150711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004878611,0.0003167661,0.734595,0.0003103041,0.0000498099,0.0003934177,0.0965438,0.001495105,0.001820785,0.001519426,0.04819672,0.1142709],"study_design_scores_gemma":[0.00001473196,0.00008037639,0.9273103,0.0001254319,0.00001151702,0.00004292279,0.04373952,0.001060068,0.0005798094,0.0001544274,0.02682627,0.00005456161],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9664006,0.0003191816,0.0004432289,0.002901464,0.00007987876,0.0001792573,0.00143568,0.0001231201,0.02811772],"genre_scores_gemma":[0.9918426,0.0002033099,0.0003311105,0.0001675567,0.000007546615,0.00005209846,0.0004058371,0.00001934819,0.006970571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9355372,"threshold_uncertainty_score":0.4677126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06305222848576099,"score_gpt":0.428410135310017,"score_spread":0.3653579068242561,"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."}}