{"id":"W2006092868","doi":"10.1016/j.asw.2008.10.004","title":"Harming not helping: The impact of a Canadian standardized writing assessment on curriculum and pedagogy","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Curriculum; Writing assessment; Pedagogy; Sociology; Psychology; Political science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002168856,0.0002109067,0.0003489325,0.0003633111,0.003077924,0.0004496031,0.0002925526,0.0001015971,0.0000829389],"category_scores_gemma":[0.0003582748,0.0001678391,0.0001639266,0.0007278214,0.0003908023,0.0004750229,0.00007529297,0.0003753738,0.00000277396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004742387,"about_ca_system_score_gemma":0.001743025,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2208007,"about_ca_topic_score_gemma":0.0161039,"domain_scores_codex":[0.9973892,0.0003831964,0.0004447042,0.000325146,0.0007262683,0.0007314864],"domain_scores_gemma":[0.9983289,0.0007059657,0.0002938328,0.0001909979,0.0002336213,0.0002466881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007877985,0.00007127399,0.9661444,0.00001984585,0.00009220604,0.00005880836,0.01306887,0.00004693269,0.001720813,0.006507233,0.0006039818,0.01165769],"study_design_scores_gemma":[0.0009911158,0.0001272959,0.8972797,0.0004861708,0.0000541701,0.00002559943,0.09737131,0.001316859,0.00018349,0.0001087658,0.001605199,0.0004503031],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9267267,0.0001183326,0.0001024695,0.001554813,0.0001451061,0.0002614995,0.000009241053,0.00005526047,0.0710266],"genre_scores_gemma":[0.9974539,0.0001805719,0.001659786,0.0001320045,0.0004344524,0.00001329175,0.000004898171,0.00002454139,0.00009649894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2046967,"threshold_uncertainty_score":0.9982199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06685673604162803,"score_gpt":0.4357627813712832,"score_spread":0.3689060453296551,"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."}}