{"id":"W2013836468","doi":"10.1080/09500790.2010.490875","title":"Assessment use, self-efficacy and mathematics achievement: comparative analysis of PISA 2003 data of Finland, Canada and the USA","year":2010,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Mathematical Sciences","keywords":"Student achievement; Mathematics education; Academic achievement; Psychology; Test (biology); Achievement test; Standardized test; Pedagogy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01158043,0.00005610737,0.000189424,0.0002493272,0.0002118205,0.00008319369,0.0002966516,0.00003496613,0.0002121174],"category_scores_gemma":[0.001145322,0.00004291307,0.000009314172,0.001842507,0.0003440428,0.0002507538,0.0001063954,0.0001900788,6.710512e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000137887,"about_ca_system_score_gemma":0.004044782,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3734736,"about_ca_topic_score_gemma":0.8909272,"domain_scores_codex":[0.9968417,0.001027359,0.0002961728,0.0001851875,0.001501677,0.0001478641],"domain_scores_gemma":[0.9968607,0.00142082,0.000175288,0.0003410744,0.00115012,0.00005196335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003113051,0.001211901,0.8807703,0.00003992162,0.0003884399,6.104295e-8,0.04424964,0.00005675967,0.0002637191,0.06201939,0.00412392,0.006844798],"study_design_scores_gemma":[0.0005699018,0.00001562851,0.9640101,0.00001373254,0.0001777702,3.438608e-8,0.01639088,0.01601341,0.000009377681,0.0005287864,0.002226186,0.00004414855],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928948,0.00006547527,0.00001799928,0.001784743,0.0001345909,0.001000384,0.00001734194,0.000001450835,0.004083178],"genre_scores_gemma":[0.996965,0.00018691,0.002387656,0.00001706957,0.0000385176,0.00005689279,0.00008234307,0.000002079677,0.0002635317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5174536,"threshold_uncertainty_score":0.717527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.274453178486928,"score_gpt":0.5499734689545585,"score_spread":0.2755202904676305,"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."}}