{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002113255,0.0003519271,0.0008006709,0.006217508,0.002848005,0.002075067,0.001208403,0.0004186275,0.001391959],"category_scores_gemma":[0.007020174,0.0002859271,0.0007803359,0.01693053,0.0007723185,0.0004596009,0.001387465,0.0005855896,0.0002390212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01537634,"about_ca_system_score_gemma":0.02725194,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9870164,"about_ca_topic_score_gemma":0.9909203,"domain_scores_codex":[0.997855,0.0001896898,0.0001676692,0.00020419,0.001115291,0.0004680566],"domain_scores_gemma":[0.9894919,0.001269028,0.001314155,0.0002457558,0.006507714,0.001171487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008815424,0.00004590594,0.9904759,0.00006229076,0.0001170821,0.00009823123,0.00198539,0.0001379207,0.0001490979,0.000151195,0.0009880317,0.005700716],"study_design_scores_gemma":[0.000003587755,0.00001340465,0.9963657,0.00002388988,0.00002911723,0.00003497462,0.002408256,0.000117911,0.0001008917,0.00000931162,0.0008832215,0.000009625251],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904974,0.0003981517,0.0001053847,0.0001318259,0.000008447061,0.00003555782,0.006535911,0.0000119034,0.002275353],"genre_scores_gemma":[0.9880618,0.0004102833,0.0002863728,0.00006359304,0.000003899208,0.00004849207,0.01018536,0.00001121916,0.0009289892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01537634,"threshold_uncertainty_score":0.1115637,"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."}}