{"id":"W2078094792","doi":"10.1007/s10763-007-9090-y","title":"Using Large-scale Assessment Datasets for Research in Science and Mathematics Education: Programme for International Student Assessment (PISA)","year":2007,"lang":"en","type":"article","venue":"International Journal of Science and Mathematics Education","topic":"Educational Environments and Student Outcomes","field":"Social Sciences","cited_by":93,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics education; Scientific literacy; Science education; Scale (ratio); Literacy; Student achievement; Educational research; Achievement test; Test (biology); Academic achievement; Psychology; Pedagogy; Standardized test; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02327967,0.0001123909,0.0001673415,0.001017909,0.0008388209,0.000712721,0.001046286,0.00004628211,0.00001476474],"category_scores_gemma":[0.001733097,0.0001011054,0.00003769144,0.0005279624,0.00129489,0.001207197,0.0001970429,0.0001673493,4.92629e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002008644,"about_ca_system_score_gemma":0.007715677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006691091,"about_ca_topic_score_gemma":0.0001379483,"domain_scores_codex":[0.9952974,0.00003225652,0.0006800831,0.0002889177,0.003262349,0.0004389512],"domain_scores_gemma":[0.9942555,0.0005738678,0.0004798058,0.0001436298,0.004299006,0.0002482013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002630936,0.009474589,0.07265723,0.0001700079,0.0000849005,0.000001684906,0.07022585,0.00002173734,0.004154203,0.7675853,0.002556007,0.07304215],"study_design_scores_gemma":[0.001801344,0.0002414457,0.1496212,0.0008085846,0.00007696407,0.00008143856,0.6122146,0.005223189,0.0003624274,0.1062585,0.1228332,0.0004770824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9478138,0.0001511184,0.02378207,0.01563173,0.006493669,0.001833118,0.00004790739,0.000008764749,0.004237791],"genre_scores_gemma":[0.6468516,0.0001903669,0.3514499,0.0003482055,0.0008105861,0.00008459485,0.00001545613,0.00001109855,0.0002381694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6613268,"threshold_uncertainty_score":0.9979097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1690225826307483,"score_gpt":0.5823773151514444,"score_spread":0.4133547325206962,"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."}}