{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0194444,0.00108538,0.001182171,0.004617534,0.001864237,0.002883821,0.00226478,0.002294532,0.002938395],"category_scores_gemma":[0.08583505,0.0005643032,0.001234972,0.007498257,0.0006288023,0.002240584,0.0043903,0.002643176,0.002177187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002451241,"about_ca_system_score_gemma":0.006348423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02373348,"about_ca_topic_score_gemma":0.0451344,"domain_scores_codex":[0.9803775,0.010236,0.002181282,0.002079827,0.004373936,0.0007514093],"domain_scores_gemma":[0.9091923,0.03080591,0.0105375,0.01827466,0.02703378,0.004155776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006696343,0.003012341,0.7973083,0.0006275388,0.001070082,0.0002178045,0.001214423,0.00929621,0.001454657,0.002154138,0.09114846,0.09182636],"study_design_scores_gemma":[0.0002215607,0.0003365486,0.9528535,0.000149708,0.0002260631,0.0001534159,0.001053919,0.01017806,0.001797791,0.002638107,0.03030078,0.00009052978],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6502891,0.0005036123,0.03779576,0.003831772,0.0004007781,0.004801696,0.2912846,0.001562039,0.009530629],"genre_scores_gemma":[0.5847388,0.0001613584,0.04725426,0.0005339531,0.00009258719,0.007644102,0.3567809,0.0001952746,0.002598779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02373348,"threshold_uncertainty_score":0.102833,"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."}}