{"id":"W2113150213","doi":"10.55016/ojs/ajer.v54i3.55237","title":"Alignment of Scores on Large-Scale Assessments and Report-Card Grades","year":2008,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Report card; Psychology; Scale (ratio); Rating scale; Mathematics education; Statistics; Clinical psychology; Applied psychology; Developmental psychology; Pedagogy; Geography; Mathematics; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002072946,0.00007567178,0.0001758799,0.0002968977,0.0005377852,0.00003637207,0.0002713249,0.00005693573,0.002276373],"category_scores_gemma":[0.002358657,0.00006565492,0.00007295659,0.0003080156,0.0004286623,0.0002405268,0.00003959146,0.0002565169,0.00002410453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001675468,"about_ca_system_score_gemma":0.003181754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002428939,"about_ca_topic_score_gemma":0.002230634,"domain_scores_codex":[0.9972133,0.0004053203,0.0004342599,0.0001536542,0.001500582,0.0002928805],"domain_scores_gemma":[0.9901766,0.00830309,0.0002865,0.0001344714,0.0008695245,0.0002298534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006004427,0.0009009631,0.8778584,0.00001647165,0.00007169259,0.000004258861,0.009158291,0.000003812881,0.0001883811,0.07757536,0.03397281,0.0001895205],"study_design_scores_gemma":[0.0005094709,0.0005851826,0.8494102,0.0001538868,0.00002594488,0.0001643321,0.0135241,0.000004991727,0.0003652006,0.01066846,0.1244296,0.0001586706],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9014595,0.0003326387,0.000002426229,0.0190839,0.0003673018,0.0001169196,0.000002867528,3.406764e-7,0.07863408],"genre_scores_gemma":[0.959152,0.0008247137,0.0003785767,0.00007167778,0.0006857257,0.000009846034,0.000009605455,0.000007333482,0.03886045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09045674,"threshold_uncertainty_score":0.9986357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2037117002265996,"score_gpt":0.5313738724859143,"score_spread":0.3276621722593147,"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."}}