{"id":"W1983949565","doi":"10.1007/s11092-008-9063-x","title":"Using data to support educational improvement","year":2008,"lang":"en","type":"article","venue":"Educational Assessment Evaluation and Accountability","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":127,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Ministry of Education and Child Care","funders":"","keywords":"Data collection; Context (archaeology); Computer science; Scale (ratio); Data science; Knowledge management; Sociology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009523775,0.0002822558,0.000309444,0.0003668474,0.0007907636,0.0003798606,0.001150019,0.00006906506,0.01716572],"category_scores_gemma":[0.002532561,0.0002437913,0.00007075669,0.0008388679,0.0001724385,0.001773869,0.0006156723,0.0001842769,0.0002764126],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008636583,"about_ca_system_score_gemma":0.007289428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002441478,"about_ca_topic_score_gemma":0.0001137195,"domain_scores_codex":[0.9923185,0.0003259483,0.001205736,0.001406622,0.004377117,0.0003661245],"domain_scores_gemma":[0.9938186,0.001460957,0.0004173559,0.001571877,0.002373523,0.0003577132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003351561,0.002356694,0.8399504,0.00001828512,0.00007072533,1.725713e-7,0.001082572,0.0003208209,0.005371096,0.01199339,0.09438781,0.04441447],"study_design_scores_gemma":[0.0004879148,0.0001286852,0.9345005,0.000007925356,0.00004411086,0.00001434336,0.001179701,0.01157585,0.00006393185,0.03753353,0.01414955,0.0003139248],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9519051,0.00005192179,0.001440684,0.03811243,0.001870631,0.001457268,0.0001948144,0.00001774548,0.00494946],"genre_scores_gemma":[0.9707683,0.00000981536,0.02274924,0.002447888,0.0008855059,0.0002988775,0.0009421558,0.00001608073,0.001882176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09455007,"threshold_uncertainty_score":0.9983383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5729116068459882,"score_gpt":0.5914743349389096,"score_spread":0.01856272809292137,"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."}}