{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1265374,0.001277422,0.00148006,0.02060845,0.001561084,0.01206372,0.003093201,0.002499757,0.00590054],"category_scores_gemma":[0.3885965,0.0007616498,0.0009013476,0.01690657,0.001697478,0.01557655,0.004697712,0.003642687,0.003100257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005038702,"about_ca_system_score_gemma":0.01302296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01253138,"about_ca_topic_score_gemma":0.008790365,"domain_scores_codex":[0.8743509,0.0764405,0.01738034,0.005099734,0.02503241,0.001696189],"domain_scores_gemma":[0.3526927,0.4151126,0.04712729,0.07983913,0.1004831,0.004745127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001007604,0.001024262,0.2506191,0.002649312,0.0007679301,0.0004091189,0.004137779,0.009264724,0.001959468,0.09824534,0.08637863,0.5435368],"study_design_scores_gemma":[0.000541212,0.001081818,0.09669526,0.009935837,0.001204533,0.000494106,0.009884036,0.06922976,0.02425292,0.2401598,0.5460322,0.0004885201],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1572601,0.006527139,0.3848421,0.1158748,0.004841809,0.005095218,0.08617444,0.006458748,0.2329256],"genre_scores_gemma":[0.6995129,0.002544351,0.2467376,0.003679458,0.0005401695,0.001826631,0.03811068,0.0003703409,0.006677733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1265374,"threshold_uncertainty_score":0.6692017,"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."}}