{"id":"W1876976565","doi":"10.1111/j.1745-3992.2010.00198.x","title":"Reporting the Percentage of Students above a Cut Score: The Effect of Group Size","year":2011,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics education; Scale (ratio); Statistics; Psychology; Reading (process); Mathematics; Geography; Cartography; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3075692,0.001223244,0.001945327,0.004067761,0.002409939,0.003070505,0.003489143,0.002104631,0.001782198],"category_scores_gemma":[0.654336,0.001110365,0.003087158,0.004799057,0.005304018,0.003552815,0.004268879,0.00250008,0.0006032989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002641438,"about_ca_system_score_gemma":0.001707794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01049613,"about_ca_topic_score_gemma":0.009130489,"domain_scores_codex":[0.5072284,0.3768885,0.03421108,0.02782593,0.05118144,0.002664583],"domain_scores_gemma":[0.08421142,0.7973049,0.04694694,0.05009352,0.02010393,0.001339323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01001756,0.0006051736,0.8779907,0.0007489296,0.00671886,0.0002510549,0.01103949,0.003305553,0.002734716,0.002364464,0.004834987,0.0793885],"study_design_scores_gemma":[0.0003183671,0.004281472,0.9664199,0.0003937517,0.002109097,0.0004308068,0.002620434,0.009466684,0.006431779,0.002249213,0.00509032,0.0001882076],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.896157,0.004903854,0.07722037,0.002567616,0.00085169,0.001925364,0.001456097,0.0007510402,0.014167],"genre_scores_gemma":[0.9777914,0.0001695992,0.01913293,0.000475804,0.00008253072,0.0008696303,0.0004348489,0.0002008903,0.0008424221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3075692,"threshold_uncertainty_score":0.8538904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3899556216284745,"score_gpt":0.5438855402313928,"score_spread":0.1539299186029183,"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."}}