{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03953705,0.00009783889,0.0001913273,0.00003967813,0.0002130492,0.00009444424,0.0004550954,0.00002394023,0.001373268],"category_scores_gemma":[0.03317422,0.00004538244,0.00006488707,0.0002139869,0.0001179918,0.0004297386,0.00008153635,0.0001182061,0.00002473365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003048049,"about_ca_system_score_gemma":0.0001512515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003700551,"about_ca_topic_score_gemma":0.00005052711,"domain_scores_codex":[0.9940634,0.001141178,0.00106062,0.0002124548,0.003411679,0.0001106974],"domain_scores_gemma":[0.9905308,0.006110097,0.00207376,0.0004303168,0.0008130316,0.00004193594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005202565,0.0005024013,0.9531571,0.00004684442,0.0001836036,6.400788e-7,0.02030051,0.00001099256,0.00193411,0.004738849,0.006600878,0.01200386],"study_design_scores_gemma":[0.0003138801,0.0003783671,0.9580823,0.00005625459,0.0001182407,0.0000177112,0.00786855,0.00002860305,0.001874361,0.001465321,0.02972298,0.00007349921],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649192,0.001573741,0.00005889601,0.01449225,0.0007190075,0.0006166679,0.000002823798,0.000004426049,0.01761299],"genre_scores_gemma":[0.9981534,0.0001425018,0.0005780228,0.0003428422,0.0001201214,0.00004017439,0.000001079458,0.000004540211,0.000617358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03323416,"threshold_uncertainty_score":0.9995396,"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."}}