{"id":"W4400449407","doi":"10.55016/ojs/ajer.v52i1.55108","title":"Establishing Performance Standards and Setting Cut-Scores","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Alberta; American Educational Research Association","keywords":"Psychology; Mathematics education; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1595481,0.001700569,0.002024745,0.02008606,0.002911658,0.00920282,0.004328266,0.003021593,0.003662208],"category_scores_gemma":[0.3103569,0.001158035,0.001839286,0.01061132,0.003337335,0.006736294,0.004748405,0.004053114,0.00349672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006944548,"about_ca_system_score_gemma":0.01228797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003224442,"about_ca_topic_score_gemma":0.004181346,"domain_scores_codex":[0.8044224,0.08447719,0.02834034,0.00552948,0.07408735,0.003143385],"domain_scores_gemma":[0.7672256,0.09370773,0.01307551,0.01058917,0.1127448,0.002657236],"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":[0.0004555007,0.0006974636,0.04048127,0.002194824,0.0002284775,0.0001547059,0.005190131,0.003116122,0.002493524,0.1287851,0.04250292,0.7736999],"study_design_scores_gemma":[0.0005344852,0.00309121,0.1296306,0.0117633,0.0005681773,0.001358892,0.01921833,0.02573971,0.03828374,0.3028095,0.4658284,0.001173709],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05012785,0.008615726,0.8396358,0.006795862,0.002953783,0.007417901,0.001386999,0.001821622,0.08124435],"genre_scores_gemma":[0.1044265,0.003162218,0.8718413,0.0008980434,0.0003499413,0.01139347,0.002281879,0.000363202,0.005283392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1595481,"threshold_uncertainty_score":0.8437814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.197383127495859,"score_gpt":0.5540258457336474,"score_spread":0.3566427182377884,"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."}}