{"id":"W154875592","doi":"10.55016/ojs/ajer.v52i1.55110","title":"The Bookmark Procedure for Setting Cut-Scores and Finalizing Performance Standards: Strengths and Weaknesses","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Strengths and weaknesses; Psychology; Medical education; Mathematics education; Pedagogy; Social psychology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.124877,0.001811344,0.002228569,0.006563957,0.002217536,0.004519745,0.006596112,0.003501388,0.009022231],"category_scores_gemma":[0.3350075,0.001374043,0.001592224,0.006828888,0.003447783,0.005890789,0.004514237,0.006377089,0.007184061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00231915,"about_ca_system_score_gemma":0.006290188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001409225,"about_ca_topic_score_gemma":0.002916676,"domain_scores_codex":[0.828961,0.1160682,0.01133683,0.005591595,0.03718799,0.0008544437],"domain_scores_gemma":[0.650733,0.2436717,0.01221542,0.03145429,0.06067519,0.001250393],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004405911,0.0002538309,0.005838504,0.001583773,0.0001741273,0.000194,0.001760251,0.002568885,0.001898751,0.07918559,0.06513612,0.8409656],"study_design_scores_gemma":[0.00043265,0.001992539,0.03822495,0.004734001,0.0003870317,0.004506284,0.002798309,0.06541697,0.02585469,0.2296709,0.6248485,0.001133227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004353634,0.001137233,0.9774253,0.00210467,0.0009601956,0.00321693,0.0006038559,0.001545187,0.00865301],"genre_scores_gemma":[0.01465308,0.0005484099,0.9743112,0.0008385488,0.0002421504,0.005255359,0.0003234875,0.0004039925,0.003423858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.875123,"threshold_uncertainty_score":0.6604208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.246463418380702,"score_gpt":0.5308511997150415,"score_spread":0.2843877813343394,"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."}}