{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01507249,0.00008838652,0.0001782425,0.0003857584,0.001069334,0.0005742265,0.0004768092,0.00004046712,0.0001672264],"category_scores_gemma":[0.5130029,0.00004944972,0.00004633049,0.0007460083,0.0002816634,0.0003469998,0.0001044969,0.0002788569,0.000001886118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005230592,"about_ca_system_score_gemma":0.0008763081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001111375,"about_ca_topic_score_gemma":0.0002610743,"domain_scores_codex":[0.9970023,0.0003229549,0.0006242908,0.0002205615,0.001493196,0.0003366914],"domain_scores_gemma":[0.6356755,0.3621181,0.0002978608,0.0001282882,0.001701807,0.00007846987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002635521,0.00006263394,0.7765542,0.00007370545,0.00003235782,3.459783e-7,0.0003919288,0.00005735747,0.0001921359,0.01357687,0.1192067,0.0895882],"study_design_scores_gemma":[0.0006062803,0.0004372147,0.6540031,0.0002679746,0.00001734263,0.0002591661,0.003246701,0.001251818,0.0003628799,0.07503062,0.2643532,0.0001636625],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720524,0.007063119,0.00006557025,0.01354612,0.0002320601,0.000160033,0.000006689393,5.112981e-7,0.006873488],"genre_scores_gemma":[0.9869354,0.0008929413,0.00337752,0.00003602655,0.0005594223,0.00001564766,0.000001006855,0.000008564387,0.008173452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4979304,"threshold_uncertainty_score":0.8224559,"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."}}