{"id":"W1509693428","doi":"10.1111/j.1365-2923.2011.04073.x","title":"Comparison of two methods of standard setting: the performance of the three‐level Angoff method","year":2011,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tehran University of Medical Sciences and Health Services; McMaster University","keywords":"Confidence interval; Standard deviation; Normative; Test (biology); Reliability (semiconductor); Statistics; Psychology; Mathematics; Medicine; Law","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004474137,0.0001108757,0.0003834114,0.0001149711,0.00007835266,0.000002061045,0.0003960295,0.0001307033,0.000741076],"category_scores_gemma":[0.006817979,0.00006173368,0.00009222861,0.0008545243,0.0005557629,0.00005188353,0.00007132403,0.0004585497,0.000001888072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007375368,"about_ca_system_score_gemma":0.002342819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001947368,"about_ca_topic_score_gemma":0.00001298462,"domain_scores_codex":[0.9974774,0.0003257217,0.0008873037,0.0001605875,0.0009927345,0.0001562621],"domain_scores_gemma":[0.9976229,0.0002814738,0.0006256936,0.0006384752,0.0007831828,0.00004828573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001103954,0.001100682,0.1845727,0.0005006013,0.00007311821,4.622483e-8,0.009973371,0.000003462256,0.002069724,0.005774743,0.01785612,0.7779651],"study_design_scores_gemma":[0.001430791,0.0006701085,0.650207,0.001428846,0.0004740151,0.00003740918,0.005687602,0.01738233,0.3047661,0.002167711,0.01555828,0.0001897692],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9145778,0.0002713798,0.06853888,0.01111052,0.001597738,0.0005875408,0.000004704997,0.00001493347,0.003296468],"genre_scores_gemma":[0.7771283,0.00001061172,0.221159,0.001368542,0.0001482198,0.00003764224,0.00001298615,0.000012235,0.0001224386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7777753,"threshold_uncertainty_score":0.816225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08162076428339296,"score_gpt":0.496944829592795,"score_spread":0.415324065309402,"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."}}