{"id":"W2061275018","doi":"10.1007/s10459-005-7853-1","title":"Standard Setting in a Small Scale OSCE: A Comparison of the Modified Borderline-Group Method and the Borderline Regression Method","year":2006,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":84,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; University of Ottawa; Medical Council of Canada","funders":"","keywords":"Scale (ratio); Set (abstract data type); Regression; Linear regression; Confidence interval; Computer science; Regression analysis; Range (aeronautics); Statistics; Standard error; Psychology; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.04849287,0.0007060727,0.001486844,0.002159333,0.001024757,0.000998626,0.00312597,0.0009004801,0.006355251],"category_scores_gemma":[0.1776139,0.000649936,0.0008941342,0.001549502,0.001102224,0.002107081,0.003356867,0.001360481,0.0008420119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008100573,"about_ca_system_score_gemma":0.001735374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002710006,"about_ca_topic_score_gemma":0.003515705,"domain_scores_codex":[0.9316841,0.05715048,0.001718582,0.002324492,0.00670035,0.0004218958],"domain_scores_gemma":[0.8405513,0.1279902,0.005677826,0.01170538,0.01224167,0.001833563],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02327874,0.002186236,0.08508895,0.001562528,0.001006295,0.0002307709,0.005553974,0.006484385,0.005018702,0.01509998,0.006383452,0.848106],"study_design_scores_gemma":[0.007244858,0.02412703,0.4392334,0.0007846711,0.002456634,0.002620491,0.009463793,0.4416355,0.01183724,0.04148864,0.01820804,0.0008998272],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4465264,0.0008769358,0.5434397,0.0004971566,0.0004129235,0.001788298,0.0003499986,0.001413859,0.00469458],"genre_scores_gemma":[0.7033413,0.0002101025,0.2928405,0.0001215219,0.00007593871,0.00147794,0.0002827089,0.0003080062,0.001342055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9515072,"threshold_uncertainty_score":0.2564579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0210771921864421,"score_gpt":0.4583212972847011,"score_spread":0.437244105098259,"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."}}