{"id":"W2989975385","doi":"","title":"Examining Accuracy of Self-Assessment of In-Training Examination Performance in a Context of Guided Self-Assessment.","year":2017,"lang":"en","type":"article","venue":"PubMed","topic":"Innovations in Medical Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Context (archaeology); Documentation; Self-assessment; Family medicine; Medicine; Medical education; Residency training; Psychology; Objective structured clinical examination; Nursing; Continuing education; Social psychology; Pedagogy; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01252127,0.0002434677,0.0002985946,0.000853867,0.0002957295,0.00116578,0.0006440631,0.0006013477,0.0004133084],"category_scores_gemma":[0.09088249,0.0002235546,0.0003324157,0.0006506476,0.0006505405,0.0009518738,0.001100643,0.0005743525,0.0002127644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000645728,"about_ca_system_score_gemma":0.000653132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005196364,"about_ca_topic_score_gemma":0.007564967,"domain_scores_codex":[0.9904355,0.005091896,0.0008146372,0.001208021,0.002133369,0.0003165291],"domain_scores_gemma":[0.9099327,0.04506914,0.03073357,0.004671704,0.008259372,0.001333422],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001032209,0.00005571985,0.9932761,0.00002254388,0.00005602186,0.00001227745,0.0007436952,0.0001358046,0.0001371871,0.00001495259,0.00008903132,0.005353447],"study_design_scores_gemma":[0.000003717236,0.000205089,0.9978157,0.00001481143,0.00001674922,0.00005991631,0.0004587271,0.0009467286,0.0002910678,0.00002387893,0.0001562928,0.000007215671],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985377,0.0001622884,0.0005121908,0.00004679274,0.00001198349,0.00002016777,0.00008114197,0.00001382407,0.0006138587],"genre_scores_gemma":[0.9992278,0.00003372935,0.0004993718,0.00002151222,0.000006200994,0.00001503785,0.00009183701,0.000002885738,0.0001016807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9874787,"threshold_uncertainty_score":0.06621957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07008870548597987,"score_gpt":0.3634521373097264,"score_spread":0.2933634318237466,"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."}}