{"id":"W2541476207","doi":"10.1097/acm.0000000000001373","title":"“It’s Complicated”: Understanding the Relationships Between Checklists, Rating Scales, and Written Comments in Workplace-Based Assessments","year":2016,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Queen's University","funders":"","keywords":"Checklist; Competence (human resources); Rating scale; Psychology; Medical education; Logistic regression; Regression analysis; Applied psychology; Medicine; Computer science; Social psychology","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":["metaresearch"],"category_scores_codex":[0.2683116,0.001219718,0.0009356162,0.008345654,0.002053529,0.009038421,0.00339657,0.002286998,0.001528617],"category_scores_gemma":[0.7341906,0.001690949,0.001231156,0.007408244,0.008516459,0.02277731,0.006835175,0.004055501,0.0003743434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005455286,"about_ca_system_score_gemma":0.006691158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009374483,"about_ca_topic_score_gemma":0.008333374,"domain_scores_codex":[0.6139162,0.3354485,0.01521039,0.00819321,0.02492579,0.002305968],"domain_scores_gemma":[0.1366857,0.7533889,0.06189834,0.0109208,0.03531748,0.001788731],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004251017,0.0004805874,0.7222779,0.001433614,0.0006041614,0.0003484373,0.1352281,0.001740513,0.0003819086,0.006236964,0.00228372,0.1285591],"study_design_scores_gemma":[0.0001163595,0.001596911,0.7738058,0.006574949,0.0005245437,0.000863085,0.1476439,0.04211071,0.001225232,0.01775993,0.007265178,0.0005133961],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9085412,0.003239083,0.07076783,0.007556589,0.0004112955,0.001171498,0.0003594181,0.0002649499,0.007688091],"genre_scores_gemma":[0.975838,0.0005001178,0.02136231,0.0007921557,0.0001234589,0.0009384129,0.0001389185,0.00005885782,0.0002477943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7316884,"threshold_uncertainty_score":0.902302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.17313581887145,"score_gpt":0.4122598643294583,"score_spread":0.2391240454580082,"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."}}