{"id":"W2619259536","doi":"10.1097/acm.0000000000001743","title":"Mixed Messages or Miscommunication? Investigating the Relationship Between Assessors’ Workplace-Based Assessment Scores and Written Comments","year":2017,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Queen's University","funders":"","keywords":"Checklist; Competence (human resources); Psychology; Medical education; Narrative; Applied psychology; Task (project management); MEDLINE; Clinical psychology; Social psychology; Medicine; Cognitive 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":[],"category_scores_codex":[0.08825563,0.0006789714,0.0006466022,0.003590522,0.001278764,0.004341174,0.001425213,0.001281397,0.002595043],"category_scores_gemma":[0.6015171,0.0007475993,0.0007138494,0.002327391,0.002550365,0.004961958,0.003833028,0.002219914,0.0005650987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002186731,"about_ca_system_score_gemma":0.003316252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002338085,"about_ca_topic_score_gemma":0.003138187,"domain_scores_codex":[0.8571224,0.09446449,0.01490923,0.005571439,0.02508228,0.002850171],"domain_scores_gemma":[0.2112057,0.5942799,0.1377266,0.01104953,0.04253184,0.003206395],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004949836,0.0002007654,0.8623737,0.0007966951,0.0003266952,0.000179069,0.0799524,0.0001936946,0.000843159,0.0006510362,0.001214735,0.05277313],"study_design_scores_gemma":[0.00004111904,0.0007740857,0.8830744,0.001670171,0.0002481229,0.0003667873,0.1029744,0.002926339,0.002353465,0.001754095,0.003674366,0.0001426359],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.986245,0.0005577584,0.006566603,0.002054706,0.0001436791,0.0002166559,0.0002552449,0.0001026697,0.003857668],"genre_scores_gemma":[0.9955454,0.0001708383,0.002785946,0.0004389415,0.00007799442,0.0003553663,0.00009440818,0.00003326553,0.0004979079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9117444,"threshold_uncertainty_score":0.466746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2379208380121478,"score_gpt":0.4677538388166853,"score_spread":0.2298330008045376,"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."}}