{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.003852055,0.0002355531,0.0004410339,0.0001905378,0.001495572,0.00005252053,0.000768749,0.0003103812,0.0001441864],"category_scores_gemma":[0.023306,0.0001407161,0.00002870534,0.0003351577,0.001571971,0.000225625,0.0002027469,0.002078495,0.00001279167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634951,"about_ca_system_score_gemma":0.0003925933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001142426,"about_ca_topic_score_gemma":0.000009345288,"domain_scores_codex":[0.9974316,0.0003201792,0.0008210682,0.0003318639,0.0007837089,0.0003115227],"domain_scores_gemma":[0.9940932,0.003306087,0.0007569275,0.001448304,0.0002118082,0.0001836999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001979979,0.00001526868,0.9516587,0.0001350319,0.00005082332,0.000001900756,0.0008631666,9.687433e-7,0.0001360514,0.004018854,0.03766555,0.005433859],"study_design_scores_gemma":[0.002416,0.0001313475,0.9838415,0.002217249,0.0003000018,0.00001699551,0.002112271,0.0008183936,0.00008577805,0.003216693,0.004698879,0.0001449238],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7025807,0.0003276556,0.001259717,0.29266,0.000286094,0.0006528607,0.000002787418,0.00004736612,0.002182801],"genre_scores_gemma":[0.9822313,0.0001237579,0.006330717,0.008142902,0.0008539755,0.0001463419,0.0001873746,0.00003219253,0.001951507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.284517,"threshold_uncertainty_score":0.9998043,"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."}}