{"id":"W4396515249","doi":"10.36834/cmej.76671","title":"Use the right words: evaluating the effect of word choice and word count on quality of narrative feedback in ophthalmology competency-based medical education assessments","year":2024,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Word (group theory); Quality (philosophy); Narrative; Computer science; Multiple choice; Natural language processing; Linguistics; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.06187216,0.0006556473,0.00117104,0.001734901,0.0008424994,0.002956483,0.001089062,0.0009391288,0.002630784],"category_scores_gemma":[0.3666881,0.0005277044,0.002409797,0.001431714,0.002072166,0.003085356,0.002465619,0.001653626,0.0005473029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002572926,"about_ca_system_score_gemma":0.00235542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002022367,"about_ca_topic_score_gemma":0.003229628,"domain_scores_codex":[0.9231514,0.03884871,0.009887528,0.005393896,0.02147312,0.0012453],"domain_scores_gemma":[0.3608877,0.5214303,0.08402357,0.01001019,0.01839641,0.005251864],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01593163,0.002007749,0.8514195,0.001501567,0.001492866,0.0001591092,0.01809997,0.001187888,0.002249192,0.000266476,0.001335305,0.1043487],"study_design_scores_gemma":[0.0004952127,0.008965241,0.9732064,0.0007403716,0.000712001,0.0001838482,0.006090503,0.003903787,0.003091031,0.0005825334,0.001864224,0.0001648491],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957038,0.000378157,0.001610511,0.0002184239,0.0000647283,0.0006250472,0.0001784547,0.00004632651,0.001174624],"genre_scores_gemma":[0.9929112,0.0001782717,0.004610889,0.000104369,0.0000372694,0.001392995,0.0001862607,0.00004442551,0.0005342777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9381278,"threshold_uncertainty_score":0.3272152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03865247458304513,"score_gpt":0.4519687203342231,"score_spread":0.413316245751178,"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."}}