{"id":"W2042618893","doi":"10.1111/medu.12637","title":"Reading between the lines: faculty interpretations of narrative evaluation comments","year":2015,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of British Columbia; London Health Sciences Centre; University of Toronto","funders":"","keywords":"Narrative; Summative assessment; Context (archaeology); Reading (process); Consistency (knowledge bases); Psychology; Interpretation (philosophy); Theme (computing); Linguistics; Formative assessment; Mathematics education; Computer science","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"],"consensus_categories":[],"category_scores_codex":[0.002759971,0.0001122647,0.0002161836,0.0001710662,0.0001009943,0.00001370278,0.0001887026,0.0001459947,0.00043948],"category_scores_gemma":[0.02258218,0.00007707788,0.00004878859,0.0007733226,0.0002348437,0.0001337315,0.00003512292,0.0003642036,0.00004406568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003805211,"about_ca_system_score_gemma":0.004035708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001046994,"about_ca_topic_score_gemma":0.000004826213,"domain_scores_codex":[0.9972851,0.0002066998,0.0006029655,0.0001878288,0.001569842,0.0001475888],"domain_scores_gemma":[0.997273,0.000137875,0.0002645067,0.0003424508,0.001859157,0.0001230039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00004672628,0.0009223179,0.06093209,0.00009575775,0.000125385,3.10544e-7,0.0456234,0.000009666129,0.00004292991,0.001134804,0.4581096,0.432957],"study_design_scores_gemma":[0.008188359,0.001253269,0.4713306,0.00379508,0.001799264,0.0001225861,0.2015987,0.05353393,0.002310526,0.01071784,0.2445848,0.0007649964],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986092,0.00009245769,0.00412768,0.08790015,0.001670055,0.0009804878,0.000004926681,0.00004193178,0.006573156],"genre_scores_gemma":[0.9888013,0.000005731628,0.002343146,0.006566245,0.0006665715,0.0001656975,0.001083527,0.0000135839,0.0003542251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.432192,"threshold_uncertainty_score":0.985651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07893513369979668,"score_gpt":0.4789530750301312,"score_spread":0.4000179413303345,"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."}}