{"id":"W4389227285","doi":"10.1016/j.amjsurg.2023.11.028","title":"Decoding medical school narrative evaluations: Is natural language processing an antidote to the leniency bias?","year":2023,"lang":"en","type":"editorial","venue":"The American Journal of Surgery","topic":"Innovations in Medical Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Cornerstone; Narrative; Leverage (statistics); Observational study; Meaning (existential); Context (archaeology); Psychology; DECIPHER; Computer science; Medicine; Linguistics; Bioinformatics; Psychotherapist; Artificial intelligence; Pathology","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":[0.01220724,0.002091993,0.002570102,0.00290446,0.002233465,0.006986129,0.003699881,0.01658474,0.00955244],"category_scores_gemma":[0.07251993,0.001021787,0.00184865,0.001001982,0.003049,0.003362932,0.001213744,0.01822146,0.004428199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0022073,"about_ca_system_score_gemma":0.004006819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002521892,"about_ca_topic_score_gemma":0.007115134,"domain_scores_codex":[0.9945828,0.001722931,0.000856656,0.0004920455,0.002119874,0.0002256939],"domain_scores_gemma":[0.917905,0.05897498,0.002439691,0.001092224,0.01681591,0.002772195],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008797651,0.0000168111,0.00007445436,0.0004399155,0.00008121983,0.000142844,0.00004463601,0.00002624664,0.0000670445,0.0004327173,0.9862991,0.01228709],"study_design_scores_gemma":[0.0003803397,0.00009760825,0.0008984554,0.002932159,0.0005933983,0.0004974772,0.0002625827,0.0008721859,0.0005018057,0.004537775,0.9883611,0.00006501887],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0002002116,0.009628071,0.0004569721,0.1056569,0.882026,0.00003908185,0.0001107662,0.00009198333,0.001789972],"genre_scores_gemma":[0.001563452,0.005751224,0.0003933386,0.03472349,0.9533964,0.00004888446,0.00004281283,0.00005594047,0.00402443],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.9877927,"threshold_uncertainty_score":0.0645588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04834093824776606,"score_gpt":0.4330420615589448,"score_spread":0.3847011233111787,"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."}}