{"id":"W2606226254","doi":"10.1097/acm.0000000000001669","title":"The Hidden Value of Narrative Comments for Assessment: A Quantitative Reliability Analysis of Qualitative Data","year":2017,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; The Wilson Centre","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Psychology; Narrative; Set (abstract data type); Argument (complex analysis); Medical education; Medicine; Family medicine; Computer science; Internal medicine; Developmental psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.009858834,0.0001531179,0.0008234546,0.0002519181,0.0004389405,0.000004873106,0.00105935,0.0001683398,0.00006568021],"category_scores_gemma":[0.04418898,0.00009323019,0.00007812625,0.0006718554,0.002066903,0.0002050304,0.000207491,0.0005831353,7.578265e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001180227,"about_ca_system_score_gemma":0.0003271917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003700096,"about_ca_topic_score_gemma":0.00001153346,"domain_scores_codex":[0.9970814,0.0003386802,0.001200104,0.0003783911,0.0007863544,0.0002150725],"domain_scores_gemma":[0.9918319,0.003250888,0.001641838,0.00202356,0.001182626,0.00006921375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001452737,0.0003371948,0.05769904,0.0009289913,0.009452698,0.00000152324,0.4347206,0.00001607285,0.003907608,0.324439,0.1455161,0.02152842],"study_design_scores_gemma":[0.007911155,0.002382765,0.3018553,0.001730118,0.01119008,0.000003554381,0.5444534,0.0762105,0.0008936573,0.03929973,0.01372099,0.0003488029],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8679757,0.0004656376,0.02652201,0.100518,0.0007228741,0.001691617,0.0002201601,0.00001758588,0.001866478],"genre_scores_gemma":[0.9853451,0.0002447219,0.01213728,0.0007955186,0.0001576085,0.00008563984,0.0008022214,0.00001361249,0.0004183135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2851393,"threshold_uncertainty_score":0.9638622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3000704535187511,"score_gpt":0.6009780716740539,"score_spread":0.3009076181553028,"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."}}