{"id":"W4388558170","doi":"10.2196/51183","title":"Generative Language Models and Open Notes: Exploring the Promise and Limitations","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute for Health and Care Research","keywords":"Generative grammar; Computer science; Linguistics; Cognitive science; Artificial intelligence; Natural language processing; Psychology; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02684588,0.001271207,0.001452408,0.001907223,0.001204469,0.008901236,0.003878706,0.002895958,0.006876762],"category_scores_gemma":[0.1453364,0.0009893568,0.001777372,0.00190074,0.004003091,0.01144307,0.005495927,0.006747878,0.001098681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002991021,"about_ca_system_score_gemma":0.003294141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02290456,"about_ca_topic_score_gemma":0.0164252,"domain_scores_codex":[0.988353,0.009497747,0.0003257667,0.0007547297,0.0008269412,0.0002417677],"domain_scores_gemma":[0.600432,0.3847208,0.003363749,0.005813119,0.004260982,0.001409342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001041956,0.0006293525,0.0334658,0.001866014,0.0007880666,0.0008246255,0.008229246,0.238523,0.0006753466,0.4788896,0.009532841,0.2255342],"study_design_scores_gemma":[0.0001298383,0.0001380567,0.001616995,0.0004183674,0.0001094774,0.0001894717,0.00179718,0.6616294,0.000353167,0.3255252,0.007998621,0.0000942693],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2098775,0.02703961,0.6610534,0.07286155,0.001006578,0.0004152812,0.001632023,0.0009838497,0.02513021],"genre_scores_gemma":[0.8429622,0.006535969,0.1415318,0.002987858,0.001008048,0.0003478912,0.001030461,0.0002282109,0.00336763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02684588,"threshold_uncertainty_score":0.1419763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4409905992849124,"score_gpt":0.5103419598562531,"score_spread":0.06935136057134073,"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."}}