{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003999365,0.00006525306,0.00009819766,0.0000704316,0.0001998794,0.00005947928,0.00007985618,0.00005432049,0.00004565815],"category_scores_gemma":[0.001681407,0.00004504062,0.00001247816,0.0002698607,0.00009380928,0.0002393451,0.00005939145,0.0001621057,0.00003147453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003484545,"about_ca_system_score_gemma":0.0008611725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004487283,"about_ca_topic_score_gemma":0.0001717166,"domain_scores_codex":[0.9992532,0.00005379742,0.0001851264,0.0001771235,0.0002003765,0.0001303556],"domain_scores_gemma":[0.9990802,0.0004181828,0.00003658249,0.0001480512,0.00009559186,0.0002213281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002793519,0.0001387684,0.00129823,0.00007495219,0.00001114077,0.000001953624,0.08746455,0.000004723773,0.0001813241,0.003762626,0.005774551,0.9012592],"study_design_scores_gemma":[0.0007843834,0.0009994324,0.1854676,0.002122801,0.0002369679,0.0002369755,0.5687338,0.1199137,0.007524875,0.08088394,0.03224349,0.0008519525],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9137747,0.0003062655,0.0001451763,0.08365383,0.0003518634,0.0008404364,8.908951e-7,0.00004218111,0.0008846013],"genre_scores_gemma":[0.9934288,0.0009537156,0.000402058,0.002717847,0.0004857962,0.001300702,0.00005432843,0.00001061577,0.0006461052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9004073,"threshold_uncertainty_score":0.2012923,"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."}}