{"id":"W6958417402","doi":"10.6084/m9.figshare.25397479","title":"Additional file 1 of Assessing the research landscape and clinical utility of large language models: a scoping review","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Toronto","funders":"","keywords":"Field (mathematics); Quality (philosophy); Key (lock); Information system; Identification (biology)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009276427,0.001483966,0.002919447,0.009838316,0.0008903922,0.003203726,0.002526833,0.002292274,0.8654088],"category_scores_gemma":[0.1679401,0.00108683,0.003249136,0.01062675,0.0005683418,0.003696535,0.002113841,0.001383867,0.06718366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002873936,"about_ca_system_score_gemma":0.006044146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008643419,"about_ca_topic_score_gemma":0.01716227,"domain_scores_codex":[0.9959341,0.001248145,0.001506536,0.0005662953,0.0005616923,0.0001832551],"domain_scores_gemma":[0.7306638,0.2470332,0.008900275,0.003185416,0.00931434,0.0009030975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[0.001356939,0.0001438308,0.002281337,0.2081534,0.0008511671,0.0001321976,0.0003356937,0.0006836223,0.0001539014,0.003446247,0.7496564,0.03280522],"study_design_scores_gemma":[0.02076989,0.0006872066,0.03112994,0.1755565,0.006804195,0.001115331,0.001352642,0.002665834,0.0007585758,0.02958404,0.7291366,0.0004391895],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.0002560848,0.0006309001,0.0005465592,0.000384625,0.00007980624,0.0007555331,0.9960639,0.0001758329,0.001106804],"genre_scores_gemma":[0.02081996,0.00590282,0.03033987,0.004454255,0.0005944441,0.03422371,0.8810155,0.001376801,0.02127267],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8654088,"threshold_uncertainty_score":0.191978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6408454034643067,"score_gpt":0.6214307580803662,"score_spread":0.01941464538394055,"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."}}