{"id":"W4402592053","doi":"10.2196/65727","title":"Peer Review of “All You Need Is Context: Clinician Evaluations of Various Iterations of a Large Language Model–Based First Aid Decision Support Tool in Ghana (Preprint)”","year":2024,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Preprint; Context (archaeology); Computer science; Decision support system; Operations research; Artificial intelligence; Engineering; World Wide Web; Geography; Archaeology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001481587,0.0001123318,0.0005102321,0.0001635104,0.00001852768,0.000005196967,0.0001056786,0.00008000366,0.0009134067],"category_scores_gemma":[0.0008757923,0.00008983987,0.0001696811,0.0003032084,0.00002657142,0.00005294108,0.00003934778,0.0001641677,0.00002788829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006225578,"about_ca_system_score_gemma":0.0003891044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002983827,"about_ca_topic_score_gemma":0.0004363229,"domain_scores_codex":[0.9979239,0.00005848369,0.0009566543,0.0002145114,0.000679855,0.0001666738],"domain_scores_gemma":[0.9986679,0.0001474858,0.0001619466,0.000400755,0.0005523225,0.00006961925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004018852,0.01185239,0.08892158,0.1526707,0.001251401,0.0005844475,0.1080392,0.001453701,0.01198023,0.02207643,0.5044352,0.09271586],"study_design_scores_gemma":[0.03121995,0.004423248,0.1034578,0.1895929,0.002969633,0.0001231651,0.005890569,0.4751136,0.01573556,0.00512251,0.1649585,0.001392557],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9408922,0.005613134,0.003149127,0.04456082,0.0002028012,0.002197303,0.0007690202,0.00004616686,0.002569434],"genre_scores_gemma":[0.9906192,0.0003260551,0.001391024,0.004997835,0.00002754284,0.0000444151,0.0001446073,0.00001348101,0.002435779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4736598,"threshold_uncertainty_score":0.9999999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03588814950062965,"score_gpt":0.4090071082436858,"score_spread":0.3731189587430562,"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."}}