{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03975648,0.0006859844,0.001339227,0.002584453,0.005240246,0.006193075,0.001945422,0.002610736,0.08043716],"category_scores_gemma":[0.4099632,0.0005963629,0.001325031,0.001473297,0.002399416,0.003242004,0.004646777,0.003507406,0.03100311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003574676,"about_ca_system_score_gemma":0.01824651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008650302,"about_ca_topic_score_gemma":0.0174297,"domain_scores_codex":[0.9538465,0.02145615,0.004555012,0.00175023,0.01691093,0.00148114],"domain_scores_gemma":[0.4771311,0.07726939,0.01068249,0.02095122,0.403011,0.01095475],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004613166,0.0001469756,0.002188675,0.0006258463,0.00006341799,0.0003361369,0.003110799,0.0001440765,0.001296708,0.0007272569,0.9107839,0.08011492],"study_design_scores_gemma":[0.0005748592,0.0004723452,0.01367687,0.001706013,0.0001489521,0.0005090905,0.01014469,0.00353998,0.00479323,0.002946639,0.9612581,0.0002291058],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"editorial","genre_scores_codex":[0.1182034,0.003167314,0.03022449,0.4278341,0.2371053,0.01701243,0.01019438,0.01030001,0.1459587],"genre_scores_gemma":[0.4927646,0.004638487,0.08812426,0.04859895,0.02889208,0.01129185,0.01500097,0.01133616,0.2993526],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.9602435,"threshold_uncertainty_score":0.2690891,"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."}}