{"id":"W4404882862","doi":"10.2196/68135","title":"Leveraging Large Language Models and Agent-Based Systems for Scientific Data Analysis: Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Bridging (networking); Data science; Computer science; Psychology; World Wide Web; Computer security","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":[0.02493112,0.001109715,0.0005413987,0.001471857,0.0006536804,0.002028083,0.00179102,0.001232552,0.001627141],"category_scores_gemma":[0.08417217,0.0004444071,0.001042877,0.001194354,0.001048337,0.002969122,0.002247497,0.001883903,0.0007424201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001757891,"about_ca_system_score_gemma":0.00255486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0102224,"about_ca_topic_score_gemma":0.008944018,"domain_scores_codex":[0.9864862,0.00955297,0.0008847937,0.000885046,0.001880121,0.0003107782],"domain_scores_gemma":[0.8775725,0.1016941,0.003347841,0.008231809,0.008269724,0.0008840126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005175536,0.008105951,0.141299,0.004421516,0.001992968,0.001675949,0.006486032,0.3314091,0.01906073,0.01072949,0.01752489,0.4521189],"study_design_scores_gemma":[0.0005632163,0.002387162,0.0179309,0.0003471272,0.0004235314,0.0003946697,0.001203558,0.9485534,0.01295269,0.00437178,0.01073548,0.0001363459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8559015,0.001742855,0.1261547,0.001367547,0.0002170768,0.002396591,0.00151486,0.004430743,0.006274028],"genre_scores_gemma":[0.8621513,0.0006168495,0.1321092,0.000355666,0.00005157973,0.0008990846,0.002327925,0.0001909125,0.001297445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02493112,"threshold_uncertainty_score":0.1318499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2977800696045079,"score_gpt":0.514166981210123,"score_spread":0.2163869116056151,"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."}}