{"id":"W4407669278","doi":"10.21203/rs.3.rs-6026144/v1","title":"AppRaise: Software for quantifying evidence uncertainty in systematic reviews using a Bayesian mixture model","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bayesian probability; Systematic review; Econometrics; Computer science; Software; Statistics; Artificial intelligence; Mathematics; MEDLINE; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04325376,0.003554181,0.003935833,0.01111951,0.0007904145,0.006284894,0.003102198,0.003780817,0.06550561],"category_scores_gemma":[0.1853991,0.006240661,0.006766767,0.007015349,0.001002341,0.006245315,0.006361599,0.003918529,0.01250145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002161265,"about_ca_system_score_gemma":0.004842875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089771,"about_ca_topic_score_gemma":0.004920974,"domain_scores_codex":[0.983848,0.009633116,0.00296886,0.001183234,0.002177754,0.0001891253],"domain_scores_gemma":[0.8147904,0.1681273,0.00599314,0.005271213,0.005284884,0.0005329733],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002758493,0.0003257003,0.004852215,0.0299318,0.01152936,0.0005377793,0.001911897,0.08210171,0.004123539,0.09343669,0.1964323,0.5720585],"study_design_scores_gemma":[0.004285165,0.0004523175,0.005105275,0.006168428,0.006152123,0.0007200665,0.0002386266,0.4014432,0.008466545,0.3308685,0.235479,0.0006206384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001719918,0.001644988,0.8998613,0.0007721465,0.0001778905,0.001019626,0.01461951,0.07763664,0.002547964],"genre_scores_gemma":[0.01615934,0.001244476,0.9573082,0.0002993909,0.00011973,0.005144021,0.004417794,0.01330666,0.002000395],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.9567462,"threshold_uncertainty_score":0.2287505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9233297706630603,"score_gpt":0.669244660493915,"score_spread":0.2540851101691454,"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."}}