{"id":"W4410541276","doi":"10.21203/rs.3.rs-6026144/v2","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; Econometrics; Computer science; Software; Statistics; Mathematics; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04325378,0.003554182,0.003935833,0.01111951,0.0007904138,0.006284888,0.003102197,0.003780816,0.06550562],"category_scores_gemma":[0.1853992,0.006240661,0.00676677,0.007015349,0.00100234,0.006245309,0.006361593,0.003918529,0.01250145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002161267,"about_ca_system_score_gemma":0.004842881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089777,"about_ca_topic_score_gemma":0.004920979,"domain_scores_codex":[0.983848,0.009633126,0.002968863,0.001183234,0.002177752,0.0001891254],"domain_scores_gemma":[0.8147902,0.1681275,0.005993139,0.005271217,0.005284888,0.0005329737],"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":[0.002758499,0.0003257008,0.004852216,0.02993179,0.01152936,0.0005377794,0.001911895,0.08210161,0.004123533,0.09343663,0.1964324,0.5720586],"study_design_scores_gemma":[0.004285172,0.0004523178,0.00510528,0.006168429,0.006152132,0.0007200666,0.0002386267,0.4014433,0.008466551,0.3308683,0.2354792,0.0006206392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001719917,0.001644987,0.8998612,0.0007721464,0.0001778907,0.001019628,0.01461952,0.07763665,0.002547964],"genre_scores_gemma":[0.01615934,0.001244476,0.9573082,0.0002993909,0.00011973,0.005144028,0.004417794,0.01330665,0.002000397],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.9567462,"threshold_uncertainty_score":0.2287506,"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."}}