{"id":"W4412164317","doi":"10.1109/wsese66602.2025.00016","title":"Can Machine Learning Support the Selection of Studies for Systematic Literature Review Updates?","year":2025,"lang":"en","type":"article","venue":"","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Selection (genetic algorithm); Machine learning; Systematic review; Artificial intelligence; Data science; MEDLINE","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":["metaresearch"],"category_scores_codex":[0.6325838,0.003005427,0.008782665,0.01637157,0.002429098,0.0100922,0.005035487,0.004852227,0.004771758],"category_scores_gemma":[0.9031031,0.00254837,0.009211019,0.01029655,0.003675803,0.01274299,0.005647251,0.003959212,0.001913408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006485359,"about_ca_system_score_gemma":0.022618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002739957,"about_ca_topic_score_gemma":0.006490753,"domain_scores_codex":[0.2675535,0.6022864,0.07913169,0.02207413,0.02748925,0.001465067],"domain_scores_gemma":[0.03101048,0.855765,0.0570717,0.02889566,0.02596817,0.001288924],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005502339,0.000418207,0.05306565,0.1253349,0.0209643,0.000534695,0.006025022,0.01960617,0.002616556,0.006130229,0.04048272,0.7193191],"study_design_scores_gemma":[0.01268116,0.004785737,0.06549089,0.124545,0.05554675,0.002742876,0.003223273,0.4672714,0.01684258,0.1541013,0.09036338,0.002405711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018895,0.07597188,0.6801077,0.07112813,0.006799079,0.04189178,0.007030114,0.008690541,0.006491211],"genre_scores_gemma":[0.3865211,0.00472708,0.5795432,0.005561624,0.001698174,0.01908223,0.002109306,0.0004244978,0.0003328691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3674162,"threshold_uncertainty_score":0.4530897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4842724611286957,"score_gpt":0.5337209233272568,"score_spread":0.04944846219856114,"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."}}