{"id":"W4416300709","doi":"10.1017/rsm.2025.10056","title":"Impact of matrix-construction assumptions on quantitative overlap assessment in overviews: A meta-research study","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; MD Precision (Canada); St. Michael's Hospital","funders":"Universitat Autònoma de Barcelona","keywords":"Pairwise comparison; Metric (unit); Guideline; Selection (genetic algorithm); Evaluation methods; Matrix (chemical analysis); Sample size determination","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7209196,0.0004160735,0.006333109,0.008097918,0.0004486465,0.0009305388,0.002905742,0.0001730459,0.01126197],"category_scores_gemma":[0.3724619,0.0002007838,0.00373055,0.01454331,0.0004411569,0.0003779705,0.0006139667,0.00140533,0.0005391341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007306567,"about_ca_system_score_gemma":0.001061968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000935139,"about_ca_topic_score_gemma":0.0002001974,"domain_scores_codex":[0.4272873,0.5339258,0.01299905,0.002695001,0.02178631,0.001306547],"domain_scores_gemma":[0.5640324,0.4130211,0.003257723,0.009819211,0.009468284,0.0004013757],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003597545,0.006517672,0.3586996,0.0004845043,0.02100259,0.00003377133,0.002952442,0.002666668,0.0067986,0.2162648,0.0176854,0.3665341],"study_design_scores_gemma":[0.0006538141,0.001467003,0.8450611,0.0003902332,0.001751211,0.000003901518,0.03670353,0.02286563,0.001065907,0.08386542,0.005752643,0.0004196192],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8444906,0.003722596,0.095983,0.001558233,0.0003123376,0.007704651,0.0001108685,0.00001492638,0.04610274],"genre_scores_gemma":[0.7480047,0.0001624086,0.247063,0.000007711708,0.00002476558,0.001361085,0.000001484138,0.00002031997,0.003354477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4863615,"threshold_uncertainty_score":0.9896418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9545881302189179,"score_gpt":0.801307371359501,"score_spread":0.1532807588594168,"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."}}