{"id":"W4408959459","doi":"10.1002/gin2.70021","title":"Comparison between two tools assessing the methodological quality of systematic reviews: ReMarQ and AMSTAR 2","year":2025,"lang":"en","type":"article","venue":"Clinical and Public Health Guidelines","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Systematic review; Quality (philosophy); Management science; Computer science; Engineering; Chemistry; MEDLINE; Epistemology; Philosophy","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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.715693,0.000295512,0.01198201,0.0001834972,0.0003506357,0.001158955,0.001326036,0.0001629684,0.0002148316],"category_scores_gemma":[0.7298055,0.0001034444,0.001286678,0.00133208,0.0004384602,0.0002746045,0.0003936293,0.0003919419,0.00003837942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001453898,"about_ca_system_score_gemma":0.0003646007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001050136,"about_ca_topic_score_gemma":0.00005143768,"domain_scores_codex":[0.5462555,0.3361503,0.1092795,0.00246041,0.004979358,0.0008750471],"domain_scores_gemma":[0.4988354,0.44757,0.03744171,0.008030128,0.006960963,0.001161782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002696524,0.00005314933,0.6269469,0.009737227,0.0001662018,1.781806e-7,0.0001124386,0.000001241685,9.350174e-7,0.008426212,0.06303074,0.2915221],"study_design_scores_gemma":[0.0006137043,0.0001342346,0.511318,0.004387415,0.0004368722,0.000004479416,0.003049264,0.006196216,5.756663e-7,0.02541904,0.4481427,0.0002974544],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2539871,0.128817,0.3789886,0.2285728,0.001088391,0.006152186,0.00004292795,0.00002577318,0.002325218],"genre_scores_gemma":[0.7920164,0.008255682,0.1599482,0.03557619,0.0009143928,0.0002269073,0.00002554361,0.00001930687,0.003017335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5380293,"threshold_uncertainty_score":0.9998779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9935692851380888,"score_gpt":0.8094921504423684,"score_spread":0.1840771346957204,"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."}}