{"id":"W2024037973","doi":"10.1371/journal.pone.0001350","title":"External Validation of a Measurement Tool to Assess Systematic Reviews (AMSTAR)","year":2007,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":579,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health; University of Ottawa","funders":"","keywords":"Medicine; Kappa; Systematic review; Cohen's kappa; MEDLINE; Internal medicine; Statistics; Mathematics; Biology","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":["metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.3319102,0.0002414865,0.005160101,0.000420541,0.00006117168,0.0003300128,0.001311935,0.00005376881,0.003257055],"category_scores_gemma":[0.1096664,0.0001179016,0.001024692,0.001299737,0.00001510271,0.0002012681,0.00009218138,0.00008656439,0.005538016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000097829,"about_ca_system_score_gemma":0.00003973188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005975118,"about_ca_topic_score_gemma":0.00002183247,"domain_scores_codex":[0.9406797,0.01156566,0.02338245,0.001074042,0.02286761,0.0004305496],"domain_scores_gemma":[0.9845258,0.002177905,0.006345265,0.003469218,0.003294396,0.0001874058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000132092,0.007847153,0.0782017,0.1826668,0.005973309,0.00003496133,0.005978943,0.0001518978,0.6451869,0.006332071,0.03704922,0.03044491],"study_design_scores_gemma":[0.002741972,0.001600335,0.07606459,0.2166452,0.02443805,0.00005046495,0.004586349,0.007922287,0.6196141,0.01527824,0.02695091,0.004107441],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6776044,0.003347412,0.3079158,0.0001902557,0.0001415034,0.006424658,0.000005855093,0.000008631025,0.004361433],"genre_scores_gemma":[0.9344482,0.00003890205,0.06167215,0.0002562301,0.0001134865,0.0002272223,0.000001700088,0.00001508186,0.003227009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2568438,"threshold_uncertainty_score":0.9976541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9088568580287464,"score_gpt":0.5118559510449199,"score_spread":0.3970009069838265,"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."}}