{"id":"W6977471544","doi":"10.6084/m9.figshare.c.7153927.v1","title":"Systems for rating bodies of evidence used in systematic reviews of air pollution exposure and reproductive and children’s health: a methodological survey","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Operationalization; Systematic review; Rating scale; Rating system; Public health; Evidence-based practice; Exposure assessment","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"other","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":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001362001,0.0002056243,0.00112784,0.0001749889,0.000007804947,0.00001202468,0.00006944771,0.0001715209,0.0000548758],"category_scores_gemma":[0.007756273,0.0001530883,0.00005319108,0.0001116314,0.000007849878,0.0000319889,0.00002984003,0.0001403094,0.000002809149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004092967,"about_ca_system_score_gemma":0.00001606158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167997,"about_ca_topic_score_gemma":0.0001107363,"domain_scores_codex":[0.9985877,0.0003393454,0.0005826715,0.000271326,0.00008905162,0.0001299083],"domain_scores_gemma":[0.9987726,0.0006680181,0.0002578523,0.0002379849,0.00003284289,0.00003067687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000007310812,0.000007841983,0.0001897783,0.8494327,0.0001487775,0.000001000093,0.0007863397,0.01066509,0.00002500232,0.00001296246,0.1385191,0.0002040584],"study_design_scores_gemma":[0.0003099871,0.0002612325,0.009242925,0.9559935,0.00008779102,0.00003680206,0.0001469522,0.03133693,0.00002740315,0.00001710689,0.001922446,0.0006169177],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0002819787,0.8617247,0.0008097813,0.00002161272,0.0002987373,0.005483296,0.1308823,0.0002736911,0.000223967],"genre_scores_gemma":[0.7646163,0.05740361,0.03315791,0.00007087276,0.002211078,0.01710871,0.07895991,0.004227322,0.04224427],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8043211,"threshold_uncertainty_score":0.9285544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2795359256211499,"score_gpt":0.3598976177604348,"score_spread":0.08036169213928485,"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."}}