{"id":"W4392861584","doi":"10.22541/au.171052397.79869572/v1","title":"Development and validation of a geographic search filter for MEDLINE (PubMed) to identify studies conducted in Germany","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Services and Policy Research","funders":"Deutsche Forschungsgemeinschaft","keywords":"MEDLINE; Data science; Computer science; Medicine; Information retrieval; Political science","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":[],"category_scores_codex":[0.04234266,0.001898958,0.004577385,0.04085272,0.001867122,0.005127666,0.002872095,0.00207965,0.009363606],"category_scores_gemma":[0.1546963,0.0007580818,0.004951372,0.01994636,0.0009509827,0.003261115,0.004482861,0.000775176,0.001951662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002371406,"about_ca_system_score_gemma":0.01531145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01148656,"about_ca_topic_score_gemma":0.02682707,"domain_scores_codex":[0.9746727,0.00545063,0.01331532,0.003182147,0.002828366,0.0005508173],"domain_scores_gemma":[0.8253415,0.1230956,0.02374523,0.007621964,0.01780112,0.002394585],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.007391415,0.0007145833,0.1758523,0.2299397,0.01703292,0.003405931,0.01302707,0.004064786,0.03079021,0.01039483,0.06788069,0.4395057],"study_design_scores_gemma":[0.004636971,0.002230895,0.5491289,0.04851284,0.04308417,0.003641268,0.008080266,0.01243296,0.01881599,0.008910208,0.2997591,0.0007663953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.3343535,0.04878511,0.1540405,0.006845706,0.001459497,0.05592754,0.3747744,0.007745179,0.01606853],"genre_scores_gemma":[0.3279613,0.00900213,0.4232786,0.001584436,0.0004071579,0.04399223,0.1900509,0.0008321915,0.002891076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9576573,"threshold_uncertainty_score":0.223932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125787265856181,"score_gpt":0.3996769114974192,"score_spread":0.2870981849118011,"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."}}