{"id":"W2574540012","doi":"10.1101/094888","title":"DataMed: Finding useful data across multiple biomedical data repositories","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; University of California, San Diego; National Institute of Environmental Health Sciences; University of California, Los Angeles; University of Manchester; Yale University; European Bioinformatics Institute; Arizona State University; McGill University; National Institute of Diabetes and Digestive and Kidney Diseases; Johns Hopkins University; Purdue University; School of Medicine, New York University; National Institutes of Health; Universitair Medisch Centrum Groningen; GlaxoSmithKline","keywords":"Metadata; Interoperability; Computer science; Big data; Data science; Data discovery; World Wide Web; Knowledge extraction; Service (business); Reusability; Information retrieval; Data mining; Software","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01875618,0.0008948182,0.001287861,0.0004908341,0.0007540468,0.003418912,0.02620116,0.000810073,0.0001459615],"category_scores_gemma":[0.02756528,0.0007072344,0.0001419874,0.001350556,0.0008894296,0.003330469,0.06736136,0.001100992,0.0011296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002403104,"about_ca_system_score_gemma":0.0009456293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002376907,"about_ca_topic_score_gemma":0.00006326786,"domain_scores_codex":[0.9857451,0.0008420601,0.002402109,0.005663464,0.003980102,0.001367121],"domain_scores_gemma":[0.9608285,0.002212074,0.001721415,0.03377285,0.0007139432,0.0007512618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003298309,0.001476672,0.06605769,0.001028182,0.00162634,0.00125145,0.0001869716,0.000007536206,0.1368798,0.00407872,0.7865837,0.0004930926],"study_design_scores_gemma":[0.0009275402,0.00003676572,0.04116811,0.0005866145,0.0001532872,6.573998e-8,0.000068912,0.001402494,0.005260673,0.00005759661,0.9490032,0.001334706],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4310168,0.002528868,0.1801584,0.009702867,0.04086142,0.003713507,0.3296916,0.002235593,0.00009090672],"genre_scores_gemma":[0.9771331,0.0003494918,0.01773878,0.0006212876,0.003532901,0.0001005367,0.0002203873,0.0001816791,0.0001218647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5461163,"threshold_uncertainty_score":0.9996482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2340761161406501,"score_gpt":0.4000028326354582,"score_spread":0.1659267164948081,"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."}}