{"id":"W3120593931","doi":"10.1101/2021.01.11.21249624","title":"Emergence and Evolution of Big Data Science in HIV Research: Bibliometric Analysis of Federally Sponsored Studies 2000-2019","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Big data; Bibliometrics; Human immunodeficiency virus (HIV); China; Library science; Metadata; Data science; Political science; Medicine; Computer science; Family medicine; Data mining; World Wide Web","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":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.00941906,0.0003087375,0.0008256886,0.1013947,0.001263305,0.005564046,0.0007757653,0.0006822577,0.001927031],"category_scores_gemma":[0.05670367,0.0001956268,0.001033212,0.170054,0.001068398,0.004068476,0.00310642,0.0005063634,0.0002981221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004033995,"about_ca_system_score_gemma":0.004634126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01629138,"about_ca_topic_score_gemma":0.0206331,"domain_scores_codex":[0.9897134,0.001981874,0.002437251,0.001132955,0.003988143,0.0007462584],"domain_scores_gemma":[0.9108327,0.03935874,0.03034305,0.003187,0.0140432,0.002235387],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001553647,0.00005102013,0.8984929,0.00335641,0.0006836331,0.0004136217,0.004880618,0.001014207,0.0007649966,0.006334595,0.006959043,0.07689365],"study_design_scores_gemma":[0.000007069666,0.00002644493,0.9748632,0.0008405187,0.0002246047,0.0002974206,0.004641022,0.001219813,0.0003484928,0.0009608344,0.01654651,0.00002408821],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9159384,0.03737231,0.001068422,0.004113837,0.0001342054,0.0001205961,0.02570109,0.0001141741,0.01543701],"genre_scores_gemma":[0.9806349,0.009855155,0.0008574079,0.0001266156,0.0001928276,0.0001012138,0.007602082,0.00002432084,0.0006054372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9905809,"threshold_uncertainty_score":0.04981333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2489796549362237,"score_gpt":0.4376911789858776,"score_spread":0.1887115240496538,"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."}}