{"id":"W2996889063","doi":"10.2196/16492","title":"Analyzing Medical Research Results Based on Synthetic Data and Their Relation to Real Data Results: Systematic Comparison From Five Observational Studies","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Synthetic data; Computer science; Data mining; Observational study; Process (computing); Relation (database); Statistics; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01545124,0.0002914108,0.0008047344,0.000445155,0.0002554276,0.0003315375,0.04002834,0.0004293341,0.00001942646],"category_scores_gemma":[0.2796405,0.0002060669,0.00002933613,0.001199848,0.000371516,0.00200118,0.1061118,0.001347039,0.000228042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001960951,"about_ca_system_score_gemma":0.0005433701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088973,"about_ca_topic_score_gemma":0.00007900177,"domain_scores_codex":[0.9917853,0.0006682579,0.002204903,0.0008952847,0.003877407,0.0005688414],"domain_scores_gemma":[0.9486431,0.02137919,0.0007548516,0.02815062,0.0005145422,0.0005576688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003010869,0.0003080048,0.001143469,0.004276535,0.000290248,0.0000321323,0.008968694,0.0001576174,0.000005414392,0.002261064,0.9667652,0.01549059],"study_design_scores_gemma":[0.0009810821,0.0001755947,0.0009042998,0.008614815,0.00001255753,0.000004960364,0.002699301,0.9814203,0.00001077335,0.003556933,0.00139612,0.000223283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2170988,0.001011771,0.3734674,0.3799792,0.002616845,0.007479009,0.009531265,0.00251877,0.006296983],"genre_scores_gemma":[0.723318,0.0005557066,0.2659751,0.001995066,0.0002369371,0.0001398048,0.007673775,0.00003871553,0.00006680809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812627,"threshold_uncertainty_score":0.9651656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2485650051275908,"score_gpt":0.4320103665125674,"score_spread":0.1834453613849766,"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."}}