{"id":"W4393131103","doi":"10.1038/s41598-024-57207-7","title":"An evaluation of the replicability of analyses using synthetic health data","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research; Mitacs; Canada Research Chairs; CHEO Research Institute; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Bill and Melinda Gates Foundation","keywords":"Replicate; Computer science; Synthetic data; Data mining; Confidence interval; Logistic regression; Metric (unit); Missing data; Statistics; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01939941,0.00008418926,0.0001815041,0.0001841779,0.0001677518,0.0002523589,0.01559404,0.00004215567,0.00001291527],"category_scores_gemma":[0.02291447,0.00005769431,0.00005594266,0.00192281,0.0004990263,0.0009403733,0.03096696,0.0001088398,7.341047e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000118848,"about_ca_system_score_gemma":0.001100673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002522238,"about_ca_topic_score_gemma":0.00003261814,"domain_scores_codex":[0.9960401,0.0003673789,0.0007101361,0.001314217,0.001377954,0.0001902056],"domain_scores_gemma":[0.954216,0.00009124142,0.0004943081,0.04485117,0.0003071893,0.00004010315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000445707,0.0006900613,0.009940475,0.0010086,0.0001738246,0.00005014257,0.00112782,0.006357729,0.3603065,0.002060036,0.1523277,0.4659526],"study_design_scores_gemma":[0.00001235447,0.00001018455,0.0008616691,0.0001209965,0.00002416972,0.00005078907,0.00002064928,0.7802472,0.0337574,0.1845216,0.0003231883,0.00004976987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8870794,0.00181978,0.097371,0.005193711,0.007288715,0.000691089,0.00004868806,0.0003763454,0.000131345],"genre_scores_gemma":[0.9469151,0.000002281476,0.05302997,0.000006104494,0.000008712528,0.000003198252,0.000024587,0.000004566285,0.000005427809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7738895,"threshold_uncertainty_score":0.9897321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3019057160476462,"score_gpt":0.4646173370680689,"score_spread":0.1627116210204227,"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."}}