{"id":"W3111335600","doi":"10.1101/2020.12.16.423084","title":"Data Augmentation Through Monte Carlo Arithmetic Leads to More Generalizable Classification in Connectomics","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Open Neuroscience Platform","keywords":"Computer science; Monte Carlo method; Resampling; Connectomics; Human Connectome Project; Pipeline (software); Connectome; Preprocessor; Variance reduction; Algorithm; Curse of dimensionality; Artificial intelligence; Dimensionality reduction; Machine learning; Pattern recognition (psychology); Data mining; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004736018,0.001060088,0.0007981228,0.0007710941,0.000571381,0.0014765,0.001255915,0.001211804,0.002557526],"category_scores_gemma":[0.01978537,0.0005477972,0.001128212,0.0007876412,0.001315975,0.001775666,0.001589518,0.003198016,0.0007173113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00102271,"about_ca_system_score_gemma":0.001161177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002270524,"about_ca_topic_score_gemma":0.003672811,"domain_scores_codex":[0.9986206,0.0006280454,0.00007317638,0.0003828025,0.0002354909,0.00005984033],"domain_scores_gemma":[0.9937128,0.003777965,0.0005334586,0.001421198,0.0004314203,0.0001231282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005849265,0.0001732291,0.006346384,0.0002421251,0.0002253757,0.0001832449,0.0002196859,0.8259938,0.02231416,0.04141644,0.004396657,0.09790402],"study_design_scores_gemma":[0.00001607922,0.00005383792,0.0008582032,0.00001728625,0.0000153206,0.0000457056,0.00001227389,0.9690773,0.006841856,0.02154913,0.001490541,0.00002257111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0433873,0.0001925545,0.952387,0.0007496813,0.0001000077,0.0001132533,0.0003891278,0.001570714,0.001110341],"genre_scores_gemma":[0.4584948,0.0002881232,0.5366043,0.0005713411,0.00009972525,0.0004754449,0.001435309,0.0004208616,0.001610004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004736018,"threshold_uncertainty_score":0.02504677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1208740381075466,"score_gpt":0.3038191802212243,"score_spread":0.1829451421136777,"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."}}