{"id":"W4317717687","doi":"10.1002/cpe.7635","title":"Performance comparison of Dask and Apache Spark on HPC systems for neuroimaging","year":2023,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Computer science; SPARK (programming language); Big data; Python (programming language); File system; Neuroimaging; Pipeline (software); Database; Operating system; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001702957,0.0001041582,0.0001517249,0.00006676205,0.0002724354,0.0001047826,0.000138869,0.00002478277,1.886378e-7],"category_scores_gemma":[0.0001294705,0.000100857,0.00001107578,0.0003403261,0.0001118001,0.0009238669,0.00009907918,0.00009106768,0.00000215665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005058054,"about_ca_system_score_gemma":0.00001563591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004070603,"about_ca_topic_score_gemma":1.423595e-7,"domain_scores_codex":[0.9990755,0.00004733271,0.0002393176,0.0003516685,0.0001329184,0.0001533131],"domain_scores_gemma":[0.9984833,0.0009999652,0.0002082549,0.0001464703,0.00009806787,0.00006396743],"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":[0.00008596609,0.0001260711,0.006854047,0.0003287408,0.00001800508,0.000003220755,0.02648223,0.02070035,0.001605719,0.07950528,0.0009336874,0.8633567],"study_design_scores_gemma":[0.0002718836,0.0001982857,0.002525155,0.00004825156,0.000007671129,0.00002100448,0.001705849,0.9888098,0.0003157086,0.0003778998,0.0055919,0.000126585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.632308,0.001286616,0.3645159,0.0008802982,0.0002781096,0.0003666463,0.000003104274,0.0001058134,0.0002554904],"genre_scores_gemma":[0.995157,0.0008126522,0.003762528,0.000125797,0.00002719225,0.00009106396,0.00000460144,0.00000494356,0.00001423673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9681094,"threshold_uncertainty_score":0.411283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07232339667677312,"score_gpt":0.3845238603157263,"score_spread":0.3122004636389532,"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."}}