{"id":"W2965856325","doi":"10.1109/works49585.2019.00010","title":"A Performance Comparison of Dask and Apache Spark for Data-Intensive Neuroimaging Pipelines","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Western Canada Research Grid; Compute Canada; McGill University","keywords":"Computer science; Pipeline transport; Python (programming language); Big data; SPARK (programming language); Cloud computing; Neuroimaging; Pipeline (software); Artificial intelligence; Data mining; Operating system; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.008267629,0.002153331,0.001384586,0.002393937,0.001575593,0.00291896,0.004746398,0.0009344999,0.003690633],"category_scores_gemma":[0.01462748,0.001107932,0.00150503,0.00375303,0.001837475,0.004470616,0.003516427,0.001878713,0.002885842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002943661,"about_ca_system_score_gemma":0.007970002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03015108,"about_ca_topic_score_gemma":0.01648588,"domain_scores_codex":[0.9928144,0.0009549813,0.0007450503,0.001672574,0.002645391,0.001167636],"domain_scores_gemma":[0.9920284,0.001954098,0.0003242697,0.001796774,0.002592549,0.001303827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.03163768,0.002712021,0.04514516,0.004693851,0.001897871,0.0009281597,0.002468437,0.213824,0.04966773,0.02592233,0.2766802,0.3444227],"study_design_scores_gemma":[0.002451451,0.001981945,0.03251139,0.000172413,0.0003420395,0.0005725665,0.001281259,0.840475,0.06162413,0.0112513,0.04686706,0.0004693863],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6473123,0.003569348,0.06015282,0.001991181,0.001185745,0.0006850744,0.01250122,0.2373755,0.0352268],"genre_scores_gemma":[0.8383771,0.001102189,0.1117126,0.0006347029,0.0001207798,0.0003760625,0.03260603,0.01007138,0.004999246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03015108,"threshold_uncertainty_score":0.05995113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2170631348330673,"score_gpt":0.3678146460030207,"score_spread":0.1507515111699533,"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."}}