{"id":"W3000137827","doi":"10.1109/works49585.2019.00010","title":"A performance comparison of Dask and Apache Spark for data-intensive neuroimaging pipelines","year":2019,"lang":"","type":"article","venue":"Espace ÉTS (ETS)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pipeline transport; Computer science; Big data; Python (programming language); SPARK (programming language); Cloud computing; Pipeline (software); Artificial intelligence; Data mining; Operating system; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.007749533,0.002056987,0.001316716,0.002324151,0.001488403,0.002705197,0.004715777,0.0009019606,0.003666775],"category_scores_gemma":[0.01323231,0.001051532,0.001480015,0.003521835,0.001694578,0.004219611,0.003365685,0.001760934,0.002747452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002794012,"about_ca_system_score_gemma":0.007587585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02842944,"about_ca_topic_score_gemma":0.01594957,"domain_scores_codex":[0.9934017,0.0008809359,0.0006959054,0.001575904,0.002373447,0.001072129],"domain_scores_gemma":[0.9929476,0.001714856,0.000300518,0.001494745,0.002344443,0.001197901],"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":[0.03173847,0.002707005,0.04522223,0.004563517,0.00191509,0.0009370501,0.002331589,0.2092097,0.04920244,0.0233917,0.2720088,0.3567725],"study_design_scores_gemma":[0.002421149,0.002033862,0.03221012,0.0001641605,0.0003339317,0.0005566393,0.001215672,0.8480343,0.05863009,0.0103595,0.04358883,0.0004516971],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6453642,0.003440386,0.06346998,0.001930425,0.001162236,0.0007166299,0.01209455,0.2370374,0.03478415],"genre_scores_gemma":[0.8412954,0.001036801,0.1115086,0.0006023434,0.0001160973,0.000393419,0.0313432,0.008964744,0.004739347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02842944,"threshold_uncertainty_score":0.05652791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0779641505925508,"score_gpt":0.3217635073926428,"score_spread":0.243799356800092,"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."}}