{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008154405,0.0005535478,0.001059861,0.0002537389,0.0004685161,0.0001442527,0.0008244496,0.0001205072,0.00004505278],"category_scores_gemma":[0.01745296,0.0005500554,0.0001262561,0.0005593979,0.0006921068,0.001058247,0.001451196,0.0004950689,0.000110438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005647241,"about_ca_system_score_gemma":0.0001567624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005427409,"about_ca_topic_score_gemma":0.00006672015,"domain_scores_codex":[0.9958808,0.0002093256,0.000667253,0.001841712,0.0006594025,0.0007414935],"domain_scores_gemma":[0.987554,0.009368569,0.0006528668,0.001542598,0.0007281889,0.0001537804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003441663,0.0007162381,0.6179162,0.003023908,0.0002604082,0.00001411956,0.01196691,0.002733251,0.2542371,0.0008208204,0.08797009,0.01689937],"study_design_scores_gemma":[0.003113228,0.001541091,0.05525077,0.0005586398,0.000287324,0.00007480996,0.007184533,0.7814475,0.07345718,0.00005225287,0.0760081,0.001024549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754992,0.001407601,0.0006395573,0.01685431,0.002956509,0.00158692,0.0003122662,0.0000653985,0.0006782447],"genre_scores_gemma":[0.993638,0.0003374928,0.0006690318,0.002569201,0.0002912182,0.00002347707,0.00001805021,0.0000716685,0.002381898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7787143,"threshold_uncertainty_score":0.9996951,"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."}}