{"id":"W4288276631","doi":"10.48550/arxiv.1907.13030","title":"A performance comparison of Dask and Apache Spark for data-intensive\\n neuroimaging pipelines","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Pipeline transport; Python (programming language); Big data; SPARK (programming language); Cloud computing; Pipeline (software); Neuroimaging; Artificial intelligence; Data mining; Operating system; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006691643,0.001911939,0.001296714,0.002531957,0.001669004,0.003066896,0.004627073,0.000973432,0.0055101],"category_scores_gemma":[0.0126679,0.0009907,0.00153195,0.003859004,0.001449784,0.004549099,0.003519234,0.001730664,0.004392806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00290362,"about_ca_system_score_gemma":0.006857962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03305207,"about_ca_topic_score_gemma":0.02097964,"domain_scores_codex":[0.9933815,0.0007623549,0.0006745443,0.001584627,0.00251529,0.00108175],"domain_scores_gemma":[0.9934185,0.001485695,0.0002390165,0.001541401,0.002156911,0.001158615],"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":[0.02229382,0.002254077,0.03393639,0.003721639,0.00151201,0.0007338475,0.001890817,0.1369196,0.03236056,0.02097828,0.3665661,0.3768329],"study_design_scores_gemma":[0.002454492,0.002109373,0.03241434,0.0002086045,0.00034825,0.000633247,0.001424551,0.8089527,0.0550352,0.01184797,0.08405834,0.0005129759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5644249,0.005314781,0.06178419,0.002526071,0.001801818,0.0006913664,0.01599497,0.284455,0.06300694],"genre_scores_gemma":[0.8082245,0.001512153,0.1192579,0.0007834748,0.0001695152,0.0003906356,0.04985053,0.01231193,0.007499574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03305207,"threshold_uncertainty_score":0.06571937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5354686898130063,"score_gpt":0.3618900155164981,"score_spread":0.1735786742965083,"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."}}