{"id":"W4241425178","doi":"10.32920/ryerson.14651544.v1","title":"Performance Evaluation of a Big Data Application on Apache Spark","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Executor; SPARK (programming language); Computer science; Big data; Node (physics); Process (computing); Computer cluster; Cluster (spacecraft); Execution time; Operating system; Database; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.002583699,0.001168604,0.0009872655,0.001140348,0.0009668413,0.00128255,0.001328119,0.0005252751,0.001240662],"category_scores_gemma":[0.005404634,0.0003392696,0.0005721851,0.002263276,0.0006146234,0.001216867,0.0007911819,0.0008268172,0.0005721617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007838812,"about_ca_system_score_gemma":0.001343192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005124186,"about_ca_topic_score_gemma":0.00213032,"domain_scores_codex":[0.9963353,0.0006115038,0.0002159503,0.0005218825,0.001697005,0.0006183545],"domain_scores_gemma":[0.9945919,0.002135233,0.0002698758,0.000498288,0.001853041,0.0006516471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01996804,0.003066529,0.05169612,0.002934458,0.0009064781,0.002517232,0.002069544,0.3834146,0.2973264,0.007194706,0.03997869,0.1889271],"study_design_scores_gemma":[0.0003822773,0.003864422,0.06301185,0.00006231204,0.0001494027,0.0005835306,0.001112211,0.7693161,0.1517268,0.001610379,0.008003199,0.0001774184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787052,0.0004841729,0.007263002,0.0002134356,0.0001559549,0.0001130701,0.0006161782,0.004675657,0.007773345],"genre_scores_gemma":[0.9908152,0.0001792304,0.006354422,0.00003231199,0.00002385274,0.00004562761,0.001193487,0.0003393879,0.001016488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005124186,"threshold_uncertainty_score":0.01366407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1393154044292805,"score_gpt":0.3111396051121099,"score_spread":0.1718242006828294,"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."}}