{"id":"W2964204686","doi":"10.1142/s0129626417400035","title":"A Comparison of Big Data Frameworks on a Layered Dataflow Model","year":2017,"lang":"en","type":"article","venue":"Parallel Processing Letters","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Dataflow; Computer science; SPARK (programming language); Abstraction; Big data; Semantics (computer science); Programming paradigm; Analytics; Programming language; Data modeling; Execution model; Theoretical computer science; Software engineering; Data science; Data mining","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":[0.006702161,0.0008732728,0.0008649687,0.00161065,0.001351426,0.005973743,0.003215521,0.001657885,0.002649171],"category_scores_gemma":[0.01191977,0.0007960849,0.00231178,0.002054364,0.002581168,0.007771891,0.004355818,0.00297969,0.0005333617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00275503,"about_ca_system_score_gemma":0.004836983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056042,"about_ca_topic_score_gemma":0.006109865,"domain_scores_codex":[0.9951303,0.001203122,0.000326201,0.0004541919,0.002119834,0.0007663608],"domain_scores_gemma":[0.9927938,0.002281358,0.0003589742,0.002343548,0.001259967,0.0009624656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006830432,0.0003002487,0.004257258,0.0003649145,0.0001535896,0.0003281609,0.00116818,0.1259095,0.004110515,0.802927,0.005844811,0.05395282],"study_design_scores_gemma":[0.0001371418,0.0002796912,0.002362282,0.0002929111,0.0001286019,0.0003293928,0.0007126798,0.7004786,0.005409493,0.2441483,0.04554745,0.0001734223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1207305,0.003086976,0.8379721,0.002496892,0.000325433,0.0003653722,0.0005190773,0.005255705,0.02924801],"genre_scores_gemma":[0.6266447,0.002402418,0.3619505,0.000665132,0.0001259725,0.0004053365,0.001096486,0.001189601,0.005519826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01056042,"threshold_uncertainty_score":0.0354448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1504414372039285,"score_gpt":0.3750884397476739,"score_spread":0.2246470025437454,"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."}}