{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004177902,0.0002211494,0.0003661695,0.0001320558,0.0006047795,0.0006881669,0.0057139,0.0001566095,0.000001110126],"category_scores_gemma":[0.0001937638,0.0002079953,0.0000476372,0.0001282675,0.0001587616,0.0008738552,0.001284604,0.0004797657,0.00001004973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002199647,"about_ca_system_score_gemma":0.00009578006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002633414,"about_ca_topic_score_gemma":0.000003080533,"domain_scores_codex":[0.998073,0.00005210149,0.0004135607,0.0007144472,0.000411995,0.0003349296],"domain_scores_gemma":[0.9957194,0.00006427954,0.0006430169,0.003400446,0.00008702037,0.0000858095],"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":[0.0000548526,0.0003539445,0.00213283,0.0001414692,0.00004077183,0.000009127045,0.001508084,0.769765,0.001097199,0.001955559,0.04003434,0.1829069],"study_design_scores_gemma":[0.0002882665,0.00003295188,0.0002886278,0.00020319,0.00000746493,0.000001945475,0.000006294069,0.9970658,0.0005168631,0.0008763855,0.0004697969,0.000242352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002663595,0.0001214561,0.9902742,0.004873535,0.0001826714,0.0001338091,0.000009259084,0.0003358173,0.001405687],"genre_scores_gemma":[0.5961292,0.0000073653,0.4025352,0.001196356,0.00006629259,0.000005978119,0.00001823006,0.00001208343,0.00002933361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5934656,"threshold_uncertainty_score":0.9996657,"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."}}