{"id":"W2901787049","doi":"10.1109/icmlc48188.2019.8949260","title":"Exploring and Evaluating the Scalability and Eficinecy of Apache Spark Using Educational Datasets","year":2019,"lang":"en","type":"article","venue":"","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"SPARK (programming language); Scalability; Computer science; Volume (thermodynamics); Big data; Machine learning; Resource (disambiguation); Variety (cybernetics); Quality (philosophy); Data mining; Data science; Artificial intelligence; Database","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":[0.01722706,0.001862917,0.001313753,0.003235299,0.00199699,0.002773494,0.002623223,0.001074643,0.0006380469],"category_scores_gemma":[0.03605243,0.0005455217,0.001151935,0.005053051,0.001640025,0.005576069,0.002361361,0.001524103,0.0002989894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001477869,"about_ca_system_score_gemma":0.002687663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01260805,"about_ca_topic_score_gemma":0.007045948,"domain_scores_codex":[0.9899136,0.003436395,0.001158718,0.001485905,0.002910175,0.001095241],"domain_scores_gemma":[0.9759259,0.01432395,0.0009566408,0.003251291,0.004267478,0.00127478],"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":[0.01036309,0.005324389,0.1325753,0.004769719,0.001968753,0.001842875,0.003612085,0.367775,0.0410024,0.01838384,0.08142836,0.3309541],"study_design_scores_gemma":[0.001117921,0.001898062,0.05040595,0.0001722202,0.0002868464,0.0005206068,0.003124258,0.8898308,0.03123438,0.009870694,0.01134394,0.0001944195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9557961,0.002636271,0.02055903,0.002032468,0.000580723,0.000549996,0.003531674,0.006630901,0.007682805],"genre_scores_gemma":[0.948177,0.001118308,0.0401164,0.0002122937,0.0001648691,0.0003011829,0.008694715,0.0004092034,0.0008060486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01722706,"threshold_uncertainty_score":0.09110647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2018872995260073,"score_gpt":0.3807257634914696,"score_spread":0.1788384639654622,"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."}}