{"id":"W3105647163","doi":"10.1109/dasc-picom-cbdcom-cyberscitech49142.2020.00115","title":"Filtering and Storing User Preferred Data: an Apache Spark Based Approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; SPARK (programming language); Data set; Data processing; Raw data; Filter (signal processing); Big data; Set (abstract data type); Data mining; Latency (audio); Database; Artificial intelligence; Computer vision; Programming language","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":[0.005687225,0.001308497,0.001904148,0.002178941,0.001548123,0.003870904,0.004641871,0.0009879721,0.001890525],"category_scores_gemma":[0.009730736,0.0008899994,0.001163151,0.003473721,0.0008690614,0.004183011,0.00218574,0.00175182,0.00150376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008720526,"about_ca_system_score_gemma":0.003457551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00350334,"about_ca_topic_score_gemma":0.003706372,"domain_scores_codex":[0.9925951,0.0007585856,0.0007156222,0.001234013,0.004136088,0.0005605195],"domain_scores_gemma":[0.9912961,0.002049448,0.0004803719,0.002866616,0.002771035,0.0005365263],"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":[0.004249336,0.001359063,0.01174591,0.001178928,0.0006226829,0.00138726,0.001636327,0.02479702,0.1251468,0.02163787,0.06758687,0.7386519],"study_design_scores_gemma":[0.0003833314,0.0005763636,0.005250618,0.0001102477,0.0002162409,0.0018772,0.0008453619,0.6783524,0.1815618,0.0353167,0.09517993,0.0003297088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02591835,0.0003811182,0.9330945,0.0006929062,0.0002050545,0.0008165002,0.0009370403,0.0342503,0.003704312],"genre_scores_gemma":[0.2012808,0.0003805938,0.7868025,0.0004119146,0.0001436865,0.0004831961,0.003318362,0.002145739,0.005033163],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005687225,"threshold_uncertainty_score":0.03007728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1994621607723113,"score_gpt":0.3007613351531675,"score_spread":0.1012991743808562,"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."}}