{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002595219,0.0001280344,0.0001327772,0.0000401159,0.00006049412,0.0003344466,0.001913206,0.00004019747,0.00000765516],"category_scores_gemma":[0.00006536319,0.0001160739,0.00001046178,0.0001840096,0.00002559734,0.001803476,0.00162244,0.0001109879,0.000004205803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189681,"about_ca_system_score_gemma":0.00002811214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004665425,"about_ca_topic_score_gemma":0.000002944279,"domain_scores_codex":[0.9987304,0.00004795147,0.0001335123,0.0007153853,0.0001766143,0.000196129],"domain_scores_gemma":[0.9982871,0.00003666061,0.00003987897,0.00145007,0.00001618467,0.0001700581],"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":[0.000155379,0.001142603,0.03476651,0.0009440686,0.0002425589,0.0001808424,0.01259633,0.0009960838,0.0631052,0.0834194,0.2123685,0.5900825],"study_design_scores_gemma":[0.0002301452,0.0001350503,0.001246282,0.00001544461,0.000007038337,0.000006803194,0.00004927455,0.9678247,0.008380398,0.00006311844,0.02175776,0.0002839762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005426311,0.0000153749,0.9898861,0.0004614678,0.00003788358,0.0001264561,0.00002363734,0.001023622,0.002999148],"genre_scores_gemma":[0.2918476,0.000001702047,0.7075608,0.0004300928,0.00005139664,0.000007979602,0.00006466331,0.000009453493,0.00002633528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9668286,"threshold_uncertainty_score":0.4733357,"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."}}