{"id":"W2735413012","doi":"10.1109/icdcs.2017.131","title":"Optimizing Shuffle in Wide-Area Data Analytics","year":2017,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; SPARK (programming language); Big data; Analytics; Distributed computing; Aggregate (composite); Data analysis; Raw data; Baseline (sea); Database; Computer network; Real-time computing; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005017858,0.00008702662,0.0001165509,0.00007923573,0.0002547088,0.0006135715,0.004718236,0.00002637831,0.000009998814],"category_scores_gemma":[0.0001066293,0.00007274259,0.00002334453,0.00009625792,0.00003354561,0.00009810209,0.005072954,0.00009816336,0.00003571714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002236378,"about_ca_system_score_gemma":0.00001961915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003573817,"about_ca_topic_score_gemma":0.0001965873,"domain_scores_codex":[0.9989831,0.00001864959,0.0001581843,0.0004241632,0.0001799712,0.0002359401],"domain_scores_gemma":[0.9963553,0.0000597972,0.00008340119,0.003431766,0.00001665394,0.00005310845],"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":[0.00001186778,0.0005803083,0.1126258,0.00008196229,0.0001601055,0.0006977872,0.002851574,0.272979,0.00005458678,0.1011552,0.07751365,0.4312882],"study_design_scores_gemma":[0.0001805039,0.00001034751,0.009409088,0.00002341738,0.000002775603,0.000001671475,0.0000316648,0.9785414,0.00001879486,0.0004791015,0.01118908,0.0001121149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05146939,0.00006901947,0.8176164,0.007658044,0.0004001807,0.0001187794,8.39171e-7,0.0002068123,0.1224605],"genre_scores_gemma":[0.9273438,0.000004164837,0.06959254,0.0003563723,0.00002984449,8.304327e-7,0.000001175751,0.000004570215,0.002666671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8758745,"threshold_uncertainty_score":0.8767735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0895041517372397,"score_gpt":0.2953768015755207,"score_spread":0.205872649838281,"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."}}