{"id":"W2791946429","doi":"10.1561/1900000055","title":"Algorithmic Aspects of Parallel Data Processing","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends in Databases","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data processing; Massively parallel; SPARK (programming language); Parallel processing; Sorting; Joins; Data processing system; Scope (computer science); Computation; Parallel computing; Distributed computing; Theoretical computer science; Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001773422,0.00008812164,0.0001191962,0.0002389907,0.0001536847,0.00009806311,0.0007470366,0.00001700296,0.00006406432],"category_scores_gemma":[0.00004218624,0.00007556283,0.000009328685,0.0005831672,0.0001379886,0.001869096,0.00114123,0.00005970044,0.000007020631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007879818,"about_ca_system_score_gemma":0.00005023447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002798654,"about_ca_topic_score_gemma":0.0003720959,"domain_scores_codex":[0.9990783,0.00002592232,0.0002080626,0.0003965367,0.00014573,0.0001454141],"domain_scores_gemma":[0.9987113,0.00005052882,0.00008820221,0.001054565,0.00005304573,0.00004230321],"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":[0.000003736553,0.0001151649,0.0006080514,0.00001282911,0.000005773638,0.000005376697,0.0001182237,0.000003409516,0.00004895749,0.04173965,0.001881657,0.9554572],"study_design_scores_gemma":[0.001076175,0.0001626854,0.04685558,0.0002551464,0.00002099793,0.00005181508,0.00008413736,0.8302687,0.0003407729,0.006352786,0.1141236,0.0004075699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002738213,0.0004914058,0.9916591,0.0003081477,0.0001919896,0.00005845571,0.0005049858,0.00005957181,0.003988096],"genre_scores_gemma":[0.5728368,0.00007390756,0.425338,0.00003782213,0.0001291193,0.000006446559,0.001495711,0.000006130645,0.00007614101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550496,"threshold_uncertainty_score":0.3081363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08973294613584182,"score_gpt":0.3603261051781024,"score_spread":0.2705931590422606,"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."}}