{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002928174,0.001307878,0.00107326,0.001698886,0.001305052,0.004685568,0.002427862,0.001362633,0.004310814],"category_scores_gemma":[0.01235852,0.0008551622,0.001333853,0.004270028,0.003282052,0.006731287,0.002894885,0.003504942,0.001805668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001721767,"about_ca_system_score_gemma":0.002017982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001283319,"about_ca_topic_score_gemma":0.001158982,"domain_scores_codex":[0.9955299,0.0009777508,0.0003687476,0.0006804139,0.002207198,0.0002360658],"domain_scores_gemma":[0.9958896,0.002379265,0.0001626448,0.0008524425,0.0006375653,0.00007859058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003673109,0.00004401791,0.0004923624,0.0004819036,0.0000456169,0.00009280739,0.0001897881,0.04527229,0.0006485624,0.8782842,0.005762414,0.06864947],"study_design_scores_gemma":[0.00001452646,0.00001495915,0.0001229305,0.0000474176,0.00001354136,0.0001075387,0.00003966266,0.09399339,0.0004725186,0.8842874,0.02087571,0.00001053224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005182051,0.009456567,0.953331,0.003435908,0.0004245716,0.000160022,0.0002126379,0.0003256033,0.02747178],"genre_scores_gemma":[0.1872294,0.02424205,0.7656401,0.001318072,0.003244953,0.0009916673,0.001387859,0.0004426966,0.01550309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004685568,"threshold_uncertainty_score":0.01548582,"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."}}