{"id":"W3003540023","doi":"10.1007/978-3-030-39951-1_18","title":"Strongly Minimal MapReduce Algorithms: A TeraSort Case Study","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Load balancing (electrical power); Algorithm; Skew; Partition (number theory); Sorting algorithm; Parallel computing; Big data; Sorting; Multiplicative function; Parallel algorithm; Theoretical computer science; Mathematics; Data mining","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005837192,0.0009078509,0.0008627697,0.000974897,0.0003658619,0.0007637962,0.006895505,0.000359906,0.00001501038],"category_scores_gemma":[0.0002258869,0.0008593615,0.0001429908,0.001111338,0.001053816,0.001432795,0.006172935,0.001616253,0.0000751158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004615984,"about_ca_system_score_gemma":0.0006235447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005036069,"about_ca_topic_score_gemma":0.0001221497,"domain_scores_codex":[0.9937756,0.00004864626,0.0007721748,0.003166146,0.001317226,0.0009202035],"domain_scores_gemma":[0.9955714,0.0004373504,0.0004026247,0.003090337,0.0002298895,0.0002683873],"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":[0.000008851709,0.0001443899,0.00009665542,0.00003291523,0.00003765908,0.03716568,0.002181631,0.007515569,0.00006213494,0.007376457,0.0000626652,0.9453154],"study_design_scores_gemma":[0.001856049,0.003869503,0.0001217775,0.0004087003,0.00007477043,0.0166381,0.00004938879,0.8038832,0.001706864,0.1631882,0.003970636,0.004232855],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008714366,0.0003200695,0.9940054,0.0007100196,0.001407462,0.001037238,0.00002951672,0.001015838,0.000603051],"genre_scores_gemma":[0.2954292,0.000009562968,0.703555,0.0004452183,0.0003648235,0.00003246267,0.000005467515,0.00005168338,0.0001065274],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9410825,"threshold_uncertainty_score":0.9993857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02671973344925698,"score_gpt":0.2746572974818853,"score_spread":0.2479375640326283,"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."}}