{"id":"W2982229230","doi":"10.48550/arxiv.1910.11125","title":"Micro-level Modularity of Computaion-intensive Programs in Big Data Platforms: A Case Study with Image Data","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Reusability; Modularity (biology); SPARK (programming language); Modular design; Modular programming; Structuring; Big data; Dataflow; Computation; Data flow diagram; Personalization; Distributed computing; Software; Programming language; Data mining; 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":[0.003598029,0.0005720172,0.0003886876,0.0009032174,0.001499556,0.001485945,0.001700293,0.001024905,0.0005942041],"category_scores_gemma":[0.01160458,0.0004419837,0.0006736058,0.001017306,0.002749359,0.002630405,0.001741615,0.001372881,0.0001583151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333759,"about_ca_system_score_gemma":0.001612072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00575577,"about_ca_topic_score_gemma":0.006842008,"domain_scores_codex":[0.9974793,0.0009652992,0.0001122795,0.0003909264,0.0007181945,0.0003340657],"domain_scores_gemma":[0.9895726,0.006285832,0.0007928158,0.001573192,0.001102545,0.0006729484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001507378,0.003030451,0.146988,0.001349018,0.0003022321,0.01147905,0.02657195,0.4220338,0.08797541,0.08193496,0.007527306,0.2093005],"study_design_scores_gemma":[0.0001551801,0.0005537418,0.02839308,0.00009210232,0.0001197489,0.001369751,0.004446516,0.8669609,0.05185472,0.031982,0.01397995,0.00009241854],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9001204,0.0002005564,0.09523106,0.0005448647,0.00001250347,0.0002267972,0.00009410051,0.0007244781,0.002845224],"genre_scores_gemma":[0.9139769,0.0001046527,0.08463934,0.00005782069,0.000009497071,0.00009207753,0.0001463912,0.0001790408,0.0007942846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00575577,"threshold_uncertainty_score":0.01902843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6740415810237886,"score_gpt":0.326351378838455,"score_spread":0.3476902021853336,"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."}}