{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006361481,0.0004302735,0.000884898,0.0009767504,0.0001591463,0.000544048,0.0109144,0.0001604197,0.00002009905],"category_scores_gemma":[0.0009271982,0.00035507,0.00009183979,0.002206669,0.0004082281,0.0009304457,0.03984825,0.0007147546,0.00009165626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202519,"about_ca_system_score_gemma":0.0004203607,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008253448,"about_ca_topic_score_gemma":0.008573844,"domain_scores_codex":[0.9934232,0.0002727002,0.0008284528,0.004273425,0.000724952,0.000477255],"domain_scores_gemma":[0.9820629,0.000584506,0.0009119774,0.01519051,0.001083392,0.0001667258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001198845,0.005888205,0.6439987,0.0004006766,0.001113264,0.05352338,0.00544059,0.2164124,0.00001791991,0.0007408909,0.01581792,0.05544717],"study_design_scores_gemma":[0.002403031,0.0002943734,0.01101304,0.0002755666,0.000249601,0.0001724427,0.05169019,0.9293087,0.000004290407,0.003379283,0.0005217617,0.0006877108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8276205,0.00001721911,0.1682621,0.00003135798,0.0009076373,0.001479777,0.00147763,0.00005247916,0.0001512666],"genre_scores_gemma":[0.9950789,0.000006569005,0.003038183,0.00002943519,0.00004767906,6.428631e-7,0.001132681,0.00002008324,0.0006458227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7128963,"threshold_uncertainty_score":0.9998901,"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."}}