{"id":"W3011588630","doi":"10.1109/escience.2019.00023","title":"Evaluation of pilot jobs for Apache Spark applications on HPC clusters","year":2019,"lang":"","type":"article","venue":"Espace ÉTS (ETS)","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"SPARK (programming language); Computer science; Big data; Supercomputer; Scheduling (production processes); Debugging; Software deployment; Operating system; Pipeline transport; Database; Distributed computing; Engineering","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":[0.007560071,0.001656229,0.0009147082,0.0009089849,0.001099467,0.001309523,0.002310993,0.0007932361,0.002418705],"category_scores_gemma":[0.021029,0.0006773695,0.0005683283,0.001286758,0.001012012,0.00175397,0.001096318,0.001375173,0.000833948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125748,"about_ca_system_score_gemma":0.001935566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01166076,"about_ca_topic_score_gemma":0.006002472,"domain_scores_codex":[0.9960176,0.001287092,0.0003592661,0.0005373569,0.001170094,0.0006285102],"domain_scores_gemma":[0.9763021,0.01219884,0.0008209303,0.002492788,0.005518884,0.002666402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.04717544,0.01137499,0.06740273,0.003737827,0.00103093,0.002380465,0.003334768,0.3654211,0.1567003,0.007771036,0.07793953,0.2557309],"study_design_scores_gemma":[0.002479946,0.01038293,0.06583913,0.0001287076,0.0001609086,0.000372164,0.001669058,0.8211744,0.07651533,0.00220166,0.01883443,0.0002413342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9660121,0.0004889461,0.01192085,0.0003301052,0.000530151,0.000580215,0.001138371,0.01245384,0.006545363],"genre_scores_gemma":[0.9682967,0.0001879569,0.02554087,0.0001103088,0.00006121057,0.0002269281,0.002863164,0.001094388,0.00161844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01166076,"threshold_uncertainty_score":0.03998196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05107269823017081,"score_gpt":0.3051105241221561,"score_spread":0.2540378258919853,"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."}}