{"id":"W4317899376","doi":"10.1007/978-3-031-25049-1_11","title":"A Deterministic Model to Predict Execution Time of Spark Applications","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; SPARK (programming language); Directed acyclic graph; Tree traversal; Execution time; Parallel computing; Cloud computing; Benchmark (surveying); Scheduling (production processes); Graph; Distributed computing; Theoretical computer science; Operating system; Algorithm; Programming language","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":[0.001307971,0.0006533923,0.000996237,0.0005617153,0.0004851817,0.00080913,0.001588094,0.0009918333,0.001371655],"category_scores_gemma":[0.003769175,0.0007778654,0.0008726382,0.0006413244,0.0005775074,0.0007113416,0.0005420853,0.001092283,0.0003418716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001349657,"about_ca_system_score_gemma":0.001561376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02220814,"about_ca_topic_score_gemma":0.01478618,"domain_scores_codex":[0.9994929,0.0001010085,0.00002968396,0.000155683,0.0001294791,0.00009123686],"domain_scores_gemma":[0.9973557,0.001980134,0.0002134294,0.0001341961,0.0002420944,0.00007446347],"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":[0.00003329702,0.00001627958,0.0003568955,0.00001227944,0.00001278651,0.00001106841,0.00000633822,0.9944922,0.0002639839,0.001589099,0.0002670409,0.002938728],"study_design_scores_gemma":[0.000001519662,0.000003755912,0.00005226529,4.727366e-7,0.000001629542,0.000001544842,3.871955e-7,0.9993894,0.00005633978,0.000460707,0.00003074878,0.000001195497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.150118,0.001034676,0.841844,0.0006128864,0.0002181173,0.00007657315,0.0008511131,0.00185958,0.003385071],"genre_scores_gemma":[0.9570668,0.0003268044,0.03733286,0.00009119234,0.0001165285,0.0001099037,0.0005851684,0.0001006783,0.004270174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02220814,"threshold_uncertainty_score":0.0441578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01903471091249719,"score_gpt":0.2435101432983835,"score_spread":0.2244754323858863,"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."}}