{"id":"W4385873399","doi":"10.36227/techrxiv.23947293","title":"SparkPerf: A Machine Learning Benchmarking Framework for Spark-based Data Science Projects","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Polytechnique Montréal","funders":"","keywords":"Benchmarking; Computer science; Software portability; Benchmark (surveying); Consistency (knowledge bases); SPARK (programming language); Machine learning; Class (philosophy); Process (computing); Software engineering; Artificial intelligence; Resource (disambiguation); Operating system; 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":[0.01649706,0.003101567,0.001971076,0.004450798,0.001554272,0.00465715,0.007703946,0.001937133,0.007202168],"category_scores_gemma":[0.02724701,0.001743336,0.00244165,0.00423419,0.001637309,0.005944917,0.005887978,0.004120067,0.005273366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002084992,"about_ca_system_score_gemma":0.00435137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006860659,"about_ca_topic_score_gemma":0.005949696,"domain_scores_codex":[0.9903105,0.003409377,0.001172635,0.001393623,0.002920927,0.0007930446],"domain_scores_gemma":[0.9912123,0.002710172,0.0006433651,0.002769208,0.001754032,0.0009108643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001619916,0.0009286158,0.01168865,0.002259953,0.0008770193,0.000705284,0.001707532,0.1480628,0.008544235,0.1206456,0.4655632,0.2373973],"study_design_scores_gemma":[0.0005380706,0.0003151182,0.003766167,0.0003404199,0.00008737168,0.0003779101,0.0003431471,0.7053652,0.01231769,0.1003081,0.1759314,0.0003094089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00768734,0.0007405583,0.6504946,0.0009771781,0.0003984427,0.00093435,0.007967752,0.3212603,0.009539399],"genre_scores_gemma":[0.1384794,0.0008936917,0.7572215,0.0008906635,0.0002110499,0.002448819,0.04874127,0.0473221,0.003791413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01649706,"threshold_uncertainty_score":0.08724582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3293414665083918,"score_gpt":0.3795579154068238,"score_spread":0.05021644889843202,"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."}}