{"id":"W4413144677","doi":"10.1109/cloud-summit64795.2025.00015","title":"SparkPerf: A Benchmarking Framework for Evaluating the Performance of Spark Data Analytics Projects","year":2025,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Polytechnique Montréal","funders":"","keywords":"Benchmarking; SPARK (programming language); Analytics; Computer science; Data science; Data analysis; Data mining; Business","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":[0.02455805,0.003428485,0.001923518,0.007569747,0.001514649,0.004526689,0.005704776,0.001487236,0.003111976],"category_scores_gemma":[0.03588847,0.0013355,0.001931397,0.005771544,0.001396944,0.005245802,0.003902669,0.002833434,0.001777585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002292427,"about_ca_system_score_gemma":0.00460232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009243177,"about_ca_topic_score_gemma":0.006481953,"domain_scores_codex":[0.9826913,0.006287517,0.002650249,0.002042737,0.005149732,0.001178506],"domain_scores_gemma":[0.9818277,0.006076304,0.001650996,0.004481432,0.004621319,0.001342234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002710966,0.001965713,0.03876479,0.003773169,0.001494679,0.0008695188,0.002666664,0.2988136,0.01590451,0.07699445,0.2447375,0.3113045],"study_design_scores_gemma":[0.0005708397,0.00118782,0.0114316,0.0004748444,0.0001666713,0.0003978779,0.0007602936,0.8528528,0.0195632,0.03537893,0.07682974,0.0003853618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07405246,0.001686684,0.6598204,0.001129615,0.0006835551,0.002947064,0.01907181,0.2197103,0.02089802],"genre_scores_gemma":[0.3236103,0.0009870615,0.6059575,0.0004145606,0.0001622989,0.002950943,0.04843346,0.01533177,0.00215206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02455805,"threshold_uncertainty_score":0.129877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1145682347822127,"score_gpt":0.3770280880300063,"score_spread":0.2624598532477935,"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."}}