{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00287224,0.0001372776,0.0002390409,0.00008977514,0.0002921377,0.00009535375,0.002407374,0.00008908698,0.000007331652],"category_scores_gemma":[0.0006869078,0.00008188237,0.00006641783,0.0008889112,0.00007990485,0.0004493691,0.0009012244,0.0001681963,0.000003396852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003699163,"about_ca_system_score_gemma":0.0003864761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003268783,"about_ca_topic_score_gemma":0.000008345465,"domain_scores_codex":[0.9983502,0.00007167539,0.0004586338,0.0004897577,0.0003379965,0.000291743],"domain_scores_gemma":[0.9960848,0.001094397,0.0001804947,0.002374206,0.000239166,0.00002694941],"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":[0.0001635685,0.0002965472,0.3850358,0.00318973,0.0003635933,8.071132e-7,0.002773498,0.009158767,0.0003275286,0.1387038,0.008110982,0.4518754],"study_design_scores_gemma":[0.000179328,0.0002108194,0.008762304,0.0003184147,0.00002965181,0.00000165514,0.0000785008,0.9866191,0.000986991,0.00192624,0.0007758741,0.0001111161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.251633,0.0001682348,0.7450739,0.0006576052,0.0007865011,0.0007274029,0.00000440645,0.00008125048,0.0008676737],"genre_scores_gemma":[0.7620057,0.00002539766,0.2374546,0.0002216044,0.00007961263,0.00004214029,0.000005114977,0.000004085594,0.0001617338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9774603,"threshold_uncertainty_score":0.447354,"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."}}