{"id":"W2954796040","doi":"10.1109/tse.2019.2925345","title":"What's Wrong with My Benchmark Results? Studying Bad Practices in JMH Benchmarks","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Vetenskapsrådet","keywords":"Java; Computer science; Benchmark (surveying); Software engineering; Open source; Statement (logic); Best practice; Empirical research; Software; Programming language; Data science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03578126,0.001489028,0.001219866,0.005410394,0.002038007,0.005827317,0.002931438,0.001945849,0.001028041],"category_scores_gemma":[0.2575427,0.001118245,0.001069184,0.006552599,0.00360075,0.007134066,0.002557928,0.003448797,0.0008943212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002841196,"about_ca_system_score_gemma":0.002150216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006064502,"about_ca_topic_score_gemma":0.008025615,"domain_scores_codex":[0.9429855,0.01676255,0.005516184,0.006461379,0.02580443,0.002469903],"domain_scores_gemma":[0.720161,0.1321191,0.03844367,0.04546117,0.05925458,0.004560407],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007901647,0.00091603,0.4994308,0.001706468,0.0009916914,0.00122649,0.01275784,0.01529324,0.02299587,0.009340058,0.05200536,0.382546],"study_design_scores_gemma":[0.000367405,0.00311464,0.5499659,0.004591341,0.001691562,0.004978426,0.02106642,0.1057496,0.1383022,0.05079616,0.1182059,0.001170455],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8482388,0.006395219,0.08478143,0.02976434,0.001764308,0.0004449777,0.002255945,0.01239734,0.01395775],"genre_scores_gemma":[0.9065382,0.001374499,0.07916202,0.004560225,0.0003046464,0.0002852498,0.001706318,0.003973196,0.002095669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9642187,"threshold_uncertainty_score":0.1892317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793363133666667,"score_gpt":0.2499328196435259,"score_spread":0.2319991883068593,"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."}}