{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006560662,0.0003459589,0.0003197946,0.0005275689,0.0001242164,0.0004778731,0.0007129869,0.0001394507,0.00002266476],"category_scores_gemma":[0.000204238,0.0003313332,0.00008064247,0.001022128,0.00002238474,0.002514214,0.00001114967,0.0007238356,0.00002736503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001652896,"about_ca_system_score_gemma":0.00009145863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001317928,"about_ca_topic_score_gemma":0.00003629336,"domain_scores_codex":[0.9977766,0.00005941518,0.0004183365,0.000764256,0.0004694482,0.0005120019],"domain_scores_gemma":[0.9971737,0.001439885,0.000219305,0.0009566428,0.00008918594,0.0001213108],"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":[0.0002215205,0.0006896333,0.008703062,0.0002962217,0.0001880915,0.000253799,0.005541131,0.8686239,0.0004141795,0.0002242849,0.0008529146,0.1139913],"study_design_scores_gemma":[0.007951595,0.003697054,0.03088642,0.01103944,0.0001614141,0.0006243855,0.0008534196,0.9127842,0.02080491,0.0007929229,0.004935997,0.005468296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07382603,0.0001375547,0.9189836,0.0001246008,0.001239265,0.000403094,0.000004083068,0.005169,0.0001127098],"genre_scores_gemma":[0.7595155,0.00004607663,0.2401284,0.00007041184,0.00003120457,0.00008155946,0.00000328382,0.00003487897,0.00008862618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6856895,"threshold_uncertainty_score":0.9999139,"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."}}