{"id":"W3119686444","doi":"10.1007/s10664-021-10024-2","title":"A pragmatic approach for hyper-parameter tuning in search-based test case generation","year":2021,"lang":"en","type":"preprint","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metric (unit); Computer science; Heuristic; Domain (mathematical analysis); Fine-tuning; Class (philosophy); Test case; Parameter space; Performance metric; Mathematical optimization; Machine learning; Artificial intelligence; Mathematics; Statistics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001151533,0.0006032107,0.0007210156,0.0007401615,0.0001115428,0.0008039682,0.001134413,0.0005431077,0.000008935895],"category_scores_gemma":[0.01529599,0.0006659634,0.0002950928,0.001057501,0.00003535188,0.0003193826,0.001223199,0.001758788,0.000004636892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006956299,"about_ca_system_score_gemma":0.0005685943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007104901,"about_ca_topic_score_gemma":0.000008229496,"domain_scores_codex":[0.9960285,0.0001272745,0.0006924334,0.001408713,0.0007257101,0.001017356],"domain_scores_gemma":[0.9913217,0.006621448,0.0000850461,0.001368477,0.0002666447,0.0003366581],"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":[0.000002706676,0.0001981865,0.01829114,0.00130623,0.00003555395,0.0007850033,0.0005943097,0.9758859,0.0002936911,0.000008718611,0.0001773861,0.002421155],"study_design_scores_gemma":[0.0005149324,0.00006858459,0.002486774,0.0002888638,0.00001414366,0.0002771346,0.00001341634,0.9948089,0.0006935905,0.00001109198,0.0001361356,0.0006864156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1932638,0.0004353355,0.8038024,0.0001511561,0.0004479176,0.0009703927,0.00002214963,0.0009043913,0.00000250882],"genre_scores_gemma":[0.4372351,0.000003036497,0.5614833,0.00006865922,0.0002161402,0.0007309055,0.0001621339,0.00008470425,0.00001606149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2439713,"threshold_uncertainty_score":0.9995791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06445494654789755,"score_gpt":0.3104760695256176,"score_spread":0.24602112297772,"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."}}