{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01881284,0.001607965,0.001888152,0.002839503,0.001588232,0.004423411,0.004110392,0.004361264,0.01137956],"category_scores_gemma":[0.1222225,0.001719407,0.001423242,0.00163902,0.002640289,0.004004139,0.006784783,0.004842739,0.002783788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001233683,"about_ca_system_score_gemma":0.003186086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001120687,"about_ca_topic_score_gemma":0.002227155,"domain_scores_codex":[0.9660568,0.02232348,0.001803803,0.001899717,0.007101922,0.0008143376],"domain_scores_gemma":[0.9330552,0.04865988,0.001868409,0.009281659,0.006240278,0.0008945048],"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":[0.001706052,0.001153658,0.003127907,0.001060838,0.0003410393,0.0007344563,0.002462666,0.0882841,0.0521111,0.153411,0.01294387,0.6826631],"study_design_scores_gemma":[0.0006419237,0.0003391444,0.0009517655,0.0002497053,0.0001556095,0.000450765,0.0003415148,0.8399852,0.01780967,0.1277058,0.0112162,0.0001528176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003469495,0.00006711989,0.9909554,0.000379376,0.00003666356,0.0004534056,0.00005442647,0.00182713,0.002756893],"genre_scores_gemma":[0.1694179,0.00005001345,0.8263435,0.0006403382,0.00005225139,0.001207958,0.0001524342,0.0007091593,0.001426409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01881284,"threshold_uncertainty_score":0.09949297,"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."}}