{"id":"W2948233389","doi":"10.1007/978-3-030-27455-9_10","title":"Revisiting Hyper-Parameter Tuning for Search-Based Test Data Generation","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Metric (unit); Replicate; Heuristic; Computer science; Baseline (sea); Software; Performance metric; Minor (academic); Space (punctuation); Machine learning; Artificial intelligence; Mathematics; Statistics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.005080804,0.001686234,0.001728198,0.00227882,0.0007333164,0.002892025,0.004652451,0.002150262,0.01001104],"category_scores_gemma":[0.04016911,0.001082624,0.001205378,0.001554399,0.001518188,0.003981145,0.003768246,0.002721552,0.003555463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001370641,"about_ca_system_score_gemma":0.002935671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004134506,"about_ca_topic_score_gemma":0.005137069,"domain_scores_codex":[0.9899836,0.004217665,0.0008172326,0.001524902,0.002773646,0.0006829888],"domain_scores_gemma":[0.9662212,0.01949074,0.001012826,0.009380869,0.003346109,0.0005482662],"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":[0.001315932,0.0005091579,0.005792066,0.0006070493,0.0002171187,0.0003513379,0.0005603531,0.08778561,0.04274691,0.01184201,0.009841297,0.8384311],"study_design_scores_gemma":[0.0002217203,0.0003037314,0.001164411,0.000203406,0.0001273303,0.0003489069,0.0001295621,0.9276706,0.03885203,0.02199062,0.008911965,0.0000757022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03327697,0.0009307367,0.9329136,0.0005537813,0.0001954573,0.0003198955,0.0002586567,0.02677326,0.004777642],"genre_scores_gemma":[0.4918447,0.000249253,0.4989577,0.0007449219,0.00009348462,0.0002643942,0.000590943,0.004102329,0.003152356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01001104,"threshold_uncertainty_score":0.0334903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1077404328298842,"score_gpt":0.338558522507848,"score_spread":0.2308180896779638,"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."}}