{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003794302,0.0004326957,0.0004874206,0.0006682597,0.0003409882,0.001806975,0.007688933,0.0002689332,0.000001294285],"category_scores_gemma":[0.005104656,0.000409552,0.00009606963,0.001144611,0.000272346,0.000663816,0.006752377,0.0008930711,0.000006878096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002403648,"about_ca_system_score_gemma":0.001199547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048051,"about_ca_topic_score_gemma":0.000006878701,"domain_scores_codex":[0.9951863,0.0001357919,0.0005303827,0.002562804,0.0008035647,0.0007811002],"domain_scores_gemma":[0.9898111,0.004850256,0.0002798582,0.004513529,0.0004216355,0.0001236027],"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":[0.000002081888,0.00003831836,0.006524108,0.0001740273,0.000003678171,0.000006986098,0.0002285796,0.2928981,0.0008393793,0.00003237216,0.0001727463,0.6990796],"study_design_scores_gemma":[0.0001698081,0.0000977124,0.0003746551,0.0006934525,0.000006661329,0.00001516786,4.827113e-8,0.9807246,0.003925843,0.01346067,0.00004552987,0.0004858779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003163311,0.0002276912,0.9900155,0.001616864,0.001560744,0.000830434,0.00002805651,0.002552491,0.000004911994],"genre_scores_gemma":[0.4497628,0.000002577875,0.5486687,0.0009821662,0.000486328,0.00002522625,0.0000543926,0.0000173905,4.623264e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6985937,"threshold_uncertainty_score":0.9998356,"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."}}