{"id":"W2772402907","doi":"10.1007/s00500-017-2945-4","title":"On the value of parameter tuning in heterogeneous ensembles effort estimation","year":2017,"lang":"en","type":"article","venue":"Soft Computing","topic":"Software Engineering Research","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Particle swarm optimization; Computer science; Software; Hyperparameter optimization; Grid; Machine learning; Data mining; Perceptron; Support vector machine; Estimation; Artificial intelligence; Artificial neural network; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0007903742,0.00009537282,0.0001295088,0.00009751026,0.0002326868,0.0001979119,0.001171238,0.00003788949,0.00000141348],"category_scores_gemma":[0.002713283,0.00007497153,0.0000445742,0.0001061799,0.00005137461,0.0001274838,0.0004481194,0.0001859849,0.00001063656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003814142,"about_ca_system_score_gemma":0.00003065888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006034712,"about_ca_topic_score_gemma":0.000002099511,"domain_scores_codex":[0.9989893,0.00004614122,0.000193066,0.0002258159,0.0002891534,0.0002565115],"domain_scores_gemma":[0.9964531,0.002522026,0.0001179417,0.0008353387,0.00003946779,0.00003213741],"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":[0.000006723315,0.00004674713,0.05595786,0.00005769599,0.00002318456,0.00004258601,0.001433526,0.7801859,0.0006408062,0.02091537,0.00004598099,0.1406437],"study_design_scores_gemma":[0.000106279,0.00003760049,0.05237615,0.0001404362,8.86415e-7,0.000008429151,0.000003003848,0.94112,0.003238102,0.002887964,0.000005717992,0.00007547446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5968236,0.00001511323,0.4027291,0.0001267283,0.0001246252,0.00007727312,1.29743e-7,0.00005485293,0.0000485645],"genre_scores_gemma":[0.9676862,5.334523e-7,0.0322306,0.00004160714,0.00002279742,0.000003067255,2.979168e-7,0.00000898655,0.000005884828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3708626,"threshold_uncertainty_score":0.3248249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02662789720180282,"score_gpt":0.2920757530750286,"score_spread":0.2654478558732258,"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."}}