{"id":"W2403271036","doi":"","title":"Surrogate benchmarks for hyperparameter optimization","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Hyperparameter optimization; Machine learning; Computer science; Artificial intelligence; Range (aeronautics); Set (abstract data type); Regression; Mathematics; Support vector machine; 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":[],"consensus_categories":[],"category_scores_codex":[0.000316483,0.00005153675,0.00005628403,0.00003994545,0.00007162758,0.000112748,0.0002896935,0.00002895889,0.00004705069],"category_scores_gemma":[0.0001718806,0.0000422969,0.00002527476,0.00009128254,0.000008466226,0.000255884,0.00004248857,0.00003595056,0.00002337777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006350312,"about_ca_system_score_gemma":0.000008552311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001051193,"about_ca_topic_score_gemma":0.000002152826,"domain_scores_codex":[0.9994845,0.00004063317,0.00009386339,0.0002035843,0.00007233652,0.000105058],"domain_scores_gemma":[0.999387,0.0001474885,0.0000397798,0.0003435087,0.00004667136,0.00003555628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006573051,0.00004658771,0.001363178,0.00001674286,0.000007540698,9.122822e-8,0.0001051427,0.06053102,0.000191886,0.6700201,0.008681272,0.2590298],"study_design_scores_gemma":[0.0001447016,0.00003881399,0.0005625833,0.000001641978,0.000001646621,9.40129e-7,0.000001752234,0.9582135,0.0001422094,0.001214326,0.03961545,0.00006244738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003897033,0.000003793451,0.9794012,0.001841384,0.0001337565,0.00008112281,7.521397e-7,0.0001122408,0.018036],"genre_scores_gemma":[0.3656774,0.00000187867,0.633159,0.0004054616,0.00003876638,0.00001701223,0.00007906212,0.000003427806,0.0006179826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8976825,"threshold_uncertainty_score":0.1724817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01026651275306719,"score_gpt":0.2379664930734289,"score_spread":0.2276999803203617,"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."}}