{"id":"W4281707786","doi":"10.48550/arxiv.2206.06779","title":"Benchmarking Bayesian neural networks and evaluation metrics for\\n regression tasks","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Bayesian probability; Artificial neural network; Computer science; Artificial intelligence; Deep neural networks; Bayesian network; Machine learning; Econometrics; Mathematics","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":[0.0177206,0.003135569,0.001698686,0.005260196,0.0007899571,0.002730525,0.003567923,0.004417942,0.002917581],"category_scores_gemma":[0.06663772,0.0005602206,0.00140271,0.003378895,0.001279332,0.003499913,0.00298326,0.003150146,0.001392105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00345271,"about_ca_system_score_gemma":0.002379515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01408749,"about_ca_topic_score_gemma":0.01327473,"domain_scores_codex":[0.9844215,0.007941404,0.001195468,0.002158369,0.003699378,0.0005838152],"domain_scores_gemma":[0.9757867,0.01549524,0.001751616,0.002419751,0.00385338,0.0006932669],"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":[0.0008912608,0.0004827573,0.008943657,0.0009284976,0.0006579396,0.00008700699,0.00008490543,0.801436,0.001675823,0.01138686,0.0126295,0.1607959],"study_design_scores_gemma":[0.00003155864,0.0001732185,0.001377379,0.0001064044,0.00003998703,0.00004971197,0.00002758951,0.9901977,0.001561721,0.005223112,0.001190282,0.00002132251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2001788,0.02162521,0.7381148,0.003580765,0.0008948013,0.0007487154,0.007397654,0.009947263,0.01751197],"genre_scores_gemma":[0.7051817,0.00426836,0.2604923,0.0007400476,0.0004079011,0.0009197622,0.02243748,0.001330104,0.004222401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0177206,"threshold_uncertainty_score":0.09371656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09183349694236233,"score_gpt":0.2370381940444209,"score_spread":0.1452046971020586,"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."}}