{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:27:14Z","timestamp":1793608034186,"version":"4.5.0"},"reference-count":178,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109699","type":"journal-article","created":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T06:23:52Z","timestamp":1791008632000},"page":"109699","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Uncertainty quantification for trustworthy deep learning: Methods and measures"],"prefix":"10.1016","volume":"206","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4650-5384","authenticated-orcid":false,"given":"H. Martin","family":"Gillis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6144-8963","authenticated-orcid":false,"given":"Thomas","family":"Trappenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109699_bib0001","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: Techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109699_bib0002","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Deep ensembles work, but are they necessary?","author":"Abe","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0003","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"On feature collapse and deep kernel learning for single forward pass uncertainty","author":"van Amersfoort","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0004","series-title":"International conference on machine learning (ICML)","first-page":"9690","article-title":"Uncertainty estimation using a single deep deterministic neural network","author":"van Amersfoort","year":"2020"},{"issue":"4","key":"10.1016\/j.neunet.2026.109699_bib0005","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1561\/2200000101","article-title":"Conformal prediction: A gentle introduction","volume":"16","author":"Angelopoulos","year":"2023","journal-title":"Foundations and Trends in Machine Learning"},{"key":"10.1016\/j.neunet.2026.109699_bib0006","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Getting a CLUE: A method for explaining uncertainty estimates","author":"Antor\u00e1n","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0007","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"A rate-distortion view of uncertainty quantification","author":"Apostolopoulou","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0008","unstructured":"Arbel, J., Pitas, K., Vladimirova, M., & Fortuin, V. (2023). A primer on bayesian neural networks: Review and debates. 10.48550\/arXiv.2309.16314."},{"key":"10.1016\/j.neunet.2026.109699_bib0009","series-title":"Information theory","author":"Ash","year":"1965"},{"key":"10.1016\/j.neunet.2026.109699_bib0010","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Pitfalls of in-domain uncertainty estimation and ensembling in deep learning","author":"Ashukha","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0011","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Scope: Selective conformal optimized pairwise LLM judging","author":"Badshah","year":"2026"},{"key":"10.1016\/j.neunet.2026.109699_bib0012","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Efficient epistemic uncertainty estimation in regression ensemble models using pairwise-distance estimators","author":"Berry","year":"2023"},{"issue":"518","key":"10.1016\/j.neunet.2026.109699_bib0013","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: A review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/j.neunet.2026.109699_bib0014","series-title":"International conference on machine learning (ICML)","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"Blundell","year":"2015"},{"key":"10.1016\/j.neunet.2026.109699_bib0015","series-title":"International conference on artificial intelligence and statistics (AISTATS)","first-page":"3905","article-title":"Learnable bernoulli dropout for Bayesian deep learning","volume":"vol. 108","author":"Boluki","year":"2020"},{"issue":"1","key":"10.1016\/j.neunet.2026.109699_bib0016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","article-title":"Verification of forecasts expressed in terms of probability","volume":"78","author":"Brier","year":"1950","journal-title":"Monthly Weather Review"},{"key":"10.1016\/j.neunet.2026.109699_bib0017","unstructured":"Brosse, N., Riquelme, C., Martin, A., Gelly, S., & Moulines, E. (2020). On last-layer algorithms for classification: Decoupling representation from uncertainty estimation. 10.48550\/arXiv.2001.08049."},{"issue":"1","key":"10.1016\/j.neunet.2026.109699_bib0018","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.inffus.2004.04.004","article-title":"Diversity creation methods: A survey and categorisation","volume":"6","author":"Brown","year":"2005","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109699_bib0019","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1356","article-title":"Posterior network: Uncertainty estimation without OOD samples via density-based pseudo-counts","author":"Charpentier","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0020","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Integral imprecise probability metrics","author":"Chau","year":"2025"},{"issue":"250","key":"10.1016\/j.neunet.2026.109699_bib0021","article-title":"A brief review of hypernetworks in deep learning","volume":"57","author":"Chauhan","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.neunet.2026.109699_bib0022","series-title":"International conference on artificial intelligence and statistics (AISTATS)","first-page":"1","article-title":"Deep gaussian process","volume":"vol. 31","author":"Damianou","year":"2013"},{"key":"10.1016\/j.neunet.2026.109699_bib0023","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Laplace redux \u2013 effortless Bayesian deep learning","author":"Daxberger","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0024","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","author":"Depeweg","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0025","unstructured":"DeVries, T., & Taylor, G. W. (2018). Learning confidence for out-of-distribution detection in neural networks. 10.48550\/arXiv.1802.04865."},{"key":"10.1016\/j.neunet.2026.109699_bib0026","series-title":"Multiple classifier systems","first-page":"1","article-title":"Ensemble methods in machine learning","volume":"vol. 1857","author":"Dietterich","year":"2000"},{"key":"10.1016\/j.neunet.2026.109699_bib0027","unstructured":"Dold, D., Kobialka, J., Palm, N., Sommer, E., R\u00fcgamer, D., & D\u00fcrr, O. (2025). Paths and ambient spaces in neural loss landscapes. 10.48550\/arXiv.2503.03382."},{"key":"10.1016\/j.neunet.2026.109699_bib0028","unstructured":"Dold, D., Sommer, E., Kobialka, J., D\u00fcrr, O., & R\u00fcgamer, D. (2026). On the construction and implications of low-loss valleys in LoRA-based bayesian inference. 10.48550\/arXiv.2605.29580."},{"key":"10.1016\/j.neunet.2026.109699_bib0029","series-title":"Conference on computer vision and pattern recognition (CVPR)","first-page":"13539","article-title":"Masksembles for uncertainty estimation","author":"Durasov","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0030","series-title":"International conference on pattern recognition (ICPR)","first-page":"1908","article-title":"AutoDEUQ: Automated deep ensemble with uncertainty quantification","author":"Egele","year":"2022"},{"issue":"8017","key":"10.1016\/j.neunet.2026.109699_bib0031","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.109699_bib0032","first-page":"1","article-title":"On the importance of uncertainty in decision-making with large language models","author":"Felicioni","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0033","first-page":"1","article-title":"Calibrated selective classification","author":"Fisch","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0034","unstructured":"Fort, S., Hu, H., & Lakshminarayanan, B. (2020). Deep ensembles: A loss landscape perspective. 10.48550\/arXiv.1912.02757."},{"key":"10.1016\/j.neunet.2026.109699_bib0035","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Exploring the limits of out-of-distribution detection","author":"Fort","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.109699_bib0036","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1111\/insr.12502","article-title":"Priors in Bayesian deep learning: A review","volume":"90","author":"Fortuin","year":"2022","journal-title":"International Statistical Review"},{"key":"10.1016\/j.neunet.2026.109699_bib0037","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Bayesian neural network priors revisited","author":"Fortuin","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0038","first-page":"1","article-title":"The Vendi score: A diversity evaluation metric for machine learning","author":"Friedman","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0039","series-title":"International conference on machine learning (ICML)","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume":"vol. 48","author":"Gal","year":"2016"},{"key":"10.1016\/j.neunet.2026.109699_bib0040","series-title":"International conference on machine learning (ICML)","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume":"vol. 70","author":"Gal","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0041","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"108","article-title":"Multi-head multi-loss model calibration","volume":"vol. 14222","author":"Galdran","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0042","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1007\/s10462-023-10562-9","article-title":"A survey of uncertainty in deep neural networks","volume":"56","author":"Gawlikowski","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.neunet.2026.109699_bib0043","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"4885","article-title":"Selective classification for deep neural networks","volume":"vol. 30","author":"Geifman","year":"2017"},{"issue":"108819","key":"10.1016\/j.neunet.2026.109699_bib0044","article-title":"Last-layer committee machines for uncertainty estimations of benthic imagery","volume":"200","author":"Gillis","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109699_bib0045","unstructured":"Gillis, H. M., Xu, I., Spadon, G., & Trappenberg, T. (2026b). Covariance last-layer ensembles: Function-space diversity for efficient uncertainty quantification. 10.48550\/arXiv.2607.23856."},{"key":"10.1016\/j.neunet.2026.109699_bib0046","first-page":"1","article-title":"Variance-gated ensembles: An epistemic-aware framework for uncertainty estimation","author":"Gillis","year":"2026","journal-title":"Transactions on Machine Learning Research"},{"issue":"477","key":"10.1016\/j.neunet.2026.109699_bib0047","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1198\/016214506000001437","article-title":"Strictly proper scoring rules, prediction, and estimation","volume":"102","author":"Gneiting","year":"2007","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/j.neunet.2026.109699_bib0048","series-title":"Conference on neural information processing systems (NIPS)","first-page":"2348","article-title":"Practical variational inference for neural networks","volume":"vol. 24","author":"Graves","year":"2011"},{"key":"10.1016\/j.neunet.2026.109699_bib0049","series-title":"International conference on machine learning (ICML)","first-page":"1321","article-title":"On calibration of modern neural networks","volume":"vol. 70","author":"Guo","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0050","series-title":"Conference on computer vision and pattern recognition workshops (CVPRW)","first-page":"1289","article-title":"Evaluating scalable Bayesian deep learning methods for robust computer vision","author":"Gustafsson","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0051","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Variational Bayesian last layers","author":"Harrison","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0052","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Training independent subnetworks for robust prediction","author":"Havasi","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0053","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1145\/3786319","article-title":"A survey on uncertainty quantification methods for deep learning","volume":"58","author":"He","year":"2026","journal-title":"ACM Computing Surveys"},{"issue":"5","key":"10.1016\/j.neunet.2026.109699_bib0054","doi-asserted-by":"crossref","first-page":"3073","DOI":"10.1007\/s10994-024-06534-x","article-title":"Machine learning with a reject option: A survey","volume":"113","author":"Hendrickx","year":"2024","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109699_bib0055","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0056","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0057","series-title":"High performance computing","first-page":"223","article-title":"Ensembles of networks produced from neural architecture search","volume":"vol. 12321","author":"Herron","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0058","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0059","unstructured":"Houlsby, N., Husz\u00e1r, F., Ghahramani, Z., & Lengyel, M. (2011). Bayesian active learning for classification and preference learning. 10.48550\/arXiv.1112.5745."},{"key":"10.1016\/j.neunet.2026.109699_bib0060","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","author":"Huang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0061","unstructured":"Huang, H.-Y., Yang, Y., Zhang, Z., Lee, S., & Wu, Y. (2024). A survey of uncertainty estimation in LLMs: Theory meets practice. 10.48550\/arXiv.2410.15326."},{"key":"10.1016\/j.neunet.2026.109699_bib0062","unstructured":"Hubin, A., &Storvik, G. (2019). Combining model and parameter uncertainty in Bayesian neural networks. 10.48550\/arXiv.1903.07594."},{"issue":"3","key":"10.1016\/j.neunet.2026.109699_bib0063","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","article-title":"Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods","volume":"110","author":"H\u00fcllermeier","year":"2021","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109699_bib0064","series-title":"Conference on uncertainty in artificial intelligence (UAI)","first-page":"1","article-title":"Subspace inference for Bayesian deep learning","volume":"vol. 115","author":"Izmailov","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0065","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"What are Bayesian neural network posteriors really like?","volume":"vol. 139","author":"Izmailov","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0066","series-title":"Aaai conference on artificial intelligence","first-page":"4264","article-title":"Maximizing overall diversity for improved uncertainty estimates in deep ensembles","author":"Jain","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0067","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Variational uncertainty decomposition for in-context learning","author":"Jayasekera","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0068","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"5546","article-title":"To trust or not to trust a classifier","author":"Jiang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0069","series-title":"Conference on computer vision and pattern recognition (CVPR)","first-page":"2372","article-title":"Multi-class active learning for image classification","author":"Joshi","year":"2009"},{"issue":"2","key":"10.1016\/j.neunet.2026.109699_bib0070","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/MCI.2022.3155327","article-title":"Hands-on Bayesian neural networks\u2013a tutorial for deep learning users","volume":"17","author":"Jospin","year":"2022","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"10.1016\/j.neunet.2026.109699_bib0071","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Is epistemic uncertainty faithfully represented by evidential deep learning methods?","volume":"vol. 235","author":"J\u00fcrgens","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0072","unstructured":"Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., Johnston, S., El-Showk, S., Jones, A., Elhage, N., Hume, T., Chen, A., Bai, Y., Bowman, S., Fort, S., Ganguli, D., Hernandez, D., Jacobson, J., Kernion, J., Kravec, S., Lovitt, L., Ndousse, K., Olsson, C., Ringer, S., Amodei, D., Brown, T., Clark, J., Joseph, N., Mann, B., McCandlish, S., Olah, C., & Kaplan, J. (2022). Language models (mostly) know what they know. 10.48550\/arXiv.2207.05221."},{"key":"10.1016\/j.neunet.2026.109699_bib0073","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Scalable best-of-N selection for large language models via self-certainty","author":"Kang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0074","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"Kendall","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0075","first-page":"1","article-title":"(Implicit) ensembles of ensembles: Epistemic uncertainty collapse in large models","author":"Kirsch","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0076","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"On pitfalls in OoD detection: Predictive entropy considered harmful","author":"Kirsch","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.109699_bib0077","doi-asserted-by":"crossref","first-page":"33","DOI":"10.2307\/1913643","article-title":"Regression quantiles","volume":"46","author":"Koenker","year":"1978","journal-title":"Econometrica"},{"key":"10.1016\/j.neunet.2026.109699_bib0078","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Being Bayesian, even just a bit, fixes overconfidence in ReLU networks","volume":"vol. 119","author":"Kristiadi","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0079","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation","author":"Kuhn","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0080","series-title":"Conference on uncertainty in artificial intelligence (UAI)","first-page":"1","article-title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","author":"Kumar","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0081","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","article-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy","volume":"51","author":"Kuncheva","year":"2003","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109699_bib0082","series-title":"International conference on medical image computing and computer assisted intervention (MICCAI)","first-page":"514","article-title":"Layer ensembles: A single-pass uncertainty estimation in deep learning for segmentation","author":"Kushibar","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0083","series-title":"Conference on neural information processing systems (NIPS)","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0084","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Deep neural networks as Gaussian processes","author":"Lee","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0085","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","author":"Lee","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0086","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0087","unstructured":"Lee, S., Purushwalkam, S., Cogswell, M., Crandall, D., & Batra, D. (2015). Why M heads are better than one: Training a diverse ensemble of deep networks. 10.48550\/arXiv.1511.06314."},{"key":"10.1016\/j.neunet.2026.109699_bib0088","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Vicinal label supervision for reliable aleatoric and epistemic uncertainty estimation","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0089","series-title":"International conference on machine learning (ICML)","first-page":"2052","article-title":"Dropout inference in Bayesian neural networks with alpha-divergences","volume":"vol. 70","author":"Li","year":"2017"},{"key":"10.1016\/j.neunet.2026.109699_bib0090","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Calibrating LLMs with information-theoretic evidential deep learning","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0091","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Revisiting logit distributions for reliable out-of-distribution detection","author":"Liang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0092","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"Liang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0093","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Accurate uncertainty estimation and decomposition in ensemble learning","author":"Liu","year":"2019"},{"issue":"42","key":"10.1016\/j.neunet.2026.109699_bib0094","first-page":"1","article-title":"A simple approach to improve single-model deep uncertainty via distance-awareness","volume":"24","author":"Liu","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0095","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Energy-based out-of-distribution detection","author":"Liu","year":"2020"},{"issue":"3","key":"10.1016\/j.neunet.2026.109699_bib0096","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","article-title":"A practical Bayesian framework for backpropagation networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.109699_bib0097","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"A simple baseline for Bayesian uncertainty in deep learning","author":"Maddox","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0098","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","author":"Malinin","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0099","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Reverse KL-divergence training of prior networks: Improved uncertainty and adversarial robustness","author":"Malinin","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0100","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Uncertainty estimation in autoregressive structured prediction","author":"Malinin","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0101","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Ensemble distribution distillation","author":"Malinin","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0102","series-title":"Conference on empirical methods in natural language processing (EMNLP)","first-page":"9004","article-title":"SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models","author":"Manakul","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0103","series-title":"European conference on machine learning","first-page":"268","article-title":"Active learning for probability estimation using Jensen-Shannon divergence","volume":"vol. 3720","author":"Melville","year":"2005"},{"issue":"9","key":"10.1016\/j.neunet.2026.109699_bib0104","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3477140","article-title":"A survey on uncertainty estimation in deep learning classification systems from a Bayesian perspective","volume":"54","author":"Mena","year":"2021","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109699_bib0105","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Revisiting the calibration of modern neural networks","author":"Minderer","year":"2021"},{"issue":"5458","key":"10.1016\/j.neunet.2026.109699_bib0106","article-title":"DropConnect is effective in modeling uncertainty of Bayesian deep networks","volume":"11","author":"Mobiny","year":"2021","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.109699_bib0107","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"NeuralSurv: Deep survival analysis with Bayesian uncertainty quantification","author":"Monod","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0108","series-title":"Conference on computer vision and pattern recognition (CVPR)","first-page":"24384","article-title":"Deep deterministic uncertainty: A new simple baseline","author":"Mukhoti","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0109","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"15288","article-title":"Calibrating deep neural networks using focal loss","author":"Mukhoti","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0110","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Uncertainty baselines: Benchmarks for uncertainty & robustness in deep learning","author":"Nado","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0111","series-title":"Aaai conference on artificial intelligence","first-page":"2901","article-title":"Obtaining well-calibrated probabilities using Bayesian binning","author":"Naeini","year":"2015"},{"key":"10.1016\/j.neunet.2026.109699_bib0112","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Towards maximizing the representation gap between in-domain & out-of-distribution examples","author":"Nandy","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0113","article-title":"Bayesian learning for neural networks","volume":"vol. 118","author":"Neal","year":"1995"},{"issue":"110796","key":"10.1016\/j.neunet.2026.109699_bib0114","article-title":"Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial","volume":"205","author":"Nemani","year":"2023","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.neunet.2026.109699_bib0115","series-title":"Conference on artificial intelligence","first-page":"7877","article-title":"Out of distribution data detection using dropout Bayesian neural networks","volume":"vol. 36","author":"Nguyen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0116","series-title":"International workshop on machine learning for signal processing (MLSP)","first-page":"1","article-title":"Layer ensembles","author":"Oleksiienko","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0117","series-title":"Advances in neural information processing systems","first-page":"2795","article-title":"Epistemic neural networks","volume":"vol. 36","author":"Osband","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0118","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Can you trust your model\u2019s uncertainty? evaluating predictive uncertainty under dataset shift","author":"Ovadia","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0119","series-title":"International conference on artificial intelligence and statistics (AISTATS)","first-page":"1","article-title":"Uncertainty in neural networks: Approximately Bayesian ensembling","volume":"vol. 108","author":"Pearce","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0120","series-title":"Advances in large margin classifiers","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"vol. 10","author":"Platt","year":"1999"},{"key":"10.1016\/j.neunet.2026.109699_bib0121","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"On the practicality of deterministic epistemic uncertainty","volume":"vol. 162","author":"Postels","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0122","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Uncertainty quantification and deep ensembles","author":"Rahaman","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0123","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"DICE: Diversity in deep ensembles via conditional redundancy adversarial estimation","author":"Ram\u00e9","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0124","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"A simple fix to Mahalanobis distance for improving near-OOD detection","author":"Ren","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0125","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Out-of-distribution detection and selective generation for conditional language models","author":"Ren","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0126","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Conformalized quantile regression","author":"Romano","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0127","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"On the epistemic uncertainty of overparametrized neural networks","author":"R\u00fcgamer","year":"2026"},{"key":"10.1016\/j.neunet.2026.109699_bib0128","series-title":"Conference on uncertainty in artificial intelligence (UAI)","first-page":"1795","article-title":"Is the volume of a credal set a good measure for epistemic uncertainty?","author":"Sale","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0129","unstructured":"Samplawski, C., Cobb, A. D., Acharya, M., & Jha, S. (2025). Scalable bayesian low-rank adaptation of large language models via stochastic variational subspace inference. 10.48550\/arXiv.2506.21408."},{"key":"10.1016\/j.neunet.2026.109699_bib0130","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Beyond top-class agreement: Using divergences to forecast performance under distribution shift","author":"Schirmer","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0131","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"3605","article-title":"Introducing an improved information-theoretic measure of predictive uncertainty","volume":"vol. 286","author":"Schweighofer","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0132","series-title":"Neural information processing systems (neurIPS)","first-page":"1","article-title":"Quantification of uncertainty with adversarial models","author":"Schweighofer","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0133","unstructured":"Segonne, P., Zainchkovskyy, Y., & Hauberg, S. (2022). Robust uncertainty estimates with out-of-distribution pseudo-inputs training. 10.48550\/arXiv.2201.05890."},{"key":"10.1016\/j.neunet.2026.109699_bib0134","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks","author":"Seitzer","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0135","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"3183","article-title":"Evidential deep learning to quantify classification uncertainty","author":"Sensoy","year":"2018"},{"key":"10.1016\/j.neunet.2026.109699_bib0136","series-title":"International conference on artificial intelligence and statistics (AISTATS)","first-page":"1","article-title":"Do Bayesian neural networks need to be fully stochastic?","volume":"vol. 206","author":"Sharma","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0137","series-title":"Conference on artificial intelligence","first-page":"9772","article-title":"Post-hoc uncertainty learning using a Dirichlet meta-model","volume":"vol. 37","author":"Shen","year":"2023"},{"issue":"63","key":"10.1016\/j.neunet.2026.109699_bib0138","first-page":"1","article-title":"A survey on uncertainty quantification of large language models: Taxonomy, open research challenges, and future directions","volume":"58","author":"Shorinwa","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109699_bib0139","unstructured":"Smith, L., & Gal, Y. (2018). Understanding measures of uncertainty for adversarial example detection. 10.48550\/arXiv.1803.08533."},{"key":"10.1016\/j.neunet.2026.109699_bib0140","unstructured":"Sommer, E., Diao, K., Robnik, J., Seljak, U., & R\u00fcgamer, D. (2026). Can microcanonical Langevin dynamics leverage mini-batch gradient noise?10.48550\/arXiv.2602.06500."},{"key":"10.1016\/j.neunet.2026.109699_bib0141","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Microcanonical Langevin ensembles: Advancing the sampling of Bayesian neural networks","author":"Sommer","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0142","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Position: The time for sampling is now! charting a new course for Bayesian deep learning","author":"Sommer","year":"2026"},{"key":"10.1016\/j.neunet.2026.109699_bib0143","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Connecting the dots: Is mode-connectedness the key to feasible sample-based inference in Bayesian neural networks?","volume":"vol. 235","author":"Sommer","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2026.109699_bib0144","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0145","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Function space diversity for uncertainty prediction via repulsive last-layer ensembles","author":"Steger","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0146","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Single-model uncertainties for deep learning","author":"Tagasovska","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0147","series-title":"International joint conferences on artificial intelligence (IJCAI)","first-page":"132","article-title":"The impact of averaging logits over probabilities on ensembles of neural networks","author":"Tassi","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0148","series-title":"Conference on empirical methods in natural language processing (EMNLP)","first-page":"5433","article-title":"Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback","author":"Tian","year":"2023"},{"issue":"11","key":"10.1016\/j.neunet.2026.109699_bib0149","doi-asserted-by":"crossref","first-page":"2719","DOI":"10.1162\/089976600300014908","article-title":"A Bayesian committee machine","volume":"12","author":"Tresp","year":"2000","journal-title":"Neural Computation"},{"issue":"94","key":"10.1016\/j.neunet.2026.109699_bib0150","first-page":"1","article-title":"A review of predictive uncertainty estimation with machine learning","volume":"57","author":"Tyralis","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.neunet.2026.109699_bib0151","series-title":"International conference on neural networks (ICNN)","first-page":"90","article-title":"Generalization error of ensemble estimators","volume":"vol. 1","author":"Ueda","year":"1996"},{"key":"10.1016\/j.neunet.2026.109699_bib0152","series-title":"Findings of the association for computational linguistics","first-page":"1909","article-title":"Non-exchangeable conformal language generation with nearest neighbors","author":"Ulmer","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0153","series-title":"International conference on artificial intelligence and statistics (AISTATS)","first-page":"3459","article-title":"Evaluating model calibration in classification","author":"Vaicenavicius","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0154","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Deep sub-ensembles for fast uncertainty estimation in image classification","author":"Valdenegro-Toro","year":"2019"},{"key":"10.1016\/j.neunet.2026.109699_bib0155","series-title":"International conference on computer vision workshops (ICCVW)","first-page":"4119","article-title":"Sub-ensembles for fast uncertainty estimation in neural networks","author":"Valdenegro-Toro","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0156","first-page":"1","article-title":"A review of Bayesian uncertainty quantification in deep a review of Bayesian uncertainty quantification in deep probabilistic image segmentation","author":"Valiuddin","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0157","first-page":"1","article-title":"Hybridflow: Quantification of aleatoric and epistemic uncertainty with a single hybrid model","author":"Van Katwyk","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109699_bib0158","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-3472-7","article-title":"Statistical Reasoning with Imprecise Probabilities","author":"Walley","year":"1991"},{"key":"10.1016\/j.neunet.2026.109699_bib0159","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Rethinking calibration of deep neural networks: Do not be afraid of overconfidence","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0160","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Credal deep ensembles for uncertainty quantification","volume":"vol. 37","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0161","series-title":"Symposium on advances in approximate bayesian inference","first-page":"1","article-title":"Bayesian OOD detection with aleatoric uncertainty and outlier exposure","author":"Wang","year":"2021"},{"issue":"10","key":"10.1016\/j.neunet.2026.109699_bib0162","doi-asserted-by":"crossref","first-page":"8923","DOI":"10.1109\/TPAMI.2025.3582518","article-title":"Evidence-based multi-feature fusion for adversarial robustness","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109699_bib0163","series-title":"International conference on machine learning (ICML)","first-page":"1","article-title":"Mitigating neural network overconfidence with logit normalization","author":"Wei","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0164","series-title":"International conference on machine learning (ICML)","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","author":"Welling","year":"2011"},{"key":"10.1016\/j.neunet.2026.109699_bib0165","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Combining ensembles and data augmentation can harm your calibration","author":"Wen","year":"2021"},{"key":"10.1016\/j.neunet.2026.109699_bib0166","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","author":"Wen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0167","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"A rigorous link between deep ensembles and (variational) Bayesian methods","author":"Wild","year":"2023"},{"key":"10.1016\/j.neunet.2026.109699_bib0168","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"4697","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","author":"Wilson","year":"2020"},{"key":"10.1016\/j.neunet.2026.109699_bib0169","series-title":"Conference on uncertainty in artificial intelligence (UAI)","first-page":"2282","article-title":"Quantifying aleatoric and epistemic uncertainty in machine learning: Are conditional entropy and mutual information appropriate measures?","author":"Wimmer","year":"2023"},{"issue":"359","key":"10.1016\/j.neunet.2026.109699_bib0170","first-page":"1","article-title":"A unified theory of diversity in ensemble learning","volume":"24","author":"Wood","year":"2023","journal-title":"Journal of Machine Learning Research"},{"issue":"9","key":"10.1016\/j.neunet.2026.109699_bib0171","first-page":"4605","article-title":"Advanced dropout: A model-free methodology for Bayesian dropout optimization","volume":"44","author":"Xie","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109699_bib0172","series-title":"International conference on learning representations (ICLR)","first-page":"1","article-title":"Can LLMs express their uncertainty? an empirical evaluation of confidence elicitation in LLMs","author":"Xiong","year":"2024"},{"key":"10.1016\/j.neunet.2026.109699_bib0173","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"OpenOOD: Benchmarking generalized out-of-distribution detection","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109699_bib0174","series-title":"Conference on neural information processing systems (neurIPS)","first-page":"1","article-title":"Uncertainty estimation by flexible evidential deep learning","author":"Yoon","year":"2025"},{"key":"10.1016\/j.neunet.2026.109699_bib0175","series-title":"Conference on knowledge discovery and data mining (KDD)","first-page":"694","article-title":"Transforming classifier scores into accurate multiclass probability estimates","author":"Zadrozny","year":"2002"},{"key":"10.1016\/j.neunet.2026.109699_bib0176","series-title":"Conference on neural information processing systems (eurIPS)","first-page":"1","article-title":"Is BatchEnsemble a single model? on calibration and diversity of efficient ensembles","author":"Zamyatin","year":"2026"},{"key":"10.1016\/j.neunet.2026.109699_bib0177","doi-asserted-by":"crossref","first-page":"5984","DOI":"10.1109\/TIP.2021.3089942","article-title":"Delving deep into label smoothing","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109699_bib0178","first-page":"1","article-title":"Basic framework and main methods of uncertainty quantification","volume":"2020","author":"Zhang","year":"2020","journal-title":"Mathematical Problems in Engineering"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011548?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011548?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:40:59Z","timestamp":1793605259000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":178,"alternative-id":["S0893608026011548"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109699","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Uncertainty quantification for trustworthy deep learning: Methods and measures","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109699","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109699"}}