Uncertainty Quantification

Also known as UQ

Follow this topic Ask about this topic

Momentum

44 papers in the last four weeks, up 110% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 431

All topics

Proper Scoring Rules for Agentic Uncertainty Quantification
May 23, 2026Suresh Raghu, Satwik Pandey, Shashwat PandeyUncertainty Quantification Agent Evaluation
Independent Researcher
Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference Components
May 23, 2026Ling Zhan, Xiaoyao Yu, Tao JiaAI for Science Uncertainty Quantification
College of Computer and Information Science, Southwest University, Chongqing, China · Chongqing Key Laboratory of Brain-Inspired Cognitive Computing and Educational Rehabilitation for Children with Special Needs, Chongqing Normal University, Chongqing, China · College of Computer and Information Science, Chongqing Normal University, Chongqing, China
Robust Fuzzy Multi-view Learning under View Conflict
May 23, 2026Siyuan Duan, Yuan Sun, Dezhong Peng +3Uncertainty Quantification Multi-View Learning
College of Computer Science, Sichuan University, Chengdu 610065, China · College of Computer Science, Sichuan University, Chengdu 610065, China, and also with the Tianfu Jincheng Laboratory, Chengdu 611130, China · Department of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UK +1
Neural Bayesian Sequential Routing
May 22, 2026Yongchao HuangUncertainty Quantification Adaptive Model Routing
Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference
May 22, 2026Tewodros Syum Gebre, Jagrati Talreja, Matilda Anokye +1Remote Sensing Image Segmentation Uncertainty Quantification
Built Environment Department, College of Science and Technology, North Carolina A&T State University, Greensboro, NC 27405 USA · United Nations University Institute for Water, Environment and Health, Richmond Hill, ON, Canada
Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks
May 22, 2026Rouaa Hoblos, Noura Dridi, Noureddine Zerhouni +1Evidential Deep Learning Uncertainty Quantification
FEMTO-ST · Universit´e Marie et Louis Pasteur, SUPMICROTECH, CNRS, Institut FEMTO-ST, F-25000 Besan¸con, France
UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians
May 21, 2026Soumya Sudhakar, Sertac Karaman, Vivienne SzeUncertainty Quantification Depth Estimation
Massachusetts Institute of Technology, Cambridge, MA 02139, USA
Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics
May 21, 2026Mitchel J. ColebankBayesian Neural Networks Uncertainty Quantification
Department of Mathematics, University of South Carolina,, Columbia, 29208, South Carolina, USA
Ternary Decision Trees with Locally-Adaptive Uncertainty Zones
May 21, 2026William SmitsUncertainty Quantification Selective Prediction
Avathon, Austin, TX, USA
A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
May 21, 2026Yinsong Chen, Samson S. Yu, Kashem M. MuttaqiUncertainty Quantification Time Series Forecasting
School of Engineering, Deakin University, Melbourne, VIC 3216, Australia · ARC Training Centre in Energy Technologies for Future Grids, School of Engineering, University of Wollongong, Wollongong, NSW 2522, Australia
Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations
May 21, 2026Birgit Kühbacher, Daan Crommelin, Niki KilbertusUncertainty Quantification Chaotic Dynamical Systems
Technical University of Munich, Munich, Germany · Helmholtz Munich, Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany +2
Towards a compositional semantics for quantitative confidence assessment in assurance arguments
May 21, 2026Benjamin Herd, Jessica Kelly, Jan Sabsch +1AI Assurance Uncertainty Quantification
Fraunhofer IKS · Munich, Germany · Luxoft GmbH +2
Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study
May 20, 2026Michael O. EnioladeUncertainty Quantification Conformal Prediction
University of the Cumberlands
A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
May 20, 2026Yinsong Chen, Samson S. Yu, Zhong Li +1Bayesian Neural Networks Feature Attribution
School of Engineering, Deakin University, Melbourne, 3216, VIC, Australia · Faculty of Mathematics and Computer Science, FernUniversität in Hagen, 58084, Germany · Department of Computing Technologies, Swinburne University of Technology, Hawthorn, 3122, VIC, Australia
ECUAS $_n$ : A family of metrics for principled evaluation of uncertainty-augmented systems
May 19, 2026Lautaro Estienne, Erik Ernst, Matías Vera +2Uncertainty Quantification Proper Scoring Rules
School of Engineering, UBA, Argentina · ICC, CONICET-Universidad de Buenos Aires, Argentina · LISN, CNRS, Université Paris-Saclay, France +4
Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation
May 19, 2026Yuxuan Gao, Megan Wang, Yi Ling YuUncertainty Quantification AI Agent Evaluation
OpenMesh · University of Pennsylvania · Columbia Univer
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
May 19, 2026Xiaoou Liu, Tiejin Chen, Dengjia Zhang +3Uncertainty Quantification Confidence Estimation in Language Models
1Arizona State University · 2Johns Hopkins University · 3Purdue +1
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
May 19, 2026Tiejin Chen, Longchao Da, Xiaoou Liu +1LLM Evaluation Uncertainty Quantification
School of Computing and Augmented Intelligence, Arizona State University
Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection
May 18, 2026Elynn Chen, Jiayu Li, Zheshi Zheng +1Tensor Networks Uncertainty Quantification
New York University · University of Michigan · Duke University
The impact of observation density on Bayesian inversion of latent dynamics in shock-dominated flows
May 18, 2026Bipin Tiwari, Muhammad Abid, Omer SanNeural Surrogate Modeling Uncertainty Quantification
Department of Mechanical and Aerospace Engineering, University of Tennessee, Knoxville Knoxville, TN 37996, USA.
Flowing with Confidence
May 18, 2026Friso de Kruiff, Dario Coscia, Max Welling +1Flow Matching Uncertainty Quantification
CuspAI · AMLab, University of Amsterdam · mathLab, SISSA
Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?
May 18, 2026Johannes A. Gaus, Jhon P. F. Charaja, Daniel HaeufleUncertainty Quantification Selective Prediction
Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience, University of Tübingen, Germany
Uncertainty-Calibrated Recommendations for Low-Active Users
May 18, 2026Bob Junyi Zou, Sai Li, Tianyun Sun +2Uncertainty Quantification Exploration-Exploitation Tradeoff
Stanford University · Stanford, CA, USA · ByteDance Inc. +2
UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
May 18, 2026Tianhao Han, Haoyang Zhang, Liang Xie +5Uncertainty Quantification Self-Supervised Learning
School of Computer Science, Shanghai Jiao Tong University · Defense Innovation Institute, Academy of Military Sciences · Tianjin Artificial Intelligence Innovation Center +3
MUSE: Multimodal Uncertainty Quantification of State Estimation
May 17, 2026Minkyung Kim, Henry Che, Bhargav Chandaka +6Uncertainty Quantification Visual-Inertial Odometry
Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, Champaign, IL 61801, USA · Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Champaign, IL 61801, USA · Department of Electrical Engineering, University of South Carolina, Columbia, SC 29208, USA
Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations
May 16, 2026Phuoc-Toan Huynh, Richard Archibald, Feng BaoUncertainty Quantification Deep Operator Networks
Department of Mathematics, Florida State University, Tallahassee, FL, USA · Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA
Scalable Uncertainty Reasoning in Knowledge Graphs
May 15, 2026Jingcheng WuProbabilistic Circuits Uncertainty Quantification
University of Stuttgart, Stuttgart, Germany
A numerical study into neural network surrogate model performance for uncertainty propagation
May 15, 2026Noah Wade, Kirubel TeferraNeural Surrogate Modeling Uncertainty Quantification
ASEE Postdoctoral Associate, U.S. Naval Research Laboratory, Washington, DC, 20375, USA · U.S. Naval Research Laboratory, Washington, 20375, DC, USA
Uncertainty-Aware Wildfire Smoke Density Classification from Satellite Imagery via CBAM-Augmented EfficientNet with Evidential Deep Learning
May 15, 2026Ranjith ChodavarapuRemote Sensing Image Understanding Evidential Deep Learning
Kent State University
Martingale Neural Operators: Learning Stochastic Marginals via Doob-Meyer Factorization
May 15, 2026Kai HidajatUncertainty Quantification Neural Operators
Department of Applied Mathematics University of Washington Seattle, WA, USA

May 23, 2026, cs.AIJ/K move · Enter open · S save

Proper Scoring Rules for Agentic Uncertainty Quantification

Suresh Raghu, Satwik Pandey, Shashwat Pandey

Independent Researcher

Uncertainty Quantification Agent Evaluation Proper Scoring Rules Uncertainty Calibration

Open paper AskPDF arXiv

Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and scalarized trajectory scores evaluate discrimination, binwise calibration, or collapsed summaries, but do not strictly elicit the full prefix-conditioned success-probability trace

q_t = P^π(Y=1 | H_t)

. Building on prequential proper scoring, we introduce the Trajectory Proper Score (TPS), a predictor-agnostic family of strictly proper trajectory-level scoring rules for any per-step uncertainty signal calibrated into a probability of eventual success. We prove that TPS strictly elicits the success-probability process under complete observation, within the chosen score family and weight schedule. We extend the construction to administratively censored trajectories by projecting the complete-data score onto the observable stopped prefix, yielding an exact

q_Z

-weighted reduced score and a tractable approximation when

q_Z

is unestimated. We further show that common trajectory evaluators target weaker objects than the full prefix-conditioned probability process: Trajectory ECE is resolution-blind, while scalarized Trajectory Brier elicits only the collapsed scalar, not the full trace. Experiments on StrategyQA, Tau2-Bench, HotpotQA, and WebShop show that these theoretical distinctions are operationally visible: probability recalibration can substantially change TPS while leaving rank metrics nearly unchanged, and the tractable censored approximation can change the verdict relative to complete-only evaluation.

Momentum

Related topics

Latest papers 431