Clay weekly context brief for the Statistics category (ISO week 2026-W42).

Clay tracks publications from the Statistics feed list. Below are recent items from this category, each with its source and a short description of what the publication covers when one is available in the source feed.

Recent publications:
1. Tree statistics improve neural simulation-based inference of epidemiological parameters over case counts alone
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.10895
   During an infectious disease outbreak, accurate estimates of epidemiological parameters such as the reproduction number and infection duration can inform the public health response.
2. postshock: An R Package for Donor-Adjusted Forecasting After Structural Shocks
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2610.11841
   We present the postshock R package, which implements and extends a donor-based framework for forecasting when a structural shock is known and the target response of interest is not yet observed.
3. Treatment Effect Modification by Latent Classes
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.10851
   Many treatments have effects that plausibly vary by latent classes.
4. Consistent intercept estimation and inference for unit-root INAR(2) processes
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2609.23339
   \citet{barczy2014asymptotic} showed that the ordinary least-squares (OLS) estimator of the innovation mean is inconsistent for a unit-root INAR(2) process.
5. Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.06297
   Recovering the forward operator of an imaging system from unpaired data avoids both calibration hardware and the clean/degraded pairs that supervision requires-pairs that, for a real lens, are often impossible to acquire.
6. BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.11116
   AI evaluation pipelines often produce conflicting judgments rather than clean labels.
7. Bayesian Estimation of Continuous Brain Connectivity with Log-Gaussian Cox Processes
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2610.11250
   Continuous structural connectivity describes the connection between any two points of the cortical surface by an intensity function.
8. Hypothesis Testing for Nonlinear and Interactive Effects Using Additive Gaussian Processes
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.10907
   Real-world data often exhibit nonlinear, interactive associations between predictors and an outcome.
9. Lambda-quantiles under the microscope
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2608.07122
   We study Lambda-quantiles, a generalisation of classical quantiles in which the constant probability level $\lambda \in [0,1]$ is replaced by a functional parameter $\Lambda \colon \mathbb{R} \to [0,1]$.
10. Finite-Sample Distribution Theory and Efficient Large-Scale Inference for Online Quantile Regression
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.05869
   This paper studies online quantile regression for large-scale and streaming data using Stochastic SubGradient Descent (SSGD) with constant learning rates.
11. Event-Aware Spatiotemporal Precipitation Forecasting with Geographic Context and Physics-Guided Regularization
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.11211
   Hourly precipitation forecasting involves several distinct statistical challenges, including spatially varying predictor-precipitation relationships, a strongly imbalanced precipitation distribution, and progressive degradation of precipitation event skill with increasing lead time.
12. Regularized Small Area Estimation with Graph Laplacian Benchmarking priors
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2610.11266
   Small area estimation (SAE) often requires both borrowing information across areas and benchmarking estimates to reliable aggregates.
13. Bayesian inference under model misspecification
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.11173
   The likelihood input to a Bayesian analysis almost never exactly represents how the data were generated, calling into question the validity of posterior inferences.
14. Estimation of the sub-Gaussian Parameter
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2606.06384
   The sub-Gaussian parameter (also called the variance proxy) of a mean-zero random variable $X$ is defined as $\xi^2_\star = \sup_{\lambda \in \mathbb{R}} L(\lambda)$ where $L(\lambda) = \frac{2}{\lambda^2} \log \mathbb{E} e^{\lambda X}$ is a weighted cumulant generating function.
15. On the Sequentially Semiseparable Structure of SDE-Induced Kernels and Efficient Algorithms for Kernel-Based Estimation Problems
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.05856
   We study kernel functions induced by a linear time-invariant (LTI) stochastic differential equation (SDE), an approach that embeds prior knowledge about the function to be estimated directly into the state-space description of the SDE.
16. How Much Does Submitting a Burst of Jobs Impact Waiting Time? An Analysis of the Jean Zay Workload Trace
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.11703
   This paper examines job waiting times on the Jean Zay supercomputer at IDRIS (Institut du D{\'e}veloppement et des Ressources en Informatique Scientifique http://www.idris.fr/), driven by the need to improve scheduling strategies for crossfacility scientific workflows.
17. Bayesian Soft-Tree Poisson Process Model for Covariate-Dependent Point Patterns
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2610.11343
   Estimating covariate-dependent intensity functions from spatial point pattern is challenging when the integrated intensity function cannot be evaluated analytically.
18. Improved E-Value Thresholds with Applications to Multiple and Sequential Testing
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.11186
   E-values provide a flexible framework for statistical inference, but the universal threshold $1/\alpha$ can be conservative when the null distribution has additional structure.
19. Handling Covariate Mismatch in Collaborative Linear Prediction
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2602.02083
   Training predictive models across multiple centers typically assumes that all centers collect the same set of covariates.
20. Isotropic Gaussian Processes Improve Vanilla Bayesian Optimization in High Dimensions
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.05780
   High-dimensional Bayesian optimization (BO) often fits Gaussian process (GP) surrogates from far fewer observations than input dimensions.
21. Regime-Aware Estimation of Large Equity Correlation Matrices: Tail-Pairwise Dependence and Dynamic Conditional Correlation Decomposition for Water and Energy
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.12166
   Equity correlation matrices are foundational to quantitative risk, yet the operational default of a single Gaussian-copula structure fit to the full sample has a structural defect: it forces asymptotic tail-independence and so cannot represent the joint moves that drive risk in stress episodes.
22. NExt-LMM: a two-stage LMM framework with near-exact variance components for genome-wide association studies
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2508.05278
   Linear mixed models (LMMs) are widely used in genome-wide association studies (GWAS) to account for population stratification and cryptic relatedness.
23. A Semiparametric Functional Generalized Linear Model for Multi-Population Data
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.11208
   Functional generalized linear models provide a flexible framework for relating a scalar response to functional and scalar predictors, but their conventional formulation requires specification of the response distribution and is typically developed for a single population.
24. Efficient quadratic entropy with distance sketches
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2610.11976
   We detail scalable methods for approximating the quadratic entropy $p^T d p$ for arbitrary distributions $p$ and common distances $d$ of negative type.
25. Retrieval-Based In-Context Learning: A Domain Adaptation Framework
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.05717
   In-context retrieval (ICR) is a retrieval-based form of in-context learning (ICL) in which demonstrations are retrieved from a source database based on similarity to the query, rather than sampled independently.
26. Mixup Barcodes for Topology-Aware Financial Decision Making
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.12396
   We present a topology-aware system based on mixup barcodes and persistent homology for financial decision making.
27. On the Convergence of Wasserstein Gradient Descent for Sampling
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2602.03413
   This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD).
28. High-Dimensional Two-Sample Covariance Testing with Null-Preserving Transformations
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2610.11249
   Testing equality of two high-dimensional covariance matrices is challenging when many entries differ only slightly.
29. Dense uniqueness and dense nonuniqueness of Fr\'echet means
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2610.11946
   From previous results it follows that probability distributions on metric spaces featuring unique Fr\'echet means are dense among measures admitting means in both the quadratic Wasserstein metric and the total variation metric.
30. Two-Sample Testing via Path-based Inference
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2610.05684
   Modern deep generative models are primarily studied for their ability to generate realistic samples, yet the generative dynamics they learn can also serve as objects of statistical inference.
31. TypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2610.11392
   System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface.
32. Robust Bayesian methods using amortized simulation-based inference
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2504.09475
   Bayesian simulation-based inference (SBI) methods are used in statistical models where simulation is feasible but the likelihood is intractable.

Sources in this brief: stat.AP (Applications); stat.CO (Computation); stat.ME (Methodology); stat.ML (Machine Learning); stat.TH (Statistics Theory).
Selected 32 of 438 available items for this weekly brief.