The urban heat island (UHI) effect amplifies heat stress in cities, increasing heat-related illness, mortality, sleep disruption, and energy demand. Because UHI intensity varies at neighborhood scales, intra-city temperature mapping is essential for assessing public health impacts, yet existing monitoring networks are sparse. Crowdsourced weather stations provide dense, hourly observations but suffer from noise and systematic biases, including preferential sampling driven by where residents install sensors. We introduce two scalable Gaussian process frameworks which adjust for preferential sampling and enable statewide, high-resolution temperature prediction. The first integrates sampling correction directly within a sparse variational Gaussian process (SVGPR+PS). The second uses a two-stage estimator involving a log-Gaussian Cox process (LGCP+GP) that estimates the sampling intensity field and incorporates it into temperature prediction. Both methods rely on inducing-point approximations and variational inference to scale beyond traditional Gaussian processes. Applied to approximately 10,000 citizen stations across North Carolina, the models generate hourly temperature fields within minutes. Validation against independent urban heat campaign data shows that the preferential sampling correction improves predictive performance, increasing average afternoon correlations across four cities from 0.26 to 0.43. This scalable framework enables neighborhood-level UHI assessment and supports studies of heat exposure disparities statewide.
Augmented inverse probability weighting (AIPW), targeted maximum likelihood estimation (TMLE), and double/debiased machine learning (DML) are three asymptotically equivalent routes to the same efficient influence function for the average treatment effect. We contribute a worked, shared-nuisance reconciliation on real data: what a practitioner must hold fixed for the routes and their software to agree, and when they do not. Using open data on smoking cessation and weight change (n = 1566), one Super Learner library, and folds matched within schemes, we build all three by hand, in full-sample, cross-fit, and double-cross-fit variants. A semi-synthetic benchmark with known sample-average effects on a fixed design grades interval coverage. The six doubly robust estimates span 3.32--3.39 kg over repeated splits. Single runs of our code and the tmle, AIPW, DoubleML, and tmle3 packages span 3.32--3.49 kg, compatible with fitting-scheme differences and single-split noise. Over 20 seeds, the three implementations sharing our library agree within 0.01 kg in median, although one is a TMLE. Agreement can fail: with in-sample nuisance fits on a binary mortality outcome, and under poor overlap in a job-training example. We recommend diagnosing overlap before choosing an estimator, and provide a reporting checklist and software code.
Multimodal fusion is studied under hybrid federation, where data are partitioned across samples and feature blocks. The proposed two-dimensional federated smooth multiple-kernel large-margin learning method (2D-FedSMKL) integrates availability-corrected modality scores, group-kernel regularization, and smooth worst-site risk aggregation. For fixed maps and propensities, the objective is convex and smooth. Curvature bounds and exact synchronous block-gradient equivalence are established for binary and multiclass scores, giving a conditional accelerated rate. An oracle-propensity binary risk bound and a propensity-perturbation result are also derived. Simulations and two public activity-recognition benchmarks assess site heterogeneity and modality absence. Worst-site aggregation improves worst-site performance under heterogeneity, including reversed and size-balanced designs. On the benchmarks, validation selects the correction; the selected model is not significantly worse than the strongest reference at the worst site, and group-regularization benefits vary by dataset.
Cross-country sentiment analysis faces three fundamental challenges: language-specific biases distort comparisons, compositional data constraints invalidate standard statistics and temporal dynamics lack rigorous testing frameworks. We introduce sentiment sensing, a framework that addresses these gaps through integrated statistical methods. By combining compositional data analysis, functional data methods, and non-parametric inference, sentiment sensing enables valid multilingual comparisons and statistically defensible detection of sentiment shifts. Our framework has been tested in two case studies, analyzing news articles from the 27 countries of the European Union on the topics of energy and artificial intelligence. Sentiment sensing focuses on multilingual sentiment analysis enabling rigorous comparative science.
Background. Many medical AI models are trained to reproduce a single reference label and hand the most likely label to the next step in a clinical workflow. A classifier can select that label correctly while providing an inadequate summary for estimating downstream risk. Methods. We use Jeffrey's rule of conditioning to specify when probabilities over intermediate states, such as diagnoses or imaging categories, can be carried forward to an outcome risk. We separate two errors of reporting only the most likely label, discarding the probability of the other states and applying the risk of patients who have the leading diagnosis to a patient who only probably has it. We also give conditions under which the label and the full distribution lead to the same decision, and we propose guardrails for device developers, regulatory reviewers, and health insurers. Results. In a hypothetical chest-pain differential, reporting only the benign leading diagnosis greatly understates the patient's risk of death or cardiac arrest, so a patient who warrants evaluation could be discharged or denied imaging. In a hypothetical BI-RADS example, the most likely category is "probably benign," yet the propagated malignancy risk exceeds the ceiling that defines that category. Conclusions. A predicted label is not an observed state, and a calibrated classifier is not automatically a valid outcome model. Clinical and insurance coverage decisions should rest on the patient's outcome risk, judged against a threshold justified by the consequences of acting and not acting. Developers should state what each model output means and check that every step between the model and the decision preserves the patient's risk.
Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels. Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator. A Transformer encoder summarizes the dose tokens, trial-conditioned cross-attention produces a fixed-dimensional trial representation, and a three-action policy chooses de-escalation, staying, or escalation. The final maximum tolerated dose (MTD) decision is deliberately kept outside the learned policy: after the planned sample size, weighted isotonic regression and a prespecified safety cap select the dose closest to the target toxicity probability. In the simulations, toxicity-penalized policies reduce DLT burden while unpenalized policies improve selection accuracy at the cost of greater toxicity. These results demonstrate a controllable safety--accuracy trade-off but do not establish superiority over conventional dose-finding designs.
Digital health interventions can provide scalable, personalized support for physical activity (PA), yet sustaining PA over the long-term remains difficult. Because affective experiences with PA are important for activity sustainment, we developed an online reinforcement learning (RL) system for the forthcoming ADAPT factorial trial that personalizes twice-daily activity suggestions aimed at improving affective associations with PA. This setting poses several challenges: participant-specific data are scarce relative to the candidate state space, important states and rewards are partially observed, interventions are frequent while the primary outcome is measured weekly, and activity suggestions can both improve PA-related experiences and increase intervention burden. We address these challenges using an expert-specified causal directed acyclic graph as an integrated RL design tool, guiding state construction, estimation of partially observed states, delayed credit assignment, and representation of beneficial and adverse intervention pathways. We further construct a longitudinal simulator calibrated from a prior micro-randomized trial to compare candidate RL designs under realistic state evolution, missingness, and participant heterogeneity before deployment. Together, this work illustrates how causal domain knowledge and prior trial data can make long-horizon, participant-specific RL more practical for digital health interventions targeting sustained behavior change.
Tree-boosting is a widely used machine learning technique for tabular data. However, its out-of-sample accuracy is critically dependent on multiple hyperparameters. In this article, we empirically compare several popular methods for hyperparameter optimization for tree-boosting including random grid search, the tree-structured Parzen estimator (TPE), Gaussian-process-based Bayesian optimization (GP-BO), Hyperband, the sequential model-based algorithm configuration (SMAC) method, and deterministic full grid search using $59$ regression and binary classification data sets. We find that the SMAC method clearly outperforms all the other considered methods on average, and it gives stable performance across a diverse collection of tabular data sets under a fixed tuning budget, which is relevant for users who cannot afford extensive manual trial-and-error tuning. We further observe that (i) a relatively large number of trials larger than $100$ is typically required for accurate tuning, (ii) using default values for hyperparameters or a full search over a small grid often yields very inaccurate models, (iii) all considered hyperparameters can have a material effect on the accuracy of tree-boosting, i.e., there is no small set of hyperparameters that is more important than others, and (iv) choosing the number of boosting iterations using early stopping yields more accurate results compared to including it in the search space for regression tasks.
Pathophysiological modelling of brain systems from microscale to macroscale remains difficult in group comparisons partly because of the infeasibility of modelling the interactions of thousands of neurons at the scales involved. Here, to address the challenge, we present a novel approach to construct differential causal networks directly from grouped electroencephalogram (EEG) data. In the proposed modular network, each node represents a locally averaged regional neural system via a canonical Jansen-Rit model while directed edges stand for node-wise input-output connections. The network is hierarchically structured in the sense that node and edge parameters are random, varying in subjects, but follow a mixed-effects model. We show that unlike the classical Jansen-Rit models, the proposed node models are locally structurally identifiable. An evolutionary optimisation algorithm for parameter inference in the proposed method is developed using a loss function derived from Chen-Fliess expansions of stochastic differential equations. The method is demonstrated by fitting the proposed modular network to grouped epileptic EEG data in both sensor- and source- levels. We identify significant changes in the parameters that characterise dynamic networks within and between brain regions. We reveal network disruptions, due to imbalance of excitatory-inhibitory interneurons and other altered epileptic brain connectivities, before and during seizure periods, and contrast them between case and control groups. The performance of the proposed method is also evaluated on synthetic data.
In recent years, air pollution, especially the particulate matter $2.5\,\mu\text{m}$ (PM2.5), has become a growing concern mainly in urban areas. Exposure to air pollution is linked to the development of numerous health conditions, such as the aggravation of respiratory diseases, cardiovascular disorders, impaired lung function, and even cancer or early death. Forecasting future levels of PM2.5 has become increasingly important, as it can provide early warnings and help prevent diseases. We propose AQBuc, a dataset for predicting PM2.5 pollution in Bucharest, Romania, introducing an understudied location, as most work in this field has focused on Asian cities. Our dataset allows us to benchmark models for predicting future levels of PM2.5 across various time horizons. We evaluate a broad range of methods, including machine learning models, such as linear regression and ensemble-based methods, deep learning models based on recurrent networks and transformers, and large language models (LLMs). Specialized time-series models handle temporal data better, especially on longer horizons, while tree ensembles are more cost-effective for short horizons. Meanwhile, LLMs struggle to capture continuous sensor dynamics without specialized architectural changes.
This textbook gives a systematic treatment of statistical machine learning for astronomical research, based on Bayesian inference. It shows how modern data analysis techniques connect to classical statistical methods and follow from familiar statistical principles. The Bayesian perspective, used throughout, gives priority to uncertainty quantification and statistical rigor, which scientific inference in astronomy needs. The textbook progresses from probability theory and Bayesian inference through supervised learning, including linear regression with measurement uncertainties, logistic regression and classification. Unsupervised learning topics cover Principal Component Analysis and clustering methods. We then introduce sampling and Markov Chain Monte Carlo, followed by Gaussian Processes as probabilistic nonparametric methods and neural networks in the broader statistical context. Our theory-focused approach derives each method from first principles with complete mathematical development and then shows its astronomical applications. We put statistical insight first and explain why algorithms work, when they are appropriate, and how they connect to broader statistical principles. From a solid grounding in classical methods and their theory, the treatment leads to modern techniques such as neural networks. With this grounding, readers can apply the methods to astronomical research with proper attention to assumptions, limits and uncertainty propagation, as large astronomical surveys require. The 22 companion tutorials apply the methods to astronomical data in Jupyter notebooks.
New federal legislation will require states with high payment error rates in the Supplemental Nutrition Assistance Program (SNAP) to pay a share of benefit costs, potentially costing some states over a billion dollars per year. These costs create substantial pressure to improve payment accuracy. One strategy to improve payment accuracy is preauthorization review, in which staff double-check applications and correct mistakes before benefits are issued. But limited staff capacity makes it important to target these reviews effectively. One leading targeting approach uses statistical risk models to prioritize cases likely to contain errors. Another novel approach uses AI to flag specific potential discrepancies for reviewers to check. For states under pressure to reduce error rates, it is unclear which approach-or combination of approaches-would reduce payment error rates most effectively. We compare these strategies through simulations using public SNAP quality control data. Under our main assumptions, risk-based review alone costs about seven times as much as combining AI flags with risk scores. This cost advantage persists across a wide range of plausible assumptions. Our findings suggest that AI-assisted preauthorization review could be a key tool to help states avoid substantial cost-sharing obligations.
Interval predictions from conformal prediction are usually read as "90% coverage", but on nested battery data that number promises the fleet average, not the individual cell. We measure the gap on 124 public LFP cells under a preregistered three-tier reporting protocol (fleet, batch, cell): pooled coverage looks healthy (0.875-0.906 across splits) while the worst cell is covered 0.1-2% of the time, with exact binomial tests against the nominal level. We then repair part of the gap with a hierarchically weighted conformal engine whose weights consume only side information frozen at prediction time - signature features, batch labels, cycle indices - and never touch residuals. The preregistered repair criterion passes: 10th-percentile cell coverage moves 0.750 to 0.830 (53% of the gap), the worst cell 0.642 to 0.694, with zero deferrals and a flat sensitivity spectrum. What the engine does not repair is localized rather than left open: under protocol drift the frozen weights harm monotonically on the SOH scale (the absolute scale is reported in full), a structural dead end we report instead of tuning away; and repair capacity is bounded by calibration-pool battery diversity, measured on both datasets. On a cross-chemistry external set the calibrated intervals collapse (0.286), while the within-domain skeleton replicates (pooled 0.933, worst cell 0.686). The deliverable is a reporting protocol - three tiers of promise anchored to measured regimes, worst-cell statistics, deferral share - that makes per-cell interval claims auditable before deployment.
In the search for new particles in high-energy physics, it is necessary to first define the signal region (SR) enriched in signal events, and then compare events in this region with the expected background distribution. While most existing search methods rely on prior domain knowledge of either the signal or the background, there has been less effort to relax both assumptions simultaneously, as methods that weaken one assumption typically rely on strong knowledge of the other. We propose Model-Agnostic Search with Smearing and Imperfect Background (MASSIB), a method that addresses this challenge by learning the density ratio of events relative to a misspecified background distribution using modern tools from machine learning, and defining the SR as the region with high density ratio. Recognizing that a naive application of this idea introduces significant bias in background estimation when interpolating from the control region to the SR, MASSIB mitigates this issue by introducing a "smeared" density ratio, which can be learned efficiently through data-level manipulation and used to define an SR that allows for accurate background estimation. By applying it to various types of simulated Large Hadron Collider (LHC) events with realistic background mismodeling, we demonstrate that MASSIB identifies a data-driven SR that achieves high signal concentration consistently across different types of signals while avoiding bias in background estimation. The method does this without making strong assumptions about either the signal or background distribution. We then show that this robustness extends to the validity and strong statistical power of the resulting hypothesis tests for signal detection, demonstrating the potential of this approach for future model-agnostic searches at the LHC.
Industrial systems continuously generate time series that vary in sampling frequency, scale, dynamics, and operating regime. Consequently a single time-series foundation model may not be able to represent all regimes effectively and retraining a large model for every new dataset or regime shift is computationally expensive. Modular foundation models address this issue by reusing specialised encoders trained on diverse datasets and by allowing the expansion of capabilities through the addition of new experts. This approach requires compact experts to minimize storage cost and a proper selection mechanism of experts for unseen data. We propose a modular foundation model framework that combines end-to-end Bayesian encoder training with uncertainty based routing. Using Singular Bayesian Neural Networks (SBNNs), we build a collection of compact Bayesian encoders whose epistemic uncertainty guides label-free selection. At the selected ranks, our Bayesian collection uses 63.8\% less storage than its deterministic counterpart. We evaluate this framework on time-series data through distribution shift, encoder selection, and probabilistic forecasting. Across seven incoming datasets, uncertainty-based routing is competitive with distance-based routing in terms of forecast MSE, while reducing average ECE from 0.086 to 0.072 and average NLL from 0.907 to 0.836. It also increases PICP90 from 82.28\% to 89.03\%. In a separate model-family comparison, we evaluate the SBNN pipeline against full-rank Bayes by Backprop, deep ensembles, and MC Dropout. The SBNN pipeline achieves an average MSE of 0.390, comparable with 0.396 for deep ensembles, 0.389 for MC dropout, and 0.443 for the full-rank Bayesian model. It uses 63.9\% fewer parameters than MC dropout, 81.9\% fewer than the full-rank model, and 92.8\% fewer than the deep ensemble.
Real-world forecasting often requires integrating heterogeneous evidence whose predictive value varies across horizons, operating regimes, and domains. We introduce FACTS-MAS, a domain-agnostic multi-agent forecasting framework that decomposes evidence into specialized channels for temporal dynamics, exogenous context, seasonality, structural information, and discrete events. Each agent generates an independently testable forecast through a common interface, while leakage-safe historical validation measures its predictive skill relative to a naive reference. These skill estimates are used to weight and combine agent forecasts, so that uninformative evidence is either removed or downweighted rather than forced to participate. A calibration procedure selects domain-specific constant means based on historical validation folds. We evaluate FACTS-MAS on weekly for-sale housing inventory from Zillow and weekly unemployment insurance claims from FRED, for 15 U.S. metropolitan areas at 4-, 8-, and 13-week forecasting horizons. Our method outperforms both a naive last-value forecast method and the TimesFM foundation model. However, a factor-adjusted exponential smoothing model performs as well as the fused forecast. The evidence therefore supports FACTS-MAS as a systematic protocol for testing, calibrating, and recomposing evidence channels before assembling them into the strongest single model for a specific application domain. Code, data, and results are available at https://github.com/Madumita24/FACTS-MAS.
National aviation-investigation databases are deep but territorial; global compilations such as the Aviation Safety Network and the Bureau of Aircraft Accidents Archives are hand-curated, apply their own inclusion thresholds, and publish no per-record lineage. The FlightFinder Occurrence Corpus harmonizes 279,485 occurrences and 131,882 attached narratives from 128 source codes -- national accident-investigation authorities, occurrence-reporting systems and four global compilations. Records are mapped into one schema; each normalized record reduces to exactly one key from an ordered ladder -- event signature, registration and date, rounded position and date, or source and native identifier -- so a missing field never creates a link, and the key is the occurrence identifier. Records the ladder cannot reach are scored in a blocked pass into an explicit merge table and applied only within an automatically approved score band or after a person confirms them. Field conflicts follow a documented source ranking; one provenance row per contributing source -- its native identifier and URL -- is retained, with attribution and licence terms per source code. Linkage error is measured on five adjudicated samples totalling 200 pairs. A recorded uniform random draw of 60 from the 3,441 merges the automatic band applies as it ships found no error; the exact two-sided 95% Clopper-Pearson upper bound on its false-merge rate is 6.0%, or 205 pairs. The measured error covers the scored band only; the ladder's deterministic joins are not adjudicated. The corpus has no exposure denominators and inherits the under-reporting of its sources. It is offered as a base for cross-national safety statistics, source-disagreement studies and narrative text mining; a frozen, DOI-referenced snapshot accompanies the live API.
Most instruments for measuring political positions, such as manifesto coding, expert surveys and text-scaling models, were built and validated on Western party systems, and they break down worst where many consequential actors never publish a manifesto, never contest a competitive election, or commit one position to a charter and act on another in office. This paper proposes a method for such settings. I treat a large language model as a single fallible rater in a panel, the way an expert survey treats one expert, and describe the panel, its synthesis, an applicability rule that keeps a blank distinct from a zero, and a lens that separates what an actor declares from what it does. Three results follow. First, a built-in experiment isolates the rubric: with a definition-free round held fixed, written axis definitions move scores by a mean of 1.8 points on a 21-point scale and tighten agreement between raters (mean absolute gap 2.81 to 2.50; r 0.81 to 0.89). Second, across nine models from eight laboratories in two countries, Krippendorff's alpha is 0.86 on an interval and 0.87 on an ordinal metric, and it held as the panel grew from five raters to nine. This is reliability and says nothing yet about validity, since models trained on overlapping data can share a bias no statistic computed from the models can detect. Third, the panel's sharpest split, a bimodal divergence on an actor's stance toward the state's foundational order, comes from a referent problem: the models agree on the facts and differ on which order counts as the regime. A blind triple-coding traces about two-thirds of such disagreement to interpretation. The worked example is the Middle East and North Africa, and the rubric, prompt and data are released in full.
This study proposes a statistically grounded framework for real-time win probability evaluation and player assessment in score-based team sports, based on minute-by-minute cumulative box-score data. We introduce a continuous dominance indicator (T-score) that maps final scores to real values consistent with win/lose outcomes, and formulate it as a time-evolving stochastic representation (T-process) driven by standardized cumulative statistics. This structure captures temporal game dynamics and enables sequential, analytically tractable updates of in-game win probability. Through this stochastic formulation, competitive advantage is decomposed into interpretable statistical components. Furthermore, we define a latent contribution index, STATS X, which quantifies a player's involvement in favorable dominance intervals identified by the T-process. This allows us to separate a team's baseline strength from game-specific performance fluctuations and provides a coherent, structural evaluation framework for both teams and players. While we do not implement AI methods in this paper, our framework is positioned as a foundational step toward hybrid integration with AI. By providing a structured time-series representation of dominance with an explicit probabilistic interpretation, the framework enables flexible learning mechanisms and incorporation of high-dimensional data, while preserving statistical coherence and interpretability. This work provides a basis for advancing AI-driven sports analytics.
Artificial intelligence (AI) models can accelerate cell-type annotation in digital pathology, but safely scaling their use requires determining, with error control, which model-generated labels can be accepted without expert review. This is challenging in evolving workflows because cell morphology and type composition may change across tissue regions and slides, making one-time calibration unreliable. We propose Conformal Annotation with Randomized Expert review under Distribution shift (CARED), a distribution-free framework that leverages randomized expert audit to achieve long-run error control for AI-assisted annotation under distribution shift. For each incoming batch, CARED uniformly selects a subset of cases for expert review and uses the acquired labels to calibrate later decisions. Among unreviewed cases, CARED determines a subset of them to safely skip expert labeling, while suggesting candidate labels for the others for downstream resolution. We prove that this workflow provides long-run control of cumulative error over both the full stream and the cells outside of the audit sample, without stationarity or exchangeability assumptions. We further enhance the framework by introducing class-conditional guarantees to ensure error control within important but rare cell types, together with a utility module to target more automatic resolutions, smaller candidate sets, and greater biological coherence, without compromising validity. Experiments on pancreas, lung, and ovary annotation streams, together with a stream constructed from real expert annotations, show that CARED controls the cumulative errors while a substantial fraction of cells (up to 70%) bypass expert review.