SEARCH · Search arXiv

Results for “stat.ME”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

219 records · Page 2Linked to original sources

arXiv2026

Different representation learning objectives recover distinct latent structures from the same psychometric data

Psychometric questionnaires contain rich item-level information, yet it remains unclear whether different representation learning objectives recover the same latent organization. We investigated this question using 757 matched teacher-child pairs from the baseline assessment of the Cyprus ProW preschool trial. Behavioral structure was characterized from child SDQ, ASBI, and CBRS item responses using principal component analysis and clustering, yielding four behavioral phenotypes. A contrastive objective substantially improved teacher-child retrieval relative to PCA-based representations, increasing Top-1 accuracy from 0.13% to 7.27% and Top-10 accuracy from 1.98% to 56.14%. However, contrastive representations preserved behavioral phenotype structure less effectively than PCA-based representations. A multi-task objective jointly optimizing alignment and behavioral prediction partially restored behavioral organization but reduced retrieval performance. These findings indicate that teacher-child correspondence and behavioral phenotypes represent distinct forms of latent organization and demonstrate that the latent structure recovered from linked psychometric data depends on the representation learning objective.

cs.AI↗

arXiv2026

The Complexities of Differential Privacy for Survey Data

The concept of differential privacy (DP) has gained substantial attention in recent years, most notably since the U.S. Census Bureau announced the adoption of the concept for its 2020 Decennial Census. However, despite its attractive theoretical properties, implementing DP in practice remains challenging, especially when it comes to survey data. In this chapter we present some results from an ongoing project funded by the U.S. Census Bureau that is exploring the possibilities and limitations of DP for survey data. Specifically, we identify five aspects that need to be considered when adopting DP in the survey context: the multi-staged nature of data production; the limited privacy amplification from complex sampling designs; the implications of survey-weighted estimates; the weighting adjustments for nonresponse and other data deficiencies, and the imputation of missing values. We summarize the project's key findings with respect to each of these aspects and also discuss some of the challenges that still need to be addressed before DP could become the new data protection standard at statistical agencies.

stat.ME↗

arXiv2026

Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements

An increasing number of scholars use AI to measure variables they subsequently include in downstream analyses. Although AI-measured variables are often analyzed as if observed without error, ignoring prediction errors in automated measurement leads to substantial bias and invalid confidence intervals in downstream analyses, even if AI measurement accuracy is high, e.g., above 90%. Existing solutions, such as design-based supervised learning and prediction-powered inference, combine error-prone AI-based measurements with gold-standard labels, which may be costly and difficult to obtain in some application areas. In this paper, we propose debiased inference with multiple imperfect measurements (DMM), a framework that combines multiple error-prone AI measurements to enable valid downstream inference without gold-standard labels. Building on the established results on CP decomposition, DMM assumes that these measurements are independent conditional on the latent true label and observed unit-level features, such as text features represented by embeddings. This framework allows for unknown misclassification rates to vary across annotation methods (e.g., large language models) and across units of annotation (e.g., texts). Under this assumption, we use semiparametric inference theory to prove that the DMM estimator is consistent and asymptotically normal, enabling valid inference for a wide range of downstream statistical analyses common in the social sciences. Our simulation results show that DMM yields valid inference and that adding accurate, though imperfect, measurements can improve efficiency. Focusing on common applications of large language model annotations, we also develop diagnostics to assess the conditional independence assumption.

stat.ME↗

arXiv2026

Aggregate Disambiguation Systems

Natural-language tasks can elicit different verdicts from protocol-following evaluators that receive the same declared information. We study aggregate disambiguation systems (ADSs). Given a task and a candidate solution, each evaluator casts a binary vote on whether the solution should be accepted, and the system aggregates the votes of a finite panel. The target is protocol reproducibility relative to an explicitly declared evaluator reference, not semantic truth. We separate fixed finite censuses, probabilistic evaluator populations, and growing-census limits, since their endpoint laws and guarantees are not interchangeable. In the population setting, we use finite samples to estimate how often a finite panel reaches the same decision as the declared evaluator population. We provide a lower confidence bound on the fraction of candidate solutions for which the disagreement probability is at most a chosen tolerance. The calculation accounts separately for sampling candidate solutions and sampling evaluators. The construction permits arbitrary dependence among columns induced by shared evaluator rows and uses exact binomial intervals at the evaluator layer and an exact one-sided binomial inversion at the generator layer. Simulations check the implementation against known population coverages and expose power limitations.

stat.ME↗

arXiv2026

Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions

This note studies the geometry of full conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score. Candidate-score convexity alone does not guarantee connected FullCP regions, even for empirical averages of losses convex in the candidate argument. For the energy-form score, each leave-one-out training comparison reduces exactly to a pairwise-dissimilarity sublevel condition. Under symmetry, a constant diagonal, a diagonal lower bound, and attainment of the associated Fréchet-type objective, all comparison regions share a minimizer; if they are convex, every nontrivial exact conformal region is star-shaped about that point. For power distances $ρ_β(x,y)=\|x-y\|^β$, this geometry holds for $β\ge1$, while the conventional energy score is strictly proper for $0<β<2$. For $d=1,β=1$, every nontrivial empirical-CRPS FullCP region is a nonempty closed interval (possibly $\mathbb R$ when $m=1$). For $1<β<2$ and $m\ge2$, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function. Combined with directional root search and classical Lipschitz extensions, they yield certified inner and outer radial envelopes of width at most $δ+2\widetilde Lh_{\mathcal U}$ and same-ray Hausdorff guarantees. An analytic two-dimensional example shows why preserving star-shaped but nonconvex geometry can matter. A staged two-dimensional study finds modest but systematic tightening of the generic certificate and frequent robust nonconvexity witnesses, with detected normalized radial departures typically small. The method is intended for low-dimensional multivariate outputs rather than high-dimensional scaling or runtime improvement.

stat.ML↗

arXiv2026

Matrix-Aware Proper Scoring Rules and Significance Testing for Correlation and Covariance Forecasts in Python

Forecasting a correlation or covariance matrix is common in risk management and portfolio construction, but evaluating such a forecast correctly is not routine: naive matrix-comparison metrics are not proper scoring rules, walk-forward evaluation windows are easy to overlap with the estimation window in ways that silently leak information, and significance testing on serially dependent forecast-error sequences needs machinery few analysts implement from scratch. corrscore is a Python package that provides matrix-aware implementations of two established proper scoring rules for this setting -- the energy score and the variogram score -- dispatched across a closed-form tractability spectrum (point, discrete-mixture, and isotropic-Gaussian-mixture forecasts are scored exactly; a general Monte Carlo ensemble falls back to sampling), a geometry-aware variant of the variogram score built from the affine-invariant distance on the correlation manifold, a zero-overlap-by-construction walk-forward backtest harness, and a bundled significance-testing suite (circular block bootstrap, the Diebold-Mariano test, and the Model Confidence Set). We describe the package's design, its point of departure from the existing scoringRules and properscoring packages, and walk through a complete worked example.

stat.ME↗

arXiv2026

When the Martingale Never Stops Firing: Anytime-Valid Gating on Real Forecast Streams

Machine learning systems are increasingly corrected while they run, and the decision of when to intervene is increasingly delegated to statistical monitors. Anytime-valid inference promises evidence that can be acted on at any moment, exactly the guarantee this setting needs, and it is moving from theory into deployed monitoring. Conformal test martingales are the change-detection instrument, and Ville's inequality caps their false-alarm probability on exchangeable data. The guarantee is conditional. A deployment inherits it only if the stream it monitors behaves exchangeably. The premise is hardest to satisfy where these monitors are most useful, on dependent data and inside loops where the monitor modifies the learner whose scores it reads. It is also rarely measured. We measure it in a pre-specified case study, where such a monitor gates the online updates of a Kalman adapter correcting frozen time-series foundation models on five forecasting streams. On exchangeable synthetic streams, the same implementation fires in at most 1 of 60 runs. On the real streams, at alpha = 0.05, 135 of 135 clean-stream runs fired. The construction does not explain the firing; the failure comes from the deployed score stream itself. Repeated fires hold the gate's drift response active, and the gated filter amplifies the very transient it was designed to prevent. The component worth keeping makes no validity claim. Huber-style gating of the filter's own updates cuts isolated-spike degradation by an order of magnitude with no dataset specific tuning. Anytime-valid methods proposed for dependent data should therefore be accompanied by null-calibration controls and mechanism traces.

cs.LG↗

arXiv2026

Estimating systematic errors in Bayesian inversion using transport maps

In indirect measurements, the sought parameters have to be determined by solving an inverse problem, typically in a Bayesian framework. Often, the accurate numerical simulation of the measuring process is computationally demanding, making it necessary to rely on approximate models. These surrogates, however, introduce an additional model error and thus may distort the resulting parameter distribution. Moreover, even with the additional speed granted by the surrogate, posterior determination through conventional means such as Markov chain Monte Carlo might be cost intensive, specifically for complicated posterior shapes. In this paper, we propose a unified framework that combines Bayesian inference, model error correction and a transport-based sampling scheme to address these issues. To train the transport scheme, we investigate two different losses: one equivalent to the Kullback-Leibler divergence associated to the transport problem and one based on an upper bound of this loss, generally known as the evidence lower bound. We demonstrate that training the transport based on the latter changes the optimisation landscape drastically, potentially introducing an undesired bias in approximating the target posterior. We compare the computational cost of our approach with established methods and underline the theoretical results with numerical examples.

stat.ME↗

arXiv2026

Balancing the privacy-utility trade-off: How to draw reliable conclusions from private data

Absolute anonymization, conceived as an irreversible transformation preventing re-identification and sensitive value disclosure, has proven to be a broken promise. Modern data protection must therefore shift toward a privacy-utility trade-off grounded in risk mitigation. Differential Privacy (DP) offers a rigorous mathematical framework for balancing quantified disclosure risk with analytical usefulness. Nevertheless, widespread adoption remains limited, largely because complex technical concepts, such as privacy-loss parameters, have yet to be translated into forms meaningful to non-technical stakeholders. This difficulty arises from randomization itself: both analysts and adversaries must draw conclusions from uncertain observations rather than deterministic values. In this work, we adopt an interpretation of the privacy-utility trade-off based on hypothesis testing to measure the uncertainty introduced by randomized mechanisms. In particular, we use the concept of relative disclosure risk to quantify the maximum reduction in uncertainty an adversary can obtain from a membership attack on protected outputs, and show this measure relates directly to standard privacy-loss parameters. We further analyze how DP affects analytical validity via its impact on hypothesis tests assessing statistical significance. Building on these results, we provide practical guidance, accessible to non-experts such as data protection authorities, for navigating the trade-off and selecting protection mechanisms and parameter values.

stat.ME↗

arXiv2024

Learning Causal Abstractions of Linear Structural Causal Models

The need for modelling causal knowledge at different levels of granularity arises in several settings. Causal Abstraction provides a framework for formalizing this problem by relating two Structural Causal Models at different levels of detail. Despite increasing interest in applying causal abstraction, e.g. in the interpretability of large machine learning models, the graphical and parametrical conditions under which a causal model can abstract another are not known. Furthermore, learning causal abstractions from data is still an open problem. In this work, we tackle both issues for linear causal models with linear abstraction functions. First, we characterize how the low-level coefficients and the abstraction function determine the high-level coefficients and how the high-level model constrains the causal ordering of low-level variables. Then, we apply our theoretical results to learn high-level and low-level causal models and their abstraction function from observational data. In particular, we introduce Abs-LiNGAM, a method that leverages the constraints induced by the learned high-level model and the abstraction function to speedup the recovery of the larger low-level model, under the assumption of non-Gaussian noise terms. In simulated settings, we show the effectiveness of learning causal abstractions from data and the potential of our method in improving scalability of causal discovery.

cs.LG↗

arXiv2026

Correcting test set contamination by spiking the training data

The literature on test set contamination largely focuses on detection, but the correction of contaminated test scores is underexplored. Our core proposal is to spike the training data by intentionally contaminating some test examples at known rates. The spiked examples can then be used to calibrate predictors of model memorization which enable principled statistical correction of inflated test scores. To evaluate different correction estimators, we first present a simulation framework based on the Hubble models. Hubble models come in minimal pairs, where the perturbed model was deliberately contaminated with several test sets, while the standard model was not, serving as the counterfactual and correction target. We consider estimators that use information from a memorization predictor, correctness predictor, or both. In simulation, we establish basic statistical intuitions and show that estimators leveraging memorization and correctness information are better than naive estimation which makes no correction at all. We then instantiate several memorization and correctness predictors, and find that simple predictors such as Platt-scaled membership inference metrics provide good signal for correction. Finally, we examine the practical considerations of spiking. Simple memorization predictors need no more than 10 examples for calibration and often transfer from one dataset to another. Taken together, spiking is a promising solution for test set contamination.

stat.ME↗

arXiv2026

Active Inference with People: a general approach to real-time adaptive experiments

Adaptive experiments optimize their design throughout data collection, which can bring substantial benefits compared to conventional experimental settings. Potential applications include, among others, computerized adaptive testing (when selecting informative tasks in ability measurements), adaptive treatment assignment (when searching for experimental conditions maximizing certain outcomes), and active learning (when choosing optimal training data for machine learning algorithms). However, implementing these techniques in real time poses substantial computational and technical challenges. In this paper, we introduce a practical and unified approach to real-time adaptive experiments that can encompass these scenarios across textual, visual, and audio tasks. Our strategy combines active inference, a Bayesian framework inspired by cognitive neuroscience, with Pyro, a probabilistic programming library, and PsyNet, a modular Python package for large-scale online behavioral experiments. Active inference provides a task-agnostic optimization objective and efficient inference strategies; probabilistic programming makes the computations practical, reducing implementation costs; and PsyNet makes the resulting procedure deployable with humans in real time across diverse behavioral paradigms. We illustrate this approach through two concrete examples: (1) an adaptive testing experiment estimating participants' ability by selecting optimal challenges, reducing the number of trials required by 30--40\%; and (2) an adaptive treatment assignment strategy that identifies the optimal treatment up to three times as accurately as a fixed design. We provide instructions to facilitate adoption of the workflow.

stat.ME↗

arXiv2026

Destroy Me: Automatic Artifact Generation for Histopathology Images

Deep learning's diagnostic utility in pathology is constrained by model vulnerability to real-world data imperfections. While current strategies favor "perfect data" by filtering low-quality regions, which can lead to the loss of valuable diagnostic context, we propose a paradigm shift: engineering models to thrive in imperfect environments using "Destroy Me", a hybrid framework for realistic artifact synthesis and robust data augmentation. Our approach combines Stable Diffusion, fine-tuned to preserve morphological continuity by realistically integrating artifacts with the underlying tissue architecture, with physics-based procedural modeling to synthesize six common artifact types: tissue folds, precipitates, blur, stitching errors, dust, and pen markers. Artifact fidelity is assessed using Kernel Inception Distance (KID) and color Wasserstein distance metrics. Validating this strategy on lung adenocarcinoma pattern classification with an nnU-Net, we confirm that models trained on "destroyed" patches consistently outperform baselines on independent real-world datasets. Specifically, we observed a 10.5% relative improvement in macro F1-score and a 15% relative increase in the Cohen's Kappa ($κ$) coefficient. Crucially, our results demonstrate that selective, impact-weighted augmentation is vital for balancing practical robustness with the preservation of subtle diagnostic features.

eess.IV↗

arXiv2026

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM applications, but suffers from resource-intensive query access. We conceptualise auditing as uncertainty estimation over a target fairness metric and introduce BAFA, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs. BAFA maintains a version space of surrogate models consistent with queried scores and computes uncertainty intervals for fairness metrics (e.g., $Δ$ AUC) via constrained empirical risk minimisation. Active query selection narrows these intervals to reduce estimation error. We evaluate BAFA on two standard fairness dataset case studies: \textsc{CivilComments} and \textsc{Bias-in-Bios}, comparing against stratified sampling, power sampling, and ablations. BAFA achieves target error thresholds with up to 40$\times$ fewer queries than stratified sampling (e.g., 144 vs 5,956 queries at $\varepsilon=0.02$ for \textsc{CivilComments}) for tight thresholds, demonstrates substantially better performance over time, and shows lower variance across runs. These results suggest that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.

cs.LG↗

arXiv2026

Lie to Me: Finding Bugs in ZK DSL Toolchains with Adversarial Witness Injection

Zero-knowledge domain-specific language (ZK DSL) toolchains compile programs into constraint systems and generate witnesses for cryptographic proofs. Bugs in these toolchains can leave the enforced constraints weaker than the source-program semantics, admitting proofs for invalid executions. Such soundness bugs may remain invisible to valid-execution testing because all valid executions still behave correctly. We present Liezz, a testing framework that generates ZK DSL programs and exposes these bugs through adversarial witness injection. For each generated deterministic program, Liezz executes two public input assignments with different outputs and splices their witnesses, combining the input of one execution with the output of the other. The resulting witness is invalid by construction. A correct toolchain must reject it; acceptance exposes a soundness bug. Controlled divergence and multiple witness-splicing strategies preserve enough consistency to expose missing constraints. Liezz also generates parameterized standard-library calls to reach complex functionality. Liezz supports Circom, Corset, Gnark, and Noir. It finds 13 bugs, including seven with soundness impact. Several are reachable only through generated standard-library calls. Under the same testing budget, a valid-execution baseline does not expose any of the soundness failures revealed by accepted injected witnesses, showing that adversarial witness injection reaches failures missed by valid-execution testing.

cs.CR↗

arXiv2026

Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI

This position paper argues that human-centered explainable AI (HCXAI) should incorporate insights from the psychology of information seeking. Drawing on Sharot and Sunstein's framework of information-seeking motives, we propose that people evaluate whether to engage with explanations based on three types of expected utility: instrumental (will it help me act better?), hedonic (will it make me feel better?), and cognitive (will it improve my understanding?). Each utility is estimated through a lens shaped by well-documented cognitive biases, including illusion of control, automation bias, unrealistic optimism, impact bias, overconfidence, and confirmation bias. These biases can lead to two failure modes: excessive information-seeking that fragments attention without improving decisions, and insufficient information-seeking that leaves critical risks and misunderstandings unexamined. This challenge is particularly acute for agentic AI systems, where explanations must support not just understanding a single output but anticipating cascading actions, assessing risks, and deciding when to intervene. By integrating information-seeking psychology into HCXAI, we advocate for a shift from making explanations available to making them sought: designing systems that account for when and why users actually want to know.

cs.AI↗

arXiv2025

Symmetry-driven embedding of networks in hyperbolic space

Hyperbolic models are known to produce networks with properties observed empirically in most network datasets, including heavy-tailed degree distribution, high clustering, and hierarchical structures. As a result, several embeddings algorithms have been proposed to invert these models and assign hyperbolic coordinates to network data. Current algorithms for finding these coordinates, however, do not quantify uncertainty in the inferred coordinates. We present BIGUE, a Markov chain Monte Carlo (MCMC) algorithm that samples the posterior distribution of a Bayesian hyperbolic random graph model. We show that the samples are consistent with current algorithms while providing added credible intervals for the coordinates and all network properties. We also show that some networks admit two or more plausible embeddings, a feature that an optimization algorithm can easily overlook.

stat.CO↗

arXiv2026

Selection-Aware Stress Testing for Interactive Agents

Agent evaluations often use one benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selected from the same data. We introduce Selection-Aware Semantic Stress Testing (\SASST{}), which learns a task reweighting from pre-execution features on discovery tasks and evaluates the same paired comparison on separate confirmation tasks. The protocol checks support and stability, uses joint bounds for all planned claims, and can return no claim. We prove conditional asymptotic validity under stated cluster assumptions. A forty-cluster audit finds Gaussian undercoverage and conservative Bonferroni $t$ bounds. In one 480-episode $τ$-bench study, a $3.75$ point discovery gain vanished on confirmation. A second-model study likewise confirmed neither a workflow benefit nor a stable stress rule.

cs.LG↗