Distribution Shift

Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto another. Although both offer complementary insights, they are usually estimated separately, and converting one into the other requires post-processing. In this paper, we estimate the density ratio between a target and a base distribution by parametrizing it through a displacement field acting on the base: the log-ratio is modeled as minus the Stein operator of the base applied to the field, up to a normalizing constant. This gives both statistical and dynamical descriptions of the distribution shift through a single convex optimization problem. Iterating this estimate-and-move step gives two inference algorithms: push-forward moves the model and corrects a pretrained sampler without retraining it, whereas pull-back moves the data closer to the base and fits a transformation model one layer at a time. Applications to distribution shift in simulation-based inference and to nonlinear independent component analysis illustrate the benefits and limitations of the approach.

Large pretrained clinical models provide a practical way to reuse learned prior knowledge across hospitals by adapting models to them. In practice, a target hospital may only have a small labeled patient cohort, a setting commonly referred to as few-shot adaptation. This requires making multiple decisions, such as which pretrained model to adapt, how much of the model to update, and which patients to use. Nevertheless, this process faces two primary challenges. First, the best adaptation strategy varies across clinical tasks. Second, evaluating and comparing candidate strategies becomes unreliable due to the small patient cohort. In this work, we introduce AutoAdapt with two core designs to deal with these challenges. The Adapter defines an extensible space of adaptation recipes, and the Automator forms a weighted recipe combination from evidence within the adaptation patients. We propose a reliability rule to ensure that only the most effective strategy on most available patients will be selected. These selected strategies then form a combination for effective few-shot adaptation. We conduct extensive experiments across critical care, emergency care, and diagnostic datasets, and the results show that AutoAdapt consistently achieves state-of-the-art performance using only a few patients for adaptation.

Long-horizon robotic manipulation is often built by chaining independently trained skills. Although each skill can be reliable in isolation, performance degrades sharply when skills are chained: each downstream skill must start from the state its predecessor leaves behind rather than from its training distribution. We study this failure mode, Observation-Space Shift (OSS), and ask what causes these skill-seam failures. Using privileged simulator resets, we find that the dominant shift comes from displaced scene state (e.g., an open drawer or secondary objects left behind by earlier skills), not from the robot's joint configuration or the object the downstream skill manipulates. To test this diagnosis, we build a fully learned detect-restore-resume system: a task-progress monitor detects the stall, a learned policy restores the displaced scene components, and seam-robust fine-tuning lets the skill resume. It recovers the seam where every tested alternative fails, which we treat as evidence for the diagnosis rather than as a general-purpose method. On the BOSS-44 benchmark, the system improves full-chain success from 7.6% to 26.5%, a 3.5x improvement over the base policy and 51% of a privileged restoration oracle, whereas best-of-K resampling, a Diffusion Policy, and world-model baselines fail to recover from the evaluated seam states. On a real Franka arm running a fine-tuned $π_{0.5}$ policy, the same monitor is limited by exterior-camera observability, yet closing the loop still recovers some otherwise-terminal failures, motivating wrist and gripper sensing. These results suggest that some long-horizon composition failures are better addressed by restoring the scene before resuming the policy than by retrying from an off-support state.

Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractive in safety-critical domains. A central challenge, however, is distribution shift: policy optimization may favor actions that are weakly supported by the offline data, rendering value estimates unreliable. Existing approaches primarily control this shift in the policy's own action space. In interactive environments such as autonomous driving, this can be insufficient: a candidate ego trajectory may remain well supported under the marginal behavior distribution while being poorly supported jointly with the surrounding-agent behavior observed in the logged interaction. We refer to this degradation in interaction support as \emph{interaction distribution shift} (IDS), and introduce \emph{Interaction-Constrained Drive Policy} (ICDP), an offline reinforcement learning framework that explicitly controls interaction-level distribution shift. Starting from the joint data distribution over ego and surrounding-agent futures, we show that joint-support degradation decomposes exactly into an ego-support component and a residual interaction-support component. We recover the latter through contrastive density-ratio estimation, isolating interaction compatibility without explicit joint-density modeling, surrounding-agent prediction, or rollouts in reactive simulators or learned world models during policy optimization. Closed-loop evaluations on nuPlan, Interplan and real-world truck experiments show that ICDP suppresses high-value yet interaction-unsupported trajectory selections and improves performance in interaction-critical driving scenarios. Project webpage: https://mahmoud-selim.github.io/ICDP/

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. In this work, we formulate ICR as a type of domain adaptation problem, where the source distribution $P$ of the database may differ from the target distribution $Q$ of the test query-label pair. We investigate the performance of ICR under a flexible class of distributional shifts that substantially extends prior work \citep{li2024fine,guo2025retrieval}, and establish theoretical guarantees that quantify the benefits and pitfalls of this learning paradigm. Our theory is verified by experiments on synthetic and language tasks.

Comparing two high-dimensional discrete distributions has always been a challenging task due to the exponentially growing state space and complex changes in interactions. A recent work suggests comparing distributions through a vector field trained using flow matching between two continuous distributions. The resulting vector field at mid-point vanishes if and only if two distributions identical. However, such a flow-based criterion does not naturally apply to discrete distributions. We extend this principle to the discrete domain and introduce the \emph{Zero Flux} criterion, a discrepancy based on local probability fluxes. Under independent coupling, we show that all local probability fluxes vanish at the midpoint if and only if two distributions are the same. This discrepancy decomposes the joint distributional difference into smaller, local contributions and can be efficiently estimated from samples. We establish finite sample error bounds for our estimator. Experiments on synthetic and real categorical data demonstrate reliable recovery of sparse dependence signals and stable tracking of distribution shifts in high dimensions.

Autoregressive modelling has achieved remarkable success in language and sequence tasks by learning to predict future states from previous observation. Mineral-exploration drillholes provide a natural but largely unexplored setting for this paradigm: as drilling proceeds, lithology is revealed sequentially from shallow to deep, making prediction of deeper strata inherently autoregressive. Existing drillhole modelling, however, is dominated by spatial interpolation and reconstruction, or largely rely on masked modelling, leaving strictly autoregressive prediction largely underexplored. We introduce DrillBench, a benchmark of 49,671 Western Australian drillholes for next-layer prediction and autoregressive stratigraphic generation across a graded transfer spectrum, from local prediction through spatial shift to cross geological province transfer. Benchmarking classical, geostatistical, and neural models reveals a clear \emph{transfer boundary}: spatial and geochemical conditioning provides large local gains but deteriorates sharply under stronger shift, whereas lithology-sequence autoregressive models transfer more robustly. Guided by this finding, we develop a backbone-agnostic recipe combining large-scale pretraining on historical drillholes with spatial retrieval of neighbouring lithology. Retrieval is most effective in weathered cover, when local spatial continuity remains informative, whereas pretraining contributes more strongly in bedrock and under broader geological shift. Together, they retain strong local performance while improving generalisation under spatial and cross-province shift, most markedly on the most distant splits. The benchmark and code are available at https://github.com/yihaoding/drillbench.

Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter-efficient distributionally robust adaptation framework that requires no true group annotations. DR-TFM adjusts attention to labeled context examples by fine-tuning an existing query scaling network or adding and training one, while keeping all other parameters fixed. We instantiate the framework with two robust objectives using estimated groups or source conditional distributions derived from training data. For TabPFN-3, adaptation updates only 0.016% of the pretrained model's parameters. Across five tabular benchmarks, DR-TFM achieves substantially higher average worst-group accuracy than pretrained TFMs and the compared robust baselines without true group annotations, while maintaining competitive mean group accuracy. DR-TFM also improves average worst-group accuracy on ACS Income and across four additional TFMs.

Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where environmental conditions may change significantly over time. Although recent advances in Visual Foundation Models (VFMs) have improved open-vocabulary semantic segmentation, these models can still suffer from domain shift, which can significantly degrade performance if they are not adapted to the current environment. Training-free domain adaptation is a relevant paradigm for adaptation, consisting of adjusting the model online using lightweight adapters. Recent approaches apply this on a per-frame basis, which is impractical for deployments on resource-constrained robotic hardware. To tackle this, we propose a multi-signal domain shift detection method for training-free continual test-time adaptation (TF-CTTA) in open-vocabulary segmentation. Our method leverages temporal coherence across consecutive frames by monitoring and combining complementary aspects of domain shift (visual change, adapter mismatch, and semantic drift) to trigger adaptation only when needed. We validate our approach on a benchmark including indoor and outdoor environments and using real robotic data. We demonstrate that our approach maintains segmentation accuracy while substantially reducing adaptations, making training-free adaptation practical and feasible for long-term, real-world robotic deployments.

Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods often assess prediction reliability using confidence or entropy, which primarily reflect the model's self-certainty for the current sample. In CTTA, accumulated target observations can provide complementary evidence for correcting the source prediction, but this history may become misaligned as the target distribution changes. The key question is therefore not how much the correction differs from the source prediction, but whether and how strongly it should be applied. This paper proposes Gain-Aware INtervention (GAIN), a backpropagation-free CTTA framework guided by a simple principle: history proposes, gain decides. GAIN maintains compact target statistics to form a correction proposal and a posterior-predictive evaluator that accounts for estimation uncertainty. The resulting source-relative gain estimates the proposal's benefit and determines a sample-specific intervention strength along a continuous path through efficient one-dimensional optimization. Gain-controlled predictions then update the target statistics online, limiting the propagation of unreliable corrections, all without backpropagation, sample storage, or replay. Across five benchmarks, our method achieves strong predictive performance, with favorable accuracy--calibration--efficiency trade-offs in continual adaptation. On ImageNet-C, for example, GAIN achieves 61.9% accuracy with near-source calibration. It remains stable under diverse and challenging continual shifts while running 15.9x faster than a representative optimization-based CTTA baseline.

Neural operators can accelerate repeated nonlinear mechanics calculations, but their accuracy can deteriorate as operating conditions move beyond the training range. This work studies whether high-fidelity solutions acquired during use can be reused to adapt a neural operator and improve subsequent mechanics-based command selection. Two hard-magnetic soft-material systems are simulated using high-fidelity finite-element (FE) models, providing reference solutions for evaluating surrogate predictions and selected commands. A neural operator predicts deformation from known material, loading, and magnetic-field inputs, while an empirical error estimator determines which predictions may be used for command selection. Selected FE evaluations supplement these predictions, and their complete loading paths are retained for periodic updates of the neural operator and estimator. In both examples, the fixed operator loses substantial accuracy when stiffness and loading move outside the training range. Updates using 16 acquired paths recover much of the lost accuracy while preserving accuracy in the nominal regime. Under the same FE evaluation budget, the updated operators also improve command selection, although the benefit varies with the operating condition. Error estimation is less consistent, with inaccurate predictions sometimes accepted and accurate predictions rejected. These results demonstrate that reusing high-fidelity loading paths can extend the useful operating range of a neural operator. However, improved forward accuracy alone does not guarantee reliable prediction acceptance, highlighting prediction-specific error assessment as a separate requirement for trustworthy decision making.

Detecting failures in World Model (WM)-based planning requires monitoring whether the model is behaviorally aligned with the current task, which in turn requires studying its internal representations. Here, we show that centroids---sub-component Jacobian row-sums---effectively identify the behavioral properties of WMs, complementing traditional activation-based knowledge signals. The centroids of a model are easily computed through Jacobian vector products and characterize how the model organizes the geometry of its input space, yielding an efficient perspective on internal representations, including the generation of task-relevant saliency maps. Evaluated on continuous control tasks using JEPA WMs, this behavioral view reveals a structural dissociation, where the encoder correctly represents the goal while the predictor remains behaviorally unresponsive. This failure mode directly predicts planning failure before any action is taken, allowing for goal resampling to recapture out-of-distribution success. Moreover, centroid-based methods outperform baseline methods as distribution-shift detectors. Together, these tools yield a behavioral monitoring stack that is operational and consequential under distribution shifts.

Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal distribution shift. To address this issue, we propose RAEGL, a Risk-Aware Evidence-Gated Learning framework for selective contextual forecasting. RAEGL retains a validated global predictor by default and activates a contextual residual only when pre-deployment evidence supports its use. The framework separates candidate selection from gate calibration and jointly evaluates randomization significance, practically meaningful gain, and temporal stability. Experiments on real-world audits and controlled panels show how RAEGL can prevent harmful contextual deployment while making conservative opportunity costs explicit. In a reconstructed Our World in Data audit, exact fallback avoids RMSE degradations of 0.0960 and 0.0239 caused by two validation-selected corrections. In a sealed World Development Indicators evaluation, a region-based correction passes the randomization test but is withheld because its gain is only 0.000092, its country-clustered 95% confidence interval crosses zero, and only 0.02% of bootstrap replicates reach the practical threshold. In controlled panels, the stability- and support-aware extension activates in 97.2% of strong, stable-context runs while rejecting all high-drift settings. These results support RAEGL as an auditable, evidence-based mechanism for managing contextual deployment risk and as a conservative alternative to validation-driven contextual selection.

Malware detection is a critical task in cybersecurity, and graph neural networks over control flow graphs have shown promising results for it. However, detectors are usually evaluated on a random split of a corpus collected over a single period, which cannot show how well a model generalizes to later samples. This study addresses that limitation with a strict temporal split: every model is trained on one period and scored once on a later one. Two corpora of control flow graphs, each node carrying 37 features, were extracted statically from 1,989 Windows portable executables: 459 graphs from 2024-2025 for training and 223 from 2026 for evaluation. Twelve variants and a flat-feature control were trained on the earlier corpus. The choice of message-passing operator changes robustness to the shift significantly, and every pairwise gap that survives correction separates an aggregating architecture from one built around a learned attentional readout. The ranking also reverses: the flat control, which sees node features but no topology, is the best in-distribution model and among the worst across the boundary, so a conventional benchmark would have rejected message passing. Neither recalibration nor ensembling substitutes for the operator choice. Attributions do not shift, but explanation validity is architecture-specific, and the most accurate operator on the later corpus is the hardest to explain. An architecture derived from the finding matches the best searched operator without search. The shift affects both malware and benign classes alike, so these are results about robustness to distribution shift, not malware evolution.

In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can exhibit weak or even negative correlation with generation FID (gFID). We attribute this misalignment to a latent distribution mismatch: reconstruction evaluates the decoder on encoder-induced latents, whereas generation uses the same decoder on latents produced by the generative model. To characterize this shift, we introduce generation-aware reconstruction (GAR), which constructs a continuous trajectory from standard reconstruction toward generation by perturbing encoder latents with noise and denoising them through the generative model before decoding. GAR probes the decoder behavior along this trajectory, making the transition from encoder to generation-time latent distributions observable and diagnosable. The resulting trajectory-based diagnostic, GAR-FID, exhibits strong empirical correlation with gFID across diverse tokenizers and scales. Importantly, intermediate GAR latents become more generation-aware while preserving correspondence with their source images, thereby retaining paired supervision that is absent for fully generated latents. This correspondence enables decoder adaptation on intermediate GAR latents, consistently improving generative quality across model scales. Overall, latent distribution mismatch provides a useful perspective for evaluating and improving latent generative models.

AI-generated music detectors are commonly compared using aggregate scores on benchmarks whose training overlap, generator lineage, source provenance, and audio-transformation history are only partially observable. This paper introduces ArtifactBench, a lineage-aware evaluation suite for measuring detector behavior across generator families and versions, real-music domains, collection-cohort shift, and inference coverage. The benchmark groups source recordings and their derived variants by content identity, separates calibration from final testing, records inference failures independently from classification errors, and reports source-level performance with uncertainty in addition to aggregate metrics. We evaluate multiple publicly available detectors under a version-pinned common protocol and examine how leakage control, cohort availability, threshold policy, and model-specific missingness alter measured performance and model ranking. On the 562-track common-success test intersection, ArtifactNet obtains 0.982 AUROC and 0.918 balanced accuracy, compared with 0.761/0.776 for the public Deezer detector; SpecTTTra and CLAM fall below 0.30 AUROC under this shifted cohort. These results also expose substantial generator- and real-domain shifts that aggregate scores alone conceal.

An AI evaluation can be perfectly reproducible and still support the wrong claim. This risk is acute in closed-loop systems: policy determines visited states, observable components, and which failures leave a measurable trace. We propose a claim-safe protocol with three actions. Refuse: abstain when a clean reference stream or matched runtime comparison lacks support. Decompose: report protocol execution, operational false admission, and structural hypotheses separately rather than as one PASS/FAIL label. Refresh: treat distribution-shift alarms as requests to invalidate and recompute a reference map, not as fault evidence. We instantiate the protocol in an aggregate-only simulator with 24 policy components, three demand regimes, two fault-mask families, and independent development and heldout seeds. The preregistered heldout contains 1,440 cases and 21,600 partition rows. Only 55/72 regime-component units were reference-admitted and 54/55 remained runtime-admitted, making abstention part of the result. Stable false admission was 0/20 represented components, with a one-sided exact 95% upper bound of 0.1391 under a frozen 0.20 rule. Within admitted units, affected clean traffic outpredicted nominal fault-cell fraction: across 540 unit-arm rows nested in 20 component clusters, the cell-minus-traffic negative-log-likelihood difference was 0.1264 nats per row, with a 95% component-cluster interval of [0.0593, 0.1918]. A drift log shows why "null" must be reference-relative: clean fault-null streams triggered 15/15, 0/15, and 14/15 alarms across three regimes, while only the middle regime matched the frozen detector reference. Rather than a universal threshold, we contribute an executable contract linking observable support, statistical calibration, and justified claims.

We study density ratio estimation and importance-weighted regression under target shift with continuous outputs. Under target shift, the conditional distribution of the inputs given the outputs remains invariant across the training and test distributions, while the output marginal distribution may change. Although this problem has been extensively studied for discrete outputs, the continuous setting is substantially less understood: the importance weights are determined by an unknown density ratio function, for which existing estimation methods lack explicit finite-sample convergence rates. We propose a spectral regularization method in a reproducing kernel Hilbert space (RKHS) for estimating the continuous density ratio from labeled training samples and unlabeled test inputs. Under a source condition with regularity parameter $ι>0$, we establish high-probability finite-sample guarantees and show that the estimator achieves the capacity-independent minimax-optimal RKHS-norm rate $O(n_η^{-ι/(2ι+2)})$. We then incorporate the estimated density ratio into importance-weighted regression and characterize the propagation of density-ratio estimation error to the final predictor. When sufficiently many samples are available for density ratio estimation, the resulting regression estimator attains the minimax-optimal rates of standard kernel regression. These results establish a finite-sample theory for continuous density ratio estimation and importance-weighted learning under target shift.

Prequential adaptation of frozen tabular foundation models under temporal drift, with each label revealed only after prediction, helps some deployments and harms others, yet current practice does not predict which. We study the sources and limits of these gains. A diagnostic anatomy attributes gains to four recurring mechanisms under a streaming protocol that removes three optimistic biases and quantifies a fourth. Within an agnostic total-variation drift class, the target conditional is only partially identified: its identified-set diameter, the \emph{wall}, is irreducible from unlabeled data uniformly in sample size. A second, orthogonal $L^2$ projection wall quantifies what the frozen representation cannot express. Two canonical mechanism priors collapse the first wall. Under stated nuisance-rate conditions, the wall can be estimated from labeled historical windows at a $\sqrt N$ rate above the margin threshold $\gamma^\star=d_0/(2\alpha_s)$. At $\gamma=0$, the conditional lower-bound program depends on an open affinity estimate; the positive-margin lower branch also remains open. Semi-synthetic data illustrate the finite-sample mechanism with calibrated exponents. Stream-level proxies on eight industrial streams fall on the difficult side under a stated roughness bound, while the equality case $\gamma=\gamma^\star$ remains unresolved.

Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes a wide variety of supervised learning such as positive-unlabeled (PU) learning, noisy label learning, and similarity-based learning. Existing UU learning assumes that the test and training distributions have the same class-conditional densities. However, this assumption rarely holds in practice due to distribution shifts. This paper proposes a distribution shift adaptation method for UU learning that uses UU data in the training distribution and a few UU data in the test distribution. The proposed method is based on the importance weighting, which minimizes the test risk by using training data with estimated importance weights. Although existing importance weighting methods cannot handle UU data, we show that it can be done in a principled manner. Thanks to the generality of UU learning, our method can handle various learning problems such as PU and noisy label learning under distribution shift within a single framework while existing methods are usually tailored to a specific problem. Moreover, it does not require any assumption of the shift types such as covariate shift. We experimentally demonstrate the effectiveness of the proposed method with real-world datasets.

Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source and target supports mismatch. Leveraging entropic optimal transport, we propose a key notion: $\gamma^{*}\!$-concept shifts, and derive a general error bound unifying covariate and $\gamma^{*}\!$-concept shifts, which applies to broad loss functions, label spaces, and stochastic labeling. We further develop estimators for these shifts with concentration guarantees, and the DataShifts algorithm, which can quantify distribution shifts and estimate the error bound in most applications - a rigorous and general tool for analyzing learning error under distribution shift.

Sensor-based AI systems are rarely operated under the conditions under which they were trained: devices, personnel and recording epochs change, and each change degrades performance in ways a random train-test split cannot reveal. We propose a staged, accountable evaluation protocol that treats the evaluation of a deployed model as a measurement with declared reference levels and a quantified uncertainty. Four cumulative generalisation stages hold out devices, subjects and time. Each stage is judged on quantiles of repeated trainings against chance references with the correct class count, an out-of-present-scope rate exposes silent misdirection towards classes that are no longer present in deployment relative to training, and an explicit decision rule ties roll-out decisions not to means but to 5% quantiles. We demonstrate the protocol on infrastructure-free geomagnetic localisation with smartphone-based recurrent classifiers in two real underground mines, including a replication of the scheme's training stages at the second site. Unchanged models are re-evaluated on data recorded 34 months after the training campaign, on a device generation unknown at training time and with a held-out surveyor. The 5% quantile of their present-conditioned precision there is 0.39 over 299 repeated trainings, 16.5 times the chance level; across the composition of the 42 reachable location classes the figure varies by +/-0.08, several times the spread between repeated runs. Repeated trainings of a single configuration show why means mislead: a bimodal configuration passes a mean-based test decisively while its 5% quantile lies more than an order of magnitude below chance.

Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.

Standard semi-supervised learning (SSL) typically relies on labelled and unlabelled data sharing a common marginal distribution. This assumption is often violated by biased spatial sampling mechanism, when labels are collected under spatially biased or preferential site selection. We treat this marginal mismatch, spatial autocorrelation, and spatial non-stationarity as three distinct mechanisms, varied independently via a labelled-sampling concentration parameter, a spatial length scale, and a non-stationarity strength parameter, and ask how mismatch degrades SSL, whether the cluster and manifold assumptions survive it, and how the resulting failure can be diagnosed. Using a controlled synthetic framework alongside PovertyMap-WILDS, California housing, socio-economic and US air quality monitoring datasets, we systematically vary the degree of mismatch while accounting for spatial autocorrelation and non-stationarity. Through a series of analyses including a segmented-regression changepoint, we show that in the synthetic generator, SSL performance does not degrade gradually but instead exhibits a threshold-like breakdown between approximately 0.71 and 0.77 once distribution mismatch becomes sufficiently severe. We further demonstrate that spatial non-stationarity contributes to performance loss independently of marginal mismatch and that models become increasingly overconfident outside the regions where labels are available. To support practical deployment, we evaluate several distribution-divergence measures as indicators of reliability and introduce a kernel-weighted local divergence metric that provides a more stable estimate of spatial mismatch than a naïve localised approach. These findings provide empirical evidence and diagnostic tools for better documenting the risk of incorporating unlabelled spatial data into semi-supervised learning workflows.

While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of approximately 59K words per book. The benchmark supports evaluation under domain, author, and language shifts. Evaluation of representative AA methods shows that no single method consistently performs best across settings, and performance generally degrades under distribution shifts. Transformer-based detectors can retain generator-related information across languages, although transfer effectiveness varies by language pair, whereas statistical and fingerprint-based detectors are more language-dependent. We envision MultiGhostBench as a valuable resource for the development and evaluation of robust AA methods. The dataset and code can be found at https://github.com/GrecoMT/MultiGhostBench.

Combining learned policies with model predictive control can leverage learned task priors while retaining online adaptation to new objectives and constraints, but performance degrades when the policy is out of distribution. In policy-guided model predictive path integral (MPPI) control, a policy-centered warm-start approach centers the sampling distribution on the policy output. When the prior is mismatched, centering the sampling distribution on the policy output restricts exploration around an unsuitable solution and prevents recovery toward the task optimum. We propose Proximal Prior Injection (ProxPI), which retains nominal-centered MPPI sampling and incorporates the policy through a soft proximity cost. This matches the in-distribution performance of existing prior-injection schemes while enabling the optimizer to escape an inaccurate policy and recover vanilla MPPI-level performance. We theoretically show that re-centering on the prior discards the optimizer's correction at every update, whereas nominal-centered sampling retains it and converges to a solution set by both the task cost and the prior, and that this failure is not removed by a larger rollout budget. Simulations and real-robot experiments demonstrate robust performance under both in-distribution and out-of-distribution tasks.

Human mobility serves as an essential proxy for understanding social, economic, and environmental dynamics in urban systems. Geospatial transferability, which measures a model's capability in a new location or unseen region, is a critical dimension for comparing different human mobility generation models. However, few studies have studied the intrinsic characteristics of geospatial transferability. To this end, this study systematically investigates the geospatial transferability of four representative human mobility generation models using a large-scale benchmark dataset of census tract level commuting flows across 2265 counties in the United States. Inspired by the domain adaptation theory in machine learning, we introduce geographic domain shift to describe the intrinsic differences in geographic feature distributions and spatial structures between source and target regions, which may jointly affect model transferability. Moreover, we propose two metrics, mutual information and spatial shift, to quantify the geographic domain shift. To examine their associations with model transferability, we employ linear mixed-effects regression to analyze the associations between geographic domain shifts and transferability. Our results reveal substantial spatial heterogeneity and asymmetry in transfer performance across regions. Both information shift and spatial shift exhibit statistically significant and complementary explanatory power. This indicates that geospatial transferability depends not only on model design but also on intrinsic geographic differences. These findings provide a novel methodological framework for evaluating and improving the geospatial transferability of human mobility generation models and support more robust and fair human mobility data synthesis across diverse regions. It also offers insights on spatial transferability for GeoAI model development.

Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves. We present Regime-Conditional Verification (RCV), a lightweight wrapper that adapts an off-the-shelf safety classifier without retraining it. RCV estimates, from the classifier's internal representations, the probability that each prediction disagrees with the deployer's policy, and selectively corrects predictions likely to be wrong. The same correctness estimates also provide a label-free signal for detecting distribution shift, enabling a maintenance loop that updates the correctness estimation layer and resorts to classifier fine-tuning only when repair fails within a label budget. Across three off-the-shelf safety classifiers and two benchmark datasets, RCV improves adherence to the deployer's policy in every classifier-dataset combination, catching up to 0.81 of previously missed unsafe content without modifying the underlying classifier. In a deployment study with ten attack campaigns, each a harm category held out of RCV's training, RCV detects every campaign in a dedicated injection panel; in the maintenance census most drift episodes are repaired without updating the classifier, and the fine-tune is reserved for the residual episodes.

What a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity. We develop a typed accounting for finite-state learning devices that separates four components: a training-side fit functional $Φ_{\mathrm{fit}}$, the record-correlation stock $J_{D}=I(M;D)$, an update-side search ledger $σ_{M}$, and an operational capital value $V(M;T,b)$. This value is the work gap between an informed protocol class and a blind class obtained by deleting the memory-read port and re-optimizing from scratch. (I) Separation: for every $n$, there is a device family on which record correlation and world correlation grow by $n\ln 2$ while the capital gain is exactly zero. In the $\mathrm{flat}^{*}$ regime, data-free updates never increase $V$. (II) Capitalization ledger: an exact $\mathrm{flat}^{*}$ extraction identity and a universal ledger identity give, for (F5$'$)-stable $M$-local updates under a no-discarded-record-correlation condition (f), the bound $η_{\mathrm{cap}}\le 1$ for the capitalization efficiency $η_{\mathrm{cap}}=ΔV/(k T\,σ_{M})$, together with necessary and sufficient conditions for equality. (III) Value retention: for the retention gap $L_{\mathrm{gen}}$ and retention ratio $ρ_{\mathrm{gen}}$ (the former carries no sign constraint; the latter is defined for positive training-side value and is not confined to $[0,1]$) we give a two-layer alignment domain: an exact exchange rate between value and the side-information-adjusted record fit $I(M';D\mid Y)$ without any record-side-information independence assumption, and a raw record-stock exchange rate under a joint side-information neutrality condition $(M,D)\perp Y$, whose boundary is marked by an explicit one-time-pad witness. These are statements about finite-device value retention under task-distribution shift, not a theory of statistical generalization.

Scientific claim verification over a cited paper requires predicting the claim--paper relation and identifying the paragraphs that justify that prediction. This setting poses two linked challenges: within-paper distractors often resemble genuine evidence, while a classifier trained on gold evidence must operate on retrieved evidence at inference. We present HNR-DAC, a two-stage framework that trains each stage on the cases it will actually encounter. Hard-Negative Reranking (HNR) quantifies evidence confusability using a base reranker's scores on non-gold paragraphs and contrasts gold evidence against the most confusable candidates. Distribution-Aligned Classification (DAC) trains on the Top-1 paragraph produced by the same frozen HNR used to construct inference inputs, while HNR's Top-3 paragraph identifiers provide the evidence output. On the NLPCC 2026 Task 10 Track 2, the final configuration obtains 97.21% Hit@3, 95.79% Macro-F1, 94.47% Joint@3, and an average score of 95.13%. The corresponding submission ranks third on the official Track 2 leaderboard while achieving the highest overall Macro-F1 of 93.05%, alongside 70.16% Joint@3 and an average score of 81.61%.