arXiv:2609.08981v2 Announce Type: replace-cross Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing inference at test time using only examples provided in the prompt, without any parameter updates. Prior theoretical work has shown that this capability extends to supervised learning tasks such as linear regression. We prove that in-context learning extends further to \emph{data generation}: frozen transformers can simulate iterative generative samplers from in-context samples. We first show that transformers can realize closed-form and smoothed closed-form diffusion samplers. The construction identifies a concrete generative role for softmax attention: it computes responsibility weights and weighted empirical averages, while feedforward layers implement Euler updates. To empirically relate these constructions to pretrained language models, we study \emph{semantic-topic sampling}: prompts consisting of words drawn from a common semantic category, such as animals, foods, or cities. Across transformer layers, the normalized hidden states exhibit a two-stage geometry: they move toward a uniform spherical reference in intermediate layers and then return to structured, topic-dependent representations near the output. We further measure an interacting-particle energy on these hidden-state clouds and observe the same U-shape pattern. We then prove that transformers can approximate an energy-based sampler, constructing the same U-shape energy across the layers.

arXiv:2605.25272v1 Announce Type: new Abstract: While aggregate leaderboard scores drive AI development, they contain substantial measurement noise whose sources and magnitudes remain unquantified, making it unclear when rankings reflect genuine capability differences versus evaluation artifacts. We introduce a framework for measuring the latent landscape in AI benchmark ecosystems. Applying Confirmatory Factor Analysis (CFA) and Generalizability Theory to 4,000+ models from the Open LLM Leaderboard, we decompose sources of ranking variance and establish: (1) structures assumed in current reporting practice underestimate the strength of relationships between benchmarks; (2) evidence of local dependence among leaderboard items, undermining uses of benchmarks as measurement instruments under current scoring systems; (3) contributor metadata explains more rank-relevant variance ($\approx9\%$) than architecture or deployment categories in this context; (4) a manifest-score "scaling law" slope has low reliability ($R_{\beta}=0.53$); by contrast, the latent general-factor size slope is highly stable across ecosystem controls ($R_g=0.97$). We are able to provide unique insights into benchmark dynamics, such as which benchmarks are a function of LLM size and which can be oppositely impacted by post-training practices. We provide actionable diagnostics to determine how benchmark rankings can be trusted and how benchmark design can be improved.

arXiv:2605.24003v1 Announce Type: cross Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data is the presence of missing observations due to cloud cover. These data gaps can lead to missed detection of critical events, such as algal blooms, in lakes of high interest to water authorities. As a result, enhancing the completeness of optical satellite datasets is crucial for improving the monitoring and prediction of algal blooms. In this study, we compared a traditional data imputation method (i.e., linear interpolation) with deep learning models for reconstructing missing spectral bands across four lakes with historical records of algal blooms. The deep learning models adopted include CNN-based architectures (i.e., CNN, Inception Resnet, and Autoencoder) and CNN-LSTM-based architectures (i.e., CNN-LSTM, Resnet-LSTM, and Autoencoder-LSTM). Our results demonstrated that deep learning models substantially outperformed the baseline linear interpolation method in imputing spectral band values within artificially masked regions. Among these models, CNN delivered the best performance across most lakes. Furthermore, we evaluated the performance of algal bloom indices (i.e., Green/Red and NDCI) derived from the imputed imagery by comparing them with the observed data. Our results demonstrate that deep learning models are effective for imputing missing data in PlanetScope SuperDove imagery, enabling more reliable applications in water monitoring.

arXiv:2605.24050v1 Announce Type: cross Abstract: Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, performance degrades as libraries grow -- by up to 21\% when scaling from a small set of helpful skills to a 202-skill library. In this work, we formulate this performance degradation as the pass rate drop between loading a library of known-helpful skills and the full library. Moreover, we propose to decompose the pass rate drop by conditioning on the skill(s) invocation -- which skills the agent selects during a trajectory -- into two effects: \emph{skill shadowing}, where the agent selects wrong skills more often as the library expands, and \emph{context overhead}, where the enlarged context degrades execution even when selection is correct. We derive upper bounds on both effects to characterize their magnitudes of impacts to the pass rate drop. Our empirical estimates of the effects and their upper bounds both show that the \emph{skill shadowing} effect grows with library size and significantly contributes to the performance degradation, whereas the \emph{context overhead} effect remains small and indistinguishable from zero. This observed asymmetry establishes that the skill selection failure, not the enlarged context, is the primary bottleneck when expanding the skill libraries.

arXiv:2605.24212v1 Announce Type: cross Abstract: Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target domain. For example, high-performing models for out-of-hospital cardiac arrest (OHCA) rely on detailed prehospital measurements routinely collected in high-resource settings but unavailable in many international registries. Existing methods either discard missing covariates, sacrificing predictive information, or rely on untestable assumptions about their target distribution. We propose DRUM (\underline{D}istributionally \underline{R}obust \underline{U}nsupervised transfer learning with structurally \underline{M}issing covariates), a framework that transfers prediction models to target populations where certain covariates are structurally absent and outcome labels are unavailable. DRUM partitions covariates into shared components ($X$), observed across all settings, and missing components ($A$), observed only in the source. Rather than imputing missing covariates, DRUM optimizes worst-case predictive performance over the unknown target distribution of $A \mid X$ using a neural network generator, with a robustness parameter controlling allowable deviation from the source conditional. We further develop a bias correction procedure that reduces sensitivity to nuisance estimation error. Simulations show substantial improvements in both mean and worst-case prediction error under distribution shift. Applied to cross-national OHCA prediction, transferring models from a US registry to multiple Asian registries where prehospital variables are unrecorded, DRUM yields better-calibrated predictions and improved clinical classification performance across sites.

arXiv:2605.24381v1 Announce Type: cross Abstract: Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve strong performance, they require domain-specific training, feature engineering, and ongoing maintenance. Large-scale foundation models have recently emerged as a zero-shot alternative, avoiding task-specific training much like LLMs. In this work, we evaluate foundation models against standard supervised approaches. Rather than focusing solely on aggregate accuracy, we analyze performance across four operational regimes: periodic human-centric systems, physically constrained processes, stochastic financial markets, and heterogeneous demand forecasting. Our results characterize optimal deployment areas. Foundation models perform well in domains with transferable periodic structures and are efficient for cold-start or long-tail scenarios. Conversely, supervised specialists maintain higher precision in systems governed by strict physical constraints. In financial domains, newer foundation models are rapidly closing the performance gap with supervised specialists. We further quantify trade-offs in inference latency, data drift adaptability, and deployment constraints. Finally, we propose a Complexity Router that assigns each series to the optimal model class using empirical features. We demonstrate that this selective routing achieves higher accuracy and significantly lower inference costs compared to deploying a universal foundation model, providing a practical framework for balancing generalization and efficiency.

arXiv:2605.24810v1 Announce Type: cross Abstract: Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data filtering are constrained to the source dataset and cannot synthesize new target behavior to improve coverage beyond the collected source trajectories. While recent model-based methods attempt to address this by learning target-aware dynamics, the generated experience is constructed only at the transition level, which leads to accumulated errors over long horizons. These limitations necessitate a shift toward trajectory-level generation for off-dynamics offline RL. We propose CEDGE, a Cross-domain Energy-guided Diffusion GEneration framework. CEDGE trains a trajectory diffusion model on source-domain trajectories and adapts the generated samples to the target domain through energy guidance. This guidance is derived by minimizing the distribution mismatch between the source and desired target-domain trajectories and is decomposed into return, domain, and behavior energy components. The resulting energy-guided trajectories are useful both for direct planning and as synthetic data for policy learning. Since target adaptation is achieved via energy guidance rather than retraining the diffusion model, CEDGE can be efficiently adapted to new target dynamics compared to previous methods. Experiments on the ODRL benchmark demonstrate that trajectory-level energy-guided generation improves diffusion planning under dynamics shifts and produces synthetic data that improves downstream target policy learning.

arXiv:2604.04274v1 Announce Type: new Abstract: Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in accelerating scientific discovery, we introduce InferenceEvolve, an evolutionary framework that uses large language models to discover and iteratively refine causal methods. Across widely used benchmarks, InferenceEvolve yields estimators that consistently outperform established baselines: against 58 human submissions in a recent community competition, our best evolved estimator lay on the Pareto frontier across two evaluation metrics. We also developed robust proxy objectives for settings without semi-synthetic outcomes, with competitive results. Analysis of the evolutionary trajectories shows that agents progressively discover sophisticated strategies tailored to unrevealed data-generating mechanisms. These findings suggest that language-model-guided evolution can optimize structured scientific programs such as causal inference, even when outcomes are only partially observed.

arXiv:2603.28532v2 Announce Type: replace-cross Abstract: Low left ventricular ejection fraction (LEF) frequently remains undetected until progression to symptomatic heart failure, underscoring the need for scalable screening strategies. Although artificial intelligence-enabled electrocardiography (AI-ECG) has shown promise, existing approaches rely solely on end-to-end black-box models with limited interpretability or on tabular systems dependent on commercial ECG measurement algorithms with suboptimal performance. We introduced ECG-based Predictor-Driven LEF (ECGPD-LEF), a structured framework that integrates foundation model-derived diagnostic probabilities with interpretable modeling for detecting LEF from ECG. Trained on the benchmark EchoNext dataset comprising 72,475 ECG-echocardiogram pairs and evaluated in predefined independent internal (n=5,442) and external (n=16,017) cohorts, our framework achieved robust discrimination for moderate LEF (internal AUROC 88.4%, F1 64.5%; external AUROC 86.8%, F1 53.6%), consistently outperforming the official end-to-end baseline provided with the benchmark across demographic and clinical subgroups. Interpretability analyses identified high-impact predictors, including normal ECG, incomplete left bundle branch block, and subendocardial injury in anterolateral leads, driving LEF risk estimation. Notably, these predictors independently enabled zero-shot-like inference without task-specific retraining (internal AUROC 75.3-81.0%; external AUROC 71.6-78.6%), indicating that ventricular dysfunction is intrinsically encoded within structured diagnostic probability representations. This framework reconciles predictive performance with mechanistic transparency, supporting scalable enhancement through additional predictors and seamless integration with existing AI-ECG systems.

arXiv:2604.02238v1 Announce Type: cross Abstract: Generative AI (GAI) reveals an irreducible human core at the center of data science: advances in GAI should sharpen, rather than diminish, the focus on human reasoning in data science education. GAI can now execute many routine data science workflows, including cleaning, summarizing, visualizing, modeling, and drafting reports. Yet the competencies that matter most remain irreducibly human: problem formulation, measurement and design, causal identification, statistical and computational reasoning, ethics and accountability, and sensemaking. Drawing on Donoho's Greater Data Science framework, Nolan and Temple Lang's vision of computational literacy, and the McLuhan-Culkin insight that we shape our tools and thereafter our tools shape us, this paper traces the emergence of data science through three converging lineages: Tukey's intellectual vision of data analysis as a science, the commercial logic of surveillance capitalism that created industrial demand for data scientists, and the academic programs that followed. Mapping GAI's impact onto Donoho's six divisions of Greater Data Science shows that computing with data (GDS3) has been substantially automated, while data gathering, preparation, and exploration (GDS1) and science about data science (GDS6) still require essential human input. The educational implication is that data science curricula should focus on this human core while teaching students how to contribute effectively within iterative prompt-output-prompt cycles using retrieval-augmented generation, and that learning outcomes and assessments should explicitly evaluate reasoning and judgment.

arXiv:2603.17717v2 Announce Type: replace-cross Abstract: Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal contextual features, from the reprocessed CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019, with the same feature space. In the first task we use machine learning (ML) algorithms, with stratified cross validation, in order to prevent network attacks, with stability and reliability. In the second task we use adversarial learning algorithms to generate synthetic data, compare them with the real ones and evaluate their fidelity, utility and privacy using the SDV framework, f-divergences, distinguishability and non-parametric statistical tests. The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.

arXiv:2603.28786v1 Announce Type: cross Abstract: This study examined how student interns in Philippine higher education use intelligent tools during their OJT. Data were collected from 384 respondents using a structured questionnaire that asked about AI tool usage, task-specific applications, and perceptions of confidence, ethics, and support. Analysis of task-based usage identified four main purposes: productivity and report writing, communication and content drafting, technical assistance and code support, and independent task completion. ChatGPT was the most commonly used AI tool, followed by Quillbot, Canva AI, and Grammarly. Students reported moderate confidence in using AI and applied these tools selectively and ethically during OJT tasks. This indicate that AI tools assist student interns in various OJT activities related to work-readiness. The study suggests that higher education programs include AI literacy and onboarding. Clear policies and fair access to AI tools are important to support responsible use and prepare students for future careers.

arXiv:2509.20702v2 Announce Type: replace-cross Abstract: Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to date focus on gene-level information. We present one of the first systematic frameworks to generate genetic variant-level embeddings across the entire human genome. Using curated annotations from FAVOR, ClinVar, and the GWAS Catalog, we construct functional text descriptions for 8.9 billion possible variants and generated embeddings at three scales: 1.5 million HapMap3/MEGA variants, 90 million imputed UK Biobank (UKB) variants, and 9 billion all possible variants. Embeddings were produced using general purpose models including both OpenAI's text-embedding-3-large and the open-source Qwen3-Embedding-0.6B models. Baseline quality control experiments demonstrate high predictive accuracy for variant-level properties, validating the embeddings as structured representations of genomic variation. We further apply them to real-world embedding-augmented genetic risk predictions that demonstrate the performance of using LLM embeddings in polygenic risk score (PRS) style predictions over the UK Biobank cohort data. These resources, publicly available on Hugging Face, provide a foundation for advancing large-scale genomic discovery and precision medicine.

arXiv:2603.23184v1 Announce Type: cross Abstract: Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection costs. In this work, we study \textit{implicit reward modeling} -- learning reward models from implicit human feedback (e.g., clicks and copies) -- as a cost-effective alternative. We identify two fundamental challenges in implicit reward modeling: (1) Implicit preference data lacks definitive negative samples, which makes standard positive-negative classification methods inapplicable; (2) Implicit preference data suffers from user preference bias, where different responses have different propensities to elicit user feedback actions, which exacerbates the difficulty of distinguishing definitive negative samples. To address these challenges, we propose ImplicitRM, which aims to learn unbiased reward models from implicit preference data. ImplicitRM stratifies training samples into four latent groups via a stratification model. Building on this, it derives a learning objective through likelihood maximization, which we prove is theoretically unbiased, effectively resolving both challenges. Experiments demonstrate that ImplicitRM learns accurate reward models across implicit preference datasets. Code is available on our project website.

arXiv:2603.23322v1 Announce Type: cross Abstract: Android's Earthquake Alert (AEA) system provided timely early warnings to millions during the Mw 6.2 Marmara Ereglisi, T\"urkiye earthquake on April 23, 2025. This event, the largest in the region in 25 years, served as a critical real-world test for smartphone-based Earthquake Early Warning (EEW) systems. The AEA system successfully delivered alerts to users with high precision, offering over a minute of warning before the strongest shaking reached urban areas. This study leveraged Large Language Models (LLMs) to analyze more than 500 public social media posts from the X platform, extracting 42 distinct attributes related to user experience and behavior. Statistical analyses revealed significant relationships, notably a strong correlation between user trust and alert timeliness. Our results indicate a distinction between engineering and the user-centric definition of system accuracy. We found that timeliness is accuracy in the user's mind. Overall, this study provides actionable insights for optimizing alert design, public education campaigns, and future behavioral research to improve the effectiveness of such systems in seismically active regions.

arXiv:2302.10426v3 Announce Type: replace Abstract: Trustworthy process monitoring seeks to build an accurate and interpretable monitoring framework, which is critical for ensuring the safety of energy conversion plant (ECP) that operates under extreme working conditions such as high pressure and temperature. Contemporary self-attentive models, however, fall short in this domain for two main reasons. First, they rely on step-wise correlations that fail to involve physically meaningful semantics in ECP logs, resulting in suboptimal accuracy and interpretability. Second, attention matrices are frequently cluttered with spurious correlations that obscure physically meaningful ones, further impeding effective interpretation. To overcome these issues, we propose AttentionMixer, a framework aimed at improving both accuracy and interpretability of existing methods and establish a trustworthy ECP monitoring framework. Specifically, to tackle the first issue, we employ a spatial adaptive message passing block to capture variate-wise correlations. This block is coupled with a temporal adaptive message passing block through an \textit{mixing} operator, yielding a multi-faceted representation of ECP logs accounting for both step-wise and variate-wise correlations. Concurrently, to tackle the second issue, we employ a sparse message passing regularizer to filter out spurious correlations. We validate the efficacy of AttentionMixer using two real-world datasets from the radiation monitoring network for Chinese nuclear power plants.

arXiv:2508.01920v2 Announce Type: replace Abstract: Identifying causal interactions in complex dynamical systems is a fundamental challenge across the computational sciences. Existing functional connectivity methods capture correlations but not causation. While addressing directionality, popular causal inference tools such as Granger causality and the Peter-Clark algorithm rely on restrictive assumptions that limit their applicability to high-resolution time-series data, such as the large-scale recordings now standard in neuroscience. Here, we introduce CITS (Causal Inference in Time Series), a nonparametric framework for inferring statistically causal structure from multivariate time series. CITS models dynamics using a structural causal model of arbitrary Markov order and statistical tests for lagged conditional independence. We prove consistency under mild assumptions and demonstrate superior accuracy over state-of-the-art baselines across simulated linear, nonlinear, and recurrent neural network benchmarks. Applying CITS to large-scale neuronal recordings from the mouse visual cortex, thalamus, and hippocampus, we uncover stimulus-specific causal pathways and inter-regional hierarchies that align with known anatomy while revealing new functional insights. We further highlight CITS ability in accurately identifying conditional dependencies within small inferred neuronal motifs. These results establish CITS as a theoretically grounded and empirically validated method for discovering interpretable statistically causal networks in neural time series. Beyond neuroscience, the framework is broadly applicable to causal discovery in complex temporal systems across domains.

arXiv:2602.22758v2 Announce Type: replace Abstract: We decompose physician disagreement in the HealthBench medical AI evaluation dataset to understand where variance resides and what observable features can explain it. Rubric identity accounts for 15.8% of met/not-met label variance but only 3.6-6.9% of disagreement variance; physician identity accounts for just 2.4%. The dominant 81.8% case-level residual is not reduced by HealthBench's metadata labels (z = -0.22, p = 0.83), normative rubric language (pseudo R^2 = 1.2%), medical specialty (0/300 Tukey pairs significant), surface-feature triage (AUC = 0.58), or embeddings (AUC = 0.485). Disagreement follows an inverted-U with completion quality (AUC = 0.689), confirming physicians agree on clearly good or bad outputs but split on borderline cases. Physician-validated uncertainty categories reveal that reducible uncertainty (missing context, ambiguous phrasing) more than doubles disagreement odds (OR = 2.55, p

arXiv:2603.02616v1 Announce Type: cross Abstract: Structural heart disease (SHD) is a prevalent condition with many undiagnosed cases, and early detection is often limited by the high cost and accessibility constraints of echocardiography (ECHO). Recent studies show that artificial intelligence (AI)-based analysis of electrocardiograms (ECGs) can detect SHD, offering a scalable alternative. However, existing methods are fully black-box models, limiting interpretability and clinical adoption. To address these challenges, we propose an interpretable and effective framework that integrates clinically meaningful ECG foundation-model predictors within a generalized additive model, enabling transparent risk attribution while maintaining strong predictive performance. Using the EchoNext benchmark of over 80,000 ECG-ECHO pairs, the method demonstrates relative improvements of +0.98% in AUROC, +1.01% in AUPRC, and +1.41% in F1 score over the latest state-of-the-art deep-learning baseline, while achieving slightly better performance even with only 30% of the training data. Subgroup analyses confirm robust performance across heterogeneous populations, and the estimated entry-wise functions provide interpretable insights into the relationships between risks of traditional ECG diagnoses and SHD. This work illustrates a complementary paradigm between classical statistical modeling and modern AI, offering a pathway to interpretable, high-performing, and clinically actionable ECG-based SHD screening.

arXiv:2512.20363v2 Announce Type: replace-cross Abstract: Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $\alpha$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew.