Classification

Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematically studied. We evaluated the cross-dataset generalization of existing ML/DL methods and assessed LLMs with multiple prompting strategies on five datasets; the best prompting strategy combined in-context examples with course-specific action verbs. Supervised ML/DL models degraded substantially on unseen datasets, whereas LLMs were more stable, suggesting a robust alternative across diverse educational contexts. Based on the best prompting strategy, we also presented a lightweight UI that supports instructors in automatically classifying large question banks; a usability study indicated low workload and high usability.

Automatic bacterial colony counting is a highly sought-after technology in modern biological laboratories because it eliminates manual counting effort. Previous work has observed that MicrobiaNet, currently the best-performing cardinality classification model for colony counting, has difficulty distinguishing colonies of three or more individuals. However, it is unclear if this is due to properties of the data together with inherent characteristics of the MicrobiaNet model. By analysing MicrobiaNet with explainable artificial intelligence (XAI), we demonstrate that XAI can provide insights into how data properties constrain cardinality classification performance in colony counting. Our results show that high visual similarity across classes is the key issue hindering further performance improvement, revising prior assertions about MicrobiaNet. These findings suggest future work should focus on models that explicitly incorporate visual similarity or explore density estimation approaches, with broader implications for neural network classifiers trained on imbalanced datasets.

In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from the double-labeling problem, all are trained to perfection.

We introduce LegalBench-BR, the first public benchmark for evaluating language models on Brazilian legal text classification. The dataset comprises 3,105 appellate proceedings from the Santa Catarina State Court (TJSC), collected via the DataJud API (CNJ) and annotated across five legal areas through LLM-assisted labeling with heuristic validation. On a class-balanced test set, BERTimbau-LoRA, updating only 0.3% of model parameters, achieves 87.6% accuracy and 0.87 macro-F1 (+22pp over Claude 3.5 Haiku, +28pp over GPT-4o mini). The gap is most striking on administrativo (administrative law): GPT-4o mini scores F1 = 0.00 and Claude 3.5 Haiku scores F1 = 0.08 on this class, while the fine-tuned model reaches F1 = 0.91. Both commercial LLMs exhibit a systematic bias toward civel (civil law), absorbing ambiguous classes rather than discriminating them, a failure mode that domain-adapted fine-tuning eliminates. These results demonstrate that general-purpose LLMs cannot substitute for domain-adapted models in Brazilian legal classification, even when the task is a simple 5-class problem, and that LoRA fine-tuning on a consumer GPU closes the gap at zero marginal inference cost. We release the full dataset, model, and pipeline to enable reproducible research in Portuguese legal NLP.

The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications predict selective prediction performance. Twenty frontier LLMs from seven families were evaluated on 524 items across six cognitive tracks. Valid models show mean Type 2 AUROC = .624 (SD = .048). Invalid models show mean AUROC = .357 (SD = .231). Cohen's d = 2.81, p = .002. The tiers order monotonically: Invalid (.357) < Indeterminate (.554) < Valid (.624). Split-half cross-validation yields median d = 1.77, P(d > 0) = 1.0 across 1,000 splits. The three-tier classification accounts for 47% of the variance in AUROC. DeepSeek-R1 drops from 85.3% accuracy at full coverage to 11.3% at 10% coverage. The screen predicts the criterion. For selective prediction, the screen matters.

We provide evidence that language models can detect, localize and, to a degree, verbalize the difference between a-semantic perturbations applied to their activations. More precisely, we either (a) apply dropout or (b) add Gaussian noise to them, at a target sentence. We then ask a multiple-choice question such as "Which of the previous sentences was perturbed?" or "Which perturbation was applied?". We test eight models from the Gemma, Llama, Mistral, Olmo, Qwen and Seed families, with sizes between 8B and 36B, all of which can easily detect and localize the perturbations, often with perfect accuracy. To investigate the mechanisms, we find that Olmo models develop this capacity during pre-training, and we rule out the hypothesis that perturbed sentences simply have lower log-likelihood. Notably, the zero-shot accuracy of Qwen3-32B and Qwen3.8-27B in identifying which perturbation was applied correlates with the perturbation strength. While this task proves hard for the remaining models, most of them can learn, when taught in context, to distinguish between dropout and Gaussian noise. Interestingly, Qwen3-32B and Qwen3.8-27B learn worse when supervised with wrong labels, again suggesting a prior towards the correct ones. Because dropout is used as a training-regularization technique, while Gaussian noise is sometimes added during inference, we discuss the possibility of a data-agnostic "training awareness" signal and the implications for AI safety.

The present study aims to investigate a cluster cleaning algorithm that is both computationally simple and capable of solving the PU classification when the SCAR condition is unsatisfied. A secondary objective of this study is to determine the robustness of the LassoJoint method to perturbations of the SCAR condition. In the first step of our algorithm, we obtain cleaning labels from 2-means clustering. Subsequently, we perform logistic regression on the cleaned data, assigning positive labels from the cleaning algorithm with additional true positive observations. The remaining observations are assigned the negative label. The proposed algorithm is evaluated by comparing 11 real data sets from machine learning repositories and a synthetic set. The findings obtained from this study demonstrate the efficacy of the clustering algorithm in scenarios where the SCAR condition is violated and further underscore the moderate robustness of the LassoJoint algorithm in this context.

Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a clinical concept -- is a recurring bottleneck in clinical quality measurement and phenotyping. A natural approach is to prompt a large language model (LLM) to generate the required codes directly, but structured clinical vocabularies are large, version-controlled, and not reliably memorized during pretraining. We propose Retrieval-Augmented Set Completion (RASC): retrieve the $K$ most similar existing value sets from a curated corpus to form a candidate pool, then apply a classifier to each candidate code. Theoretically, retrieve-and-select can reduce statistical complexity by shrinking the effective output space from the full vocabulary to a much smaller retrieved candidate pool. We demonstrate the utility of RASC on 11,803 publicly available VSAC value sets, constructing the first large-scale benchmark for this task. A cross-encoder fine-tuned on SAPBert achieves AUROC0.852 and value-set-level F10.298, outperforming a simpler three-layer Multilayer Perceptron (AUROC0.799, F10.250) and both reduce the number of irrelevant candidates per true positive from 12.3 (retrieval-only) to approximately 3.2 and 4.4 respectively. Zero-shot GPT-4o achieves value-set-level F1~0.105, with 48.6% of returned codes absent from VSAC entirely. This performance gap widens with increasing value set size, consistent with RASC's theoretical advantage. We observe similar performance gains across two other classifier model types, namely a cross-encoder initialized from pre-trained SAPBert and a LightGBM model, demonstrating that RASC's benefits extend beyond a single model class. The code to download and create the benchmark dataset, as well as the model training code is available at: https://github.com/mukhes3/RASC.

Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant portion of future traffic at near-zero marginal inference cost. The open questions are when the surrogate is reliable enough to deploy, what it handles versus defers, and how that boundary evolves as data accumulates. We introduce TRACER (Trace-based Adaptive Cost-Efficient Routing), an open-source system that trains ML surrogates on an LLM's own production traces and governs deployment through a parity gate: the surrogate is activated only when its agreement with the LLM exceeds a user-specified threshold α. To make the routing boundary transparent, TRACER generates interpretability artifacts describing which input regions the surrogate handles, where it plateaus, and why it defers. On a 77-class intent benchmark with a Sonnet 4.6 teacher, TRACER achieves 83-100% surrogate coverage depending on the quality target α; on a 150-class benchmark, the surrogate fully replaces the teacher. On a natural language inference task, the parity gate correctly refuses deployment because the embedding representation cannot support reliable separation. The system is available as open-source software.

Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners. When training data exhibits Markov dependence, as in time-series forecasting, reinforcement learning (RL) replay buffers, and spatial grids, this classical guarantee degrades in ways that existing theory does not fully quantify. We provide a minimax characterization of this phenomenon for discrete classification in a fixed-dimensional Markov setting, together with an adaptive algorithm that matches the rate on a graph-regular subclass. We first establish an information-theoretic lower bound for stationary, reversible, geometrically ergodic chains in fixed ambient dimension, showing that no measurable estimator can achieve excess classification risk better than $Ω(\sqrt{\Tmix/n})$. We then prove that, on the AR(1) witness subclass underlying the lower-bound construction, dependence-agnostic uniform bagging is provably suboptimal with excess risk bounded below by $Ω(\Tmix/\sqrt{n})$, exhibiting a $\sqrt{\Tmix}$ algorithmic gap. Finally, we propose adaptive spectral routing, which partitions the training data via the empirical Fiedler eigenvector of a dependency graph and achieves the minimax rate $\mathcal{O}(\sqrt{\Tmix/n})$ up to a lower-order geometric cut term on a graph-regular subclass, without knowledge of $\Tmix$. Experiments on synthetic Markov chains, 2D spatial grids, the 128-dataset UCR archive, and Atari DQN ensembles validate the theoretical predictions. Consequences for deep RL target variance, scalability via Nyström approximation, and bounded non-stationarity are developed as supporting material in the appendix.

Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications. Current ad-hoc confidence calibration methods attempt to fix this during training but face a fundamental trade-off: two-phase training methods achieve strong classification performance at the cost of training instability and poorer confidence calibration, while single-loss methods are stable but underperform in classification. This paper addresses and mitigates this stability-performance trade-off. We propose Socrates Loss, a novel, unified loss function that explicitly leverages uncertainty by incorporating an auxiliary unknown class, whose predictions directly influence the loss function and a dynamic uncertainty penalty. This unified objective allows the model to be optimized for both classification and confidence calibration simultaneously, without the instability of complex, scheduled losses. We provide theoretical guarantees that our method regularizes the model to prevent miscalibration and overfitting. Across four benchmark datasets and multiple architectures, our comprehensive experiments demonstrate that Socrates Loss consistently improves training stability while achieving more favorable accuracy-calibration trade-off, often converging faster than existing methods.

Fine-tuning a pretrained classifier leaves some samples reliably learned and others cycling between correct and incorrect. Curriculum learning, data pruning and dataset cartography assume that pattern is a property of the sample, untested. We record per-sample correctness at every epoch while fine-tuning ResNet-18 and DeiT-Small on an imbalanced retinal OCT dataset and CUB-200-2011, matching samples by image identity and holding the split fixed across seeds. Per-sample retention is reproducible: cross-run Spearman correlation of the fitted decay constant is 0.37 to 0.59 over ten seeds. It is architecture-specific: two runs of one backbone agree more than two backbones on identical data (0.45 and 0.59 within against 0.30 between on OCTDL). Loss after five frozen-backbone epochs predicts a different run's decay constant at 0.29 to 0.43. The Ebbinghaus exponential does not survive: monotone decay, the one shape it can represent, is 0.1% to 0.8% of samples, and on traces that do forget mean R-squared is negative in all four configurations. A power law and a free-asymptote variant fail on the same traces: the defect is monotonicity. Across five sampling arms with matched exposure, prioritisation ratios of 2.7x to 28x, and an online variant, none of 48 comparisons against uniform sampling survives Benjamini-Hochberg correction, though three seeds detect only about four accuracy points. A stable, cheap difficulty score does not buy generalisation through sampling. Patient-grouped splitting, the remedy for a leak reaching 76% to 78% of OCT test images, moves that dataset's headline metrics by less than their run-to-run spread.

The Model Context Protocol (MCP) is a new and emerging technology that extends the functionality of large language models, improving workflows but also exposing users to a new attack surface. Several studies have highlighted related security flaws, but MCP attack detection remains underexplored. To address this research gap, this study develops and evaluates a range of supervised machine learning approaches, including both traditional and deep-learning models. We evaluated the systems on the detection of malicious MCP tool descriptions in two scenarios: (1) a binary classification task distinguishing malicious from benign tools, and (2) a multiclass classification task identifying the attack type while separating benign from malicious tools. In addition to the machine learning models, we compared a rule-based approach that serves as a baseline. The results indicate that several of the developed models achieved 100% F1-score on the binary classification task. In the multiclass scenario, the SVC and BERT models performed best, achieving F1 scores of 90.56% and 88.33%, respectively. Confusion matrices were also used to visualize the full distribution of predictions often missed by traditional metrics, providing additional insight for selecting the best-fitting solution in real-world scenarios. This study presents an addition to the MCP defence area, showing that machine learning models can perform exceptionally well in separating malicious and benign data points. To apply the solution in a live environment, a middleware was developed to classify which MCP tools are safe to use before execution, and block the ones that are not safe. Furthermore, the study shows that these models can outperform traditional rule-based solutions currently in use in the field.

We develop a high-precision classifier to measure artificial intelligence (AI) patents by fine-tuning PatentSBERTa on manually labeled data from the USPTO's AI Patent Dataset. Our classifier substantially improves the existing USPTO approach, achieving 97.0% precision, 91.3% recall, and a 94.0% F1 score, and it generalizes well to Chinese patents based on citation and lexical validation. Applying it to granted U.S. patents (1976-2023) and Chinese patents (2010-2023), we document rapid growth in AI patenting in both countries and broad convergence in AI patenting intensity and subfield composition, even as China surpasses the United States in recent annual patent counts. The organization of AI innovation nevertheless differs sharply: U.S. AI patenting is concentrated among large private incumbents and established hubs, whereas Chinese AI patenting is more geographically diffuse and institutionally diverse, with larger roles for universities and state-owned enterprises. For listed firms, AI patents command a robust market-value premium in both countries. Cross-border citations show continued technological interdependence rather than decoupling, with Chinese AI inventors relying more heavily on U.S. frontier knowledge than vice versa.

Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural networks empirically learn useful features, a principled account of what makes a representation "good" remains elusive. We study unsupervised categorization of transformations between pairs of inputs under algebraic constraints. Classical disentanglement favors mutually independent factors and fails when factors are coupled. Our prior Galois-theoretic approach decomposes a group via normal subgroups by learning a product of two transformations with one factor constrained to a normal subgroup, covering both commutative and non-commutative cases. That method, however, relied on auxiliary assumptions (e.g., motion and isometry restrictions) not required by decomposition theory, and ablations did not separate theory-based from auxiliary effects. We propose parameter division for a single transformation: we split its parameter into components, impose homomorphism constraints mapping the full transformation to one component, and identify the normal subgroup as the set of transformations when that component is fixed to the identity. This formulation drops the previous auxiliary assumptions and applies more broadly. We evaluate on image pairs involving rotation, translation, and scale; ablations show that group-decomposition constraints drive appropriate categorization.

Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to the size of the company registers, manual annotation is costly, and fine-tuning models with every update in industry classification schemes requires significant data collection. We replicate the manual expert verification by using existing or easily retrievable multimodal resources for industry classification. We present MONETA, the first multimodal industry classification benchmark with text (Website, Wikipedia, Wikidata) and geospatial sources (OpenStreetMap and satellite imagery). Our dataset enlists 1,000 businesses in Europe with 20 economic activity labels according to EU guidelines (NACE). Our training-free baseline reaches 62.10% and 74.10% with open and closed-source Multimodal Large Language Models (MLLM). We observe an increase of up to 22.80% with the combination of multi-turn design, context enrichment, and classification explanations. We will release our dataset and the enhanced guidelines.

Automotive engineering development increasingly relies on heterogeneous 3D data, including finite element (FE) models, body-in-white (BiW) representations, CAD geometry, and CFD meshes. At the same time, engineering teams face growing pressure to shorten development cycles, improve performance and accelerate innovation. Although artificial intelligence (AI) is increasingly explored in this domain, many current methods remain task-specific, difficult to interpret, and hard to reuse across development stages. This paper presents a practical graph learning framework for 3D engineering AI, in which heterogeneous engineering assets are converted into physics-aware graph representations and processed by Graph Neural Networks (GNNs). The framework is designed to support both classification and prediction tasks. The framework is validated on two automotive applications: CAE vibration mode shape classification and CFD aerodynamic field prediction. For CAE vibration mode classification, a region-aware BiW graph supports explainable mode classification across vehicle and FE variants under label scarcity. For CFD aerodynamic field prediction, a physics-informed surrogate predicts pressure and wall shear stress (WSS) across aerodynamic body shape variants, while symmetry preserving down sampling retains accuracy with lower computational cost. The framework also outlines data generation guidance that can help engineers identify which additional simulations or labels are valuable to collect next. These results demonstrate a practical and reusable engineering AI workflow for more trustworthy CAE and CFD decision support.

Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout sets available at training time. We address this by reframing nonstationary classification as time series prediction: rather than predicting from the current input alone, we condition the classifier on a sequence of historical labeled examples that extends beyond the training cutoff. To scale to large sequences, we introduce a learned discrete retrieval mechanism that samples relevant historical examples via input-dependent queries, trained end-to-end with the classifier using a score-based gradient estimator. This enables the full corpus of historical data to remain on an arbitrary filesystem during training and deployment. Experiments on synthetic benchmarks and Amazon Reviews '23 (electronics category) show improved robustness to distribution shift compared to standard classifiers, with VRAM scaling predictably as the length of the historical data sequence increases.

Reliable radar pulse classification is essential in Electromagnetic Warfare for situational awareness and decision support. Deep Neural Networks have shown strong performance in radar pulse and RF emitter recognition; however, on their own they struggle to efficiently learn new pulses and lack mechanisms for expressing predictive confidence. This paper integrates Uncertainty Quantification with Lifelong Learning to address both challenges. The proposed approach is an Evidential Lifelong Classifier (ELC), which models epistemic uncertainty using evidence theory. ELC is evaluated against a Bayesian Lifelong Classifier (BLC), which quantifies uncertainty through Shannon entropy. Both integrate Learn-Prune-Share to enable continual learning of new pulses and uncertainty-based selective prediction to reject unreliable predictions. ELC and BLC are evaluated on 2 synthetic radar and 3 RF fingerprinting datasets. Selective prediction based on evidential uncertainty improves recall by up to 46% at -20 dB SNR on synthetic radar pulse datasets, highlighting its effectiveness at identifying unreliable predictions in low-SNR conditions compared to BLC. These findings demonstrate that evidential uncertainty offers a strong correlation between confidence and correctness, improving the trustworthiness of ELC by allowing it to express ignorance.

Machine learning (ML) models have achieved strikingly high accuracies in spectroscopic classification tasks, often without a clear proof that those models used chemically meaningful features. Existing studies have linked these results to data preprocessing choices, noise sensitivity, and model complexity, but no unifying explanation is available so far. In this work, we show that these phenomena arise naturally from the intrinsic high dimensionality of spectral data. Using a theoretical analysis grounded in the Feldman-Hajek theorem and the concentration of measure, we show that even infinitesimal distributional differences, caused by noise, normalisation, or instrumental artefacts, may become perfectly separable in high-dimensional spaces. Through a series of specific experiments on synthetic and real fluorescence spectra, we illustrate how models can achieve near-perfect accuracy even when chemical distinctions are absent, and why feature-importance maps may highlight spectrally irrelevant regions. We provide a rigorous theoretical framework, confirm the effect experimentally, and conclude with practical recommendations for building and interpreting ML models in spectroscopy.

The prevailing IR-threshold paradigm posits a positive correlation between imbalance ratio (IR) and oversampling effectiveness, yet this assumption remains empirically unsubstantiated through controlled experimentation. We conducted 12 controlled experiments (N > 100 dataset variants) that systematically manipulated IR while holding data characteristics (class separability, cluster structure) constant via algorithmic generation of Gaussian mixture datasets. Two additional validation experiments examined ceiling effects and metric-dependence. All methods were evaluated on 17 real-world datasets from OpenML. Upon controlling for confounding variables, IR exhibited a weak to moderate negative correlation with oversampling benefits. Class separability emerged as a substantially stronger moderator, accounting for significantly more variance in method effectiveness than IR alone. We propose a 'Context Matters' framework that integrates IR, class separability, and cluster structure to provide evidence-based selection criteria for practitioners.

Government agencies must register, classify and route every citizen appeal within statutory time limits, and much of this work is still done by hand. We describe AI Appeals Processor, a classification and routing component deployed in a CPU-only government environment, and report what its evaluation and deployment taught us. On 10,000 real Russian-language appeals from a cross-domain dataset, we compare Bag-of-Words and TF-IDF with SVM, fastText, Word2Vec+LSTM and multilingual BERT on a three-way appeal-type task. On a held-out test set of 1,500 appeals, BERT reaches 82% accuracy and Word2Vec+LSTM 78%, against 67% for individual operators measured on an expert-adjudicated gold standard. We deployed the LSTM: in a workflow where an operator verifies every prediction, its lower training cost made frequent retraining on operator-verified labels practical, while the four-point accuracy gap did not change the operator's task. End-to-end handling time fell by 53-56% across four appeal-length bands (unweighted mean 22.5 to 10.25 minutes); model inference takes under two seconds of this. Most residual errors trace to the label taxonomy rather than the model: the statutory definitions of complaints and applications overlap, and many appeals carry two intents. A post-deployment audit of production classifications, made after several retraining cycles by operators who saw the assigned category, judged more than 95% correct; we explain why this figure is not comparable with the test-set result.

We construct algorithms with optimal error for learning with adversarial noise. The overarching theme of this work is that the use of randomized hypotheses can substantially improve upon the best error rates achievable with deterministic hypotheses. - For $η$-rate malicious noise, we show the optimal error is $\frac{1}{2} \cdot η/(1-η)$, improving on the optimal error of deterministic hypotheses by a factor of $1/2$. This answers an open question of Cesa-Bianchi et al. (JACM 1999) who showed randomness can improve error by a factor of $6/7$. - For $η$-rate nasty noise, we show the optimal error is $\frac{3}{2} \cdot η$ for distribution-independent learners and $η$ for fixed-distribution learners, both improving upon the optimal $2 η$ error of deterministic hypotheses. This closes a gap first noted by Bshouty et al. (Theoretical Computer Science 2002) when they introduced nasty noise and reiterated in the recent works of Klivans et al. (NeurIPS 2025) and Blanc et al. (SODA 2026). - For $η$-rate agnostic noise and the closely related nasty classification noise model, we show the optimal error is $η$, improving upon the optimal $2η$ error of deterministic hypotheses. All of our learners have sample complexity linear in the VC-dimension of the concept class and polynomial in the inverse excess error. All except for the fixed-distribution nasty noise learner are time efficient given access to an oracle for empirical risk minimization.

This paper presents a systematic, cost-aware evaluation of large language models (LLMs) for receipt-item categorisation within a production-oriented classification framework. We compare four instruction-tuned models available through AWS Bedrock: Claude 3.7 Sonnet, Claude 4 Sonnet, Mixtral 8x7B Instruct, and Mistral 7B Instruct. The aim of the study was (1) to assess performance across accuracy, response stability, and token-level cost, and (2) to investigate what prompting methods, zero-shot or few-shot, are especially appropriate both in terms of accuracy and in terms of incurred costs. Results of our experiments demonstrated that Claude 3.7 Sonnet achieves the most favourable balance between classification accuracy and cost efficiency.

Early detection of highly pathogenic avian influenza (HPAI) and endemic poultry diseases is critical for global food security. While computer vision models excel at classifying diseases from fecal imaging, deploying these systems at scale is bottlenecked by farm data privacy concerns and institutional data silos. Furthermore, existing open-source agricultural datasets frequently suffer from severe, undocumented data contamination. In this paper, we introduce $\textbf{FecalFed}$, a privacy-preserving federated learning framework for poultry disease classification. We first curate and release $\texttt{poultry-fecal-fl}$, a rigorously deduplicated dataset of 8,770 unique images across four disease classes, revealing and eliminating a 46.89$\%$ duplication rate in popular public repositories. To simulate realistic agricultural environments, we evaluate FecalFed under highly heterogeneous, non-IID conditions (Dirichlet $α=0.5$). While isolated single-farm training collapses under this data heterogeneity, yielding only 64.86$\%$ accuracy, our federated approach recovers performance without centralizing sensitive data. Specifically, utilizing server-side adaptive optimization (FedAdam) with a Swin-Small architecture achieves 90.31$\%$ accuracy, closely approaching the centralized upper bound of 95.10%. Furthermore, we demonstrate that an edge-optimized Swin-Tiny model maintains highly competitive performance at 89.74$\%$, establishing a highly efficient, privacy-first blueprint for on-farm avian disease monitoring.

Side-scan sonar (SSS) mine classification is a challenging maritime vision problem characterized by extreme data scarcity and a large domain gap from natural images. While self-supervised learning (SSL) and general-purpose vision foundation models have shown strong performance in general vision and several specialized domains, their use in SSS remains largely unexplored. We present Mine-JEPA, the first in-domain SSL pipeline for SSS mine classification, using SIGReg, a regularization-based SSL loss, to pretrain on only 1,170 unlabeled sonar images. In the binary mine vs. non-mine setting, Mine-JEPA achieves an F1 score of 0.935, outperforming fine-tuned DINOv3 (0.922), a foundation model pretrained on 1.7B images. For 3-class mine-like object classification, Mine-JEPA reaches 0.820 with synthetic data augmentation, again outperforming fine-tuned DINOv3 (0.810). We further observe that applying in-domain SSL to foundation models degrades performance by 10--13 percentage points, suggesting that stronger pretrained models do not always benefit from additional domain adaptation. In addition, Mine-JEPA with a compact ViT-Tiny backbone achieves competitive performance while using 4x fewer parameters than DINOv3. These results suggest that carefully designed in-domain self-supervised learning is a viable alternative to much larger foundation models in data-scarce maritime sonar imagery.

Next-generation radio astronomy surveys are delivering millions of resolved sources, yet scalable morphology analysis remains difficult across heterogeneous telescopes and imaging pipelines. We present STRADAViT, a self-supervised continued-pretraining framework for learning transferable radio-astronomy encoders from Vision Transformer (ViT) backbones. It combines mixed-survey data curation, radio astronomy-aware training-view generation, and a ViT-MAE-initialized encoder family with optional register tokens. It supports reconstruction-only, contrastive-only, and two-stage branches. Our pretraining dataset comprises 512x512 radio astronomy cutouts drawn from four complementary sources (MeerKAT, ASKAP, LOFAR/LoTSS, and SKA SDC1 simulated data). We evaluate transfer with linear probing (LP) and fine-tuning (FT) on three morphology benchmarks spanning binary and multi-class settings (MiraBest, LoTSS DR2, and Radio Galaxy Zoo). An exploratory three-fold ablation grid guides selection of a register-based two-stage checkpoint using a fixed cross-dataset criterion. Across subsequent 15-seed paired downstream evaluations on fixed partitions, this checkpoint improves linear-probe Macro-F1 over its ViT-MAE initialization on all three benchmarks and improves fine-tuning on MiraBest and RGZ DR1, while LoTSS DR2 fine-tuning declines; all six differences remain statistically supported after Holm correction. A parallel DINOv2 experiment yields mixed adaptation effects: the procedure transfers, but the benefit is not uniform. STRADAViT thus improves frozen ViT representations while retaining clear dataset-dependent limitations and remaining below task-specialized methods on standard MiraBest classification.

Label-scarce visual classification under decentralized and heterogeneous data is a fundamental challenge in pattern recognition, especially when sites exhibit partially overlapping class sets. While self-supervised federated learning (SSFL) offers a promising solution, existing studies commonly assume the same data heterogeneity pattern throughout pre-training and fine-tuning. Moreover, current partitioning schemes often fail to generate pure partially class-disjoint data settings, limiting controllable simulation of real-world label-space heterogeneity. In this work, we introduce SSFL for diatom classification as a representative real-world instance and systematically investigate stage-specific data heterogeneity. We study cross-site variation in unlabeled data volume during pre-training and label-space misalignment during downstream fine-tuning. To study the latter in a controllable setting, we propose PreDi, a partitioning scheme that disentangles label-space heterogeneity into two orthogonal dimensions, namely class Prevalence and class-set size Disparity, enabling separate analysis of their effects. Guided by the resulting insights, we further propose PreP-WFL (Prevalence-based Personalized Weighted Federated Learning) to adaptively strengthen rare-class representations in low-prevalence scenarios. Extensive experiments show that SSFL consistently outperforms local-only training under both homogeneous and heterogeneous settings. The pronounced heterogeneity in unlabeled data volume is associated with improved representation pre-training, whereas under label-space heterogeneity, prevalence dominates performance and disparity has a smaller effect. PreP-WFL effectively mitigates this degradation, with gains increasing as prevalence decreases. These findings provide a mechanistic basis for characterizing label-space heterogeneity in decentralized recognition systems.

LLM API calls have become a standard programming primitive, but they create a program boundary that disrupts traditional dataflow analysis. A runtime value may be inserted into a natural-language prompt through a template placeholder, transformed opaquely by the LLM, and returned as code, JSON, or text consumed by downstream logic. Existing analyses such as taint analysis and program slicing require a dataflow summary that describes how a callee maps inputs to outputs; an LLM call provides no such summary, breaking analysis at what we call the NL/PL boundary. We introduce PRISM, the first reachability model for this boundary. PRISM abstracts the missing dataflow summary of an LLM call as placeholder-to-output reachability. Because the LLM's internal transformation is opaque, the only observable signal is the input-output relationship, which spans an unbounded range of behaviors. PRISM therefore uses a finite taxonomy grounded in quantitative information flow theory. It classifies placeholder-output behavior into 25 labels along two dimensions: information preservation and output modality. Each label yields a reachability predicate for a placeholder. The model is sound with respect to its labeling, with residual error bounded empirically. PRISM is dependable and effective. Independent models and human annotators assign its labels consistently (Fleiss' kappa >= 0.72), and the labels cover 8,119 real-world pairs, leaving no pair unclassifiable; the Good-Turing discovery probability is 0.09%. For taint analysis, PRISM nearly doubles the conservative baseline and outperforms a direct LLM baseline, achieving F1 = 81.7%. Across six real OpenClaw CVEs, it detects every vulnerable flow and confirms every patch (F1 = 100%). In backward slicing, it removes about a quarter of irrelevant code without discarding any true dependency.

Learning from quantum data using classical machine learning models has emerged as a promising paradigm toward realizing quantum advantages. Despite extensive analyses on their performance, clean and fully labeled quantum data from the target domain are often unavailable in practical scenarios, forcing models to be trained on data collected under conditions that differ from those encountered at deployment. This mismatch highlights the need for new approaches beyond the common assumptions of prior work. In this work, we address this issue by employing an unsupervised domain adaptation framework for learning from imperfect quantum data. Specifically, by leveraging classical representations of quantum states obtained via classical shadows, we perform unsupervised domain adaptation entirely within a classical computational pipeline once measurements on the quantum states are executed. We numerically evaluate the framework on quantum phases of matter and entanglement classification tasks under realistic domain shifts. Across both tasks, our method outperforms source-only non-adaptive baselines and target-only unsupervised learning approaches, demonstrating the practical applicability of domain adaptation to realistic quantum data learning.