The Inference Report

Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major budget-allocation problem rather than a routine preprocessing step. We formulate scaling-law fitting as budget-aware sequential experimental design: given a finite pool of runnable experiments with heterogeneous costs, choose which runs to execute so as to maximize extrapolation accuracy in a high-cost target region. We then propose an uncertainty-aware method for sequentially allocating experimental budget toward the runs most useful for target-region extrapolation. Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total training budget. Our code is available at https://github.com/PlanarG/active-sl.

The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents spend the tokens? (2) Which models are more token-efficient? and (3) Can agents predict their token usage before task execution? In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks. We analyze trajectories from eight frontier LLMs on SWE-bench Verified and evaluate models' ability to predict their own token costs before task execution. We find that: (1) agentic tasks are uniquely expensive, consuming 1000x more tokens than code reasoning and code chat, with input tokens rather than output tokens driving the overall cost; (2) token usage is highly variable and inherently stochastic: runs on the same task can differ by up to 30x in total tokens, and higher token usage does not translate into higher accuracy; instead, accuracy often peaks at intermediate cost and saturates at higher costs; (3) models vary substantially in token efficiency: on the same tasks, Kimi-K2 and Claude-Sonnet-4.5, on average, consume over 1.5 million more tokens than GPT-5; (4) task difficulty rated by human experts only weakly aligns with actual token costs, revealing a fundamental gap between human-perceived complexity and the computational effort agents actually expend; and (5) frontier models fail to accurately predict their own token usage (with weak-to-moderate correlations, up to 0.39) and systematically underestimate real token costs. Our study offers new insights into the economics of AI agents and can inspire future research in this direction.

Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, including simulated interviews with asylum seekers. While many works highlight the new potential applications of LLMs, there are risks of LLMs encoding and perpetuating harmful biases about non-dominant communities across the globe. To better evaluate and mitigate such harms, more research examining how LLMs portray diverse individuals is needed. In this work, we study how national origin identities are portrayed by widely-adopted LLMs in response to open-ended narrative generation prompts. Our findings demonstrate the presence of persistent representational harms by national origin, including harmful stereotypes, erasure, and one-dimensional portrayals of Global Majority identities. Minoritized national identities are simultaneously underrepresented in power-neutral stories and overrepresented in subordinated character portrayals, which are over fifty times more likely to appear than dominant portrayals. The degree of harm is amplified when US nationality cues (e.g., ``American'') are present in input prompts. Notably, we find that the harms we identify cannot be explained away via sycophancy, as US-centric biases persist even when replacing US nationality cues with non-US national identities in the prompts. Based on our findings, we call for further exploration of cultural harms in LLMs through methodologies that center Global Majority perspectives and challenge the uncritical adoption of US-based LLMs for the classification, surveillance, and misrepresentation of the majority of our planet.

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate.

The emergence of large language models has enabled vibe coding, a natural language approach to programming in which users describe intent and AI generates or revises code, potentially broadening access to programming while preserving meaningful learning outcomes. We investigate its educational value through a month-long online hackathon that welcomed participants from multiple countries, ranging from complete beginners to experienced developers. The hackathon offered three tracks with increasing technical demands. Spark emphasized basic frontend functionality and dynamic features such as buttons, forms, and API calls. Build required backend or database integration. Launch targeted production ready web applications, including deployment. Participants were required to develop projects using only LLM generated code without manual edits and submitted complete chat histories, source code, demo videos, and functionality reports. We assessed educational effectiveness with a mixed methods design that combined standardized project evaluations across functionality, user interface and user experience design, impact, prompt quality, and code readability, along with post-hackathon surveys of perceived learning outcomes and thematic analysis of open-ended feedback. Our findings describe how participants with different backgrounds engage with vibe coding as task complexity increases, how the no manual editing constraint shapes prompting and debugging practices, and what these patterns imply for integrating AI assisted development into programming education and competitive learning environments.

ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structural properties of the network, i.e., the number of binary variables in associated formulations and the tightness of the continuous LP relaxation. These properties are determined during training, yet standard training objectives (prediction loss with classical weight regularization) offer no mechanism to directly control them. This work studies training regularizers that directly target downstream MILP tractability. Specifically, we propose simple bound-based regularizers that penalize the big-M constants of MILP formulations and/or the number of unstable neurons. Moreover, we introduce an LP relaxation gap regularizer that explicitly penalizes the per-sample gap of the continuous relaxation at training points. We derive its associated gradient and provide an implementation from LP dual variables without custom automatic differentiation tools. We show that combining the above regularizers can approximate the full total derivative of the LP gap with respect to the network parameters, capturing both direct and indirect sensitivities. Experiments on non-convex benchmark functions and a two-stage stochastic programming problem with quantile neural network surrogates demonstrate that the proposed regularizers can reduce MILP solve times by up to four orders of magnitude relative to an unregularized baseline, while maintaining competitive surrogate model accuracy.

The plan existence problem asks, given a goal in the form of a formula in modal logic, an initial epistemic state (a pointed Kripke model), and a set of epistemic actions, whether there exists a sequence of actions that can be applied to reach the goal. We prove that even in the case where the preconditions of the epistemic actions have modal depth at most 1, and there are no postconditions, the plan existence problem is undecidable. The (un)decidability of this problem was previously unknown.

We investigate whether neural models trained exclusively on modern morphological data can recover cross-lingual lexical structure consistent with historical reconstruction. Using BantuMorph v7, a transformer over Bantu morphological paradigms, we analyze 14 Eastern and Southern Bantu languages, extract encoder embeddings for their noun and verb lemmas, and identify 728 noun and 1,525 verb cognate candidates shared across 5+ languages. Evaluating these candidates against established historical resources-the Bantu Lexical Reconstructions database (BLR3; 4,786 reconstructed Proto-Bantu forms) and the ASJP basic vocabulary-we confirm 10 of the top 11 noun candidates (90.9%) align with previously reconstructed Proto-Bantu forms, including *-ntU 'person' (8 languages), *gombe 'cow' (9 languages), and *mUn (9 languages). Extending to verbs, 12 verb cognates align with reconstructed Proto-Bantu roots, including *-bon- 'see' and *-jIm- 'stand', each attested across wide geographic ranges. Cross-model validation using an independent translation model (NLLB-600M) confirms these patterns: both models recover cognate clusters and phylogenetic groupings consistent with established Guthrie-zone classifications (p < 0.01). Cross-lingual noun class analysis reveals that all 13 productive classes maintain >0.83 cosine similarity across languages (within-class > between-class, p < 10^-9). Our dataset is restricted to Eastern and Southern Bantu, so we interpret these results as recovering shared Bantu lexical structure consistent with Proto-Bantu rather than definitively distinguishing Proto-Bantu retentions from later regional innovations.

We present a method for discovering morphological features in low-resource Bantu languages by combining cross-lingual transfer learning with unsupervised clustering. Applied to Giriama (nyf), a language with only 91 labeled paradigms, our pipeline discovers noun class assignments for 2,455 words and identifies two previously undocumented morphological patterns: an a- prefix variant for Class 2 (vowel coalescence - the merger of two adjacent vowels - of wa-, 95.1% consistency) and a contracted k'- prefix (98.5% consistency). External validation on 444 known Giriama verb paradigms confirms 78.2% lemmatization accuracy, while a v3 corpus expansion to 19,624 words (9,014 unique lemmas) achieves 97.3% segmentation and 86.7% lemmatization rates across all major word classes. Our ensemble of transfer learning from Swahili and unsupervised clustering, combined via weighted voting, exploits complementary strengths: transfer excels at cognate detection (leveraging ~60% vocabulary overlap) while clustering discovers language-specific innovations invisible to transfer. We release all code and discovered lexicons to support morphological documentation for low-resource Bantu languages.

Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking often achieve superior performance but are computationally prohibitive and prone to noise inherent in perplexity estimation. We propose Utility-Aligned Embeddings (UAE), a framework designed to merge these advantages into a practical, high-performance retrieval method. We formulate retrieval as a distribution matching problem, training a bi-encoder to imitate a utility distribution derived from perplexity reduction using a Utility-Modulated InfoNCE objective. This approach injects graded utility signals directly into the embedding space without requiring test-time LLM inference. On the QASPER benchmark, UAE improves retrieval Recall@1 by 30.59%, MAP by 30.16% and Token F1 by 17.3% over the strong semantic baseline BGE-Base. Crucially, UAE is over 180x faster than the efficient LLM re-ranking methods preserving competitive performance, demonstrating that aligning retrieval with generative utility yields reliable contexts at scale.

While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous representations, yet their performance lags behind verbalized CoT. We propose $\textbf{Abstract Chain-of-Thought}$, a discrete latent reasoning post-training mechanism in which the language model produces a short sequence of tokens from a reserved vocabulary in lieu of a natural language CoT, before generating a response. To make previously unseen ''abstract'' tokens useful, we introduce a policy iteration-style warm-up loop that alternates between (i.) bottlenecking from a verbal CoT via masking and performing supervised fine-tuning, and (ii.) self-distillation by training the model to generate abstract tokens from the prompt alone via constrained decoding with the codebook. After warm-up, we optimize the generation of abstract sequences with warm-started reinforcement learning under constrained decoding. Abstract-CoT achieves up to $11.6\times$ fewer reasoning tokens while demonstrating comparable performance across mathematical reasoning, instruction-following, and multi-hop reasoning, and generalizes across language model families. We also find an emergent power law distribution over the abstract vocabulary, akin to those seen in natural language, that evolves across the training phases. Our findings highlight the potential for post-training latent reasoning mechanisms that enable efficient inference through a learned abstract reasoning language.

Respiratory airflow signals provide critical insight into breathing mechanics, yet conventional analysis methods remain limited in their ability to characterize the internal structure of individual breaths. Traditional approaches treat airflow as a quasi-periodic signal and rely on global descriptors such as tidal volume or peak flow, obscuring sub-breath events that reflect neuromuscular coordination and compensatory breathing strategies. This study introduces a parametric framework for decomposing inspiratory airflow into a small number of time-localized components with explicit amplitude, onset time, and duration parameters. Unlike spectral or data-adaptive methods, the proposed approach employs physiologically grounded basis functions, Half-Sine, Gaussian, and Beta, to represent intrabreath waveform morphology through constrained nonlinear optimization. Evaluation across 8,276 breaths demonstrates high reconstruction accuracy (mean squared error $<$ 0.001 for four-component models) and robust parameter precision under moderate noise. Component-derived features describing sub-breath timing and coordination improved classification of cognitive fatigue states arising from cognitive-respiratory competition by up to 30.7% in Matthews correlation coefficient compared with classical respiratory metrics. These results establish that modeling airflow as a sum of parameterized, time-localized primitives provides an interpretable and precise foundation for quantifying intrabreath organization, compensatory breathing dynamics, and respiratory motor control adaptation under cognitive-respiratory dual-task demands.

Selecting a small, high-quality subset from a large corpus for fine-tuning is increasingly important as corpora grow to tens of millions of datapoints, making full fine-tuning expensive and often unnecessary. We propose CRAFT (Clustered Regression for Adaptive Filtering of Training data), a vectorization-agnostic selection method for training sequence-to-sequence models. CRAFT decomposes the joint source-target distribution and performs a two-stage selection: (i) match the validation source distribution through proportional budget allocation across k-means clusters, and (ii) within each source cluster, select training pairs whose target embeddings minimize a conditional expected distance derived from the validation target distribution. We prove that proportional cluster allocation bounds the continuous KL divergence between selected and validation distributions, with the residual controlled by cluster diameters. We evaluate CRAFT on English-Hindi translation by selecting training data from 33 million NLLB sentence pairs and fine-tuning mBART via LoRA. CRAFT achieves 43.34 BLEU, outperforming TSDS (41.21) by 2.13 points on the same candidate pool and encoder while completing selection over 40 times faster. With TF-IDF vectorization, the entire pipeline completes in under one minute on CPU. TAROT achieves 45.61 BLEU, but CRAFT completes selection in 26.86 seconds versus TAROT's 75.6 seconds, a 2.8 time speedup.

The increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado's AI Act. While existing research examines bias through technical or regulatory lenses, both perspectives overlook a fundamental challenge: modern AI hiring systems operate within complex supply chains where responsibility fragments across data vendors, model developers, platform providers, and deploying organizations. This paper investigates how these dependency chains complicate bias evaluation and accountability attribution. Drawing on literature review and regulatory analysis, we demonstrate that fragmented responsibilities create two critical problems. First, bias emerges from component interactions rather than isolated elements, yet proprietary configurations prevent integrated evaluation. A resume parser may function without bias independently but contribute to discrimination when integrated with specific ranking algorithms and filtering thresholds. Second, information asymmetries mean deploying organizations bear legal responsibility without technical visibility into vendor-supplied algorithms, while vendors control implementations without meaningful disclosure requirements. Each stakeholder may believe they are compliant; nevertheless, the integrated system may produce biased outcomes. Analysis of implementation ambiguities reveals these challenges in practice. We propose multi-layered interventions including system-level audits, vendor guidelines, continuous monitoring mechanisms, and documentation across dependency chains. Our findings reveal that effective governance requires coordinated action across technical, organizational, and regulatory domains to establish meaningful accountability in distributed development environments.

A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can obscure the contribution of individual documents, making attribution difficult and contributing to the ``lost-in-the-middle'' effect, where relevant information in long contexts is overlooked. Concatenation also scales poorly: computational cost grows quadratically with context length, a problem that becomes especially severe when the context includes visual data, as in visual question answering. Attempts to mitigate these issues by limiting context length can further restrict performance by preventing models from benefiting from the improved recall offered by deeper retrieval. We propose Bayesian Ensemble Retrieval-Augmented Generation (BERAG), along with Bayesian Ensemble Fine-Tuning (BEFT), as a RAG framework in which language models are conditioned on individual retrieved documents rather than a single combined context. BERAG treats document posterior probabilities as ensemble weights and updates them token by token using Bayes' rule during generation. This approach enables probabilistic re-ranking, parallel memory usage, and clear attribution of document contribution, making it well-suited for large document collections. We evaluate BERAG and BEFT primarily on knowledge-based visual question answering tasks, where models must reason over long, imperfect retrieval lists. The results show substantial improvements over standard RAG, including strong gains on Document Visual Question Answering and multimodal needle-in-a-haystack benchmarks. We also demonstrate that BERAG mitigates the ``lost-in-the-middle'' effect. The document posterior can be used to detect insufficient grounding and trigger deflection, while document pruning enables faster decoding than standard RAG.

Graph neural networks achieve strong node-classification accuracy, but their learned message passing entangles ego attributes, neighborhood smoothing, high-pass graph differences, class geometry, and classifier boundaries in an opaque representation. This obscures why a node is classified and what feature-level graph-learning mechanisms a dataset requires. We propose WG-SRC, a white-box signal-subspace probe for prediction and graph dataset diagnosis. WG-SRC replaces learned message passing with a fixed, named graph-signal dictionary of raw features, row-normalized and symmetric-normalized low-pass propagation, and high-pass graph differences. It combines Fisher coordinate selection, class-wise PCA subspaces, closed-form multi-alpha ridge classification, and validation-based score fusion, so prediction and analysis use explicit class subspaces, energy-controlled dimensions, and closed-form linear decisions. As a white-box graph-learning instrument, WG-SRC uses predictive performance to validate its diagnostics: across six node-classification datasets, the scaffold remains competitive with reproduced graph baselines and achieves positive average gain under aligned splits. Its atlas, produced by a predictor, decomposes behavior into raw-feature, low-pass, high-pass, class-geometric, and ridge-boundary components. These operational feature fingerprints distinguish low-pass-dominated Amazon graphs, mixed high-pass and class-geometrically complex Chameleon behavior, and raw- or boundary-sensitive WebKB graphs. As intrinsic classifier outputs rather than post-hoc explanations, these fingerprints provide post-evaluation guidance for later analysis and dataset-specific modification. Aligned mechanistic interventions support this guidance by indicating when high-pass blocks act as removable noise, when raw features should be preserved, and when ridge-type boundary correction matters.

Equivalence class partitioning is a well-established test design technique mandated by safety standards such as ISO~26262 for systematic testing of safety software. In industrial practice, however, its application to legacy undocumented embedded firmware is often hindered by incomplete or outdated functional specifications. This paper proposes a binary-level methodology for inferring output-oriented equivalence classes directly from compiled firmware, without relying on source-level annotations or external documentation. The approach combines control-flow reconstruction and guided symbolic execution to analyze individual functions and group execution paths according to indistinguishable observable behavior, including return values and output parameters. An optional post-processing step produces human-readable representations to support comprehension and documentation. The methodology is evaluated in an industrial automotive context through a practitioner-based study assessing correctness and interpretability. Results indicate strong alignment with expert expectations and a positive perception of readability and usefulness for supporting function understanding and test design. These findings demonstrate the feasibility and practical relevance of binary-level equivalence class inference for systematic testing of legacy undocumented safety-embedded software.

Batch processes are inherently transient and typically nonlinear, motivating nonlinear model predictive control (NMPC). However, adopting NMPC is hindered by the cost and unavailability of dynamic models. Thus, we propose to use Gaussian Processes (GP) in a model-learning NMPC scheme (GP-MLMPC) for batch processes. We initialize the GP-MLMPC using data from a single initial trajectory, e.g., from a PI controller. We iteratively apply the NMPC embedded with GPs to run batches and update the GP with new observations from each iteration, thereby achieving batch-wise improvements. Using uncertainty quantification from the GPs, we formulate chance constraints to enforce safe operation to the required confidence levels. We demonstrate our approach in \textit{silico} on a semi-batch polymerization reactor for tracking and economic objectives over durations of two hours, and the reactor temperature is constrained in a range of $\pm2^\circ C$ around its setpoint. After only four batch iterations, tracking error from the GP-MLMPC scheme converged to a reduction of $83\%$, compared to the initial trajectory. Furthermore, under an economic objective, the GP-MLMPC resulted in a 17-fold increase in final product mass by iteration 8, compared to the initial trajectory. In both cases, the resulting GP-MLMPC performance is on par with the full-model NMPC, which shows that the optimal controller can be learned by the approach. By collecting samples around the optimal trajectory, the GP-MLMPC remains sample-efficient across iterations and achieves quick convergence. Thus, the proposed GP-MLMPC scheme presents a promising data-efficient approach for the control of nonlinear batch processes without mechanistic knowledge.

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented, evaluation remains reliant on quantitative proxies whose alignment with human utility is unverified. In this work, we use a unified amortized framework to isolate semantic differences between eight Shapley variants under the low-latency constraints of operational risk workflows. We conduct a large-scale empirical evaluation across four risk datasets and a realistic fraud-detection environment involving professional analysts and 3,735 case reviews. Our results reveal a fundamental misalignment: standard quantitative metrics, such as sparsity and faithfulness, are decoupled from human-perceived clarity and decision utility. Furthermore, while no formulation improved objective analyst performance, explanations consistently increased decision confidence, signaling a critical risk of automation bias in high-stakes settings. These findings suggest that current evaluation proxies are insufficient for predicting downstream human impact, and we provide evidence-based guidance for selecting formulations and metrics in operational decision systems.

Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines, enabling the generation of multiple semantically equivalent query variants. However, executing the full pipeline for every reformulation is computationally expensive, motivating selective execution: can we identify the best query variant before incurring downstream retrieval and generation costs? We investigate Query Performance Prediction (QPP) as a mechanism for variant selection across ad-hoc retrieval and end-to-end RAG. Unlike traditional QPP, which estimates query difficulty across topics, we study intra-topic discrimination - selecting the optimal reformulation among competing variants of the same information need. Through large-scale experiments on TREC-RAG using both sparse and dense retrievers, we evaluate pre- and post-retrieval predictors under correlation- and decision-based metrics. Our results reveal a systematic divergence between retrieval and generation objectives: variants that maximize ranking metrics such as nDCG often fail to produce the best generated answers, exposing a "utility gap" between retrieval relevance and generation fidelity. Nevertheless, QPP can reliably identify variants that improve end-to-end quality over the original query. Notably, lightweight pre-retrieval predictors frequently match or outperform more expensive post-retrieval methods, offering a latency-efficient approach to robust RAG.

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and EvoCodeBench have been created to evaluate LLMs by requiring them to generate code from natural language requirements. However, in enterprise applications and team development, developers typically write code based on structured designs or specifications rather than raw natural language descriptions. This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate software development tasks. To address this gap, we propose RealBench, a repository-level code generation benchmark aligned with real-world industry software development practices. Each example includes both natural language requirements and UML diagrams as system design, matching how developers typically receive specifications. Based on the constructed benchmarks, we conduct a systematic evaluation of advanced LLMs' code generation capabilities when provided with structured system designs. The experimental results reveal key insights in current LLMs' capabilities for repo-level code generation aligned with real-world software development practices. First, we notice that regarding repo-level code generation, LLMs show much worse performance and there are significant performance gaps among LLMs. Second, LLMs are good at finding and creating modules defined in UML diagrams, but the quality of generated modules is often poor due to grammar and logic errors. Third, generating the entire repository at once is the best generation strategy on smaller repositories, while generating a complex repository with the module-by-module strategy works better compared to other strategies.

For the use case of comparing the performance of clustering algorithms whose output is a contingency table, a single performance metric for contingency tables is needed. Such a metric is vital for comparative performance analysis of clustering algorithms. A survey of publicly available literature did not show the presence of such a metric. Metrics do exist for vector pairs of truth values and predicted values, which are an alternative form of output of clustering algorithms. However, the metrics for vector pairs do not reveal the presence of detailed features that are apparent in contingency tables. This paper presents the Associativity Peakiness (AP) metric, which characterizes aspects of clustering algorithm performance that are critical for predicting a clustering algorithm's performance when deployed. The AP metric is analogous to measures of quality for confusion matrices that are outputs of supervised learning algorithms. This paper presents results from simulations in which 500 contingency tables were generated for multiple test scenarios. The results show that for the use case of evaluating clustering algorithms, the AP metric characterizes performance of contingency tables with higher dynamic range than publicly available metrics, and that it is computationally more efficient than comparable publicly available metrics.

Proponents of software verification suggest that code simplicity is linked to the effort to verify code, hypothesizing that formal verifiers produce fewer false positive warnings and require less manual intervention when analyzing simpler code. A recent meta-analysis study found empirical support for this hypothesis: a small correlation between the sum of verifier warnings and human-derived code comprehensibility metrics. Based on this finding, we conjectured that using the sum of verifier tool (verifier) warnings to represent program semantic information as an input feature to machine learning (ML) models for code comprehensibility prediction can enhance their performance, when combined with traditional syntactic and developer features. To test this conjecture, we performed a control-treatment experiment incorporating the verifier warning sum feature into machine learning models from the literature, and conducted a comparative analysis of their performance against models trained only on syntactic and developer features. We found no significant difference in the prediction performance of models with and without the warnings feature. Our findings suggest that while a correlation exists, the verifier warning sum offers limited discriminative power: combining syntactic and developer features is just as effective for predicting human-judged code comprehensibility.

Mutants support testing and debugging in two roles: (i) as test goals and (ii) as substitutes for real faults. Hard-to-kill mutants provide better guidance for test improvement, while realism is essential when mutants are used to simulate real bugs. Building on these roles, selective mutation for deep learning (DL) aims to reduce the cost of mutant generation and execution by choosing operator configurations that yield resistant and realistic mutants. However, the DL literature lacks a unified measure that captures both aspects. This study presents a probabilistic framework to quantify mutant quality along two complementary axes: resistance and realism. Resistance adapts the classical notion of hard-to-kill mutants to the DL setting using statistical killing probabilities, while realism is measured via the generalized Jaccard similarity between mutant and real-fault detectability patterns. The framework enables ranking and filtering of low-quality mutation-operator configurations without assuming a specific use case. We empirically evaluate the approach on four datasets of real DL faults. Three datasets (CleanML, DeepFD, and DeepLocalize) are used to estimate and select high-quality operator configurations, and the held-out defect4ML dataset is used for validation. Results show that quality-driven selection reduces the number of generated mutants by up to 55.6% while preserving typical levels of resistance and realism under baseline-aligned selection thresholds. These findings confirm that dual-objective selection can lower cost without compromising the usefulness of mutants for either role.

Malware development and detection have undergone significant changes in recent years as modern concepts, such as machine learning, have been used for both adversarial attacks and defense. Despite intensive research on Windows Portable Executable (PE) files, there is minimal work on Linux Executable and Linkable Format (ELF). In this work, we summarize the academic papers submitted in this field and develop a new adversarial malware generator for the ELF format. Using a variety of metrics, we thoroughly evaluated our generator and achieved an Evasion Rate of 67.74 % while changing the confidence of the malware detector by -0.50 in the mean case for the dataset used. In our approach, we chose MalConv as the target classifier. Using this classifier, we found that the most successful modifications used strings typical of benign files as a data source. We conducted a variety of experiments and concluded that the target classifier appears sensitive to strings at any location within the executable file.

Predicting customers' long-term revenue from sparse and irregular transaction data is central to marketing resource allocation in non-contractual settings, yet existing approaches face a trade-off. Traditional probabilistic customer base models deliver robust long-horizon forecasts by imposing strong structural assumptions, while flexible machine-learning models often require substantial training data and careful tuning. We propose a variational-autoencoder-based model that preserves the process-based likelihood of established attrition-transaction-spend models conditional on customer heterogeneity, but replaces the restrictive parametric mixing distribution with a flexible latent representation learned by encoder-decoder networks. The resulting approach (i) provides a single model for customer attrition, transactions and spending, (ii) remains reliable when contextual covariates are unavailable, and (iii) flexibly incorporates rich covariates and nonlinear effects when they are available. This design balances structural stability with the flexibility needed to capture complex purchase dynamics. Across multiple real-world datasets and prediction horizons, the proposed model improves upon the latest benchmarks. Businesses benefit directly, as a better assessment of customers' future revenues improves the efficiency of campaign targeting. For research, this work provides guidance on how to embed domain-specific models into the variational autoencoder framework, enabling flexible representation learning while retaining an econometrically meaningful process structure.

The Gaussian mixture model is widely used in unsupervised learning, owing to its simplicity and interpretability. However, a fundamental limitation of the classical Gaussian mixture model is that it forces each observation to belong to exactly one component. In many practical applications, such as genetics, social network analysis, and text mining, an observation may naturally belong to multiple components or exhibit partial membership in several latent components. To overcome this limitation, we propose the mixed membership sub-Gaussian model, which extends the classical Gaussian mixture framework by allowing each observation to belong to multiple components. This model inherits the interpretability of the classical Gaussian mixture model while offering greater flexibility for capturing complex overlapping structures. We develop an efficient spectral algorithm to estimate the mixed membership of each individual observation, and under mild separation conditions on the component centres, we prove that the estimation error of the per-individual membership vector can be made arbitrarily small with high probability. To our knowledge, this is the first work to provide a computationally efficient estimator with such a vanishing-error guarantee for a mixed-membership extension of the Gaussian mixture model. Extensive experimental studies demonstrate that our method outperforms existing approaches that ignore mixed memberships.

Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a more nuanced understanding of the types of modeling errors that speech encoder models make, and in particular the difference between the structure of embeddings for high-performance and low-performance SGs. This paper proposes a framework typifying two types of error that can occur in modeling phonemes in ASR systems: random error/high variance in phoneme embedding, vs systematic error/embedding bias. We find that training phoneme classification probes only on a single, typically disadvantaged SG, sometimes improves performance for that SG, which is evidence for the existence of SG-level bias in phoneme embeddings. On the other hand, we find that speakers and SGs with higher levels of phoneme variance are the same as those with worse phoneme prediction accuracy. We conclude that both types of error are present in phoneme embeddings and both are candidate causes for SG-level unfairness in ASR, though random error is likely a greater hindrance to fairness than systematic error. Furthermore, we find that finetuning encoder models using a fairness-enhancing algorithm (domain enhancing and adversarial training) changes neither the benefits of in-domain phoneme classification probe training, nor measured levels of random embedding error.

This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained across temporal windows on the EMBER2024 dataset, and drift is quantified by comparing extracted rule representations using feature importance, prediction agreement, activation stability, and coverage metrics. These metrics are correlated with both accuracy degradation and data distribution shift as complementary drift indicators. The approach is evaluated across six malware families using fixed-interval and clustering-based windowing in family-vs-benign and family-vs-family settings, and compared against RIPPER and Transcendent baselines. Results show that fixed two-month windowing with feature-level Pearson correlation is the most reliable configuration, being the only one where all family pairs produce positive drift-accuracy correlations. The methods are complementary - no single approach dominates across all pairs.

Joint measurements on multiple copies of a quantum state provide access to nonlinear observables such as $\operatorname{tr}(ρ^t)$, but whether replica number marks a sharp information-theoretic resource boundary has remained unclear. For every fixed order $t\ge 3$, existing protocols show that $\lceil t/2\rceil$ replicas already suffice for polynomial-sample estimation of $\operatorname{tr}(ρ^t)$, yet it has remained open whether one fewer replica must necessarily incur a sample-complexity barrier growing with the dimension. We prove that this is indeed the case in the sample/copy-access model with replica-limited joint measurements: any protocol restricted to $\lceil t/2\rceil-1$ replicas requires dimension-growing sample complexity, while $\lceil t/2\rceil$ replicas suffice by prior work. Thus the exact replica threshold for fixed-order pure moments is $\lceil t/2\rceil$. Equivalently, for fixed-order pure moments, one additional coherent replica is not merely useful but marks the exact threshold between polynomial-sample estimation and a dimension-growing regime in the replica-limited model. We further show that the same threshold law extends to a broad family of observable-weighted moments $\operatorname{tr}(Oρ^t)$, including Pauli observables and other observables with bounded operator norm and macroscopic trace norm. Coherent replica number therefore acts as a genuinely discrete resource for nonlinear quantum-state estimation.

This study investigates the structural organisation of Dante's Divina Commedia through a symbolic representation based on vowel-consonant (V/C) encoding. Modelling the resulting sequence as a four-state Markov chain yields a parsimonious index of graphemic memory, capturing the balance between persistence and alternation patterns. Across the poem, this index exhibits a slight but consistent increase from the Inferno to the Paradiso, indicating a directional shift in local dependency structure. Trigram-level analysis shows that this trend is driven by a restricted set of recurrent configurations, interpreted as graphemic probes linking the Markov representation to identifiable lexical environments in the text. These probes display distinct behaviours: configurations involving two transitions more frequently emerge across word boundaries, reflecting interactions between adjacent tokens, whereas configurations with fewer transitions are largely confined to intra-lexical structures. Part of the signal is further shaped by orthographic phenomena, particularly apostrophised forms, highlighting the role of writing conventions alongside phonological and lexical organisation. A complementary classification analysis identifies cantica-specific terms, providing lexical anchors through which graphemic probes can be related to the structure of the poem. This organisation is reflected not only in the separation of the three cantiche, but also in a continuous trajectory across the text. Overall, the results show that simple probabilistic models applied to symbolic text representations can uncover structured interactions between local dependencies, lexical distribution, orthographic encoding, and large-scale organisation, providing an interpretable framework for linking local symbolic dynamics to higher-level textual organisation.

Self-supervised learning in healthcare has largely relied on invariance-based objectives, which maximize similarity between different views of the same patient. While effective for static anatomy, this paradigm is fundamentally misaligned with clinical diagnosis, as it mathematically compels the model to suppress the transient pathological changes it is intended to detect. We propose a shift towards Action-Conditioned World Models that learn to simulate the dynamics of disease progression, or Event-Conditioned. Adapting the LeJEPA framework to physiological time-series, we define pathology not as a static label, but as a transition vector acting on a patient's latent state. By predicting the future electrophysiological state of the heart given a disease onset, our model explicitly disentangles stable anatomical features from dynamic pathological forces. Evaluated on the MIMIC-IV-ECG dataset, our approach outperforms fully supervised baselines on the critical triage task. Crucially, we demonstrate superior sample efficiency: in low-resource regimes, our world model outperforms supervised learning by over 0.05 AUROC. These results suggest that modeling biological dynamics provides a dense supervision signal that is far more robust than static classification. Source code is available at https://github.com/cljosegfer/lesaude-dynamics

Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sounding claims. These dynamics are not only global but also deeply local, manifesting in culturally specific controversies that require careful analysis. Motivated by this, we examine 100 YouTube transcripts that promote or debunk cow urine (gomutra) as a health remedy, focusing on rhetorical strategies such as appeals to authority, efficacy appeals, and conspiracy framing. We employ large language models (LLMs) including GPT-4, GPT-4o, GPT-4.1, GPT-5, Gemini 2.5 Pro, and Mistral Medium 3 to annotate transcripts using a 14-category taxonomy of persuasive tactics. Our analysis reveals that promoters predominantly rely on efficacy appeals and social proof, while debunkers emphasize authority and rebuttal. Human evaluation of a subset of annotations yielded 90.1\% inter-annotator agreement, confirming the reliability of our taxonomy and validation process. This work advances computational methods for misinformation analysis and demonstrates how LLMs can support large-scale studies of cultural discourse online.

Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to synthesize implementation logic alongside formal specifications that are subsequently proven correct by a mathematical verifier. However, the transition from informal natural language to precise formal specification remains an arduous task. Our work addresses this by providing the NaturalLanguage2VerifiedCode (NL2VC)-60 dataset: a collection of 60 complex algorithmic problems. We evaluate 11 randomly selected problem sets across seven open-weight LLMs using a tiered prompting strategy: contextless prompts, signature prompts providing structural anchors, and self-healing prompts utilizing iterative feedback from the Dafny verifier. To address vacuous verification, where models satisfy verifiers with trivial specifications, we integrate the uDebug platform to ensure functional validation. Our results show that while contextless prompting leads to near-universal failure, structural signatures and iterative self-healing facilitate a dramatic performance turnaround. Specifically, Gemma 4-31B achieved a 90.91\% verification success rate, while GPT-OSS 120B rose from zero to 81.82\% success with signature-guided feedback. These findings indicate that formal verification is now attainable for open-weight LLMs, which serve as effective apprentices for synthesizing complex annotations and facilitating high-assurance software development.

Recent advancements in large language models have led to significant improvements across various tasks, including mathematical reasoning, which is used to assess models' intelligence in logical reasoning and problem-solving. Models are evaluated on mathematical reasoning benchmarks by verifying the correctness of the final answer against a ground truth answer. A common approach for this verification is based on symbolic mathematics comparison, which fails to generalize across diverse mathematical representations and solution formats. In this work, we offer a robust and flexible alternative to rule-based symbolic mathematics comparison. We propose an LLM-based evaluation framework for evaluating model-generated answers, enabling accurate evaluation across diverse mathematical representations and answer formats. We present failure cases of symbolic evaluation in two popular frameworks, Lighteval and SimpleRL, and compare them to our approach, demonstrating clear improvements over commonly used methods. Our framework enables more reliable evaluation and benchmarking, leading to more accurate performance monitoring, which is important for advancing mathematical problem-solving and intelligent systems.

Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all heads uniformly for every input, regardless of task requirements or input complexity. In many scenarios, particularly for coarse-grained tasks such as text classification, the relevant information is often global and does not require the full diversity of attention heads. As a consequence, using a fixed number of heads can introduce unnecessary computational cost or lead to suboptimal performance when the allocation does not match the input. To address this limitation, we introduce BudgetFormer, a Transformer architecture equipped with an adaptive multi-head attention mechanism that dynamically allocates computational resources. Our approach learns, for each input, both a head budget corresponding to the number of attention heads required, and a relevance distribution that selects the most informative heads. We also propose a training strategy based on an exploration and exploitation trade-off, allowing the model to discover effective head configurations before converging to efficient usage patterns. Experiments on text classification tasks of varying complexity show that our method reduces inference cost in terms of FLOPs and memory, while also achieving performance that can surpass standard full multi-head attention. These results highlight the potential of adaptive head allocation as a principled approach to improving both efficiency and effectiveness in Transformer models.

As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity to a strict operational requirement. Our work is motivated by the explanations of autoregressive neural predictions on dynamic physical fields, as in weather forecasting. Gradient-based feature attribution methods are widely used to explain the predictions on such data, in particular due to their scalability to high-dimensional inputs. It is also interesting to remark that gradient-based techniques such as SmoothGrad are now standard on images to robustify the explanations using pointwise averages of the attribution maps obtained from several noised inputs. Our goal is to efficiently adapt this aggregation strategy to dynamic physical fields. To do so, our first contribution is to identify a fundamental failure mode when averaging perturbed attribution maps on dynamic physical fields: stochastic input perturbations do not induce stationary amplitude noise in attribution maps, but instead cause a geometric displacement of the attributions. Consequently, pointwise averaging blurs these spatially misaligned features. To tackle this issue, we introduce WassersteinGrad, which extracts a geometric consensus of perturbed attribution maps by computing their entropic Wasserstein barycenter. The results, obtained on regional weather data and a meteorologist-validated neural model, demonstrate promising explainability properties of WassersteinGrad over gradient-based baselines across both single-step and autoregressive forecasting settings.

We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adversarial perturbations - and how these features impact test performance. We show that models trained only on nonrobust features achieve well above chance accuracy across five MedMNIST classification tasks, confirming their predictive value in-distribution. Conversely, adversarially trained models that primarily rely on robust features sacrifice in-distribution accuracy but yield markedly better performance under controlled distribution shifts (MedMNIST-C). Overall, nonrobust features boost standard accuracy yet degrade out-of-distribution performance, revealing a practical robustness-accuracy trade-off in medical imaging classification tasks that should be tailored to the requirements of the deployment setting.

Autonomous agent systems such as OpenClaw introduce significant efficiency challenges due to long-context inputs and multi-turn reasoning. This results in prohibitively high computational and monetary costs in real-world development. While quantization is a standard approach for reducing cost and latency, its impact on agent performance in realistic scenarios remains unclear. In this work, we analyze quantization sensitivity across diverse complex workflows over OpenClaw, and show that precision requirements are highly task-dependent. Based on this observation, we propose QuantClaw, a plug-and-play precision routing plugin that dynamically assigns precision according to task characteristics. QuantClaw routes lightweight tasks to lower-cost configurations while preserving higher precision for demanding workloads, saving cost and accelerating inference without increasing user complexity. Experiments show that our QuantClaw maintains or improves task performance while reducing both latency and computational cost. Across a range of agent tasks, it achieves up to 21.4% cost savings and 15.7% latency reduction on GLM-5 (FP8 baseline). These results highlight the benefit of treating precision as a dynamic resource in agent systems.

In software-defined vehicles, automotive middleware plays a fundamental role in enabling efficient communication, integration, and coordination among software components. This paper examines how well two of the currently most popular middleware frameworks, ROS 2 Jazzy and AUTOSAR Adaptive Platform R24-11, meet practical requirements elicited from automotive software engineers at one of the major automotive supplier companies, ZF Group. Our objective is to provide insight into an otherwise difficult-to-obtain industrial perspective and support a clearer understanding of priorities in the development and evaluation of middleware for automotive applications.

Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenecks at long sequences. A key challenge is to design foundation models that maintain performance and long-context efficiency with minimal training overhead. We introduce SpikingBrain2.0 (SpB2.0), a 5B model that advances both architecture and training efficiency of its predecessor. Our contributions are two-fold. (1) Architectural Innovation: We propose Dual-Space Sparse Attention (DSSA), an inter-layer hybrid of Sparse Softmax Attention (MoBA) and Sparse Linear Attention (SSE), achieving an improved performance-efficiency trade-off for long-context modeling. SpB2.0 further supports dual quantization paths: INT8-Spiking coding enables sparse event-driven computation, while FP8 coding accelerates inference on modern GPUs. (2) Enhanced Training Strategy: We develop an optimized Transformer-to-Hybrid (T2H) pipeline with dual conversion paths for LLMs and VLMs using curated open-source data. Empirically, SpB2.0-5B and SpB2.0-VL-5B recover most of the base Transformer (Qwen3-4B) capability with under 7k A100 GPU hours. SpB2.0 achieves a 10.13x TTFT speedup at 4M context and supports over 10M tokens on 8 A100 GPUs under vLLM, where full-attention models exceed memory limits. It also demonstrates strong cross-platform compatibility, enabling FP8 GPU inference (2.52x speedup at 250k) and efficient neuromorphic execution (64.31% sparsity, with 70.6% and 46.5% area and power reduction at 500MHz). Overall, SpikingBrain2.0 provides a practical pathway for lightweight, multimodal, spiking foundation models, highlighting the potential of combining brain-inspired mechanisms with efficient architectures for resource-constrained and edge scenarios.

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection. This paper proposes a robust defense framework based on bilevel optimization, explicitly modeling the strategic interaction between a defender and an attacker as an adversarial co-evolutionary process. We evaluate our approach using the MAB-malware framework against three distinct malware families: Mokes, Strab, and DCRat. Our experimental results demonstrate that while standard classifiers and basic adversarial retraining often remain vulnerable, showing evasion rates as high as 90 %, the proposed bilevel optimization approach consistently achieves near-total immunity, reducing evasion rates to 0 - 1.89 %. Furthermore, the iterative framework significantly increases the attacker's query complexity, raising the average cost of successful evasion by up to two orders of magnitude. These findings suggest that modeling the iterative cycle of attack and defense through bilevel optimization is essential for developing resilient malware detection systems capable of withstanding evolving adversarial threats.

Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers. HiLight avoids compressing or rewriting the input, which can discard or distort evidence, by training a lightweight Emphasis Actor to insert minimal highlight tags around pivotal spans in the unaltered context. A frozen Solver then performs downstream reasoning on the emphasized input. We cast highlighting as a weakly supervised decision-making problem and optimize the Actor with reinforcement learning using only the Solver's task reward, requiring no evidence labels and no access to or modification of the Solver. Across sequential recommendation and long-context question answering, HiLight consistently improves performance over strong prompt-based and automated prompt-optimization baselines. The learned emphasis policy transfers zero-shot to both smaller and larger unseen Solver families, including an API-based Solver, suggesting that the Actor captures genuine, reusable evidence structure rather than overfitting to a single backbone.

Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to manipulation. We introduce a data-free signal based on the matrix von Neumann (spectral) entropy of the final-layer updates, which measures the diversity of the information contributed. We instantiate two practical schemes: (i) SpectralFed, which uses normalized entropy as aggregation weights, and (ii) SpectralFuse, which fuses entropy with class-specific alignment via a rank-adaptive Kalman filter for per-round stability. Across CIFAR-10/100 and the naturally partitioned FEMNIST and FedISIC benchmarks, entropy-derived scores show a consistently high correlation with standalone client accuracy under diverse non-IID regimes - without validation data or client metadata. We compare our results with data-free contribution estimation baselines and show that spectral entropy serves as a useful indicator of client contribution.

Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present a comparative study of cross-stage context passing on DriveLM-nuScenes using two complementary mechanisms. The explicit variant evaluates three prompt-based conditioning strategies on a domain-adapted 4B VLM (Mini-InternVL2-4B-DA-DriveLM) without additional training, reducing NLI contradiction by up to 42.6% and establishing a strong zero-training baseline. The implicit variant introduces gated context projectors, which extract a hidden-state vector from one stage and inject a normalized, gated projection into the next stage's input embeddings. These projectors are jointly trained with stage-specific QLoRA adapters on a general-purpose 8B VLM (InternVL3-8B-Instruct) while updating only approximately 0.5% of parameters. The implicit variant achieves a statistically significant 34% reduction in planning-stage NLI contradiction (bootstrap 95% CIs, p < 0.05) and increases cross-stage entailment by 50%, evaluated with a multilingual NLI classifier to account for mixed-language outputs. Planning language quality also improves (CIDEr +30.3%), but lexical overlap and structural consistency degrade due to the absence of driving-domain pretraining. Since the two variants use different base models, we present them as complementary case studies: explicit context passing provides a strong training-free baseline for surface consistency, while implicit gated projection delivers significant planning-stage semantic gains, suggesting domain adaptation as a plausible next ingredient for full-spectrum improvement.

As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learning (RL) has emerged as a promising paradigm for training MLLM agents on dynamic GUI tasks, its effective application faces a dilemma. Standard Offline RL often relies on static step-level data, neglecting global trajectory semantics such as task completion and execution quality. Conversely, Online RL captures the long-term dynamics but suffers from high interaction costs and potential environmental instability. To bridge this gap, we propose SOLAR-RL (Semi-Online Long-horizon Assignment Reinforcement Learning). Instead of relying solely on expensive online interactions, our framework integrates global trajectory insights directly into the offline learning process. Specifically, we reconstruct diverse rollout candidates from static data, detect the first failure point using per-step validity signals, and retroactively assign dense step-level rewards with target-aligned shaping to reflect trajectory-level execution quality, effectively simulating online feedback without interaction costs. Extensive experiments demonstrate that SOLAR-RL significantly improves long-horizon task completion rates and robustness compared to strong baselines, offering a sample-efficient solution for autonomous GUI navigation.

The emergence of large-scale pretrained foundation models has transformed computer vision, enabling strong performance across diverse downstream tasks. However, their potential for physics-based inverse problems, such as accelerated cardiac MRI reconstruction, remains largely underexplored. In this work, we investigate whether natural-domain foundation models can serve as effective image priors for accelerated cardiac MRI reconstruction, and compare the performance obtained against domain-specific counterparts such as BiomedCLIP. We propose an unrolled reconstruction framework that incorporates pretrained, frozen visual encoders, such as CLIP, DINOv2, and BiomedCLIP, within each cascade to guide the reconstruction process. Through extensive experiments, we show that while task-specific state-of-the-art reconstruction models such as E2E-VarNet achieve superior performance in standard in-distribution settings, foundation-model-based approaches remain competitive. More importantly, in challenging cross-domain scenarios, where models are trained on cardiac MRI and evaluated on anatomically distinct knee and brain datasets--foundation models exhibit improved robustness, particularly under high acceleration factors and limited low-frequency sampling. We further observe that natural-image-pretrained models, such as CLIP, learn highly transferable structural representations, while domain-specific pretraining (BiomedCLIP) provides modest additional gains in more ill-posed regimes. Overall, our results suggest that pretrained foundation models offer a promising source of transferable priors, enabling improved robustness and generalization in accelerated MRI reconstruction.

Estimating racial disparity requires individual-level race data, which are often unavailable due to the sensitivity of collecting such information. To address this problem, many researchers utilize Bayesian Improved Surname Geocoding (BISG), which have critically relied on Census surname data. Unfortunately, these data capture race-surname relationships only for common surnames, omitting approximately 10% of the US population. We show that predictive performance degrades substantially for individuals with such omitted, uncommon surnames because standard BISG implementation relies on a uninformative generic prior in these cases. To address this limitation, we propose embedding-powered BISG (eBISG), which uses pre-trained text embeddings to represent names as dense vectors and trains neural networks on 2020 Census surname and first-name data to estimate race probabilities for names not covered in the Census. We compare five approaches: standard BISG using only surnames, BIFSG incorporating first name probabilities, surname embedding for unlisted names, surname and first name embedding combining both, and a full-name embedding trained on voter file data from Southern states that captures interactions between name components. We show that each successive eBISG approach improves race prediction, with the full-name embedding yielding the largest gains, particularly for Hispanic and Asian voters whose surnames are absent from the Census list.

Thanks to the latest advances in learning and robotics, domestic robots are beginning to enter homes, aiming to execute household chores autonomously. However, robots still struggle to perform autonomous manipulation tasks in open-ended environments. In this context, this paper presents a method that enables a robot to manipulate a wide spectrum of articulated objects. In this paper, we automatically generate different robot low-level trajectory primitives to manipulate given object articulations. A very important point when it comes to generating expert trajectories is to consider the diversity of solutions to achieve the same goal. Indeed, knowing diverse low-level primitives to accomplish the same task enables the robot to choose the optimal solution in its real-world environment, with live constraints and unexpected changes. To do so, we propose a method based on Quality-Diversity algorithms that leverages sparse reward exploration in order to generate a set of diverse and high-performing trajectory primitives for a given manipulation task. We validated our method, QDTraj, by generating diverse trajectories in simulation and deploying them in the real world. QDTraj generates at least 5 times more diverse trajectories for both hinge and slider activation tasks, outperforming the other methods we compared against. We assessed the generalization of our method over 30 articulations of the PartNetMobility articulated object dataset, with an average of 704 different trajectories by task. Code is publicly available at: https://kappel.web.isir.upmc.fr/trajectory_primitive_website

Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurrently satisfy the following two practical requirements: (1) provide ownership verification capability under black-box suspect model access once the stolen encoders are used in downstream tasks; (2) be robust under adversarial watermark detection or removal, because the watermark samples form a distinguishable out-of-distribution (OOD) cluster. We propose ArmSSL, an SSL watermarking framework that assures black-box verifiability and adversarial robustness while preserving utility. For verification, we introduce paired discrepancy enlargement, enforcing feature-space orthogonality between the clean and its watermark counterpart to produce a reliable verification signal in black-box against the suspect model. For adversarial robustness, ArmSSL integrates latent representation entanglement and distribution alignment to suppress the OOD clustering. The former entangles watermark representations with clean representations (i.e., from non-source-class) to avoid forming a dense cluster of watermark samples, while the latter minimizes the distributional discrepancy between watermark and clean representations, thereby disguising watermark samples as natural in-distribution data. For utility, a reference-guided watermark tuning strategy is designed to allow the watermark to be learned as a small side task without affecting the main task by aligning the watermarked encoder's outputs with those of the original clean encoder on normal data. Extensive experiments across five mainstream SSL frameworks and nine benchmark datasets, along with end-to-end comparisons with SOTAs, demonstrate that ArmSSL achieves superior ownership verification, negligible utility degradation, and strong robustness against various adversarial detection and removal.

Problem definition: Data-driven models in machine learning have enabled efficient management of production systems. However, a majority of machine learning models are devoted to modeling the mean response or average pattern, which is inappropriate for studying abnormal extreme events that are often of primary interest in aircraft manufacturing. Since extreme events from heavy-tailed distributions give rise to prohibitive expenditures in system management, sophisticated extreme models are urgently needed to analyze complex extreme risks. Engineering applications of extreme models usually focus on individual extreme events, which is insufficient for complex systems with correlations. Methodology/results: We introduce an extreme spatial model for multi-output response control systems that efficiently captures the dynamics using a bilinear function on two spatial domains for control variables and measurement locations. Marginal parameter modeling and extremal dependence have been investigated. In addition, an efficient graph-assisted composite likelihood estimation and corresponding computational algorithms are developed to cope with high-dimensional outputs. The application to composite aircraft production shows that the proposed model enables comprehensive analyses with superior predictive performance on extreme events compared to canonical methods. Managerial implications: Our method shows how to use an extreme spatial model for predicting extreme events and managing extreme risks in complex production systems such as aircraft. This can help achieve better quality management and operation safety in aircraft production systems and beyond.

Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that adapts LLM outputs to learner abilities, using China's national curriculum (CSE) as a representative case. Our framework enables precise control over lexical complexity through a four-tier grading system, supported by a comprehensive suite of new resources: graded vocabulary lists and a multi-turn dialogue corpus. Our core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimizing dialogue quality. This method significantly outperforms conventional approaches, achieving low out-of-vocabulary rates and high diversity while enhancing conversational naturalness and pedagogical value. While grounded in the CSE, our framework is designed for flexibility and can be readily adapted to other educational standards. Our models, data, and code will all be open-sourced, providing a scalable platform for personalized English speaking practice that effectively addresses the unique challenges faced by K-12 learners in non-immersive environments.

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive Learning (CL). Instead of explicitly operating a classification, CL has the NN produce an embedding space where projections of similar data are pulled together, while projections of dissimilar data are pushed apart. In the case of Supervised CL (SCL), labels are adopted as similarity criteria, thus creating an embedding space where the projected data points are well-clustered. SCL provides crucial advantages over CE with regard to adversarial robustness and out-of-distribution detection, thus making it a more natural choice in safety-critical scenarios. In the present paper, we empirically show that NNs for image classification trained with SCL present higher-quality feature attribution explanations than CL with regard to faithfulness, complexity, and continuity. These results reinforce previous findings about CL-based approaches when targeting more trustworthy and transparent NNs and can guide practitioners in the selection of training objectives targeting not only accuracy, but also transparency of the models.

Objective: To propose and retrospectively validate an integrated framework addressing three barriers to clinical translation of readmission prediction: lack of explainability, absence of deployment reliability infrastructure, and inadequate demographic fairness evaluation. Materials and Methods: We constructed a cohort of 415231 adult admissions from the MIMIC-IV database (30-day readmission prevalence 18.0%), split 70/15/15. Logistic regression, XGBoost, and LightGBM models were trained on 26 features. SHAP provided per-patient explanations. Fairness was evaluated across 16 subgroups using AUC-ROC, false negative rate (FNR), and positive predictive value (PPV). Calibration was assessed using Brier scores and calibration curves. Results: XGBoost achieved AUC-ROC 0.696 (95% CI 0.691-0.701), outperforming or matching the LACE baseline (AUC 0.60-0.68). LightGBM achieved best calibration (Brier 0.146). Prior admissions were the dominant predictor. All subgroups met equity thresholds (delta AUC <= 0.05, delta FNR <= 0.10). Conclusion: This framework delivers competitive performance, clinically actionable explanations, and strong demographic equity. Code is publicly available at https://github.com/Tomisin92/readmission-prediction.

Feature engineering for Electronic Health Records (EHR) is complicated by irregular observation intervals, variable measurement frequencies, and structural sparsity inherent to clinical time series. Existing automated methods either lack clinical domain awareness or assume clean, regularly sampled inputs, limiting their applicability to real-world EHR data. We present \textbf{FeatEHR-LLM}, a framework that leverages Large Language Models (LLMs) to generate clinically meaningful tabular features from irregularly sampled EHR time series. To limit patient privacy exposure, the LLM operates exclusively on dataset schemas and task descriptions rather than raw patient records. A tool-augmented generation mechanism equips the LLM with specialized routines for querying irregular temporal data, enabling it to produce executable feature-extraction code that explicitly handles uneven observation patterns and informative sparsity. FeatEHR-LLM supports both univariate and multivariate feature generation through an iterative, validation-in-the-loop pipeline. Evaluated on eight clinical prediction tasks across four ICU datasets, our framework achieves the highest mean AUROC on 7 out of 8 tasks, with improvements of up to 6 percentage points over strong baselines. Code is available at github.com/hojjatkarami/FeatEHR-LLM.

Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy is the hybrid system paradigm, which balances cost and quality by serving most requests with a small model and selectively routing a fraction to a large model. However, existing routing strategies often rely on heuristics, external predictors, or absolute quality estimation, which fail to capture whether the large model actually provides a worthwhile improvement over the small one. In this paper, we formulate routing as a budget allocation problem and identify marginal gain, i.e., the large model's improvement over the small model, as the optimal signal for budgeted decisions. Building on this, we propose \textbf{RouteLMT} (routing for LLM-based MT), an efficient in-model router that predicts this expected gain by probing the small translators prompt-token representation, without requiring external models or hypothesis decoding. Extensive experiments demonstrate that our RouteLMT outperforms heuristics, quality/difficulty estimation baselines, achieving a superior quality-budget Pareto frontier. Furthermore, we analyze regression risks and show that a simple guarded variant can mitigate severe quality losses.

Evaluating LLM-generated business ideas is often harder to scale than generating them. Unlike standard NLP benchmarks, business idea evaluation relies on multi-dimensional criteria such as feasibility, novelty, differentiation, user need, and market size, and expert judgments often disagree. This paper studies a methodological question raised by such disagreement: should an automatic judge approximate an aggregate consensus, or model evaluators individually? We introduce PBIG-DATA, a dataset of approximately 3,000 individual scores across 300 patent-grounded product ideas, provided by domain experts on six business-oriented dimensions: specificity, technical validity, innovativeness, competitive advantage, need validity, and market size. Analyses show substantial expert disagreement on fine-grained ordinal scores, while agreement is higher under coarse selection, suggesting structured heterogeneity rather than random noise. We then compare three judge configurations: a rubric-only zero-shot judge, an aggregate judge conditioned on mixed evaluator histories, and a personalized judge conditioned on the target evaluator's scoring history. Across dimensions and model sizes, personalized judges align more closely with the corresponding evaluator than aggregate judges, and evaluator agreement correlates with similarity of judge-generated reasoning only under personalized conditioning. These results indicate that pooled labels can be a fragile target in pluralistic evaluation settings and motivate evaluator-conditioned judge designs for business idea assessment.

Handwritten Arabic manuscripts preserve the Arab world's intellectual and cultural heritage, and writer identification supports provenance, authenticity verification, and historical analysis. Using the Muharaf dataset of historical Arabic manuscripts, we evaluate writer identification from individual line images and, to the best of our knowledge, provide the first baselines reported under both line-level and page-disjoint evaluation protocols. Since the dataset is only partially labeled for writer identification, we manually verified and expanded writer labels in the public portion from 6,858 (28.00%) to 21,249 lines (86.75%) out of 24,495 line images, correcting inconsistencies and removing non-handwritten text. After further filtering, we retained 18,987 lines (77.51%). We propose a Convolutional Neural Network (CNN)-based model with attention mechanisms for closed-set writer identification, including rare two-writer lines modeled as composite writer-pair classes. We benchmark fourteen configurations and conduct ablations across different feature extractors and training regimes. To assess generalization to unseen pages, the page-disjoint protocol assigns all lines from each page to a single split. Under the line-level protocol, a fine-tuned DenseNet201 with attention achieves 99.05% Top-1 accuracy, 99.73% Top-5 accuracy, and 97.44% F1-score. Under the more challenging page-disjoint protocol, the best observed results are 78.61% Top-1 accuracy, 87.79% Top-5 accuracy, and 66.55% F1-score, thus quantifying the impact of page-level cues. By expanding the Muharaf dataset's labeled subset and reporting both protocols, we provide a clearer benchmark and a practical resource for historians and linguists engaged with culturally and historically significant documents. The code and implementation details are available on GitHub.

Hundreds of millions of people use artificial intelligence (AI) for writing assistance. Here, we evaluated how AI writing assistance distorts writer personas - their perceived beliefs, personality, and identity. In three large-scale experiments, writers (N=2,939) wrote political opinion paragraphs with and without AI assistance. Separate groups of readers (N=11,091) blindly evaluated these paragraphs across 29 socially salient dimensions of reader perception, spanning political opinion, writing quality, writer personality, emotions, and demographics. AI writing assistance produced persona distortions across all dimensions: with AI, writers seemed more opinionated, competent, and positive, and their perceived demographic profile shifted towards more privileged groups. Writers objected to many of the observed distortions, yet continued to prefer AI-assisted text even when made aware of them. We successfully mitigated objectionable persona distortions at the model level by training reward models on our experimental data (10,008 paragraphs, 2,903,596 ratings) to steer AI outputs towards faithful representation of writer stance. However, this came at a cost to user acceptance, suggesting an entanglement between desirable and undesirable properties of AI writing assistance that may be difficult to resolve. Together, our findings demonstrate that persona distortions from AI writing assistance are pervasive and persistent even under realistic conditions of human oversight, which carries implications for public discourse, trust, and democratic deliberation that scale with AI adoption.

Continuous estimation of high-dimensional finger kinematics from forearm surface electromyography (EMG) could enable natural control for hand prostheses, AR/XR interfaces, and teleoperation. However, the complexity of human hand gestures and the entanglement of forearm muscles make accurate recognition intrinsically challenging. Existing approaches typically reduce task complexity by relying on classification-based machine learning, limiting the controllable degrees of freedom and compromising on natural interaction. We present an end-to-end framework for continuous EMG-to-kinematics regression using only consumer-grade hardware. The framework combines an 8-channel EMG armband, a single webcam, and an automatic synchronization procedure, enabling the collection of the EMG Finger-Kinematics dataset (EMG-FK), a 10-h dataset of synchronized EMG and 15 finger joint angles from 20 participants performing rich, unconstrained right-hand motions. We also introduce the Temporal Riemannian Regressor (TRR), a lightweight GRU-based model that uses sequences of multi-band Riemannian covariance features to decode finger motion. Across EMG-FK and the public emg2pose benchmark, TRR outperforms state-of-the-art methods in both intra- and cross-subject evaluation. On EMG-FK, it reaches an average absolute error of $9.79 °\pm 1.48$ in intra-subject and $16.71 °\pm 3.97$ in cross-subject. Finally, we demonstrate real-time deployment on a Raspberry Pi 5 and intuitive control of a robotic hand; TRR runs at nearly 10 predictions/s and is roughly an order of magnitude faster than state-of-the-art approaches. Together, these contributions lower the barrier to reproducible, real-time EMG-based decoding of high-dimensional finger motion, and pave the way toward more natural and intuitive control of embedded EMG-based systems.

Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).

In this study, deep learning is used to estimate kinetic parameters for modeling itaconic acid production based on real batch experiments conducted at different agitation speeds and reactor scales. Two deep learning strategies, namely direct deep learning (DDL) and generative conditional flow matching (CFM) are compared and benchmarked against nonlinear regression as a reference method. Compared with DDL, CFM consistently yields more accurate results. The concentration profiles predicted by CFM closely match those obtained from nonlinear regression, whereas DDL results in larger deviations. Similar behavior is observed in the scale-up experiments, where the CFM model again generalizes better and is more robust than the direct approach. These findings demonstrate that CFM can reliably predict system behavior across different operating conditions and scales, offering a flexible and data-efficient framework for parameter estimation in dynamic bioprocess models.

We introduce two federated learning frameworks for the classical SPDnet model operating on symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. Unlike standard Euclidean averaging, which violates orthogonality, our approach preserves geometric structure through two efficient aggregation strategies: ProjAvg, projecting arithmetic means onto the Stiefel manifold, and RLAvg, approximating tangent-space averaging via retractions and liftings. Both methods are computationally efficient, independent of the optimizer, and enable scalable federated learning for signal processing applications whose features are SPD matrices. Simulations on EEG motor imagery benchmarks show that FedSPDnet outperforms federated EEGnet in F1 score and robustness to federation and partial participation, while using fewer parameters per communication round.

Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleading labels by focusing on dominant but incidental visual factors. Prior work such as FALCON introduced contrastive examples -- inputs that are semantically similar to activating examples but elicit low activations -- to sharpen explanations, but it primarily addresses subspace-level interpretability rather than scalable neuron-level labeling. We revisit contrastive explanations for neuron-level labeling in two stages: (1) candidate label generation with vision language models (VLMs) and (2) label assignment with CLIP-like encoders. First, we show that providing contrastive image sets to VLMs yields candidate labels that are more specific and more faithful. Second, we introduce Contrastive Semantic Projection (CSP), an extension of SemanticLens that incorporates contrastive examples directly into its CLIP-based scoring and selection pipeline. Across extensive experiments and a case study on melanoma detection, contrastive labeling improves both faithfulness and semantic granularity over state-of-the-art baselines. Our results demonstrate that contrastive examples are a simple yet powerful and currently underutilized component of neuron labeling and analysis pipelines.

Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-modality: for instance, data in video form are not directly interpretable as events. In this work, we present SnapLog, an approach to extract event data from videos by converting frames to feature vectors using image embeddings and performing temporal segmentation through frame-wise similarity matrices. A generalized few-shot classification is then used to assign labels to the video segments, yielding labeled, timestamped sub-sequences of frames that are interpretable as events. Conventional process mining techniques can be used to analyze the resulting data. We show that our approach produces logs that accurately reflect the process in the videos.

AI assistants can increasingly generate and evolve test cases. The challenge is no longer merely to produce them, but also to help engineers understand why a generated artefact exists and what supports it. Existing work has focused on classifying testing techniques, linking requirements to tests and structuring system assurance arguments, but it does not explicitly represent the argumentation behind individual test design decisions. We propose a conceptual taxonomy and a structured template for AI-assisted test generation that characterizes a test case by its test goal, claim, reason, and evidence. The taxonomy is intended for both constructive use during test design and retrospective use during review, to assess the quality of the attached argument rather than the plausibility or objective value of the generated test cases.

Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation and representation interference within fixed capacities, whereas Mixture-of-Experts (MoE) variants resort to indiscriminate expansion, incurring expert redundancy and a routing bottleneck reliant on additional data-driven optimization. To resolve these challenges, we propose MADE-IT (Manifold-Aware Dynamic Expert Evolution and Implicit rouTing), an adaptive CMM method that orchestrates expert management and activation by grounding intrinsic expert representations in manifold geometry. We introduce a projection-based subspace affinity metric coupled with a distribution-aware adaptive threshold mechanism to guide autonomous expert evolution, harmonizing diversity with architectural parsimony. Furthermore, to bypass parameterized gating networks, we design a data-free and training-free implicit routing mechanism that activates experts via feature-subspace alignment. Extensive experiments demonstrate that MADE-IT consistently outperforms strong baselines in accuracy and robustness across long-horizon and shuffled task sequences, while significantly pruning redundant experts, particularly within generic modules and early layers.

A core component of any AI-Augmented Business Process Management System (ABPMS) is the process frame, which gives the system process-awareness and defines the boundaries in which the system must operate. Compared to traditional process models, the process frame should, in principle, provide a somewhat more permissive representation of the managed processes, such that the (semi) autonomous behavior of an ABPMS, referred to as framed autonomy, could emerge. At the same time, it is not limited to a single linguistic or symbolic formalism and may incorporate heterogeneous knowledge ranging from predefined procedures to commonsense rules and best practices. In this paper, we conceptualize the notion of an ABPMS process frame as a hybrid business process representation, consisting of semi-concurrently executed procedural and declarative process models. We rely on our earlier works to outline the execution semantics of this type of process frame, arguing in favor of adopting the open-world assumption of the declarative paradigm also for procedural process models. The latter leads to a constraint-like interpretation, where each procedural model is considered to constrain the activities within that model, without imposing explicit execution requirements nor limitations on activities that may be present in other models. This is analogous to existing declarative languages, such as Declare, where each constraint has a direct effect only on the specific activities being constrained. Given this similarity, we propose mapping subsets of discovered declarative constraints into equivalent semi-concurrently executed procedural fragments, thus laying the foundation for a corresponding process (frame) discovery approach.

Microservice is a popular software architecture that relies on decentralized teams and clear service ownership to support modularity and scalability. However, in practice, developers frequently contribute across multiple services, creating organizational coupling (OC) that gradually erodes architectural boundaries and increases coordination overhead. This study proposes a vision for behavior-driven architectural governance through gamification in microservice systems to influence developer behavior and reduce OC. Our approach introduces a gamified framework that continuously mines repository data to detect architectural boundary violations and increasing service dependencies, and translates those signals into gameful designs, including points, badges, leaderboards, and architecture improvement quests. We outline a conceptual framework that integrates repository mining, architectural metrics, and gamification mechanisms to encourage developers to maintain service boundaries and improve architectural maintainability. Furthermore, we present an evaluation roadmap to assess the impact of gamified OC governance and developer engagement. This work aims to open a new research direction at the intersection of software architecture governance, socio-technical analysis, and gamification, highlighting the potential of behavioral incentives to support sustainable microservice evolution.

Collective intelligence refers to the ability of a group to achieve outcomes beyond what any individual member can accomplish alone. As large language model agents scale to populations of millions, a key question arises: Does collective intelligence emerge spontaneously from scale? We present the first empirical evaluation of this question in a large-scale autonomous agent society. Studying MoltBook, a platform hosting over two million agents, we introduce Superminds Test, a hierarchical framework that probes society-level intelligence using controlled Probing Agents across three tiers: joint reasoning, information synthesis, and basic interaction. Our experiments reveal a stark absence of collective intelligence. The society fails to outperform individual frontier models on complex reasoning tasks, rarely synthesizes distributed information, and often fails even trivial coordination tasks. Platform-wide analysis further shows that interactions remain shallow, with threads rarely extending beyond a single reply and most responses being generic or off-topic. These results suggest that collective intelligence does not emerge from scale alone. Instead, the dominant limitation of current agent societies is extremely sparse and shallow interaction, which prevents agents from exchanging information and building on each other's outputs.

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this reflects a deeper absence: a principled organisational layer that governs how a workforce of agents is assembled, governed, and improved over time, decoupled from what individual agents know. To fill this gap, we introduce \emph{OneManCompany (OMC)}, a framework that elevates multi-agent systems to the organisational level. OMC encapsulates skills, tools, and runtime configurations into portable agent identities called \emph{Talents}, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven \emph{Talent Market} enables on-demand recruitment, allowing the organisation to close capability gaps and reconfigure itself dynamically during execution. Organisational decision-making is operationalised through an \emph{Explore-Execute-Review} ($\text{E}^2$R) tree search, which unifies planning, execution, and evaluation in a single hierarchical loop: tasks are decomposed top-down into accountable units and execution outcomes are aggregated bottom-up to drive systematic review and refinement. This loop provides formal guarantees on termination and deadlock freedom while mirroring the feedback mechanisms of human enterprises. Together, these contributions transform multi-agent systems from static, pre-configured pipelines into self-organising and self-improving AI organisations capable of adapting to open-ended tasks across diverse domains. Empirical evaluation on PRDBench shows that OMC achieves an $84.67\%$ success rate, surpassing the state of the art by $15.48$ percentage points, with cross-domain case studies further demonstrating its generality.

We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M << n is a small number of learned hub tokens. We demonstrate it in two from-scratch architectures: a Jamba-style hybrid and a 12-layer Transformer; retrofit into pretrained models is a tested negative case. HubRouter implements an encode-decode-score-council pipeline: M learned hubs cross-attend to all tokens, tokens project against hubs for routing fingerprints, a score head selects top-k tokens, and a sparse council attends only to the selected subset. We validate HubRouter in three settings. (1) Hub-Jamba yields a nominal 4.2% PPL improvement (200.2 vs 209.0, single seed; possibly within seed noise) and up to ~90x training throughput at sequence length 1024 in matched PyTorch-native baselines; an optimised baseline would narrow this to ~10-15x. (2) Graduated replacement of 25% of Transformer attention layers gives the best perplexity in our matched-budget sweep (268.0 vs 282.4 pure Transformer). (3) Hub-GPT provides strictly causal routing, achieving PPL 211.5 +/- 0.4 over 3 seeds (post council-causal fix); approximately 3 PPL worse than Jamba's 208.5 +/- 0.7, a measurable quality cost for avoiding O(n^2) computation. Post-fix, chunk size C has little effect; the pre-fix chunk-size benefit was an artifact of a bidirectional-council leak we found in adversarial review. A multi-seed hub-count sweep (~105 runs across M=1-32) reveals M=8-14 as the reliably-converging sub-band (4-5/5 seeds); M=6 is rescued to 5/5 by orthogonal regularization, while M>=20 shows increasing seed sensitivity. Companion paper arXiv:2603.20997 (Basu, 2026) defines the routing diagnostic task. Code and scripts will be released.

Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is particularly attractive due to its versatility, efficiency, and effectiveness in natural language generation. However, KGW's effectiveness degrades significantly under low-entropy settings such as code generation and mathematical reasoning. A crucial step in the KGW method is random vocabulary partitioning, which enables adjustments to token selection based on specific preferences. Our study revealed that the next-token probability distribution plays an critical role in determining how much, or even whether, we can modify token selection and, consequently, the effectiveness of watermarking. We refer to this characteristic, associated with the probability distribution of each token prediction, as \emph{watermark strength.} In cases of random vocabulary partitioning, the lower bound of watermark strength is dictated by the next-token probability distribution. However, we found that, by redesigning the vocabulary partitioning algorithm, we can potentially raise this lower bound. In this paper, we propose SSG (\textbf{S}ort-then-\textbf{S}plit by \textbf{G}roups), a method that partitions the vocabulary into two logit-balanced subsets. This design lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. Experiments on code generation and mathematical reasoning datasets demonstrate the effectiveness of SSG.

The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often compositional and execution-dependent, making them difficult to assess from textual descriptions alone. However, existing research and benchmarks typically assume well-specified functionalities, controlled candidate pools, or only executable task queries, leaving realistic agent search scenarios insufficiently studied. We introduce AgentSearchBench, a large-scale benchmark for agent search in the wild, built from nearly 10,000 real-world agents across multiple providers. The benchmark formalizes agent search as retrieval and reranking problems under both executable task queries and high-level task descriptions, and evaluates relevance using execution-grounded performance signals. Experiments reveal a consistent gap between semantic similarity and actual agent performance, exposing the limitations of description-based retrieval and reranking methods. We further show that lightweight behavioral signals, including execution-aware probing, can substantially improve ranking quality, highlighting the importance of incorporating execution signals into agent discovery. Our code is available at https://github.com/Bingo-W/AgentSearchBench.

Heat exposure connects the built environment and public health, directly shaping the livability and sustainability of urban areas. Understanding the spatial heterogeneity of heat exposure and its drivers is vital for climate-adaptive urban planning. However, most planning-oriented studies rely on land surface temperature (LST), and whether LST adequately represents human heat exposure and how it differs from physiologically relevant heat stress remains insufficiently examined. Here, adopting Landsat-retrieved 30-m LST and GPU-accelerated 1-m universal thermal climate index (UTCI) in Singapore, this study establishes a comprehensive "Modeling-Comparing-Assessing" framework to systematically evaluate the spatial and mechanistic discrepancies between the two metrics. We further investigate pronounced non-stationary and threshold-based quantitative relationships of the two metrics with urban factors by employing a novel geographically weighted XGBoost (GW-XGBoost) and generalized additive model (GAM) workflow. Our results demonstrate notable discrepancies in spatial patterns of LST and UTCI, along with substantial spatial heterogeneity in how 2D and 3D urban factors impact these two thermal metrics, as revealed by explainable GW-XGBoost models (global out-of-bag R2 = 0.855 for LST and 0.905 for UTCI, respectively). Crucially, spatially explicit SHAP interprets that sky view factor plays a central role in explaining UTCI variability but exhibits a comparatively marginal independent contribution to LST, indicating that LST inadequately captures shading-driven and radiative processes governing actual human heat stress. Notably, SHAP-GAM analysis indicates that higher albedo is associated with increased UTCI. These novel findings provide evidence for integrating physiologically relevant thermal indices to inform targeted heat risk management and climate-adaptive urban planning.

Accurate requirement-to-code traceability is crucial for software maintenance. However, existing IR- and embedding-based methods are heavily dependent on lexical similarity, often yielding incomplete or inconsistent links across projects and languages and incurring high cost from long-context retrieval and prompting. This paper presents R2Code, an LLM-based semantic traceability framework designed to improve trace link accuracy while reducing inference cost. R2Code integrates three components: 1) a decomposition-enhanced Bidirectional Alignment Network (BAN) that aligns four-layer requirement semantics with corresponding code structures to support cross-level semantic matching; 2) a Self-Reflective Consistency Verification (SRCV) module that conducts explanation-guided consistency checking to calibrate link reliability; and 3) a Dynamic Context-Adaptive Retrieval (DCAR) mechanism that adjusts retrieval granularity and filters contexts using semantic-overlap weighting for efficient context utilization. Experiments on five public datasets spanning multiple domains and two programming languages demonstrate that R2Code consistently outperforms the strongest baselines, achieving an average F1 gain of 7.4%, while reducing token consumption by up to 41.7% through adaptive context control.

Predicting individual cognitive decline in Alzheimer's disease (AD) is difficult due to the heterogeneity of disease progression. Reliable clinical tools require not only high accuracy but also fairness across demographics and robustness to missing data. We present CognitiveTwin, a digital twin framework that predicts patient-specific cognitive trajectories. The model integrates multi-modal longitudinal data (cognitive scores, magnetic resonance imaging, positron emission tomography, cerebrospinal fluid biomarkers, and genetics). We use a Transformer-based architecture to fuse these modalities and a Deep Markov Model to capture temporal dynamics. We trained and evaluated the framework using data from 1,666 patients in the TADPOLE (Alzheimer's Disease Neuroimaging Initiative) dataset. We assessed the model for prediction error, demographic fairness, and robustness to missing-not-at-random (MNAR) data patterns. ognitiveTwin provides accurate and personalized predictions of cognitive decline. Its demonstrated fairness across patient demographics and resilience to clinical dropout make it a reliable tool for clinical trial enrichment and personalized care planning.

We consider the following fundamental problem: given a database D, Boolean conjunctive query (CQ) q, and fact f in D, decide whether f is relevant to q wrt. D, i.e., does f belong to a minimal subset S of D such that S |= q. Despite being of central importance to query answer explanation, the combined complexity of deciding query relevance has not been studied in detail, leaving open what makes this problem hard, and which restrictions can yield lower complexity. Relevance has already been shown to be harder than query evaluation: namely, $Σ^p_2$-complete for CQs, even over a binary signature. We further observe that NP-hardness applies already to (acyclic) chain CQs. Our work identifies self-joins (multiple atoms with the same relation) as the culprit. Indeed, we prove that if we forbid or bound the occurrence of self-joins, then relevance has the same complexity as query evaluation, namely, NP (without structural restrictions) and LogCFL (for bounded hypertreewidth classes). In the ontology setting, we establish an analogous result for ontology-mediated queries consisting of a CQ and DL-Lite_R ontology, namely that relevance is no harder than query answering provided that we bound the interaction width (which generalizes both self-join width and a recently introduced 'interaction-free' condition). Our results thus pinpoint what makes relevance harder than query evaluation and identify natural classes of queries which admit efficient relevance computation.

Latent variables pose a fundamental challenge to causal discovery and inference. Conventional local methods focus on direct neighbors but fail to provide macro level insights. Cluster level methods enable macro causal reasoning but either assume clusters are known a priori or require causal sufficiency. Moreover, directly applying single variable causal discovery methods to cluster level problems violates causal sufficiency and leads to incorrect results. To overcome these limitations, this paper proposes L2C (Local to Cluster Causal Abstraction), a unified framework that bridges local structure learning and cluster level causal discovery. Unlike prior work that requires a complete manual assignment of micro variables to clusters, L2C discovers the partition automatically from local causal patterns. Our solution leverages a cluster reduction theorem to reduce any cluster to at most three nodes without loss of causal information, applies local causal discovery to identify direct causes, effects, and V structures in the presence of latent variables, and performs macro level causal inference via cluster level calculus on the learned cluster graph. L2C does not assume causal sufficiency, as latent variables are handled through local discovery. Theoretical analysis shows that L2C ensures soundness, atomic completeness, and computational efficiency. Extensive experiments on synthetic and real world data demonstrate that L2C accurately recovers ground truth clusters and achieves superior macro causal effect identification compared to existing baselines.

Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a synthetic node-classification benchmark on contextual stochastic block model graphs, where labels are generated by a controllable mixture of local and far-shell signals. We define distance-misaligned training as a mismatch between where label-relevant information lies and where the model allocates communication over graph distance. On this benchmark, we find three points. First, the preferred graph-distance bias changes systematically with task locality. Second, an oracle adaptive controller, given offline access to the task-side distance target, nearly matches the best fixed bias across regimes and strongly improves over a neutral baseline on mixed and local tasks. Third, a task-agnostic zero-gap controller is weaker, indicating that adaptation alone is not enough and that the control target matters. These results suggest that distance-resolved diagnosis is useful for understanding Graph Transformer failures and for designing graph-aware control.

Even when decoding with temperature $T=0$, large language models (LLMs) can produce divergent outputs for identical inputs. Recent work by Thinking Machines Lab highlights implementation-level sources of nondeterminism, including batch-size variation, kernel non-invariance, and floating-point non-associativity. In this short note we formalize this behavior by introducing the notion of \emph{background temperature} $T_{\mathrm{bg}}$, the effective temperature induced by an implementation-dependent perturbation process observed even when nominal $T=0$. We provide clean definitions, show how $T_{\mathrm{bg}}$ relates to a stochastic perturbation governed by the inference environment $I$, and propose an empirical protocol to estimate $T_{bg}$ via the equivalent temperature $T_n(I)$ of an ideal reference system. We conclude with a set of pilot experiments run on a representative pool from the major LLM providers that demonstrate the idea and outline implications for reproducibility, evaluation, and deployment.

Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition has a hidden failure mode. In a high-overlap, non-adaptive 8-domain continual LM, all shared-routing projection baselines collapse close to vanilla forgetting (12.5--12.8 vs. 13.2). A 0.5% replay buffer is the strongest shared alternative but still reaches 11.6, while fixed-strength decoupling falls below vanilla at 14.1. Only adaptive decoupled routing remains stable at 9.4, improving over vanilla by 3.8 units. On a 16-domain stream, its gain over the strongest shared-routing projection baseline grows to 4.5--4.8 units. The failure is largely invisible on clean benchmarks. We explain this effect through Adam's second-moment pathway: in the tested regime, projection induces a 1/(1-alpha) inflation of the old-direction effective learning rate, matching measurements within 8% across eight alpha values. The same conflict appears with penalty methods, replay mixing, and at 7B scale under LoRA. Our fix routes the modified gradient only to the first moment while preserving magnitude-faithful second-moment statistics, with overlap-aware adaptive strength. This simple change is the only tested configuration that consistently avoids collapse across methods, optimizers, and scale.

K-plane clustering (KPC), hyperplane clustering, and mixture regression all essentially fall within the same class of problems. This problem can be conceptualized as clustering in relatively high-dimensional K subspaces or K linear manifolds. Traditional KPC or fuzzy KPC models demonstrate a pronounced susceptibility to outliers, as they presuppose that the projection distance between data points and the plane normal vector adheres to the L2 distance. Meanwhile, the assumption of infinitely extending clusters adversely affects clustering performance. To solve these problems, this paper proposed a new robust fuzzy local k-plane clustering (RFLkPC) method that combines the mixture distance of hinge loss and L1 norm. The RFLkPC model assumes that each plane cluster is bounded to a finite area, which can flexibly and robustly handle plane clustering tasks with outliers or not. The corresponding model and optimization algorithms of RFLkPC were provided. Compared to other related models on this topic, a large number of experiments verify the efficiency of RFLkPC on simulated data and real data. The source code for the proposed RFLkPC method is publicly available at https://github.com/xuelin-xie/RFLkPC.

Unified Modeling Language (UML) Use Case and Class Diagrams are fundamental modeling notations in Software Engineering (SE) education due to their importance for requirements and model-based engineering, yet their relevance is underestimated by students, who tend to dismiss the topic as secondary. Gamification has been adopted to make modeling education more appealing, but existing tools focus almost exclusively on class diagrams, leaving support for use cases and other notations unexplored. In 2025, we designed UMLegend, a gamified tool for class diagrams that offered dynamic feedback to help students learn correct modeling practices and multiple long-term mechanics to increase engagement, and performed a study with the tool. With this paper, we describe how we enhanced UMLegend following the results of the experiment so that it can support more modeling languages, with use case diagrams being added to the type of available exercises in the tool. The revised version has been refactored to have a modular architecture, to make it easier to add other software engineering topics and additional modeling notations. We also describe the potential impact we expect the new version to have, and outline a longitudinal study we intend to perform in 2026 where we will assess whether long-term UML gamification leads to improved student performance.

The Super Learner (SL) is a widely used ensemble method that combines predictions from a library of learners based on their predictive performance. Interval predictions are of considerable practical interest because they allow uncertainty in predictions produced by an individual learner or an ensemble to be quantified. Several methods have been proposed for constructing interval predictions based on the SL, however, these approaches are typically justified using asymptotic arguments or rely on computationally intensive procedures such as the bootstrap. Conformal prediction (CP) is a machine learning framework for constructing prediction intervals with finite-sample and asymptotic coverage guarantees under mild conditions. We propose coupling CP with the SL through a natural construction that mirrors the original SL framework, using individual learner weights and combining learner-specific conformity scores via a weighted majority vote. We characterize the properties of the resulting SL-based prediction intervals for continuous outcomes. We cover settings under exchangeability, potential violations of exchangeability, and data-generating mechanisms exhibiting heteroscedasticity, sparsity, and other forms of distributional heterogeneity. A comprehensive simulation study shows that the conformalized SL achieves valid finite-sample coverage with competitive performance relative to the true data-generating mechanism. A central contribution of this work is an application to predicting creatinine levels using socio-demographic, biometric, and laboratory measurements. This example demonstrates the benefits of an ensemble with carefully selected learners designed to capture key aspects of complex regression functions, including non-linear effects, interactions, sparsity, heteroscedasticity, and robustness to outliers.R

One of the major limits of kernel ridge regression (KRR) is that storing and manipulating the kernel matrix K_n for n samples requires O(n^2) space, which rapidly becomes unfeasible for large n. Nystrom approximations reduce the space complexity to O(nm) by sampling m columns from K_n. Uniform sampling preserves KRR accuracy (up to epsilon) only when m is proportional to the maximum degree of freedom of K_n, which may require O(n) columns for datasets with high coherence. Sampling columns according to their ridge leverage scores (RLS) gives accurate Nystrom approximations with m proportional to the effective dimension, but computing exact RLS also requires O(n^2) space. (Calandriello et al. 2016) propose INK-Estimate, an algorithm that processes the dataset incrementally and updates RLS, effective dimension, and Nystrom approximations on-the-fly. Its space complexity scales with the effective dimension but introduces a dependency on the largest eigenvalue of K_n, which in the worst case is O(n). In this paper we introduce SQUEAK, a new algorithm that builds on INK-Estimate but uses unnormalized RLS. As a consequence, the algorithm is simpler, does not need to estimate the effective dimension for normalization, and achieves a space complexity that is only a constant factor worse than exact RLS sampling.

Rejection sampling is a technique for sampling from difficult distributions. However, its use is limited due to a high rejection rate. Common adaptive rejection sampling methods either work only for very specific distributions or without performance guarantees. In this paper, we present pliable rejection sampling (PRS), a new approach to rejection sampling, where we learn the sampling proposal using a kernel estimator. Since our method builds on rejection sampling, the samples obtained are with high probability i.i.d. and distributed according to f. Moreover, PRS comes with a guarantee on the number of accepted samples.

Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, particularly in gloss-free settings. Recent SLT systems increasingly adopt CLIP-like Vision-Language pretraining (VLP) for cross-modal alignment, but the random in-batch contrast provides few, batch-dependent negatives and may mislabel semantically similar (or even identical) pairs as negatives, introducing noisy and potentially inconsistent alignment supervision. In this work, we first conduct a preliminary trajectory-based analysis that tracks negative video-text similarity over training. The results show that only a small subset of negatives exhibits the desired behavior of being consistently pushed away, while the remaining negatives display heterogeneous and often non-decreasing similarity dynamics, suggesting that random in-batch negatives are frequently uninformative for effective alignment. Inspired by this, we propose Selective Contrastive Learning for SLT (SCL-SLT) with a Pair Selection (PS) strategy. PS scores candidate negatives using similarity dynamics from reference checkpoints and constructs mini-batches via a curriculum that progressively emphasizes more challenging negatives, thereby strengthening contrastive supervision while reducing the influence of noisy or semantically invalid negatives.