# Research Papers — 2026-07 · bundle page 87 of 222 > Full-text markdown of papers #4301–4350 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/87 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/86.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/88.md) ### Censoring-Aware In-Context Learning for Generalized Supplier Lead Time Estimation in Supply Chain Planning Authors: Christopher Wang, Sebastien Ouellet, Behrouz Haji Soleimani, Ali Etemad Published: 2026-07-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18530v1 Supplier lead time forecasting is a central input to material requirements planning, inventory optimization, and supply chain risk management. However, many industrial lead time datasets are naturally right-censored: at the time forecasts are required, some orders have not yet arrived. Standard regression and classification approaches discard this information, while conventional survival models require task-specific modeling. We propose LeadTime-ICL (LT-ICL), a censoring-aware in-context learning model for probabilistic lead time forecasting. LT-ICL combines a transformer backbone with a conditional normalizing-flow head, producing a full predictive distribution over lead times. The model is pretrained on synthetic right-censored lead time tasks, enabling in-context adaptation to new industrial datasets without task-specific parameter updates. We provide theoretical support for this formulation by showing that excess CRPS is bounded by prior misspecification and amortized approximation errors, providing clear direction for improving forecasting performance. We evaluate LT-ICL on 24 proprietary supply-chain datasets spanning seven industries. LT-ICL achieves the lowest point-forecasting error on 15 of the 24 datasets, and the lowest probabilistic forecasting error on 14 datasets, yielding the best average rank across both. These results support right-censored probabilistic forecasting as a practical formulation for supplier lead time prediction and demonstrate that pretrained in-context models can provide accurate, low-adaptation-cost forecasting for industrial planning systems. --- ### EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration Authors: Jia-Kai Dong, Yi-Cheng Lin, Hung-yi Lee Published: 2026-07-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.18529v2 Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their pedagogical quality. Existing automatic judges do not fully address this setting because teaching quality depends on multimodal evidence and should be evaluated with respect to the intended learner rather than as a universal property. We present EduPanel, a rubric-grounded, learner-conditioned LLM judge that decomposes evaluation across specialized agents to produce interpretable assessments for different aspects of teaching quality. Across expert studies, architecture ablations, and learner-persona analyses, EduPanel achieves reliability comparable to a median human expert. In expert evaluation, its feedback improves scoring accuracy (MAE 0.87 to 0.73), while experts remain able to detect unreliable outputs (AUC = 0.77) instead of accepting them blindly. These results suggest that EduPanel can serve as effective assistants for educational evaluation rather than replacements for human experts. --- ### Adaptive Two-Stage Online Learning for Service-Affecting Failure Detection in Mobile Core Networks Authors: J. du Toit, G. Fita, J. Salzwedel, A. Stoltz, R. Wolhuter Published: 2026-07-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.18522v1 Mobile network operators monitor aggregated traffic volumes to assess the operational health of core network infrastructure. Reliable failure detection is challenging due to strong temporal structure, non-stationarity, measurement artefacts, and extreme class imbalance, which limit static threshold-based monitoring. This paper proposes a two-stage online learning framework for traffic-based failure detection in mobile core networks. Stage I incrementally models normal traffic dynamics using lightweight regression with time-aware features. Stage II analyses prediction residuals together with contextual indicators to detect genuine service-affecting network failures. The framework operates fully online under a prequential evaluation protocol, enabling continuous adaptation with low computational overhead. Across linear and non-linear models, the proposed two-stage architecture achieves the best precision-recall trade-off, attaining the highest recall, F1-score, and AUC at acceptable false positive rates. These results demonstrate the importance of explicit residual decomposition for reliable failure detection in streaming mobile core network data. --- ### Signed Rectified Flow: Negativity-Controlled Generation Authors: Runlong Liao, Baiyu Su, Lizhang Chen, Qiang Liu Published: 2026-07-20 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.18516v1 We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $π^{sign} = (1+α)π^+ - απ^-$, where $α>0$, $π^+$ is the distribution to promote, and $π^-$ is the distribution to suppress. Although direct sampling from a signed measure is not well-defined, Signed RF induces a valid generative process that concentrates probability in regions where the signed measure is positive while provably excluding regions dominated by its negative component. It therefore provides a principled framework for incorporating negative information and exclusion constraints into generative modeling. We analyze the signed continuity equation underlying Signed RF and use a charged-particle interpretation to explain how negative mass forms exclusion barriers. This theory further motivates practical adaptive guidance algorithms. Across several applications, Signed RF improves the fidelity-diversity trade-off on ImageNet, reduces nearest-neighbor similarity in anti-memorization experiments, and reduces nudity induced by adversarial prompts in Stable Diffusion 3.5 while preserving CLIP and aesthetic scores. --- ### Automated Data Engineering and Feature Selection for the Case Study of Warpage Detection in Fused Deposition Modeling Authors: Saleh Valizadeh Sotubadi, Nazanin Mahjourian, Vinh Nguyen Published: 2026-07-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18515v1 This study contributes toward development of an Automated Data Processing (ADP) framework designed to evaluate and reinforce optimal machine learning model-feature combinations for predictive tasks in fused deposition modeling (FDM) process datasets. The methodology is centered around a reinforcement learning-inspired policy updating mechanism, where multiple machine learning models are trained on both full feature sets and feature subsets selected through Shapley-based Explainable AI (SHAP XAI) across 217 datasets. At each episode, the framework assesses the predictive accuracy and F1-scores of each model-feature pair, computes a scalar reward, and updates $Q$ values to guide future model selection. SHAP XAI feature importance was employed to generate reduced yet informative feature subsets to enable the framework to explore performance with dimensionality. The policy was shown to evolve over multiple episodes, with reward distributions used to visualize performance stability. Overall, results indicate that leveraging the ADP framework through XAI algorithms successfully converges toward optimal model-feature configurations with improved accuracy and stability. Specifically, the proposed framework improves the test-set AUC from 0.9248 to 0.9731 and increases the mean reward value by more than fifty percent compared with the baseline full-feature configuration. --- ### Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists Authors: Arnavi Chheda-Kothary, Lucy Lu Wang, Joseph Chee Chang, Jonathan Bragg Published: 2026-07-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.18514v1 Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have traditionally relied on static alternative text to access figures in papers, the rise of artificial intelligence (AI) has made interactive question-answering (QA) a feasible paradigm for visual exploration; yet little is known about how scientists use visual QA in practice or how to improve its accessibility. In this work, we interview five BLV and five sighted scientists across different STEM fields to understand how they use two AI tools, ChatGPT and Gemini, to query multimodal scientific documents. Our findings characterize how scientists review multimodal content, including existing practices (along with accessibility workarounds) for engaging with visuals, and feedback on the suitability of AI-generated responses to multimodal queries. We further find that vague or incomplete image descriptions, as well as incorrect AI outputs more broadly, can cause both BLV and sighted scientists to abandon AI workflows. To support future research, we additionally contribute a dataset of 115 queries and responses from our participants' interactions with the AI tools for papers in their field. We close by discussing implications for AI-powered scientific QA systems, emphasizing considerations for access across abilities and domains. --- ### DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer Authors: Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi Published: 2026-07-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.18510v1 Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \textbf{DuSPiT}, a \textbf{Du}al-branch \textbf{S}ub\textbf{P}atch \textbf{Pi}xel \textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention. Our results show that DuSPiT generates images with richer details and stronger fine-grained structures, while also achieving a better quality--efficiency trade-off than prior pixel-space diffusion transformers. --- ### Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation Authors: Jiabing Yang, Yixiang Chen, Yuan Xu, Qisen Ma, Tao Yu, Peiyan Li, Yingda Li, Yan Huang, Liang Wang Published: 2026-07-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.18508v1 Preference over model-generated emotion descriptions is emerging as a standard evaluation metric for multimodal emotion understanding, exemplified by the MER2026 MER-Prefer track on EmoPrefer. Such benchmarks assume that predicting the preferred description requires grounded cross-modal understanding of the video. We conduct a systematic shortcut audit of EmoPrefer using content-blind probes. A simple logistic regression using only description length and generator identity, without processing the text, video, or audio, performs comparably to LoRA-finetuned 7B text and audio-visual judges (65.8 versus 66.8 WAF on EmoPrefer-V2). Generator identity is recoverable from description text with 99.5 percent accuracy, every candidate pair contrasts two distinct generators, and the human preference labels agree with a fold-exclusive per-generator win-rate prior on 66 percent of the evaluated pairs. When the human label conflicts with this prior, trained judges still follow the style prior on 63 to 80 percent of the pairs. On a length-matched subset that neutralizes verbosity bias, the tested media configurations yield no statistically significant improvement, while an ODIN-inspired diagnostic that decouples the style shortcut leaves its content head near chance. These results do not imply that human preferences are inherently stylistic or that the descriptions contain no emotional information. Instead, they show that the current scores can be reached without verifying either description against the video. We recommend source-balanced pairing, strict length control, counter-stereotypical sliced reporting, and multi-annotator consensus for future cross-generator evaluations. Code is available at https://github.com/jiabingyang01/EmoPrefer-Audit. --- ### Now We Know? A Systematic Comparison of TerraMind and THOR Authors: Frederick Schindlegger, Kenzo Bounegta, Eva Gmelich Meijling, Johannes Jakubik, Arnt-Børre Salberg, Theodor Forgaard, Nicolas Longepe, Valerio Marsocci Published: 2026-07-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.18504v2 Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much of the gap is architecture, how much is decoder capacity, and how much is a use-case-specific artefact? This study addresses that gap through a controlled comparison of two GFMs developed under European Space Agency's $Φ$-lab with contrasting design philosophies: THOR, which introduces a compute-adaptive architecture supporting variable patch sizes and unifies Sentinel-1, -2, and -3 data at their native resolutions; and TerraMind, a multimodal generative GFM pretrained with a dual-scale token/pixel objective that enables any-to-any cross-modal generation (Thinking-in-Modalities) to infer missing sensors at inference time. Rather than reporting a single leaderboard, we investigate the axes along which the two architectures actually differ - patch size, decoder complexity, finetuning regime, input modality, and model scale - across ten use cases spanning segmentation and regression in diverse domains, including climate disaster response, methane leak detection, snow monitoring, or sea ice mapping. We find that architectural design choices - patch size and decoder type in particular - explain more performance variance than model identity itself, that the two models embody complementary investment strategies (pretraining-time scale for TerraMind versus inference-time tokenisation for THOR), and that correctly interpreting results requires dataset-level characterisation. The resulting picture is not a single winner but a set of hypotheses and a diagnostic ablation methodology that we expect to generalise to future GFMs beyond THOR and TerraMind. --- ### Semi-Automated Detection of Gaps in LLM Security Knowledge Authors: Shufan Chai, Liangliang Sun, Jessica Staddon Published: 2026-07-20 Categories: cs.CR, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.18496v4 Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on identifying areas in which LLM security "knowledge" may be insufficient. Popular strategies for identifying LLM security knowledge gaps include building corpora of challenge questions or task benchmarks, strategies that require substantial manual work and security expertise to design and execute. We introduce a partially-automated method for assessing LLM knowledge of a security area. The method uses authoritative information from Consumer Protection Agencies (CPAs) to identify instability in LLM responses that can be indicative of knowledge gaps. We demonstrate the method for 2 security topics, identity theft and impostor scams, and 5 LLMs in 2 leading LLM families, Gemini and GPT, using publicly available information about identity theft and impostor scams from 6 CPAs. The method distinguishes between models that have and don't have sufficient knowledge to accurately identify the security topics in text narratives. --- ### Towards an Automated Test of LLM Security Knowledge Authors: Shufan Chai, Liangliang Sun, Jessica Staddon Published: 2026-07-20 Categories: cs.CR, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.18496v3 Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on identifying areas in which LLM security "knowledge" may be insufficient. Popular strategies for identifying LLM security knowledge gaps include building corpora of challenge questions or task benchmarks, strategies that require substantial manual work and security expertise to design and execute. We introduce a partially-automated method for assessing LLM knowledge of a security area. The method uses authoritative information from Consumer Protection Agencies (CPAs) to identify instability in LLM responses that can be indicative of knowledge gaps. We demonstrate the method for 2 security topics, identity theft and impostor scams, and 5 LLMs in 2 leading LLM families, Gemini and GPT, using publicly available information about identity theft and impostor scams from 6 CPAs. The method distinguishes between models that have and don't have sufficient knowledge to accurately identify the security topics in text narratives. --- ### Attractor Geometry Determines the Identifiability Limits of System Discovery Authors: Matteo Gallo, Fabio Anselmi, Paolo Lazzari Published: 2026-07-20 Categories: cs.LG, nlin.CD arXiv: https://arxiv.org/abs/2607.18490v1 Symbolic discovery of governing equations from data is limited not only by algorithm design and data volume, but by the geometry of the attractor: what the long-run dynamics allow to be recovered. Using a within-system design on Lorenz-84, where one forcing parameter drives fixed-point, limit-cycle, and chaotic regimes while the governing equations and library stay fixed, we show that a single number, $λ_{\min}(M)$, the smallest eigenvalue of the invariant-measure moment matrix, sets the identifiability ceiling for both sparse regression (SINDy) and evolutionary symbolic regression (PySR). Derived from the Birkhoff ergodic theorem and obtained from a short reference trajectory before any run, $λ_{\min}(M)$ measures how fully the attractor covers function space: where it vanishes, recovery is impossible for any algorithm, sparse or combinatorial alike; as it grows, both algorithms improve. Chaos raises $λ_{\min}(M)$ by spreading the attractor, but also enlarges it and amplifies noise; because noise enters SINDy's regression bottleneck linearly and PySR's discrimination channel superlinearly, the same transition can push the two methods in opposite directions, so deeper chaos is not uniformly better. Parameter-free mechanistic scores from this framework transfer without refitting to a held-out Lorenz-96 system, confirming mechanism rather than curve-fitting; a criterion read from the equations predicts when added chaos will not improve conditioning. We also introduce Soft F1, a coefficient-weighted structural metric that resolves performance differences invisible to binary-success and predictive scores. The first question of discovery is then not which algorithm, but what the attractor permits. --- ### The Open Ant: A Robot Platform for Reinforcement Learning Research Authors: Elena Sorina Lupu, Patrick Spieler, Khurram Javed, Kris De Asis, John D. Martin, Martha Steenstrup, Joseph Modayil Published: 2026-07-20 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2607.18488v1 Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations. The predominance of simulations makes translating research to physical reality uncertain for both algorithms and researchers. We propose a physical platform that is designed to simplify the transition. In this paper, we present the Open Ant: a physical variant of the commonly used Gymnasium Ant environment, along with a simulation. We demonstrate that competent walking policies can be learned from scratch in approximately one hour directly from the physical robot's experience for two substantially different RL algorithms: SARSA($λ$) and Soft Actor-Critic (SAC). Separately, we show policies that were learned in simulation transfer to reality. We also examine how well the platform supports a nimble experimental ecosystem. Specifically, we observe the speed with which new users from diverse backgrounds achieve their first success with the platform, and how easily the platform can be repaired and updated when hardware issues arise. Both the hardware design and software are available as open-source on GitHub for ease of customization. In summary, we advocate for the use of the Open Ant for RL researchers who frequently use simulated environments, so they can more easily include robot experiments in their evaluations. --- ### Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing Authors: Jie Li Published: 2026-07-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.18485v1 Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial instructions in a log, tool description, shared file, or peer-agent message may redirect the agent beyond the task the user assigned, even though every resulting command is authenticated and permitted for that account. We refer to this as the hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings. HPC security, by contrast, has mature controls for identity and isolation but does not ordinarily represent the intent of a particular task. This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific workflows, and examines where current controls fall short. It concludes with a research agenda and a plan for an empirical benchmark, TaskBound. --- ### Governing Well in the Algorithmic Age: The Foundations of Digital Statecraft Authors: Zeynep Engin, Tim Gordon, Viviana Bastidas, Tom Crick, Jon Crowcroft, Jean-Martin Denis, David J. Hand, Ed Humpherson, Lauren Maffeo, Jakob Mökander, Irene Ng, Anastasija Nikiforova et al. Published: 2026-07-20 Categories: cs.CY, cs.AI, cs.ET, cs.SI, eess.SY arXiv: https://arxiv.org/abs/2607.18483v3 The digital substrate - data, algorithms, infrastructure, platforms, applications - is being governed without adequate conceptual foundations. The ability and legitimacy required to govern this substrate, and to govern with it, are simultaneously misaligned, contested, and structurally absent. We introduce digital statecraft as the organising concept for this emerging field, arguing that 'digital' reconstitutes the statecraft question rather than merely extending its domain. The concept operates on two dimensions - statecraft over digital systems, concerning the authority and capacity of the state in relation to the digital substrate itself, and statecraft with digital systems, concerning the deployment of algorithmic tools as instruments of governing authority. And it rests on two foundational requirements, technical coherence and legitimate authority, that are genuinely in tension. We derive ten principles of digital statecraft from these foundations, each naming a condition whose absence produces an identifiable and structural governance failure: public interest first, human-machine complementarity, governability by design, systemic coherence, hybrid institutions, adaptive governance, human centricity and civic agency, accountable and traceable authority, judgment across time, and the non-delegable core. This article takes the state as the starting point, the institutional form that developed historically in response to the problem of effective and legitimate public governance, and the only current candidate for which the full set of legitimacy conditions is institutionally available. But the digital statecraft programme holds open a deeper question than just whether states can reform themselves: governing well in the algorithmic age may require rethinking the boundaries, scale, and affiliative basis of statehood itself. --- ### Governing Well in the Algorithmic Age: The Foundations of Digital Statecraft Authors: Zeynep Engin, Tim Gordon, Viviana Bastidas, Tom Crick, Jon Crowcroft, Jean-Martin Denis, David J. Hand, Lauren Maffeo, Jakob Mökander, Irene Ng, Anastasija Nikiforova, Giulio Quaggiotto et al. Published: 2026-07-20 Categories: cs.CY, cs.AI, cs.ET, cs.SI, eess.SY arXiv: https://arxiv.org/abs/2607.18483v1 The digital substrate of states -- data, algorithms, infrastructure, platforms, applications -- is being governed without adequate conceptual foundations. The ability and legitimacy required to govern this substrate, and to govern with it, are simultaneously misaligned, contested, and structurally absent. We introduce digital statecraft as the organising concept for this emerging field, arguing that 'digital' reconstitutes the statecraft question rather than merely extending its domain. The concept operates on two dimensions - statecraft over digital systems, concerning the authority and capacity of the state in relation to the digital substrate itself, and statecraft with digital systems, concerning the deployment of algorithmic tools as instruments of governing authority. And it rests on two foundational requirements, technical coherence and legitimate authority, that are genuinely in tension. We derive ten principles of digital statecraft from these foundations, each naming a condition whose absence produces an identifiable and structural governance failure: public interest first, human-machine complementarity, governability by design, systemic coherence, hybrid institutions, adaptive governance, human centricity and civic agency, accountable and traceable authority, judgment across time, and the non-delegable core. This article takes the state as the starting point, the institutional form that developed historically in response to the problem of effective and legitimate public governance, and the only current candidate for which the full set of legitimacy conditions is institutionally available. But the digital statecraft programme holds open a deeper question than just whether states can reform themselves: governing well in the algorithmic age may require rethinking the boundaries, scale, and affiliative basis of statehood itself. --- ### Search-on-Graph-R1: Training Large Language Models to Search Knowledge Graphs with Reinforcement Learning Authors: Jia Ao Sun, Hao Yu, Fengran Mo, Zhan Su, Yuchen Hui, Bang Liu, Jian-Yun Nie Published: 2026-07-20 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.18481v1 Knowledge graph question answering (KGQA) requires navigating from topic entities to an answer several relations away. Recent methods prompt a frontier LLM to explore the graph through a retrieval tool, but their reliance on frontier-scale inference makes them costly to deploy. We present Search-on-Graph-R1 (\sogrone{}), which internalizes this navigation into a compact 8B model through supervised fine-tuning (SFT) followed by reinforcement learning (RL). Our central idea is to scaffold a frontier teacher with each question's gold SPARQL query, so the teacher traverses a known answer-bearing path with a live \texttt{Search} tool rather than having to discover the path itself. Since every call executes against a live Freebase server, the resulting trajectories are grounded in the knowledge graph by construction. On WebQSP, CWQ, and GrailQA, \sogrone{} at 8B surpasses every frozen frontier-LLM system in our comparison and posts the strongest results on CWQ of any system we compare against. It does so using no auxiliary module at inference and no LLM judge during training. Isolating each training stage shows that SFT and RL contribute complementary gains, our approach transfers across model families, and RL learns to reach answers in fewer \texttt{Search} calls than its SFT initialization. --- ### Hybrid Latent-Structural Fusion (HLSF) for Cyber Anomaly Detection Authors: Dorianis M. Perez, Maksim E. Eren, Bryan E. Kaiser Published: 2026-07-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.18479v1 Malicious anomalous activity detection is a fundamental challenge for cyber security systems. Both tensor decomposition under statistical framework with CANDECOMP-PARAFAC alternating Poisson regression (CP-APR) and normalizing flows have proven to be powerful unsupervised machine learning methods that model multi-dimensional data and capture complex and multi-faceted details of behavior profiles in cyber security applications. In this study, we propose Hybrid Latent-Structural Fusion (HLSF), a weighted anomaly fusion framework integrating CP-APR structural anomaly scores with latent-space density scores derived from normalizing flows. In our experiments, we show that the HLSF framework improves anomaly detection performance on a dataset of real-world compromised user credentials collected from the large enterprise network of Los Alamos National Laboratory (LANL) during a red-teaming exercise, compared with using CP-APR or normalizing flows alone. --- ### Structured Output Collapses Answer Diversity Across 44 Language Models Authors: Tapan Parikh Published: 2026-07-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.18476v1 When a language model must choose one answer from a large space of equally valid options, a format clause -- "Reply with JSON only" -- changes which answer it chooses. We re-run the One-Word Census (arXiv:2607.12796): 31 wide-answer-space category prompts asked of 44 models, now with the reply requested in JSON -- no schema enforcement, no constrained decoding, only the request. Convergence deepens sharply: on the unconstrained "Pick a word" prompt the modal answer rises from 41% to 64% of the pool and distinct answers fall from 52 to 36; mean answer-choice surprisal drops from 1.80 to 1.58 bits. The tax is progressive: six of 44 models move individually (BH-FDR q=.10), all toward the mode, led by the most distinctive models, while the conformist floor is immobile. It is a sharpener, not a re-indexer -- the plain-chat modal answer survives in 28 of 31 categories. Defaults are register-indexed: a within-run re-sample (n=20) finds JSON shifts 53% of a model's stable chat defaults, mostly back to the crowd, and installs defaults absent from chat (Claude Fable 5 answers "cerulean" for colour 0% of the time in chat, 100% in JSON). Full-battery controls reveal a register gradient: compression is significant and specific to the answer-delivery formats models are trained to speak (JSON -0.22 bits, p=.0002; XML -0.19, p=.002), absent for YAML and CSV, and reversed for an arbitrary bracket wrapper (+0.13, p=.009) -- weighing the mechanism toward tool-use post-training. Enforcing the schema at the decoder (response_format) compresses no further than the request (-0.03 bits): the collapse lives in the model's response to the register, not the decoder. Structured output is how software consumes language models, and that surface is served by a measurably more homogeneous model than the chat surface on which models are evaluated, compared, and chosen. --- ### RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts Authors: Yuxin Xiong, Xunyi Jiang, Rohan Surana, Xintong Li, Sheldon Yu, Nikki Lijing Kuang, Ryan A. Rossi, Jingbo Shang, Tong Yu, Julian McAuley, Junda Wu Published: 2026-07-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18470v1 Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose \textbf{Reference-Relative Policy Optimization (RRPO)}, which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons. RRPO first uses \emph{stratified conditional rollouts} to construct positive and negative anchor sets, and then trains a metric projection head with a set-contrastive objective to compare candidate rollouts against these anchors. The resulting alignment scores directly define contrastive advantages: during policy optimization, the projection head is frozen, and the scores are centered within each rollout group in a standard group-relative objective. We evaluate RRPO using anchor-based contrastive advantages throughout policy optimization, without relying on task ground-truth verifiers. Across verifiable reasoning, open-ended generation, and post-SFT settings, RRPO remains competitive with verifier-based optimization, improves over weakly supervised baselines, and provides additional gains after supervised fine-tuning. --- ### Weak-to-Strong Learning in Decision Making Authors: Jingwei Ji, Renyuan Xu Published: 2026-07-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.18467v2 Many operational decisions rely on predictive models that estimate uncertain outcomes conditional on observable contexts. Training such models, however, often faces a fundamental data asymmetry: labeled outcomes are scarce or costly to obtain, while contextual covariates are abundant. Motivated by this data asymmetry, we develop a decision-aware weak-to-strong (W2S) framework that leverages both labeled and unlabeled data to improve contextual stochastic optimization. Specifically, we first train a weak model using limited labeled data and then use it to generate predicted outcome distributions on unlabeled contexts. These distributions provide soft supervision for training a strong model. We establish a non-asymptotic upper bound on the excess decision risk of W2S and a complementary lower bound for a strong-only benchmark. Their comparison yields explicit sufficient conditions under which W2S improves downstream decision performance. The key quantity is the correlation dimension between the weak and strong feature representations: when it is small, abundant unlabeled data reduce the effect of teacher errors along non-overlapping directions. A synthetic newsvendor experiment and a comment moderation experiment based on real-world data provide empirical evidence consistent with the theory. --- ### Weak-to-Strong Learning in Decision Making Authors: Jingwei Ji, Renyuan Xu Published: 2026-07-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.18467v1 Many operational decisions rely on predictive models that estimate uncertain outcomes conditional on observable contexts. Training such models, however, often faces a fundamental data asymmetry: labeled outcomes are scarce or costly to obtain, while contextual covariates are abundant. Motivated by this data asymmetry, we develop a decision-aware weak-to-strong (W2S) framework that leverages both labeled and unlabeled data to improve contextual stochastic optimization. Specifically, we first train a weak model using limited labeled data and then use it to generate predicted outcome distributions on unlabeled contexts. These distributions provide soft supervision for training a strong model. We establish a non-asymptotic upper bound on the excess decision risk of W2S and a complementary lower bound for a strong-only benchmark. Their comparison yields explicit sufficient conditions under which W2S improves downstream decision performance. The key quantity is the correlation dimension between the weak and strong feature representations: when it is small, abundant unlabeled data reduce the effect of teacher errors along non-overlapping directions. A synthetic newsvendor experiment and a comment moderation experiment based on real-world data provide empirical evidence consistent with the theory. --- ### ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization Authors: Kaiyuan Tang, Chaoli Wang Published: 2026-07-20 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2607.18466v1 Recent advances in differentiable Gaussian splatting have highlighted the potential of primitive-based approaches as alternative scene representations for interactive, high-quality, volume visualization (VolVis) of large datasets. However, the explicit nature of current primitive-based methods, combined with isolated optimization for each VolVis scene, results in redundant, non-compact representations. We present ECoNGS, an efficient compressive neural Gaussian splatting framework for VolVis scene representation. ECoNGS employs lightweight neural networks to dynamically predict implicit, editable Gaussian splats from explicit anchor points, effectively combining model compactness and parameter efficiency of implicit representations with high-performance rendering of explicit primitives. We explore a joint learning strategy that clusters geometrically similar scenes and shares parameters across them, significantly reducing overall training time and model size while maintaining reconstruction fidelity. To achieve a more compact scene representation, we further compress the explicit anchor attributes using a neural entropy model that estimates their probability distributions, enabling compact storage via entropy coding. We systematically investigate Gaussian initialization strategies and propose a simple yet effective scheme tailored for VolVis scenes, improving reconstruction accuracy and accelerating convergence. We evaluate ECoNGS qualitatively and quantitatively across various univariate and multivariate VolVis scenes, highlighting its superior performance over prior methods in training time, reconstruction quality, and model size. In particular, compared with the prior method iVR-GS, ECoNGS improves reconstruction quality by up to 2.2 dB in PSNR while reducing the model size by up to 6.1x and the training time by up to 5.9x. The code is available at https://github.com/TouKaienn/ECoNGS. --- ### AHEAD: Advancing Multi-Class Label Aggregation with Interpretable Cross-Annotator Modeling Authors: Ju Chen, Sijia Xu, Jun Feng, Zhiqiang Gao, Zhengyi Yang Published: 2026-07-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.18465v1 Crowdsourced labeling provides valuable labeled data for domains across natural language processing, computer vision, and video. Label aggregation aims to infer latent true labels from noisy and biased annotations, with the key lying in annotator reliability estimation. Despite promising progress, existing approaches struggle with one real-world bottleneck: most individual annotators label only a small subset of tasks, making accurate annotator estimation highly intractable. In this paper, we focus on the considerably more challenging multi-class label aggregation and propose AHEAD (cross-Annotator learning and High-confidEnce Annotator-guideD label aggregation), a cross-annotator learning framework that advances annotator reliability estimation by leveraging the population-level data. Specifically, AHEAD first learns high-dimensional cross-annotator contexts via a graph neural network, deriving multi-view, complementary annotator embeddings by aggregating individual-level annotator features with contextual information. These embeddings are then decoded into interpretable annotator-specific confusion matrices to fit the observed labels. We formulate a composite objective incorporating high-confidence annotators to alleviate the unsupervised training issues faced by prior models. Experiments on 10 real-world datasets spanning NLP, CV, Video, and Audio show that AHEAD substantially improves label accuracy, increasing average accuracy from 68.75% to 73.23%, with gains of up to 14.9% in the best case. Meanwhile, scalability experiments on the largest dataset further demonstrate the overall superiority of our method. --- ### Competitive and Complementary Tools Authors: David C. Krakauer Published: 2026-07-20 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2607.18460v1 Humans have always externalized thought onto tools, from the tally and the abacus to the map and, now, large language models. I model the agent, the tool, and the task as one dynamical system in which competence (what the user retains) and reliance (what the user outsources) co-evolve, and find that the outcome is bistable. Above a critical tool availability the competent state is destroyed and competence collapses toward a low dependent floor as the user outsources completely. Lowering availability does not reverse the collapse until a far lower threshold, so history of practice rather than the current tool fixes the state. Two users with the same present access can therefore occupy opposite and lasting states, one competent and one dependent, decided only by which they built first. The collapse threshold depends jointly on the competence a user brings to a task and on the tool's transparency, the fraction of its working a user can reconstruct. In the case where an agent faces an uncertain goal, a tool can cause agency itself to transfer to the tool and the human-agent becomes an agentic-instrument, irreversibly, because the tool's model is too large to internalize. The model is tested against several independent data sets, including GPS and map use, arithmetic expertise, and language models. These results reframe how tools should be built, how artificial intelligence is deployed, and what a tool-resistant education might require. --- ### Estimating Rare Events in Language Models with Proper Evaluation Authors: Nikita Y. Parulekar, Anqi Liu Published: 2026-07-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18454v1 Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling. While recent work has formalized Low Probability Estimation, existing pipelines remain fragile in the rarest regimes: estimators can suffer zero-estimate collapse or systematic bias, and standard evaluation losses can become unstable or poorly matched to asymmetric safety costs. In this work, we introduce Gradient Activation Adaptive Multi-Level Splitting (GA-AMLS), which adapts rare-event Monte Carlo methods to the continuous activation space of language models. Specifically, GA-AMLS uses a gradient-based MCMC kernel to navigate activation space, eliminating the zero-estimate collapse of input-space search and replacing the independence assumptions of prior activation-space estimators with conditional sampling under an explicit, heavier-tailed activation prior. We also propose the Shifted-Power Bregman (SPB) Loss, a proper scoring rule that remains finite for zero-estimates and offers tunable asymmetry between underestimation and overestimation penalties. Experiments on small transformer models reveal a bias-variance tradeoff: GA-AMLS achieves the lowest loss under symmetric evaluation, reducing average log-space squared error relative to the strongest baseline across model sizes, while methods with overestimation bias prevail under asymmetric penalties. Our findings highlight that estimator choice should be matched to deployment context. More broadly, our work establishes activation space as a tractable domain for rare-event estimation in language models, circumventing the brittleness of discrete input-space search. --- ### CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging Authors: Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn Published: 2026-07-20 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.18451v3 A foundation encoder is pretrained once on a large image corpus and then reused with its weights frozen. Each new task is solved by training a small head on the features it produces. This setup is common in medical imaging, where labeled cases are scarce and a frozen encoder can be reused across findings. All downstream tasks then depend on the class separation present in that fixed feature space. Encoder selection usually uses the area under the receiver operating characteristic curve (AUROC) of a trained downstream head. AUROC measures the predictive information a head can extract from the features, but it does not measure class separation in the frozen feature space. A positive image that lies near a negative image in feature space has a bounded normalized margin under any Lipschitz head. Chance-calibrated neighborhood discordance (CANDOR) measures this feature-space separation without training a head. For a positive image, it compares the k nearest positive-label neighbors with the k nearest negative-label neighbors, among images acquired the same way. Discordance rate D is the share of positives whose opposite-label neighbors are nearer. Drawing the 2 candidate sets at equal size makes the labels interchangeable, so label-independent features have chance level D=1/2 without simulation. We apply CANDOR to 22 frozen encoders on 605,443 images from 20 public datasets, covering 8 binary tasks in 7 domains. On every task, the best encoder is below 1/2. A discordant image bounds the normalized margin of every Lipschitz head on that encoder. A selector that is shown the true label and chooses among 11 encoders reduces the miss rate from 0.359 to 0.028. Discordance is associated with occlusion retention and with none of pretraining objective, parameter count, release year, or finding size. The fixed chance level lets D be computed for a frozen encoder before any downstream head is trained. --- ### CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders Authors: Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn Published: 2026-07-20 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.18451v1 Frozen encoders are chosen by how well a lightweight head reads a finding from their features, not whether the geometry separates it. Nearest-neighbor discordance does, but with unequal banks the opposite-label neighbor wins on density, not geometry, so prevalence alone makes an uninformed encoder look blind. We introduce CANDOR, a discordance measure whose equal-size banks are symmetric under a label swap, fixing its chance level at exactly one half. Across 22 encoders, 20 datasets from 7 domains, and 605,443 images, this correction reverses the conclusion. Collapse falls below chance almost everywhere, so no encoder is blind, yet all are weak: the best chest model reads pneumothorax at 84.5 AUROC and still places 18.4% of those positives nearer an opposite-label film than its own kind in the same hospital. The same encoder that resolves bird species at 4.5 leaves chest findings at 42.8 and glaucoma at 49.8, at chance and worse than random weights. Such a case caps the normalized margin of any Lipschitz head, yet some head among eleven is correct on all but 2.8% of cases where one head misses 35.9%: the deficit is selection, not information. Erasure retention is associated with collapse; we detect no association with the objective, scale, recency, or size of the finding. Because the chance level is fixed, CANDOR can be read before any head is trained, flagging which findings a frozen encoder supports poorly. --- ### PathReportEval: A Systematic Benchmark for Pathology Report Generation Authors: Suryakant Singh, Sejuti Majumder, Beatrice Knudsen, Joel Saltz, Prateek Prasanna Published: 2026-07-20 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.18448v1 Pathology report generation from whole-slide images (WSIs) is a rapidly growing multimodal learning problem, yet progress is difficult to measure because existing studies use heterogeneous datasets, model settings, visual encoders, and evaluation protocols. Moreover, commonly used natural language generation metrics, including BLEU, ROUGE, and METEOR, primarily reward lexical similarity and often fail to detect clinically consequential errors such as omitted diagnoses, hallucinated findings, or discordant tumor attributes. We present a standardized benchmark and evaluation framework for pathology report generation. The benchmark evaluates four representative methods across three datasets (TCGA, HistAI, and REG 2025) using three pathology foundation encoders (CONCHv1.5, UNI2-h, and H-Optimus-1). Our framework standardizes preprocessing, feature extraction, training, decoding, and evaluation, enabling fair comparison across models while providing a modular platform for integrating new methods, datasets, and encoders. A central contribution is the Clinical Report Quality Score (CRQS), a clinically grounded metric for evaluating factual correctness. CRQS maps reference and generated reports into structured clinical attributes and measures four complementary dimensions: clinical fact coverage, key information recall, hallucination rate, and clinical discordance, producing both an overall score and interpretable sub-scores. Experiments demonstrate that conventional language-generation metrics are weakly aligned with clinical correctness and frequently overestimate report quality. In contrast, CRQS reveals clinically meaningful differences between models and encoders that lexical metrics fail to capture. Together, the benchmark, public plug-and-play framework, and CRQS establish a reproducible foundation for rigorous evaluation of pathology report generation. --- ### Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs Authors: Sam Relins, Daniel Birks Published: 2026-07-20 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.18446v1 Purpose: Understanding how much of routine policing involves vulnerable people could inform resourcing, training, and multi-agency response, yet administrative data provide limited insight. We explore whether an LLM-based classification pipeline, developed on open-source US police data, can be adapted to estimate the prevalence of four vulnerability indicators - mental ill health, substance misuse, alcohol dependence, and homelessness - in UK police incident narratives, and when outputs can be treated as defensible measurements. Methods: We analyse nearly 3,000 de-identified incident logs from a UK police force, using a multi-stage pipeline combining repeated model inference, label aggregation, structured human review, and statistical correction. The pipeline runs on a locally hosted open-weight LLM, reflecting the secure environments police must work in. Results: LLMs can produce meaningful, if imperfect, prevalence estimates at scale. Mental ill health indicators are present in approximately one in five incidents, with lower prevalence for other indicators. However, naive LLM deployment is unreliable: single-pass classifications are unstable, and aggregated outputs systematically over-assign indicators relative to human judgement. Correcting these biases required substantial human input and statistical adjustment, leaving considerable uncertainty. Conclusions: While LLMs can extract information from unstructured police data, their outputs cannot be treated as valid measurements without careful methodological support. At the population level, defensible estimates are achievable but resource-intensive; at the individual level, errors remain frequent and unpredictable, limiting suitability for operational decisions. This study highlights both the potential and the constraints of LLM-based measurement in applied settings. --- ### ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration Authors: Chengheng Li-Chen, Kyuhee Kim Published: 2026-07-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.18445v1 Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating LM and on heuristic thresholds with no closed-form calibration. We introduce ChainMark, an active watermark that partitions the vocabulary into S states via keyed SHA-256 and forces a hard Markov transition on a fraction rho of positions; the detector replays the partition from the same key in O(n) hash operations, with no LM access. We derive a closed-form S*(n, rho, alpha) mapping a target FPR, text length, and budget to the minimum state count (Theorem 1), prove a universal robustness threshold delta* = 1 - 1/sqrt(2) approximately 29.3% that is invariant in (S, rho, n) (Theorem 2), and generalise both to any k-regular transition topology (Theorem 3). Across three instruction-tuned LLMs and four domains, ChainMark strictly dominates KGW and SWEET under translation and random-substitution attacks at matched budget; a one-corpus empirical recalibration restores the 1% target FPR on natural-language text. --- ### Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives Authors: Polina Tsvilodub, Fausto Carcassi, Michael Franke Published: 2026-07-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.18443v1 Pragmatic language use requires reasoning about alternatives: the alternative expressions a speaker might have chosen, or the alternative interpretations a listener might entertain. Formal and computational models of pragmatics must therefore specify the sets of alternatives that interlocutors reason over, which is often done through manual specification. Here we propose a framework, ScAffolded Generative models for Explanation (SAGE), that combines the explanatory transparency of cognitive models with the generative flexibility of language models (LMs). SAGE decomposes a pragmatic process into three kinds of modules: proposers, which use LMs to generate an open-ended space of candidate alternatives; evaluators, which assess those alternatives (e.g., their semantics, complexity, or typicality); and selectors, which implement the rule-based computational steps of a cognitively motivated task analysis. We assess SAGE in three case studies spanning pragmatic generation and interpretation-referential expression generation, manner (M-)implicatures, and Gricean conversational implicatures. SAGE models are evaluated critically using established methods from computational cognitive modeling, including ablations, baseline comparisons, and quantitative fit to human data. Across studies, SAGE models achieved high accuracy and often outperformed baselines, but component-level analyses reveal an asymmetry: LM proposers reliably generated alternatives well-suited to pragmatic modeling, whereas LM evaluators are better at providing intuitive judgements rather than judgements of theoretical or formal measures. We discuss the promise and the limitations of neuro-symbolic models as candidate explanatory accounts of human pragmatic language use. --- ### Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains Authors: Liam Swayne Published: 2026-07-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.18438v1 Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 (xHigh), scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information extraction (with a focus on web search), problem-solving, general knowledge, and data analysis. No restrictions are imposed outside of the model harness, and models are explicitly encouraged to leverage code-execution, web searches, and all available tools. All problems are composed of two to thirteen subproblems and do not require multi-modal input or output. --- ### Surprise Forcing: What to Remember, When to Skip in Long Video Generation Authors: Shuwei Shi, Zhen Li, Muyao Niu, Chuanhao Li, Bo Zheng, Kaipeng Zhang, Yinqiang Zheng Published: 2026-07-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.18436v1 Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly across a highly non-stationary sequence. A rolling key-value cache forgets distant visual evidence even when that evidence remains important, while every generated chunk receives the same number of denoising passes irrespective of its actual difficulty. We introduce Surprise Forcing, a training-free framework that treats both limitations as online resource-allocation problems. A Surprise-Gated Memory Bank summarizes evicted frames with value-token descriptors, evaluates them using complementary global-deviation and nearest-neighbor novelty signals, and regulates admission through a feedback-controlled budget in normalized score space. Priority-based replacement and relevance-aware routing then keep the external memory compact and useful. In parallel, Surprise-Aware Denoising estimates chunk difficulty from the maximum adjacent-frame cosine distance after the first denoising pass and uses a local percentile scheduler to skip intermediate steps for comparatively easy chunks. Experiments on VBench, VBench-Long, and VBench-2.0 show that the proposed allocation strategy improves long-horizon consistency and visual quality while retaining real-time streaming throughput. --- ### Intelligence from Learnable Novelty Authors: Yanbo Zhang, Michael Levin Published: 2026-07-20 Categories: cs.LG, cs.AI, nlin.AO arXiv: https://arxiv.org/abs/2607.18433v1 Intelligence appears under different names in different fields: as data compression in statistics and machine learning, as universal computation in dynamical systems, and as adaptive behavior in agents. Each field carries its own objective, and the two most influential drives often fail in mirror image: novelty search, which seeks surprise, is transfixed by a noisy television screen, while the free-energy principle, which avoids surprise, is most content in a dark room. Both failures have a single cause: each objective treats as one quantity the surprise a learner can convert into knowledge and the surprise it never can. Here we show that the learnable part of that information, which we call learnable novelty, yields the seemingly disparate projections of intelligence, and we give a closed-form estimator of it built on a cheap and differentiable reservoir computer. Used as a measure, with no supervision of any kind, the estimator recovers decades of complexity classification, ranking the Turing-complete rule~110 highest among the elementary cellular automata. Used as an objective, its gradient carries a neural cellular automaton from simple dynamics into a regime of solitons, the traveling, colliding structures by which rule~110 computes, as well as organizes the representation of an image encoder around the ten digit classes of MNIST, fully unsupervised: no label ever enters training. Handed to a reinforcement-learning agent as an intrinsic reward, it supplies the exploration that task rewards lack, improving on the task baseline in nine of ten environments and collapsing in none. Complexity generation, abstraction, and exploration, ordinarily pursued with unrelated objectives in separate fields, thus emerge from ascent on one differentiable quantity, and the projections of intelligence gain a common quantitative footing. --- ### Building a European Multilingual Evaluation Dataset: The MMLU Localisation Project within the EMT Network Authors: Pilar Sánchez-Gijón, Susana Valdez, Sofía Calvo Del Barrio, Florence Bellemont, Anna Kokkinidou, Mihai Cristian Brasoveanu Published: 2026-07-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.18432v1 This paper reports on a collaboration between the Directorate-General for Translation (DGT) and the European Master's in Translation (EMT) to localise the MMLU dataset into 11 European languages. Beyond creating a more inclusive benchmark for LLM evaluation, the project offers master's students authentic, project-based professional training in translation, revision, project management, and multilingual coordination, while highlighting key methodological, administrative, and workflow challenges. --- ### Using binary silver labels in electronic health records-based computable phenotyping algorithms Authors: Shuhe Wang, Matthew T. Slaughter, Jennifer C. Nelson, Brian D. Williamson Published: 2026-07-20 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.18431v1 Gold-standard phenotype labels are often unavailable at scale in electronic health record (EHR) studies because they require manual chart review. Weakly supervised phenotyping methods instead use silver-standard labels, such as diagnosis-code counts, natural language processing (NLP) mentions, medication indicators, or laboratory thresholds. PheNorm is widely used for this purpose, but its original formulation was designed for count-valued silver labels and relies on log transformation, utilization normalization, and Gaussian mixture modeling. These steps are not directly suited to binary silver labels, which are common and may be highly informative. We propose Binary PheNorm, an extension that uses binary silver labels directly in the corruption-and-regression denoising step and produces a continuous phenotype score without EM calibration. We also consider a lasso-regularized version for high-dimensional EHR settings and combined models using both binary and count labels. In simulations, Binary PheNorm achieved strong discrimination using binary labels alone and often improved performance when combined with count labels. In anaphylaxis, AUC increased from 0.793 for an epinephrine-mention indicator to 0.891-0.892 after Binary PheNorm. In acute pancreatitis, AUC increased from 0.736 for a lipase-threshold indicator to 0.805-0.819. These results support Binary PheNorm as a practical weakly supervised approach when informative binary silver labels are available. --- ### Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT Authors: Tanveer Ahmed, Seyedali Pourmoafil Published: 2026-07-20 Categories: cs.CR, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2607.18429v2 Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to evade detection. This paper reports a controlled, pairwise comparison of two phishing-detection approaches a TF-IDF + Logistic Regression baseline and a fine-tuned DistilBERT transformer trained on a unified corpus of 82,255 emails drawn from six public datasets and evaluated under three conditions: normal in-distribution, synthetic phishing, and adversarial phishing. Both models exceeded 98% accuracy on clean data yet degraded sharply under adversarial testing: TF-IDF + LR fell to 64.00% (a 34.59-percentage-point drop) and DistilBERT fell to 63.64% (a 35.40-percentage-point drop) a gap of only 0.36 percentage points, equivalent to a single email in the 275-sample adversarial test set. LIME, SHAP, and attention-rollout analysis indicate the two models relied on different evidence yet showed similar vulnerability. Pairwise error analysis shows the models agreed on 54.9% of adversarial samples but each made a similar number of exclusive errors (24 and 25 respectively), indicating partly complementary rather than identical failure modes. The results show that clean-data accuracy does not predict adversarial robustness, and that adversarial testing should be a standard part of phishing-detection evaluation. --- ### Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT Authors: Tanveer Ahmed, Seyedali Pourmoafil Published: 2026-07-20 Categories: cs.CR, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2607.18429v1 Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to evade detection. This paper reports a controlled, pairwise comparison of two phishing-detection approaches a TF-IDF + Logistic Regression baseline and a fine-tuned DistilBERT transformer trained on a unified corpus of 82,255 emails drawn from six public datasets and evaluated under three conditions: normal in-distribution, synthetic phishing, and adversarial phishing. Both models exceeded 98% accuracy on clean data yet degraded sharply under adversarial testing: TF-IDF + LR fell to 64.00% (a 34.59-percentage-point drop) and DistilBERT fell to 63.64% (a 35.40-percentage-point drop) a gap of only 0.36 percentage points, equivalent to a single email in the 275-sample adversarial test set. LIME, SHAP, and attention-rollout analysis indicate the two models relied on different evidence yet showed similar vulnerability. Pairwise error analysis shows the models agreed on 54.9% of adversarial samples but each made a similar number of exclusive errors (24 and 25 respectively), indicating partly complementary rather than identical failure modes. The results show that clean-data accuracy does not predict adversarial robustness, and that adversarial testing should be a standard part of phishing-detection evaluation. --- ### Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps Authors: Marcos Moran, David Rodriguez, Luka Nenadic, Norman Sadeh, Jose M. Del Alamo Published: 2026-07-20 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2607.18424v1 Automated analyses of privacy policies enable large-scale assessments of transparency in digital ecosystems, yet existing auditing pipelines remain predominantly English-centric. This limits their ability to systematically evaluate multilingual environments, as in the European Union, where many services disclose privacy practices only in local languages. This paper examines whether large language models (LLMs) can extend privacy policy analysis beyond English without requiring language-specific adaptation, thus empowering large-scale auditing in linguistically diverse app ecosystems. We assemble an evaluation corpus spanning all 24 official EU languages from translated versions of two established expert-annotated datasets (OPP-115 and MAPP) and assess translation fidelity through automated metrics and targeted legal-expert review. Our LLM-based classifier for identifying categories of personal data collection achieves stable cross-lingual performance, with macro-F1 scores ranging between 0.91 and 0.94. We then leverage this capability in a large-scale audit of 2,611 Android applications from the Spanish Google Play Store. Combining multilingual privacy policy analysis with the evaluation of corresponding privacy labels and runtime network traffic exposes an important linguistic barrier: public-sector apps predominantly provide privacy policies in Spanish, whereas popular commercial apps mostly provide them in English. We reveal systematic discrepancies between declared and observed practices, especially in public-sector apps. Overall, our results indicate how English-only privacy audits can systematically obfuscate transparency gaps in multilingual environments. --- ### PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors Authors: Nicola Aladrah, Fabio Anselmi Published: 2026-07-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.18422v1 Overparameterized models often have continuous parameter symmetries, so different parameters define the same predictor. We show that PAC--Bayesian analysis should be performed on the quotient predictor space: pushing a prior and posterior to the quotient preserves the empirical and population Gibbs risks while removing the nonnegative KL contribution caused solely by how the two distributions differ among parameterizations of the same predictor. Quotienting alone does not determine which prior to use. We construct a canonical choice of one parameterization for each predictor and account for the geometric volume of its equivalent parameterizations. This transforms a neutral reference prior into a data-independent prior that reflects the model's implicit bias. It approximates the ideal but inadmissible posterior-matched prior, which would minimize the KL term by depending on the training data. The resulting certificate is tighter exactly when this geometry-induced prior has smaller KL divergence from the learned quotient posterior than the neutral prior. We test this prediction in Fourier regression with a Hadamard parameterization and in Query-Key attention, using ordinary SGD without an explicit regularizer. The implicit-bias prior reduces the mean quotient-space KL by \(40.69\%\) and the mean PAC--Bayes certificate by \(21.40\%\) in the Fourier-Hadamard experiment. The smaller, prior-scale-dependent improvement in Query-Key attention confirms the predicted conditional nature of the effect. --- ### Convolution for Large Language Models Authors: Yuchuan Tian, Yingte Shu, Wei He, Shuo Zhang, Tianchen Zhao, Chao Xu, Xinghao Chen, Yunhe Wang, Hanting Chen, Yu Wang Published: 2026-07-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.18413v1 Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality of natural language. We study whether lightweight depthwise convolutions can supply this local inductive bias without materially increasing model size. Our macro-level ablation compares convolution at 17 locations in a Qwen3 Transformer block and finds the best results when convolution is applied to the projected queries, keys, and values before attention. A subsequent micro-level study favors a residual depthwise convolution with kernel size $k=3$, without additional normalization or activation. Across Qwen3 models and several pre-training data budgets, this design improves the average accuracy on seven downstream benchmarks while adding less than $0.01\%$ parameters. A representation-level case study further suggests that the convolution makes repeated token IDs more sensitive to their immediate context. These results support depthwise convolution as a lightweight complement to self-attention for modeling short-range token interactions. --- ### Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs Authors: Huizhe Zhang, Yuchang Zhu, Huazhen Zhong, Liang Chen, Zibin Zheng Published: 2026-07-20 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2607.18412v1 Dynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems. Due to the scarcity of labeled data in real-world dynamic graphs, recent studies have introduced generative or contrastive paradigms (e.g., masked graph autoencoders or graph contrastive learning) to generate task-agnostic graph embeddings. However, these methods typically rely on complex edge-level reconstruction objectives and tailored graph augmentation strategies. This incurs substantial computational overhead when scaling to large-scale dynamic graphs. In this paper, we propose SG-JEPA, a joint spiking embedding predictive architecture for large-scale dynamic graphs. In contrast to existing self-supervised methods, SG-JEPA partitions nodes into context and target sets along the temporal dimension to learn embeddings that are predictive of each other via additional spatial-temporal information. Furthermore, through encoding sequential inputs into coarse-to-fine spike count embeddings, spiking neurons enable SG-JEPA to adapt to the varying computational constraints of downstream tasks. Extensive experiments demonstrate that SG-JEPA achieves competitive or even superior performance over discriminative baselines on node classification, while effectively scaling to the dynamic graph with 13 million edges. SG-JEPA avoids the complex machinery (negative sampling, graph augmentations, edge-level reconstruction, etc.), resulting in superior training efficiency and memory scalability compared with prior self-supervised dynamic graph baselines. --- ### Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability Authors: Taewoon Kim, Vincent François-Lavet, Michael Cochez Published: 2026-07-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18368v3 Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-graph memory in RoomKG, where hidden state and observations are represented as Resource Description Framework (RDF) graphs and memory is augmented with temporal RDF triple annotations. The model combines knowledge-graph encoding of memory contents with value heads for question answering, exploration, and forgetting, yielding a controller that is both adaptive and inspectable. This gives the work a direct Semantic Web grounding through RDF-based representation, annotation-compatible graph semantics, and graph-based symbolic operations over explicit memory state. On train/test room splits at long-term memory capacity of 512, the qualifier-aware StarE-GNN configuration achieves the best held-out performance among the compared symbolic, neural, and neuro-symbolic systems while preserving step-level traceability of memory-management decisions. --- ### AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report Authors: AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu et al. Published: 2026-07-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.18367v1 Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly. It enable us to create customized, explorable, and continuously evolving virtual world from text, an image, or video. Realizing this vision requires four tightly coupled capabilities: interaction, persistent spatiotemporal consistency, stable long-horizon generation, and efficient response. We present AlayaWorld, an interactive long-horizon video world model that generates 24-fps video at 540p and 720p. Built on a 15B video diffusion transformer, AlayaWorld generates short latent chunks autoregressively under camera trajectories and switchable text prompts. Its bounded visual context combines a persistent sink frame, compressed temporal history, geometry-aligned spatial memory, and recent-frame conditioning. To reduce long-term drift, the model is trained with corrupted histories and prediction residuals collected from its own roll-outs. We further introduce a discrete autoregressive distillation formulation that combines distribution-matching distillation, self-forcing++, and consistency distillation, reducing inference from approximately 30 sampling steps to four steps per chunk. On iWorld-Bench, AlayaWorld achieves the best performance over long-horizon generation. Conceived as a full-stack, open-source, and long-term project, AlayaWorld is intended to provide an extensible foundation for future research on interactive video world models. --- ### Operational Hallucination and Safety Drift in AI Agents Authors: Shasha Yu, Fiona Carroll, Barry L. Bentley Published: 2026-07-20 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2607.18366v1 Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabilities where initial alignment degrades over time. This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift, the gradual erosion of declared safety intent leading to constraint-violating actions (e.g., textual refusal followed by reconnaissance and unsafe execution), and Operational Hallucination, persistent repetitive tool calls indicative of flawed state perception (e.g., livelocks even in legitimate tasks). Through controlled multi-turn evaluation on high-stakes ethical dilemmas, malicious requests, and benign controls, we quantify these phenomena using declaration-action gap and livelock metrics, demonstrating their cross-model prevalence under direct execution protocols. Root-cause analysis attributes the instabilities to the decoupling of reasoning context from execution state in current agent loops. We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, runtime state tracking, and forced termination primitives. Post-hoc simulation on captured failure trajectories shows the layer can intercept observed violations without false positives on benign cases. This work advances agent reliability by shifting focus from linguistic safeguards to enforceable architectural mechanisms for responsible agentic AI. --- ### Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion Authors: Jordan Dowdy, Jean Chagas Vaz Published: 2026-07-20 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.18365v1 Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain. Traditionally, these RL locomotion frameworks are position-based, making the policy less adaptable to terrain types and requiring state estimation techniques in the observation space, i.e., linear velocity. Moreover, these RL frameworks often use small, lightweight quadrupeds that are limited in their viability for high-complexity tasks due to hardware constraints. This work explores an RL torque control framework for heavyweight high-torque quadrupeds. The RL framework in this paper can traverse rough terrain and effectively track a desired linear velocity without requiring knowledge of the agent's current velocity. Using Nvidia's Isaac Sim and Isaac Lab, simulation results of the RL torque control policy are shown on the Unitree B1 quadruped, achieving speeds of 3.5 m/s and 1.5 rad/s. In addition, the quadruped can walk up and down stairs without the aid of an exteroceptive sensor. --- ### A Controlled Study of Attention-Only Transformers Authors: Henry Ndubuaku, Karen Mosoyan, Jakub Mroz, Noah Cylich, Satyajit Kumar, Parkirat Sandhu, Roman Shemet, Justin H Lee Published: 2026-07-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.18363v1 Feed-forward networks hold two thirds of a transformer's non-embedding parameters, yet the architecture has not received a necessity test that controls parameters, compute, and depth at once. We pretrain attention-only decoder transformers (Simple Attention Networks, SANs) against standard transformers matched separately for parameter count, training FLOPs, and depth (2 to 48 layers), for up to 105B tokens at 6M to 87M parameters. Deleting feed-forward layers in place is costly: the standard transformer leads by 0.47 nats at matched depth and 0.26 nats at matched FLOPs. Reallocating the freed budget into attention depth closes the gap: at matched parameters the difference is 0.006 nats (0.27 percent of loss), reproducible to one part in ten thousand across seed pairs, shrinking across 5B, 30B, and 105B budgets, and holding near 0.02 nats across a 29x size range. Three measurements localize the remaining gap to parametric recall: attention-only models are better on context-grounded answers and worse where knowledge must come from weights. Weight spectra show why: routing matrices (Q/K) crystallize early, content matrices accumulate rank slowly, and removing feed-forward layers relocates this accumulation to the attention output projection. QK-normalization, not feed-forward layers or residual gating, keeps 48-layer attention-only stacks trainable. The deficit concentrates on low-context query prediction and localizes there entirely by the largest budget. A pre-registered test confirms the account: it predicts a 0.02 to 0.05 nat gap on knowledge-dense web text; a matched pair trained on fineweb-edu measures 0.040. Within the tested regime, attention does the rest. --- ### Physical Self-Supervised Learning: IMU Sensing without Manual Labels Authors: Yuyang Leng, Renyuan Liu, Shaohan Hu, Peijun Zhao, Chun-Fu Chen, Songqing Chen, Shuochao Yao Published: 2026-07-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.18361v2 Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogeneous devices, placements, and users. Existing unsupervised and self-supervised methods reduce but do not remove this dependence, still requiring labeled data for domain adaptation and largely ignoring known physical structure. We propose physical self-supervised learning, an autoencoder-style paradigm for label-free IMU sensing. We replace the conventional neural decoder with an auto-adaptive physics decoder, a learnable family of kinematic equations that enforces explicit physical structure while adapting across environments, and adopt a hybrid two-stage IMU encoder with reconstruction in a structured latent space to mitigate sensor noise. Our framework further introduces probabilistic frequency-spatial constraints to disentangle sensor and object motion, a multi-view kinematic tree to exploit sparse physical self-supervised signals, and an uncertainty-aware formulation to handle the inherent ambiguity of IMU inference. Evaluated on inertial tracking and full-body motion capture over public datasets and realistic deployments, physical self-supervised learning reduces errors by up to 5x for tracking and 4x for motion capture in challenging generalization scenarios, consistently outperforming state-of-the-art supervised and self-supervised baselines without any labels. Our code is available at https://github.com/YuyangLeng/physical-ssl-imu-label-free --- ### HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers Authors: Patrik Reizinger, Wieland Brendel Published: 2026-07-20 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.18360v1 Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set. Rule- and LLM-based verifiers are emerging, but no shared benchmark compares them and gives detailed failure diagnostics. We close that gap with HALLMARK (Hallucination benchmark): 2,526 BibTeX entries spanning 14 hallucination types, three difficulty tiers, six diagnostic sub-tests per entry, and a contamination-resistant held-out split. On it we evaluate a DOI-lookup baseline, frontier LLMs zero-shot, tool-augmented agents, and our own rule-based, co-designed verifier bibtex-updater. Across the benchmark one result is consistent: the false-positive rate, not recall, decides whether a verifier is deployable. HALLMARK makes it concrete through three failure modes: agentic lookups buy recall but inflate false positives; at a venue-realistic base rate, the order-of-magnitude spread in false-positive rates (FPRs) -- not recall -- governs whether a verifier's flags are mostly true catches or mostly noise; and most LLMs over-flag papers published past their training cutoff, where only the two latest-cutoff models hold their false-positive rate near in-distribution levels (a signal we report as descriptive, since it is confounded with possible recall of those entries). Thus FPR is the deployment bottleneck, but an undetected fabrication remains the costlier error for the scientific record. ---