arXiv:2605.30656v1 Announce Type: new
Abstract: In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the empowerment objective, which maximizes an agent's influence over the environment and is widely used for unsupervised skill learning. We show that empowerment agents induce two distinct representations -- forward and backward -- that capture complementary aspects of the state, and both of which are invariant to control-irrelevant features. Thus, empowerment maximization leads agents to learn an implicit, control-centric model of the world. Our analysis highlights the importance of learning representations through interaction rather than from passive datasets: interaction aimed at maximizing control is essential for learning useful invariance properties, a perspective that aligns closely with the causal learning literature.
Science Journals
arXiv:2603.09632v4 Announce Type: replace
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI applications. However, most existing 3DGS methods operate in isolation, focusing on specific domains. In this paper, we introduce X-GS, an extensible framework consisting of two major components. The X-GS-Perceiver unifies a broad range of 3DGS techniques to enable real-time online SLAM with semantic distillation. The X-GS-Thinker accommodates multimodal models, enabling them to seamlessly interface with the Perceiver to complete downstream tasks. In our implementation of X-GS, the Perceiver leverages the latest vision foundation models to improve online SLAM performance and employs three key mechanisms to accelerate semantic distillation. The Thinker can be built upon both contrastive and generative vision-language models and utilizes the Perceiver's semantic Gaussian splats to unlock capabilities such as 3D visual grounding and scene captioning. Experimental results on diverse benchmarks demonstrate the efficiency and newly unlocked multimodal capabilities of the X-GS framework.
arXiv:2605.30675v1 Announce Type: new
Abstract: Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucination, the field has largely focused on measuring and improving calibration, the accuracy of uncertainty judgments to task efficacy. In this work, we investigate the relatively underexplored question of how similar large language model uncertainty is to human uncertainty. We investigate the presence and strength of human-similar uncertainty signals, deemed uncertainty alignment, in large language model overt behavior and internal activation patterns. We identify whether the models show evidence of simultaneous alignment and calibration on a variety of datasets covering both multiple choice and open ended factual recall. And we characterize the effect of instruct fine-tuning on each of these facets.
arXiv:2605.30694v1 Announce Type: new
Abstract: Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local information into globally coherent behavior. This paper proposes a common categorical formulation: a Universal Decision Learner (UDL) extends a partially specified decision functor from observed contexts to new contexts by a pair of universal constructions. Left Kan extensions express rollout, aggregation, and candidate generation; right Kan extensions express consistency, constraint satisfaction, and fixed-point semantics. The central claim is not that every decision problem has the same algorithm, but that many decision formalisms instantiate the same universal problem: extend local behavioral data canonically, then characterize the globally coherent extensions. We give the abstract UDL construction, prove its universal comparison property, define Kan-invariant behavioral equivalence and minimal abstractions, and show how Bellman equations, planning recursions, causal interventions, online regret, and equilibria arise as special cases. The supplementary material develops the reinforcement-learning specialization in more detail.
arXiv:2605.30696v1 Announce Type: new
Abstract: Safe navigation often relies on well-defined conditions based on the shape of robots and obstacles, and can be challenging when they have irregular geometries. While Control Barrier Functions (CBFs) offer an efficient mechanism to enforce safe set forward invariance, common shape surrogates (e.g., spheres or super-ellipsoids) either are overly conservative in unstructured scenes or require many local primitives, which inflates constraint counts and degrades real-time performance. In this paper, we introduce a novel geometry-aware Control Barrier Function (CBF) based on Bernstein-Polynomial Signed Distance Fields (BP-SDFs). It provides a unified way to represent the obstacles and robots, so as to represent the barrier function with a unified minimum distance. Benefiting from the differentiability of the Bernstein polynomials, one can easily enforce the control constraints in a closed loop. We validate the method's efficiency and performance to guarantee safety in single-robot navigation and heterogeneous multi-robot collision avoidance via simulations under different environments.
arXiv:2605.30701v1 Announce Type: new
Abstract: Sensitive and fast mid-infrared (MIR) spectroscopy is highly attractive in a variety of applications including astronomical observation, pharmaceutical synthesis, and environmental monitoring. However, the performance of conventional MIR spectrometers has long been hindered by the limited sensitivity of narrow-bandgap detectors and/or the deficient brightness of broadband light sources. Here, we devise and implement an ultra-sensitive and broadband MIR upconversion spectrometer, which integrates a supercontinuum source covering 1.5-4.2 $\mu$m based on a silicon nitride nanophotonic waveguide. High-efficiency and low-noise nonlinear frequency upconversion is realized based on coincidence pulsed pumping with spectro-temporal optimization, which enables to leverage silicon detectors for facilitating MIR single-photon spectroscopy at 0.2 photons/nm/pulse. Furthermore, the upconversion-based array spectrometer is manifested with high-speed spectral acquisition rates beyond 200 kHz, which is about ten-fold faster than the state-of-the-art scan rates for FTIR-based spectrometers at a comparable spectral resolution. The achieved features of broadband spectral coverage, single-photon sensitivity, and sub-MHz refreshing rate might open up new possibilities in infrared transient spectral measurements in combustion analysis, high-throughput sorting and reaction tracking, among others.
arXiv:2605.30702v1 Announce Type: new
Abstract: Active mid-infrared (MIR) imagers capable of retrieving three-dimensional (3D) structure and reflectivity information are highly attractive in a wide range of biomedical and industrial applications. However, the infrared 3D imaging at low-light levels is still challenging due to the deficiency of sensitive and fast MIR sensors. Here we propose and implement a MIR time-of-flight imaging system that operates at single-photon sensitivity and femtosecond timing resolution. Specifically, back-scattered infrared photons from a scene are optically gated by delay-controlled ultrashort pump pulses through nonlinear frequency upconversion. The upconverted images with time stamps are then recorded by a silicon camera to facilitate the 3D reconstruction with high lateral and depth resolutions. Moreover, an effective numerical denoiser based on spatiotemporal correlation allows us to reveal the object profile and reflectivity under photon-starving conditions with a detected flux below 0.05 photons/pixel/second. The presented MIR 3D imager features with high detection sensitivity, precise timing resolution, and wide-field operation, which may open new possibilities in life and material sciences.
arXiv:2605.30820v1 Announce Type: new
Abstract: We establish a fundamental principle in coherent wave-optical computing: restricting the modulation manifold from continuous complex-valued to binary amplitude suppresses stochastic-noise up-conversion while preserving classification fidelity, yielding a counter-intuitive less-is-more robustness law. Seven-layer binary-amplitude-mask D2NN (BM-D2NN) achieve 90.9% (MNIST) and 81.9% (Fashion-MNIST) test accuracy, within 2~4 pp of continuous-modulation D2NN (C-D2NN). Under pixel-wise Gaussian noise N(m,{\sigma}^2), spanning zero-mean (shot noise) to nonzero-mean (thermal/readout) regimes, BM-D2NN outperform C-D2NN by up to 32.8 pp (MNIST) and 18.5 pp (Fashion-MNIST). We analytically derive a noise-contribution metric C, governed by a transmission-bias factor K computable from clean data alone, that is consistently smaller for binary modulation than for continuous modulation (as verified for all test samples), guaranteeing the robustness ordering without noisy simulation. BM-D2NN additionally deliver a 6.79-fold higher imaging-plane intensity for clean data input. These results establish a quantitative physical principle connecting modulation-manifold geometry to noise robustness, applicable to any coherent optical processor in the z/{\lambda} >> 1 regime.
arXiv:2605.30703v1 Announce Type: new
Abstract: Single-pixel cameras have recently emerged as promising alternatives to multi-pixel sensors due to reduced costs and superior durability, which are particularly attractive for mid-infrared (MIR) imaging pertinent to applications including industry inspection and biomedical diagnosis. To date, MIR single-pixel photon-sparse imaging has yet been realized, which urgently calls for high-sensitivity optical detectors and high-fidelity spatial modulators. Here, we demonstrate a MIR single-photon computational imaging with a single-element silicon detector. The underlying methodology relies on nonlinear structured detection, where the encoded time-varying pump patterns are optically imprinted onto the MIR object image through sum-frequency generation. Simultaneously, the MIR radiation is spectrally translated into the visible region, thus permitting infrared single-photon upconversion detection. Then, the use of advanced algorithms of compress sensing and deep learning allows us to reconstruct MIR images under sub-Nyquist sampling and photon-starving illumination. The presented paradigm of single-pixel upconversion imaging is featured with single-pixel simplicity, single-photon sensitivity, and room-temperature operation, which would establish a new path for sensitive imaging at longer infrared wavelengths or terahertz frequencies, where high-sensitivity photon counters and high-fidelity spatial modulators are typically hard to access.
arXiv:2605.30711v1 Announce Type: new
Abstract: Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control. We frame memory evolution as a novelty-detection problem and propose SAGE, a Spherical Adaptive Gate for memory Evolution that scores candidate facts with a von Mises-Fisher-based density estimator over memory embeddings and routes them with an adaptive threshold that tracks memory-store geometry. SAGE resolves clearly novel facts as ADD, clearly redundant facts as NOOP, and sends only uncertain cases to an LLM merge step, reducing expensive write-time reasoning. On LoCoMo, SAGE achieves the best average token-F1 against Mem0 on all seven open-weight backbone comparisons, while on GPT-4o-mini it reduces add-phase API cost by 3.4$\times$ and add-phase latency by 2.5$\times$ with only a small average judge-score gap. As a drop-in binary gate for A-Mem, SAGE skips roughly 16-18% of LLM calls across five models with minimal quality change on open-weight backbones. These results suggest that novelty-aware write control is a practical lever for improving both memory quality and system efficiency in long-term agentic memory.
arXiv:2605.30808v1 Announce Type: new
Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-training on real human preference data raises privacy concerns, as these datasets often contain sensitive user prompts and human judgments. To address this, we propose DPPrefSyn, a novel algorithm for generating differentially private (DP) synthetic preference data to enable privacy-preserving preference alignment. DPPrefSyn is a principled framework grounded in the Bradley-Terry preference model and the intrinsic geometric structure of pairwise human preference data. It first learns an underlying preference model from private data with formal differential privacy guarantees, and then leverages the learned model together with public prompts to synthesize high-quality preference data. It exploits the shared linear structure of per-cluster reward models to effectively capture heterogeneous human preferences in private datasets, and leverages DP Principal Component Analysis (DP-PCA) to improve learning accuracy. Extensive experimental results demonstrate that DPPrefSyn achieves competitive alignment performance under strong DP guarantees. These findings highlight the potential of synthetic preference data as a practical alternative for privacy-preserving preference alignment across a broad range of applications. To the best of our knowledge, this is the first work to generate DP synthetic preference data for LLM alignment. Our code is available at https://github.com/gfengyu/Differentially-Private-Preference-Data-Synthesis.
arXiv:2605.30713v1 Announce Type: new
Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-language models (VLMs) remain underexplored. We present a systematic study of TTC across seven VLMs and six benchmarks, specifically analyzing feature-based scoring and majority voting methods. We find that feature heuristics fail and voting yields only modest gains in single-model settings. We theoretically show that this limitation stems from a lack of prediction diversity: when outputs are highly correlated, voting provides little benefit. In contrast, multi-model ensembles offer richer diversity, yet standard majority voting fails to account for varying model capabilities. To address this, we propose Entropy-based TTC (ETTC), which selects the most confident prediction based on predictive entropy. Our method reduces to majority voting in the single-model case, but in model ensembles, it leverages confidence disparities to prioritize stronger models. We prove that ETTC outperforms majority voting under mild assumptions and empirically demonstrate that it consistently surpasses both voting and the best individual model. Crucially, our results show that smaller models can synergistically enhance larger ones, unlocking ensembling gains not achievable with standard strategies.
arXiv:2605.30720v1 Announce Type: new
Abstract: Forecasting agricultural commodity prices in emerging economies is difficult due to high volatility, frequent supply disruptions, and strong cultural influences on demand. This study introduces the Kalimati Vegetable Price Index (KVPI), a new inverse-volatility weighted composite index that aggregates 135 daily wholesale commodities from Kathmandu over ten years (2013-2023). By creating a stable macro-level signal, the KVPI reduces the noise inherent in modelling individual crops. A rich set of 64 causally valid features was developed, including festival lead-lag effects, rolling statistics, and calendar variables. Fourteen forecasting models spanning statistical, tree-based, deep learning, hybrid, and transformer architectures were rigorously evaluated across short (7-day), medium (14- and 30-day), and long-term (90-day) horizons. Tree-based ensembles proved notably robust, while classical statistical models and complex transformers struggled with the noisy dataset. The proposed Momentum-Corrected Online Stacking Ensemble achieved the strongest performance, yielding a Root Mean Square Error (RMSE) of 1.771, an exceptionally low Mean Absolute Percentage Error (MAPE) of 0.68%, and explaining 84.5% of the variance (R-squared = 0.845) at the 90-day horizon. This open-source pipeline provides policymakers and supply chain actors in Nepal and similar markets with a practical, reliable tool for anticipating price movements and strengthening food security.
arXiv:2603.08721v2 Announce Type: replace
Abstract: New AI accelerators with novel instruction set architectures (ISAs) often require developers to manually craft low-level kernels, a time-consuming and error-prone process that does not scale across hardware targets. This delays emerging hardware platforms from reaching the market. While prior LLM-based code generation has shown promise in mature GPU ecosystems, it remains unclear whether agentic LLM systems can quickly produce valid and efficient kernels for emerging hardware with new ISAs. We present KernelCraft: the first benchmark for evaluating an LLM agent's ability to generate and optimize low-level kernels for customized accelerators through a function-calling, feedback-driven workflow. We evaluate agent performance across three emerging accelerators on more than 20 machine-learning tasks, each with five diverse task configurations. Across four leading reasoning models, the strongest agents generate functionally correct kernels for unseen ISAs within a few refinement steps and produce optimized kernels that match or outperform compiler baselines. These results demonstrate KernelCraft's potential to accelerate the accelerator chip development cycle. KernelCraft is available at https://kernelcraft-cam.github.io/.
arXiv:2605.30727v1 Announce Type: new
Abstract: Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive information from its local context. This risk is amplified by the mosaic effect, where individual queries may appear harmless but become revealing in aggregate. We introduce MosaicLeaks, a benchmark of 1,001 multi-hop deep research tasks that chain private enterprise documents and a public web corpus, forcing agents to make external queries that depend on local information. We evaluate leakage with an adversary LLM that observes only the agent's external queries and attempts to infer private information at three levels: the agent's research intent, answers to specific private questions and verifiable claims about the enterprise documents. We find that models across families and sizes frequently leak at all three levels, that zero-shot privacy prompting reduces but does not eliminate leakage and that reinforcement learning for task performance alone worsens leakage. To address this, we propose Privacy-Aware Deep Research (PA-DR), an RL framework that combines situational rewards for task success with a learned privacy classifier to provide dense credit assignment over both per-query and mosaic-level leakage. Training Qwen3-4B-Instruct with PA-DR improves accuracy from 48.7% to 58.7% and reduces answer and full-information leakage from 34.0% to 9.9%.
arXiv:2605.30745v1 Announce Type: new
Abstract: Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. However, this semantic abstraction creates a critical vulnerability in open-world deployment: the ``Hubris of Semantics'', where models force-fit unknown anomalies into known categories with high confidence due to the lack of explicit negative knowledge. To address this \textit{Open-World Trustworthiness Paradox}, we propose \textbf{Immuno-VLM}, a bio-inspired framework that adapts the biological principle of \textbf{Immunological Negative Selection} to high-dimensional latent spaces. Departing from traditional Open-Set Recognition methods that rely on passive density estimation or inefficient pixel-space outlier generation, Immuno-VLM leverages the generative reasoning of Large Language Models to actively hallucinate ``Semantic Antibodies'', textual descriptions of near-distribution outliers (e.g., look-alikes, contextual anomalies) that effectively bound the decision space of known classes.Extensive experiments on ImageNet-1K and four challenging OOD benchmarks reveal that Immuno-VLM establishes a new state-of-the-art.
arXiv:2605.30749v1 Announce Type: new
Abstract: Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians.
While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces.
Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space.
To instantiate this insight, we introduce \textbf{FLAG} (\textbf{F}low policy with \textbf{L}atent-\textbf{A}ugmented \textbf{G}uidance).
FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective.
We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to high-dimensional control tasks.
Furthermore, FLAG achieves state-of-the-art performance across challenging benchmarks. Our project webpage: https://flag-rl.github.io/
arXiv:2605.30757v1 Announce Type: new
Abstract: Chain-of-thought prompting and looped Transformers both give a fixed model more test-time computation, but they differ in what they remember. Chain-of-thought stores intermediate state in generated tokens that remain in the context, whereas a looped Transformer carries state through recurrent hidden activations. We argue that this persistent mutable memory is a central resource for test-time reasoning.
We compare three memory regimes, the compressed latent loop, the full sequence-state loop, and the chain-of-thought scratchpad. Our main result shows that a compressed loop is limited by the size of its recurrent state. Running the loop longer adds computation but does not by itself create a growing scratchpad, so a loop with a small recurrent state remains a small-space reasoner even when run for many steps. Under a standard complexity assumption, such loops cannot decide problems that are P-complete under logspace reductions, whereas polynomial-length chain-of-thought can.
The separation is specific to compressed loops, as full sequence-state loops carry state at every input position and live in a memory-rich regime closer to explicit scratchpads. Controlled pointer-chasing and associative-recall sweeps illustrate this memory-budget view, with performance sensitive to whether the persistent-state budget matches the task's working-memory demand.
arXiv:2605.30776v1 Announce Type: new
Abstract: Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distributions. Existing work aims to mitigate the harm of this shift by finetuning the policy on trajectory data sampled from a diffusion model. Inspired by this line of work, we propose DUAL: an efficient \textbf{D}iffusion \textbf{U}ncertainty-\textbf{A}ware framework for offline-to-online reinforcement \textbf{L}earning. DUAL utilizes the prior knowledge of the diffusion model to distill a fast-sampling diffusion actor policy and transition model in the offline phase. DUAL also employs a Laplace approximation and distance transition-state-shift detection, thereby using uncertainty quantification to improve exploration versus exploitation in the online phase. We formally show that our actor loss with the Laplace approximation provides a proxy for a principled estimate of epistemic uncertainty. Empirically, DUAL improves the online expected return over O2O-RL baselines across multiple settings and environments.
arXiv:2605.30736v1 Announce Type: new
Abstract: The rapid development of large language models, each with distinct capabilities and inference costs, raises a practical deployment question: given an incoming request, which model should handle it? We present OrcaRouter, a production-oriented LLM router that combines a LinUCB-based contextual bandit over lexical and sentence-embedding features with a hybrid offline-online learning protocol. Offline, OrcaRouter obtains full-information feedback by evaluating each candidate model on a curated set of routing prompts, yielding a reward matrix used to fit one ridge regressor per arm. At deployment time, it initializes from these parameters and can optionally continue learning from bandit feedback, updating only the selected model's arm after observing its reward. At the time of our RouterArena submission (May 20, 2026), OrcaRouter-Adaptive ranked second on the public RouterArena leaderboard with an arena score of 72.08, achieving 75.54% accuracy at a cost of USD 1.00 per 1,000 queries.
arXiv:2605.30784v1 Announce Type: new
Abstract: Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-world scenarios often involve heterogeneous sensing modalities such as LiDAR and RGB cameras, making LiDAR-Camera Cross-modal Gait recognition (LCCGR) a critical yet challenging task due to the substantial modality gap between 2D videos and 3D point cloud sequences. To address this challenge, we propose TCFDNet, a Text-guided Cross-modal Feature Disentanglement Network, which leverages modality-aware textual priors as semantic anchors to guide the learning of disentangled modality-shared representations. Specifically, we construct a Gait Modality Text Dictionary (GMTD) using large language models to generate rich semantic descriptions of gait across modalities and viewpoints. A CLIP-based Multi-grained Feature Encoder then aligns visual and textual features within a unified vision-language space. Furthermore, the Text-guided Feature Disentanglement (TFD) module selects the topk matched textual descriptions to reconstruct modality-specific representations and derive modality-shared features via residual decomposition and orthogonality constraints. To mitigate the fragility of the disentangled shared features, we propose a Feature Stability Enhancement (FSE) module, which models spatial and channel-wise correlations to improve feature robustness. In addition, a cross-modal patch exchange strategy is introduced to further improve generalization. Extensive experiments on SUSTech1K and FreeGait datasets demonstrate that TCFDNet achieves new state-of-the-art results and validate the effectiveness of the proposed modules.
arXiv:2605.31273v1 Announce Type: new
Abstract: While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 layers, scaled CRL still struggles with long-horizon goal-conditioned planning due to the uniformity-tolerance dilemma inherent in contrastive losses. We introduce Survival Reinforcement Learning (SRL), an online classification-based alternative that extends the survival value learning framework by maximizing the agent's dwell time at target goals. SRL bypasses the structural constraints of CRL and mitigates the "bang-bang" control solutions inherent to survival frameworks, which often induce undesirable behavior in complex dynamical systems. Evaluated across diverse robotic benchmarks, scaled SRL matches state-of-the-art CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks. Our results provide strong additional evidence that classification-based methods may serve as a key primitive in the broader effort to scale reinforcement learning.
arXiv:2605.29299v2 Announce Type: replace
Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres, where timely inference, limited hardware, and local handling of patient images are vital for practical, privacy-preserving clinical prescreening. Here we present Pocket-Dentist, an efficiency-aware benchmark for dental multimodal question answering that brings together three datasets spanning approximately 1,159 patients, five task types and seven metrics. Across typical 14 VLMs, our results reveals an interesting observation: compact VLMs (e.g., 2B-parameter models) outperform larger VLMs in accuracy while requiring substantially lower computational costs in dental image understanding. Deployed locally on an iPhone 17 Pro, our finetuned compact VLM Pocket-Dentist-2B processed each sample in 4.31 s, reducing latency by 4.9-fold and memory use by 2.3-fold compared with a 7B baseline.
arXiv:2605.30791v1 Announce Type: new
Abstract: Community anchor institutions (CAIs), such as libraries, schools, and community centers, are critical for providing Internet access to un- or under-served individuals and communities. Because many of these institutions are themselves under-provisioned, analyzing the reliability and quality of their Internet service is important. Doing so at scale requires knowing the IP addresses of these institutions so that broadband measurement and policy evaluation can occur. Unfortunately, these IPs are not systematically documented. As a first step towards widespread, scalable evaluation of CAI Internet connectivity, this paper presents Reverse IP Geolocation (RG), a new framework to infer IP addresses from physical address data. A key insight is that CAI street addresses are publicly known, which allows us to identify a candidate set of IPs from commercial geolocation that are likely serving the location associated with a CAI. In this paper, \textbf{we focus on US public libraries}, which offer both geographic diversity across thousands of locations, and some publicly available institutional records (\eg{}WHOIS registrations) that enable systematic validation of our approach. Our approach offers a novel integration of IP geolocation databases, DNS PTR records, WHOIS registrations, broadband provider data, and active measurements to identify IPs likely assigned to libraries and validate them. Based on evaluations, our approach can map a library to its IP prefix approx. half of the time, with coverage across all US states, as well as urban and rural areas. Our results highlight the feasibility of mapping CAI presence in IP space and offer a foundation for large-scale, remote broadband infrastructure evaluation.
arXiv:2605.30803v1 Announce Type: new
Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric asking for a response to be ``helpful and factual'' can reward polished answers that invent facts or violate user intent. We treat reusable rubrics as measurement specifications: changing the rubric changes the response quality measurement induced by a fixed judge. We introduce PReMISE, a framework that, given pairwise human-preference data, (i) discovers a policy-level rubric set, and (ii) audits any rubric set under LLM-judge use along four axes: structural adequacy, reliability, preference fit, and adversarial robustness. Across rubric sources no raw source is simultaneously reliable, preference-predictive, and adversarially robust; and high inter-rater agreement does not imply low exploitability. PReMISE is the only rubric source to score non-trivially on applicability, specificity, and effective dimensionality simultaneously. We contribute two audit-targeted repair operations: preference-rank selection raises judge accuracy on paired responses from $65.0\%$ to $68.6\%$, competitive with the strongest rubric-discovery baselines and leading on two of three judges in our cross-judge sweep; reliability-constrained refinement reduces the rate at which exploit responses receive high scores from $46.4\%$ to $36.0\%$ with little change in inter-judge agreement ($\alpha{=}.531\to.519$).