arXiv:2603.25710v2 Announce Type: replace
Abstract: We introduce a contravariant idempotent adjunction between (i) the category of ranked monads on $\mathsf{Set}$; and (ii) the category of internal categories and internal retrofunctors in the category of locales. The left adjoint takes a monad $T$-viewed as a notion of computation, following Moggi-to its localic behaviour category $\mathsf{LB}T$. This behaviour category is understood as "the universal transition system" for interacting with $T$: its "objects" are states and the "morphisms" are transitions. On the other hand, the right adjoint takes a localic category $\mathsf{LC}$-similarly understood as a transition system-to the monad $\Gamma\mathsf{LC}$ where $(\Gamma\mathsf{LC})A$ is the set of $A$-indexed families of local sections to the source map which jointly partition the locale of objects. The fixed points of this adjunction consist of (i) hyperaffine-unary monads, i.e., those monads where term $t$ admits a read-only operation $\bar{t}$ predicting the output of $t$; and (ii) ample localic categories, i.e., whose source maps are local homeomorphisms and whose locale of objects are strongly zero-dimensional. The hyperaffine-unary monads arise in earlier works by Johnstone and Garner as a syntactic characterization of those monads with Cartesian closed Eilenberg-Moore categories. This equivalence is the Stone duality for monads; so-called because it further restricts to the classical Stone duality by viewing a Boolean algebra $B$ as a monad of $B$-partitions and the corresponding Stone space as a localic category with only identity morphisms.
Science Journals
arXiv:2604.07993v2 Announce Type: replace
Abstract: Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.
arXiv:2604.10959v2 Announce Type: replace
Abstract: Intelligent Transportation Systems increasingly depend on heterogeneous data from roadside cameras, UAV imagery, LiDAR, and in-vehicle sensors, yet the lack of unified data standards, model interfaces, and evaluation protocols across these sources hampers reproducibility, cross-dataset benchmarking, and cross-region transferability of research findings. Existing trajectory datasets follow incompatible conventions for coordinate systems, object representations, and metadata fields, forcing researchers to build custom preprocessing pipelines for each dataset and simulator combination. To address these challenges, we propose Ozone, a unified platform for transportation research organized around five interconnected layers -- Hardware, Data, Model, Evaluation, and Prototype -- each with standardized schemas, automated conversion pipelines, and interoperable interfaces. In the first release, the data schema unifies four trajectory datasets -- NGSIM, highD, CitySim, and UTE -- into a canonical format with oriented bounding boxes, kinematic variables, and pre-computed surrogate safety measures. Digital-twin maps in CARLA and calibrated traffic models provide integrated benchmarking environments. Case studies in human-factor research, traffic scene generation, and safety-critical modeling demonstrate that Ozone reduces experiment setup time by 85%, achieves 91% cross-city transfer efficiency for safety models, and improves cross-dataset reproducibility to within 3% variance. The source code and datasets are publicly available.
arXiv:2603.29501v2 Announce Type: replace
Abstract: Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower target updates improve stability but reduce the recency of learning signals, hindering convergence speed. We propose Target-Aligned Reinforcement Learning (TARL), a simple drop-in refinement for existing algorithms that emphasizes transitions for which the target and online network estimates are highly aligned. By focusing updates on well-aligned targets, TARL mitigates the adverse effects of stale target estimates while retaining the stabilizing benefits of target networks. We empirically demonstrate consistent improvements within discrete and continuous control algorithms across various benchmark environments without any hyperparameter tuning, including a 38.18% peak score gain on Atari-10, while incurring less than a 4% increase in wall-clock time.
arXiv:2605.19074v1 Announce Type: new
Abstract: The rapid global expansion of solar photovoltaic (PV) capacity-reaching a record 597 GW in 2024-highlights the urgent need for robust forecasting models to mitigate the grid instability caused by the intermittent nature of solar irradiance. While deep learning-based direct forecasting using ground-based sky images (GSI) has emerged as a dominant approach, existing literature is often constrained by single-architecture evaluations and an exclusive focus on single-horizon (point) prediction. This paper proposes a transition from traditional single-horizon estimation toward a multi-horizon forecasting framework, leading to an architecture-independent improvement in accuracy. We hypothesize and demonstrate experimentally that joint optimization over a sequence of future values allows deep neural networks to better capture latent inter-step temporal dependencies by avoiding precocious convergence of the network in terms of both weight gradients and filter diversity. Leveraging this architecture-independent improvement that integrates sequential sky imagery with historical PV generation data, we evaluate the models' abilities to predict power output across multiple discrete future time steps simultaneously. Our methodology is validated through a comparative analysis across diverse deep learning architectures. The results demonstrate that this multi-horizon approach significantly enhances predictive accuracy and robustness across the entire forecast horizon while maintaining computational parsimony. By achieving superior performance with negligible overhead compared to single-horizon models, this work provides a scalable and efficient solution to improve the resilience of modern power grids.
arXiv:2605.19510v1 Announce Type: new
Abstract: Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objective that contains only two fundamental loss terms. Despite the simplicity of the learning objective, MetaTrans embodies an advanced UVDA idea, that is, handling the spatial and temporal divergence of cross-domain videos separately, through a subtle model architecture design. By implementing a temporal-static subtraction module, MetaTrans effectively removes spatial and temporal divergence. Extensive empirical evaluations, particularly on various cross-domain action recognition tasks, show substantial absolute adaptation performance enhancement and significantly superior relative performance gain compared with state-of-the-art UVDA baselines.
arXiv:2605.19639v1 Announce Type: new
Abstract: Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual Generation (RVG), we formalize the Reason-Reflect-Rectify (R^3) loop as a core framework and introduce R^3-Bench, a benchmark of over 600 expert-annotated instances that quantifies iterative reasoning and rectification capabilities. Evaluation on R^3-Bench reveals a critical gap: while state-of-the-art models can identify generation errors, they fail to generate actionable rectification instructions. To bridge this gap, we propose R^3-Refiner, a dual-stage framework leveraging Group Relative Policy Optimization (GRPO) and a Hierarchical Reward Mechanism (HRM) to better align rectification with reflective reasoning. Experiments show that R^3-Refiner achieves significant improvements on R^3-Bench (+12.0% in Reflective Verdict Score, +9.0% in Rectification Score), and can be seamlessly integrated with various MLLMs to enhance the generation quality of different T2I models on GenEval++ and T2I-CompBench. Code is available at https://github.com/xiaomoguhz/R3-Bench.
arXiv:2605.19834v1 Announce Type: new
Abstract: To support operations and passenger-facing services, transit agencies need reliable passenger load trajectories. Currently, load estimates are typically inferred from imperfect sensing systems rather than fully observed, and the accuracy of modern automatic passenger counting (APC) systems still varies with station layout, flow intensity, and operating conditions. To address the challenges of robust passenger load estimation from heterogeneous data streams, including incremental count errors, evidence conflicts, and context-dependent sensor reliability, we propose a closed-loop, state-centric, multi-agent framework. This method enforces physical feasibility at every step, allocates trust dynamically among evidence sources, and feeds physics-derived violation residuals back into training for robustness improvement. The architecture consists of a unified stop-event backbone, a coupled Perception--Physical--Fusion loop for stop-by-stop inference, and optional trip-level macro-correction and closed-loop calibration modules.
arXiv:2605.16692v2 Announce Type: replace
Abstract: We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is a planner that aims to find an action sequence that maximizes the estimated return. The return is estimated using a learned model and value networks, each of which can introduce error. EfficientTDMPC proposes to reduce this error in two ways. First, it introduces an ensemble of dynamics models and averages the return estimates across those models and across different rollout depths. Second, it adds the option to apply an uncertainty penalty to the planner objective, yielding a planner that avoids actions with uncertain return estimates. It then adds practical improvements which increase buffer data freshness and reduce compute. Lastly, we find that our contributions enable EfficientTDMPC to benefit more from a higher update-to-data (UTD) ratio, further improving sample efficiency. To the best of our knowledge, in the low data regime of each benchmark, EfficientTDMPC achieves state-of-the-art (SOTA) in terms of sample efficiency on HumanoidBench-Hard and DMC hard, while matching SOTA on DMC easy.
arXiv:2605.18769v1 Announce Type: new
Abstract: Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high retrieval costs and overlook that collaborative signals from similar users can enhance personalized generation for the current user. We propose ClusterRAG, a Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation. ClusterRAG represents users through their profile documents, organizes users into semantically coherent clusters using density-based clustering, and performs retrieval at both the cluster and document levels via cluster-level similarity and fine-grained ranking. Extensive experiments on the LaMP benchmark demonstrate that jointly leveraging the target user's profile and profiles from top similar users consistently yields the best performance across diverse tasks. Further analysis shows that ClusterRAG integrates seamlessly with different dense retrievers and rankers, and remains effective when paired with both fine-tuned and zero-shot language models.
arXiv:2605.18788v1 Announce Type: new
Abstract: In a recent paper, Cao et al. investigated numerically a structure made of two cascaded metasurfaces to realize angle-independent filters. Their calculations show a remarkable performance, with a perfect angle-independent response up to 70 degrees. However, despite several attempts and interactions with the authors, we have been unable to replicate these simulations. This Comment discuss (1) our failed attempts at reproducing the authors' calculations, (2) the lack of any physical explanation for such angle-independent behavior, (3) the fact that the results of Cao et al. can, in fact, be well reproduced by simulations which use incorrect boundary conditions.
arXiv:2605.18863v1 Announce Type: new
Abstract: Nitrogen-vacancy (NV) center ensembles provide a powerful platform for high-precision temperature sensing, with ongoing efforts to further enhance their measurement performance. In ensemble NV optically detected magnetic resonance (ODMR) spectra, commonly used Lorentzian and Voigt fitting models fail to accurately describe the spectral shape near the resonance frequency, leading to degraded precision in resonance-frequency determination and, consequently, temperature estimation. In this work, we analytically establish a new fitting method, termed dip-peak fitting, for extracting the resonance frequency from ensemble cw-ODMR spectra. Starting from a physical model that describes ensemble cw-ODMR spectra as a convolution of single-NV responses with distributed zero-field splitting and strain, we show that the spectral feature near resonance can be accurately approximated by a single Lorentzian function with a background term. The proposed fitting model reproduces the cw-ODMR spectrum around resonance more faithfully than conventional approaches, enabling faster and more accurate resonance-frequency determination under weaker microwave excitation. Experiments using fluorescent nanodiamond ensembles confirm the robustness and applicability of this method for high-precision temperature sensing.
arXiv:2605.18884v1 Announce Type: new
Abstract: Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large language models excel at multimodal reasoning, they typically treat emotion categories as independent labels, ignoring the rich hierarchical taxonomy of human psychology. Moreover, lacking external contextual knowledge makes them highly susceptible to over-interpreting noisy cues, further complicating fine-grained emotion classification. To address these issues, we propose \textbf{HyperEmo-RAG}, a retrieval-augmented generation framework that leverages a structured emotional knowledge base. Our framework introduces two key innovations. 1) Hierarchical hyperbolic grounding. Recognizing the inherent hierarchical tree structure of emotion taxonomies, we jointly embed hierarchical emotion labels and multimodal samples into a continuous hyperbolic space (Poincar\'e ball) and design a hierarchical beam-search deliberation process that progressively retrieves samples from coarse to fine-grained levels. 2) Structured evidence injection. Based on the retrieved evidence, we construct an evidence graph and inject the structured knowledge as explicit cognitive context into the LLM through a Tree-Aware Attention mechanism and an EmotionGraphFormer, preserving the integrity of graph-structured information. Experiments on multiple datasets demonstrate that HyperEmo-RAG significantly outperforms existing methods.
arXiv:2512.05721v2 Announce Type: replace
Abstract: Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational priorities. To bridge this gap, we introduce BERTO, a BERT-based framework for traffic prediction and energy optimization in cellular networks. Built on transformer architectures, BERTO achieves high prediction accuracy while enabling a single fine-tuned model to operate across multiple forecasting regimes via natural-language operator prompts. By combining a Balancing Loss Function (BLF) with prompt-based conditioning, BERTO adaptively shifts its forecasting bias toward underprediction or overprediction depending on the operator's desired trade-off between power savings and service quality. This allows the same model to dynamically generate different decision-aware forecasts without retraining or modifying model parameters. Experiments on real-world datasets demonstrate that BERTO can operate across a flexible range of approximately 1.4 kW in power consumption while balancing 9x variation in service level agreement (SLA) violations, making it well suited for intelligent RAN deployments.
arXiv:2605.18946v1 Announce Type: new
Abstract: We investigate the dependence of the plasmoid-mediated magnetic reconnection rate on the magnetic Prandtl number using two-dimensional magnetohydrodynamic simulations of two coalescing magnetic islands. For Lundquist numbers below the onset of the plasmoid instability, the reconnection rate follows the expected Sweet-Parker scaling and decreases with increasing magnetic Prandtl number. However, once the current sheet becomes plasmoid unstable, the dependence on the magnetic Prandtl number weakens considerably. In the fully plasmoid-mediated regime, we find reconnection rates that remain nearly independent of the magnetic Prandtl number over the explored parameter range. We show that the largest reconnection rates are associated with strongly non-linear phases involving plasmoid interactions and mergers. We further compare our results with simulations of the boundary-driven Taylor problem, where previous studies reported a stronger magnetic Prandtl number dependence, and provide a possible explanation for the differing scalings obtained in the two setups. These results may have implications for reconnection-mediated decay in magnetically dominated turbulence and related astrophysical systems.
arXiv:2605.19149v1 Announce Type: new
Abstract: Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart agents based on state-of-the-art models. They helpfully continue to look for ways to complete their tasks.
We introduce, characterize, and measure a new type of agent failure we call \emph{accidental meltdown}: unsafe or harmful behavior in response to a benign environmental error, in the absence of any adversarial inputs. Because meltdowns are not captured by the existing reliability or safety benchmarks, we develop a taxonomy of meltdown behaviors. We then implement an agent-agnostic infrastructure for injecting simulated local and remote errors into the rollout environment and use it to systematically evaluate agent systems powered by GPT, Grok, and Gemini.
Our evaluation demonstrates that meltdowns (e.g., conducting unauthorized reconnaissance or subverting access control) of varying severity and success occur in 64.7\% of agent rollouts that encounter simulated errors, spanning all combinations of agent system, backing model, and error type. In over half of these meltdowns, unsafe behaviors are not reported to the user. Comparing behaviors of the same agents with and without errors, we find that exploration in response to errors is correlated with unsafe and harmful behavior.
arXiv:2605.19150v1 Announce Type: new
Abstract: State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured by their ability to model finite-state automaton (FSA) transitions, but come at a prohibitively high compute and memory cost. In contrast, most structured transition matrix forms are highly efficient both in runtime and memory consumption, but suffer from limited expressivity. Building on recent work on structured sparse SSMs, we propose Flash PD-SSM, a novel SSM that achieves comparable throughput to widely-used structured SSMs with significantly better expressivity guarantees. Flash PD-SSM maintains a trainable set of structured sparse matrices, a single one of which is discretely selected at each time-step, enabling FSA expressiveness at the level of unstructured matrices while maintaining the efficiency required for training models at scale. First, we validate Flash PD-SSM against a suite of alternative models on synthetic mechanistic and state-tracking tasks, finding that its theoretical expressivity is achieved in practice. Second, on multivariate time-series tasks involving sequences of length over 17,000, we find that Flash PD-SSM defines a new state-of-the-art (SoTA) accuracy among competing SSM methods. Finally, we demonstrate that Flash PD-SSM is an effective drop-in replacement for hybrid LLMs, yielding improvements both in natural language state-tracking and in common language modeling scenarios. The model exhibits increased throughput and decreased memory consumption compared to SSMs widely used in frontier language models.
arXiv:2605.19529v1 Announce Type: new
Abstract: When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Generative-Evaluative Agreement (GEA), a validity criterion measuring whether an LLM's scoring function recovers the skill levels its generative function was instructed to produce. In the first direct measurement of GEA on a two-stage adaptive assessment, the model recovers roughly half the intended variance r = 0.698 with systematic positive bias. GEA is strong r > 0.7 for syntactically verifiable skills but near zero for design-level skills, and low-skill overestimation inflates scores near the routing threshold. We argue that granular, skill-decomposed rubrics are the principal proposed mechanism for strengthening GEA and outline complementary mitigations.
arXiv:2605.19357v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabilities required in practice. Most benchmarks are manually curated or domain-generic, limiting scalability and alignment with real scientific use cases. In this paper, we propose a new framework named SciCustom to address the problem. It enables the custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs. SciCustom first organizes scientific knowledge into ontology-grounded knowledge units with controlled granularity and trains a tagger to map large-scale data instances into this knowledge space. Given a custom requirement, relevant knowledge units are identified via voting-based multi-model consensus. These units enable relevance-aware benchmark retrieval via binary search, followed by proxy subset selection and data-grounded benchmark generation for efficient evaluation. Experiments in chemistry and healthcare demonstrate that SciCustom reveals fine-grained differences in LLM scientific capabilities that standard benchmarks overlook, while requiring neither expert annotation nor synthetic question generation. This work provides a scalable and application-aware foundation for benchmarking scientific capabilities in LLMs. The source code is available at https://github.com/yjwtheonly/SciCustom.
arXiv:2605.19360v1 Announce Type: new
Abstract: The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing deep learning-based detection methods rely on computationally intensive and energy-demanding inference algorithms, limiting their scalability. Here, we present a hybrid digital-analog deepfake video detection framework that combines a lightweight digital front-end with a spatially multiplexed optical decoding back-end for massively parallel analog inference through a programmable spatial light modulator. By simultaneously processing 15 or more video streams within a single optical propagation pass, the system enables high-throughput and accurate video-level authenticity prediction at reduced computational cost compared with purely digital methods. We validated this hybrid deepfake video processor using different datasets spanning classical face-swapping, real-world deepfake recordings, and fully AI-generated videos. Using a spatially multiplexed experimental set-up operating in the visible spectrum, we achieved average deepfake detection accuracy, sensitivity and specificity of 97.79%, 99.86% and 95.72%, respectively, on the Celeb-DF video dataset with 15 videos tested in parallel in a single optical pass per inference. The multiplexed optical decoder also demonstrates resilience against various types of video degradation, noise, compression, experimental misalignments and black-box adversarial attacks. Our results show that integrating optical computation into AI inference enables simultaneous gains in throughput, energy efficiency, and adversarial robustness - three properties that are difficult to achieve together in purely digital systems.
arXiv:2605.18881v1 Announce Type: new
Abstract: In dynamic flow fields, various animals exhibit remarkable odor search capabilities despite relying on stochastic detections. Interestingly, there exists an optimal time window for integrating these detections that maximizes search efficiency. To understand the underlying mechanism, we investigate the navigation performance of Reinforcement Learning (RL) agents in unsteady flows under varying memory lengths and flow conditions. Without any predefined models, the agents develop a flow-assisted casting strategy and adaptively adjust both the geometry of their search trajectories and the concentration threshold for initiating casting to maximize the success rate. The agent's average speed toward the odor source exhibits a non-monotonic dependence on memory length, which can be explained by the "sector-search" model.
arXiv:2605.18905v1 Announce Type: new
Abstract: Neural operators have emerged as a powerful, discretization-invariant framework for solving partial differential equations (PDEs). Although established approaches like the Deep Operator Network (DeepONet) have successfully achieved universal approximation for operators, and architectures such as Fourier Neural Operators (FNOs) have shown algebraic convergence rates, a precise theoretical connection between the continuous theory and its discrete numerical implementation remains a challenge. Specifically, the relationship between the continuous formulation and the discrete numerical stability has yet to be fully explored. In this paper, we address this gap by establishing theoretical guarantees for the discretization error and stability of neural operator approximation schemes. We prove analytical bounds that link solution regularity to input discretization, providing a formal quantification of neural operator accuracy under real-world numerical constraints. We derive these bounds to the specific cases of State Space Model-based Neural Operators (SS-NOs) and FNOs, thus providing a new discretization error theorem for these models. Additionally, through an input-to-state stability (ISS) analysis, we formally assess the impact of discretization on the stability of SS-NOs results obtained in the continuous domain. Our empirical experiments on 1D and 2D benchmarks validate our theoretical bounds and show the robustness of SS-NOs under varying resolutions.
arXiv:2605.18980v1 Announce Type: new
Abstract: A new symbolic algorithm to compute sums of squares multipliers (certificates) to witness the membership of non-negative univariate polynomials in a saturated univariate quadratic module is presented. Certificates are first computed in terms of natural generators introduced by Kuhlmann and Marshall for an Archimedean saturated quadratic module; natural generators can be easily read-off from a semialgebraic set. In the univariate case, an Archimedean quadratic module is also a preordering since it is closed under multiplication; certificates have different representations when a polynomial is viewed as a member in a quadratic module versus in a preordering An algorithm is given to compute certificates of natural generators in terms of the original generators; it uses a construction introduced by Kuhlmann, Marshall, and Schwartz known as the ``Basic Lemma'', which splits the non-negative factors of generators. To compute a quadratic module certificate, certificates of products of natural generators are computed using a detailed case analysis based on the types of natural generators.
An implementation of the algorithms proposed in Maple is also discussed. The certificates obtained using this implementation are compared with those generated by RealCertify. We discuss examples where RealCertify is unable to find certificates while the proposed method is successful.
arXiv:2605.18773v1 Announce Type: new
Abstract: Traditional facility management often relies on centralized decision-making structures that limit stakeholder participation, leading to misalignment with occupant needs and reduced satisfaction. This paper proposes a novel blockchain- and Decentralized Autonomous Organization (DAO)-based framework for community-based facilities management in smart buildings. The framework comprises two key components: a decentralized governance platform that facilitates transparent collective decision-making through blockchain-based voting, and a maintenance management platform with an incentivization mechanism that encourages building occupants to actively contribute to facility upkeep through tokenized rewards. System evaluation includes cost analysis, scalability, data security considerations, usability testing, and semi-structured interviews with facility managers and researchers to assess the platform's usefulness, challenges, and adoption potential. The findings demonstrate the framework's potential as a viable incentivization solution for engaging stakeholders in the collective upkeep and improvement of building infrastructure.
arXiv:2605.18857v1 Announce Type: new
Abstract: For most of the history of information retrieval (IR), search results were designed for human consumers who could scan, filter, and discard irrelevant information on their own. This shaped retrieval systems to optimize for finding and ranking more relevant documents, but not keeping results clean and minimal, as the human was the final filter. However, LLMs have changed that by lacking this filtering ability.
To address this, we introduce Bits-over-Random (BoR), a chance-corrected measure of retrieval selectivity that reveals when high success rates mask random-level performance. We measure selectivity as $BoR = \log_{2}\left(\frac{\mathrm{P}_{obs}}{\mathrm{P}_{rand}}\right)$, where $\mathrm{P}_{rand}$ is the hypergeometric baseline for the chosen success rule (here, coverage: $ \geq1 $ relevant in top-$K$).
On the 20 Newsgroups dataset, BM25 and SPLADE both report $>99$% success at $K=100$ (coverage), yet $BoR \approx 0$, indicating random-level selectivity at that depth. When the expected coverage ratio $\left(\frac{K \cdot \bar{R}_{q}}{N}\right)$ exceeds 3-5, the baseline dominates and selectivity collapses. Downstream retrieval-augmented generation (RAG) evaluation confirms this pattern: LLM accuracy can degrade substantially at $K=100$, consistent with the near-zero BoR ceiling. In contrast, BoR remains positive on BEIR/SciFact and on MS MARCO (where 41 systems cluster within 0.2 bits of the theoretical ceiling despite a 13-point recall gap), confirming baseline predictions across sparse and large-scale settings. We further show that the collapse boundary applies to LLM agent tool selection, where small catalog sizes cause selectivity to vanish even with perfect selectors. These findings suggest reporting BoR alongside traditional metrics and reconsidering depth choices when additional retrieval provides negligible selectivity gains while inflating computational costs.