# Research Papers — 2026-08 · bundle page 139 of 240

> Full-text markdown of papers #6901–6950 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-08/page/139
[← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/138.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-08/page/140.md)

### Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

Authors: Xiaoyan Feng, Yanjun Zhang, He Zhang, Leo Yu Zhang, Shirui Pan
Published: 2026-08-13
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.12713v1

Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness allows an adversary to alter critical content while retaining attribution, a vulnerability known as piggyback spoofing. We introduce an innovative watermark that jointly provides provenance and tamper evidence. It co-embeds a robust signal and a fragile signal into each generated token. The signals share the same mechanism but use independent keys and different seeding windows over normalized text, making one resilient to edits and the other sensitive to reader-visible changes. Multiple rounds of unbiased tournament reweighting preserve the expected generation distribution, while a periodic round-allocation pattern controls the trade-off between the two signals. At detection, their scores form a two-dimensional space supporting three decisions: Intact, Tampered, and No-Watermark. Across two large language models and two prompt datasets, our method demonstrates the highest tamper-detection rate among the evaluated methods while maintaining competitive attribution robustness and perplexity. Ablation studies show that reliable three-state detection requires a well-defined notion of intactness, co-embedding of the two signals, and complementary sensitivity to edits.

---

### Federated Compositional Muon Optimizer for Matrix-Wise Models

Authors: Wang Yan, Feihu Huang
Published: 2026-08-13
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2608.12710v2

Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these methods are still not particularly well-suited for hierarchical structured problems. To fill this gap, we propose an effective federated compositional Muon (FedCoMuon) optimizer to solve distributed matrix-wise compositional optimization problems. Specifically, our FedCoMuon optimizer builds on compositional gradient tracking and orthogonalized momentum. Moreover, we propose a variance reduced variant of FedCoMuon (FedCoMuon-VR) based on a momentum-based variance reduced technique. In theory, we analyze the convergence properties of our algorithms under the non-i.i.d. and non-convex settings. In particular, we prove that our FedCoMuon-VR obtains a lower sample complexity of $O(ε^{-3})$ for finding an $ε$-stationary solution than the existing FedMuon algorithms. Extensive numerical experiments on robust federated learning and task-distributed risk-sensitive meta learning show that our proposed methods are competitive with existing compositional baselines and achieve the best reported accuracy in several settings.

---

### Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level

Authors: Yicong Jiang, Feihu Huang
Published: 2026-08-13
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2608.12704v3

Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works have been begun to study the multi-objective bilevel optimization, the proposed methods rely on the (strongly) convex lower level problems. In fact, these multi-objective bilevel learning problems are generally nonconvex, and particularly their lower level problems are nonconvex. To fill this gap, we propose a class of Multi-Objective Moreau Envelope based Hessian-free Algorithms (MOMEHA) for the multi-objective bilevel learning problems with nonconvex lower level. Specifically, our method uses the Moreau envelope to relax the original problem into a multi-objective single-level optimization with an envelope constraint. In particular, our method retains computational advantages of being single-loop and Hessian-free in the multi-objective setting by incorporating a smooth weighted Tchebycheff scalarization. Furthermore, we propose a momentum-based variant of MOMEHA (i.e., MB-MOMEHA) method for the stochastic multi-objective bilevel learning problems. In theory, we provide the convergence properties of our algorithms under both deterministic and stochastic setting. Some experiments on few-shot meta-learning and neural architecture search demonstrate that our methods outperform the existing approaches in Pareto front, validating its effectiveness and robustness.

---

### A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family

Authors: Rishi Shah, Rishav Shrestha
Published: 2026-08-13
Categories: cs.LG, cs.AR, cs.DC
arXiv: https://arxiv.org/abs/2608.12700v2

Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept it if the output is close to a reference. A kernel can pass that test and still be silently wrong. It can return an ordinary number where the true answer is a NaN or an infinity, differ from run to run, break when the shape changes, or accumulate in fp16 where the reference keeps an fp32 total. We build the instrument that checks correctness properly: a contract-grade verifier of twelve adversarial gates, each a property a correct kernel must satisfy, several of them tolerance-free, so no choice of threshold can explain a failure away. Aimed outward, the verifier audits 2,638 machine-generated kernels that a public system's own harness had already accepted as correct. It finds 39.5% broken beyond any tolerance argument and 62.1% carrying at least one violation. The field's standard test accepts 1,487 kernels the verifier rejects, against only 14 the other way. We defend the finding four independent ways: a 7/7 positive control, a threshold-calibration sweep, 98.5% agreement with the reference benchmark's own correctness code, and a stratified hand-audit. Aimed inward, the verifier judges a kernel of our own: the first native Blackwell tcgen05 training backward for the gated-linear-recurrence (GDN) family, including the reverse-state stage the field still runs on a fallback. We establish its correctness independently, against a double-precision oracle, and train five family members through it. The correctness signal behind reported progress in kernel generation is far weaker than the numbers suggest, and a set of tolerance-free contracts would close most of the gap.

---

### Class Geometry as Supervision for Sample-Efficient Open-World Detection

Authors: Akash Rao, Zhou Chen, Revanth Reddy Palem, Udhav Ramachandran, Ruth Scimeca, Sathyanarayanan N. Aakur
Published: 2026-08-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.12698v1

Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is especially challenging in scarce-data settings such as biomedical and scientific imaging, where rare categories may have only a few annotated examples and fine-grained classes differ by subtle morphology. Prototype-based detectors are natural for this regime, but they typically learn class prototypes as independent anchors, ignoring relational structure among classes. We propose class-geometry supervision (CGS), a general framework that constrains learned prototype or class-representation spaces to preserve visual or semantic class dissimilarities estimated from training data. CGS introduces a dissimilarity-preserving objective that aligns pairwise distances among learned class representations with a target class-geometry matrix while retaining the standard task loss. We instantiate the same objective across prototype recognition, few-shot biomedical object detection, open-set detection, novel-class insertion, and OWOD adaptation on COCO. Experiments show that CGS improves sample efficiency in recognition and ova detection, substantially strengthens novel-class insertion, and improves unknown recall on COCO while retaining much of the known-class detection performance. Ablations show that meaningful visual geometry provides the most reliable gains, while random geometry can help novel separation but is less consistent for few-shot detection. These results suggest that relational class geometry is an effective supervisory signal for building calibrated and extensible open-world detectors under limited supervision.

---

### The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning

Authors: Ahmed Sameh, Ramzi Al-Sharawi, Yogatheesan Varatharajah
Published: 2026-08-13
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2608.12695v2

Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency in real-world ambulatory recordings. We present a controlled study on the Icentia11k single-lead dataset that varies (i) the input horizon (16 seconds, 1 minute, 5 minutes, and 10 minutes) and (ii) the front-end representation (continuous convolutional patch embeddings vs. fixed vector-quantized tokens), while holding the Transformer backbone and training protocol constant. Representations are assessed by downstream abnormal rhythm detection and by patient-level retrieval that probes cross-session stability. Our results show that increasing temporal context beyond 16-second snapshots yields stronger transfer and higher retrieval accuracy, with the strongest performance achieved by the 5- and 10-minute models, indicating improved capture of slow-varying rhythm dynamics and individual-specific structure. Across all evaluated horizons, continuous patch embeddings outperform discretized tokens, suggesting that quantization can discard clinically relevant waveform detail. These findings motivate ECG foundation models that emphasize extended context and continuous encoders for clinical prediction and similarity-based applications. Our code and pretrained models are publicly available at https://github.com/muha-0/ecg-ssl-representation-learning.

---

### Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging

Authors: Zhi Qiao, Xintong Wu, Yichu He, Feng Shi
Published: 2026-08-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.12689v1

Multi-parametric magnetic resonance imaging (mpMRI) is a cornerstone for brain tumor diagnosis and treatment, yet current AI models face critical limitations: their lack of natural language interaction and interpretability impedes spatial information integration and cross-modal reasoning required clinically. Key challenges arise from significant physical meaning differences across modalities, spatial misalignment due to scan intervals, and the need for complex multi-feature interpretation in tasks like glioma grading. While visual-language models (VLMs) show promise in cross-modal understanding, existing methods focus mainly on 2D image modeling, neglecting direct perception of 3D volumetric space. Although 3D VLMs have been proposed for report generation and feature alignment in 3D CT imaging, mpMRI applications demand collaborative inference across multiple imaging modalities-a requirement unmet by current solutions. To address this, we introduce Mr3D-VL, a dedicated visual-language foundation model for multi-parametric 3D MRI. With 4 billion parameters, it employs an unsupervised pre-trained shared 3D encoder and 4D rotational positional embedding for dual modality-spatial integration. Its cross-modal projection layer uses a multi-resolution feature implantation strategy to enhance feature perception across resolutions. Experimental results show significant improvements over existing 4B/7B/30B domain-specific and general-purpose models in text generation tasks, achieving a BERTScore of 0.856 for report generation, with question-answering accuracy at 0.713 and multiple-choice accuracy at 0.912.

---

### Finding the Needle in a Haystack: Test-Time Analog Circuit Representation Adaptation for Bayesian Optimization

Authors: Fin Amin, Sounak Dutta, Paul D. Franzon
Published: 2026-08-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.12687v1

Bayesian optimization (BO) is a sample-efficient framework for analog circuit topology search, where evaluating each candidate topology can require costly simulation. However, representation-based BO methods typically treat circuit embeddings as fixed after encoder training. This creates a mismatch between representation learning and optimization: embeddings learned to encode or reconstruct circuit structure are not necessarily organized according to the figure of merit (FoM) being optimized. This paper introduces Test-Time Analog Representation Adaptation for Bayesian Optimization (TTARO), an online deep-kernel BO framework that adapts circuit representations throughout the search process. Starting from pretrained circuit embeddings, TTARO jointly learns a nonlinear feature transformation and a Gaussian-process surrogate using the FoM labels of the circuits evaluated so far. Following each new evaluation, TTARO updates the representation and surrogate before selecting the next candidate. We compare TTARO with conventional Gaussian Process-based BO over fixed embeddings and with Deep Kernel Learning (DKL), which learns the representation only from the initial evaluated designs and keeps it fixed throughout the remainder of the search. By continually incorporating newly observed FoM labels into representation learning, TTARO aligns the search space with the optimization objective as BO progresses. In our experiments, TTARO reduces regret AUC by 15.2% on average relative to BO and by 20.7% relative to DKL across 40 encoder/kernel/acquisition settings, outperforming prior art in most settings with reductions as large as 46.7%.

---

### High-resolution Calibrated Probabilistic Hourly Precipitation from a Deterministic Forecast

Authors: Thomas M Hamill
Published: 2026-08-13
Categories: physics.ao-ph, stat.ML
arXiv: https://arxiv.org/abs/2608.12685v2

An ``Attention Residual U-Net'' method is described for probabilistic quantitative precipitation forecasting (PQPF) that predicts the hourly probability of no precipitation plus the distribution of positive precipitation from a weighted mixture of two Gamma distributions. The neural network is trained on patches of numerical weather prediction (NWP) hourly precipitation from The Weather Company's convection-permitting GRAF (Global high-Resolution Atmospheric Forecasting) model along with terrain information and column-average relative humidity from the National Oceanic and Atmospheric Administration's (NOAA's) Global Forecast System (GFS). The target data are NOAA's Multi-Radar, Multi-Sensor (MRMS) gauge-corrected, quality controlled radar data sampled to the same grid as the GRAF data. The network outputs distributional parameters for each model grid point. Training uses negative log-likelihood as a proper scoring rule, with climatological initialization for stable convergence. Inference is performed as a single forward pass over the contiguous United States (CONUS) domain, with edge-replication padding to satisfy the network's spatial-divisibility requirement. The subsequent forecasts are spatially detailed, highly reliable, and skillful with respect to climatology and a simpler reference forecast method. The method is particularly useful for estimating probabilities in regions with large terrain variation.

---

### FUSE: Active Functional Affordance Grounding through Adaptive Semantic-Geometric Evidence Acquisition

Authors: Zhou Chen, Sathyanarayanan N. Aakur
Published: 2026-08-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2608.12683v1

Embodied agents must often identify and interact with objects based on their function rather than their identity, requiring them to actively acquire observations that reveal discriminative functional evidence. Existing affordance grounding methods operate from fixed viewpoints and lack mechanisms for deciding where to look when functional cues are occluded or incomplete. We introduce Active Functional Affordance Grounding, a new task in which an agent sequentially explores a scene to identify and spatially ground an object satisfying a functional query. To address this problem, we propose FUSE, an adaptive semantic-geometric evidence acquisition framework that combines explicit uncertainty-driven exploration with a learned amortized planner to efficiently select informative viewpoints. We further introduce a Habitat-based benchmark for evaluating active functional grounding. Experiments show that FUSE achieves the highest observed non-oracle grounding performance while reducing computation by 1.33x relative to fully explicit exploration, and remains effective across multiple affordance knowledge sources.

---

### Demand Transfer Estimation at Scale via Restricted Logit Modeling

Authors: Lakshya Garg, Deep Narayan Mishra, Swapnil Yadav, Haoan Wang, Sujal Alugubelli, Karthik Kumaran, Anupriya Sharma
Published: 2026-08-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.12680v1

Item demand forecasting is an integral component of store assortment optimization. Existing literature focuses on learning a suitable customer choice model and using this model to determine the value of an objective function (i.e. expected demand) with respect to an assortment proposal. However, for large item universe with many categories, this approach can prove inefficient, needing a separate demand forecast for every possible item assortment. An alternate approach exists whereby we combine the efficiency of forecasting item demand independently, while at the same time applying adjustments to the independent forecasts that account for the relations between item demand and the availability of other similar items on the shelf. Central to this approach is the estimation of Demand Transfer (DT) coefficients. These DT coefficients represent the percent of a particular target item's (item that the customer walked in the store to buy) demand that is redirected to each other item in the universe should the target item be removed from the shelf. We introduce an approach that allows us to compute these DT coefficients on large item universes (assortments having 1 million+ items). Experiments on data as well as historical transaction data for multiple locations within categories demonstrate that when certain reasonable assumptions about substitution behavior are satisfied, our procedure is able to accurately estimate underlying DT coefficients and lead to improvements in demand forecasting.

---

### Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies

Authors: Conor F. Hayes, Elliot Meyerson, Kajetan Schweighofer, Roberto Dailey, Babak Hodjat, Risto Miikkulainen, Xin Qiu
Published: 2026-08-13
Categories: cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2608.12679v1

Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The usual approach is to present the problem to the model and use its answer as the proposed solution. However, beyond this best guess, discovery can be enhanced by increasing test-time compute. In a process called pass@k, the model is allowed to explore the solution space and generate diverse candidate solutions. Unfortunately, the standard approach to post-training LLMs through Reinforcement Learning (RL) may limit pass@k: the model's output distribution narrows around high-reward outputs, causing the solution coverage to collapse. The alternative is to use Evolution Strategies (ES), a population-based, gradient-free post-training method that optimizes directly in weight space through random perturbations. As this paper shows, ES achieves consistently higher pass@k than RL and produces a broader output distribution with greater solution coverage. This coverage in turn makes it possible to achieve better results in e.g. standard math benchmarks. Thus, ES provides a better foundation for post-training in discovery problems and other domains where diverse solution coverage is critical.

---

### The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis

Authors: Danial Sharifrazi, Saadat Behzadi, Julakha Jahan Jui, Mojtaba Mohammadi, Nouman Javed, Roohallah Alizadehsani, Prasad N. Paradkar, Asim Bhatti
Published: 2026-08-13
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2608.12677v1

Detecting infection-related behavioral changes in mosquitoes from video data is challenging because mosquitoes are small, move rapidly and irregularly, and are affected by environmental factors such as background, lighting, and shadows, which can make reliable feature extraction difficult. In this study, a YOLO- and Contrastive Language-Image Pre-training (CLIP)-based vision-language framework is proposed to classify mosquito flight frames of uninfected and Dengue virus serotype 2 (DENV2)-infected mosquitoes. First, YOLO is used to isolate mosquito regions from the background. Then, visual features extracted from video frames are aligned with biologically meaningful textual prompts in a shared embedding space. The multimodal model was fine-tuned using supervised bidirectional contrastive learning and evaluated through frame-level image-text similarity-based classification. The results show that the proposed method achieved 98.54% accuracy and 99.91% sensitivity at the frame level. After temporal aggregation of frame-level information, the model achieved complete video-level performance. The ablation results showed that fine-tuning and CLIP-based representations were essential for this domain, while the textual branch provided semantic image-text alignment rather than an accuracy advantage over the vision-only model. These findings suggest that vision-language models can provide a useful framework for analyzing infection-related biological behaviors from video data.

---

### Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

Authors: Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari, Fahad Alotaibi, Khalid A. Alobaid, Mohamad Mahmoud Al Rahhal
Published: 2026-08-13
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2608.12675v2

Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG has focused on preventing unauthorized users from accessing sensitive data. However, another important problem that is often overlooked in RAG privacy research is that external generators have access to the query and the retrieved documents, which may contain confidential information that could potentially be misused or accessed for unintended purposes. In this paper, we introduce the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information. SEAG introduces a lightweight model that locates sensitive entities, generates corresponding aliases, and constructs an entity replacement table. The table is used to replace sensitive words in the user's query and in the retrieved documents before they are forwarded to an external generator. For this purpose, two datasets were constructed: one for fine-tuning SEAG models to generate entity replacement tables, and another for evaluating the entire SEAG framework. The experimental results demonstrate the success of the SEAG framework. As for the User metric, which measures the ability of the model to provide a correct response to the user while hiding sensitive information from the external generator, all SEAG models achieved over 80% accuracy. Additional analysis further evaluated the ability of SEAG models Qwen-3, LLaMA-3.2, and Phi-4 to hide all sensitive entities within given documents. The results show good performance with total accuracies of 77.83%, 76.73%, and 74.91%, respectively.

---

### Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy

Authors: Ravi Teja Chunduri, Srikaran Reddy Boya, Deep Narayan Mishra, Ajay Kumar B, Karthik Kumaran, Pranay Kona
Published: 2026-08-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.12674v1

Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions of active items, manual governance of price relationships is infeasible. Inconsistent pricing across item variants distorts customer value perception and cannibalizes sales. To address this, we present a scalable, context-aware Multi-Agent Framework designed to automate the construction of "Lines and Ladders" pricing taxonomies. Our framework employs specialized LLM agents to construct these coherent pricing structures by identifying key attributes, extracting multi-modal values, and applying hierarchical grouping logic. Evaluated on real-world enterprise data and deployed in production, our 3-Agent system achieves an F1-score of 0.83 for Lines, outperforming single-agent baselines by mitigating cognitive overload. The system achieves >90% precision and >75% recall in Food & Consumables, and 80.2% assignment accuracy in the unstructured General Merchandise catalog.

---

### On the Expressive Power of Transformers

Authors: Phokion Kolaitis, Rik Sengupta
Published: 2026-08-13
Categories: cs.AI, cs.CC
arXiv: https://arxiv.org/abs/2608.12671v1

Multi-layer transformers form the critical component of essentially all large language models (LLMs) in use today. Because of their ubiquity and computational capability, there is a rapidly growing body of work that aims to precisely calibrate the expressive power of transformers as language recognizers by comparing them against standard models of computation studied for decades by the theoretical computer science community. In this endeavor, circuit complexity has by and large emerged as the "correct" branch of computational complexity to analyze the expressive power of transformers; the reason is that parameterizing transformers by the various resources they use, such as attention and precision, leads to direct comparisons with different classes of circuits parameterized by resources such as type of gates, size, and depth. Here, we present an overview of selected results that delineate the expressive power of transformers using concepts and methods from circuit complexity.

---

### Designing AI Pipelines for Decision-Ready ITSM Intelligence

Authors: Archan Dutta, Yash Dharmadhikari, Marat Valiullin, Rahul Guha, Alexander Liss
Published: 2026-08-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.12670v1

IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are difficult for sales and executive stakeholders to convert into actionable intelligence. This paper presents a sociotechnical AI pipeline, designed and evaluated following design science research principles, that transforms raw ITSM exports into a multilevel decision-support artifact. The pipeline combines LLM-based schema normalization, HDBSCAN sub-topic clustering, and hierarchical agglomerative clustering to generate executive-facing Main-topics and granular Sub-topics. A stakeholder evaluation across six artifacts and five raters from Sales Engineering and customer success roles shows that all four decision-support metrics, interpretability, actionability, trust, and likelihood of use, on average exceed 4.0 out of 5.0, with trust as the most consistent signal. The findings position ITSM analytics as an Information Systems (IS) problem of transformation, abstraction, and human-centered design.

---

### Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation

Authors: Rémi Bourgerie, Šarūnas Girdzijauskas, Viktoria Fodor
Published: 2026-08-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.30277v1

Implicit Graph Neural Networks (IGNNs) define node representations as fixed points of message-passing operators, enabling effectively infinite-depth propagation, iteration-independent parameterization, and flexible test-time computation. Yet these benefits depend on the equilibrium being unique and attainable by fixed-point iteration. Existing constructions often impose constraints on recurrent updates to obtain these guarantees, limiting the transformations available at equilibrium. This raises a central question: can IGNNs gain expressiveness through richer, edge-dependent transformations while retaining the inherent strengths of their equilibrium formulation? We introduce SheafDEQ, a subhomogeneous deep-equilibrium architecture with adaptive neural-sheaf propagation. Its learned, matrix-valued sheaf restriction maps can align, mix, or reverse neighbouring representations. Under mild regularity conditions, we prove that SheafDEQ admits a unique equilibrium reached globally by fixed-point iteration from any positive initialization. Contractivity further guarantees convergence under bounded communication staleness. We evaluate SheafDEQ on distributed-inference tasks requiring repeated nonlocal aggregation and on community detection whose rewiring increasingly favours cross-community interactions. SheafDEQ improves over fixed-propagation implicit baselines on Sums, MNIST Terrain, and Coordinates, and on community detection as connectivity becomes increasingly heterophilic. Continued-iteration diagnostics show decreasing residuals and low prediction sensitivity after 100 iterations for initialization scales from $0.001$ to $10$, while delayed-update experiments show low sensitivity to bounded communication staleness.

---

### Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness

Authors: Alokendu Mazumder, Ayaan Mohd, Harshit Rawat, Arnab Roy, Mayank Baranwal, Punit Rathore
Published: 2026-08-12
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2609.30276v1

We analyze the original same-step coordinate-wise AdaGrad under generalized smoothness and heavy-tailed noise with bounded variance. In this setting, local curvature may grow sub-quadratically with the gradient norm, and stochastic gradients are assumed to have only bounded conditional second moments. We show that unclipped AdaGrad can become \emph{anisotropically miscalibrated}: under heavy-tailed noise, the adaptive denominator can learn the geometry of rare noise shocks rather than the local curvature of the objective, leading to a persistent directional distortion that blocks finite-horizon Euclidean progress. We then prove that clipping repairs this failure mode. Our main result is a finite-horizon high-probability guarantee for the original non-lagged AdaGrad update, yielding $\frac1T\sum_{t=0}^{T-1}\|\nabla f(x_t)\|^2=\mathcal{O}\left(\frac{d\big(\sqrt{\log T} + \log \frac{1}δ\big)}{\sqrt{T}}\right),$ and hence $\widetilde{\mathcal O}(\varepsilon^{-2})$ complexity. This shows that, for AdaGrad under heavy-tailed noise, clipping is a structural stabilizer of the adaptive geometry rather than merely a robustness heuristic.

---

### Cosine Similarity Is Not Evidence: Measuring the Noise Floor of Interpretability Transfer Under Quantization

Authors: Pranav Varshney
Published: 2026-08-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.30275v1

A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpretability artifacts are calibrated on full-precision weights, deployed on quantized ones, and certified as surviving the change by scale-invariant statistics (cosine similarity, correlation, AUROC) that are reported without their noise floor. For the difference-in-means direction estimator, the split-half floor is governed by one dimensionless number, $κ= nρ^2/d$. The closed form $\mathbb{E}(\cos) \approx (1+4/κ)^{-1}$ is classical; the missing input is the class separation $ρ$, which we measure on real activations; no compression-transfer study we know of reports it. On Qwen2.5-1.5B-Instruct, $ρ= 33$--$61$ across depth, so two independent runs of the estimator agree to $0.978$--$0.994$ by sampling alone. A published cosine of $0.996$ between full-precision and quantized refusal directions therefore cannot be read as preservation without the $n$ it was computed at, which is not reported. Where $n$ is known, we judge each low-bit cosine against the split-half null measured within that quantized model, because a full-precision null assumes the low-bit estimator has the same variance. That assumption is exactly what a null exists to test. The result is plain: at INT4 the direction rotated, and the deficit exceeds the estimator's own noise. At INT8 we detect no movement, which is not an equivalence claim. We also show that a scale-invariant statistic cannot distinguish translation from attenuation of a transferred decision variable, although the two call for opposite remedies. We close with reporting recommendations that cost one forward pass. Code, data, and a one-cell reproduction are released at https://github.com/pvarshh/quantinterp

---

### Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025

Authors: Amr Sobhy
Published: 2026-08-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.28487v1

News headlines frame public issues both by what they select and by how they word it, yet computational framing work typically collapses these operations into a single score. We introduce a two-dimensional framework that separates salience framing, measured through four wording devices (loaded vocabulary, blame attribution, threat framing, rhetorical question), from selection framing, measured through outlet-level story-form and high-charge distributions. We build a 10,000-headline French supervision set using three LLM annotators with majority-vote resolution and human arbitration, validate the labels against two annotator-independent blind human studies, and apply the strongest classifier to 902,111 deduplicated headlines from 25 French outlets (2022-2025). Three main findings emerge. First, salience and selection divergence are positively correlated yet leave nearly half of outlet-level variance unexplained, populating interpretively distinct off-diagonal cells in a four-cell outlet typology. Second, default classification thresholds systematically inflate corpus-level salience estimates; a precision-floor recalibration protocol corrects this distortion. Third, group-mention analysis reveals sharply unequal salience contexts: headlines mentioning Jews, the Far-right, and Muslims carry the highest detected salience rates, which broad event-context composition does not fully explain (residuals are descriptive, not same-event causal estimates; per-group lexicon precision is reported alongside). To our knowledge, this is the largest framing-focused French headline audit to date; we release the supervision set, lexicons, and analysis code.

---

### A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System

Authors: Hamid Saadatfar, Rohollah Hedayati-Nasab, AmirHossein Eshghi, Arash Hajihashemi
Published: 2026-08-12
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.26243v1

The rapidly increasing student population has posed serious challenges to the traditional academic advising process. This study designs and implements a multi-purpose intelligent system to support students' academic progress, based on a two-part hybrid framework: (1) an advanced model for grade prediction and (2) a rule-based recommendation engine. Using a dataset containing 416,558 educational records from the University of Birjand, students were first divided into homogeneous clusters using the Gaussian Mixture Model (GMM). Subsequently, a Stacking Ensemble model combining Random Forest, Gradient Boosting, and MLP was trained specifically for each cluster. Evaluation results demonstrated that the Stacking model outperformed base models across all clusters, achieving a final aggregated RMSE of 2.35. The second component is an expert system that provides intelligent recommendations by synergizing educational regulations with the grades predicted by the first component. This system has been implemented as a practical tool on the University of Birjand portal, offering students real-time feedback such as semester GPA prediction, probation risk warnings, and course suggestions for GPA improvement.

---

### Damage Predicts Recovery: When Calibration Data Matters in Compressing Financial LLMs

Authors: Junyi Ye, Mengjia Yu, Debapriya Hazra, Guiling Wang
Published: 2026-08-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.26241v1

Post-training quantization and pruning rely on a small calibration corpus. Whether specialized domains such as finance require domain-matched calibration data remains unsettled. We argue that the answer depends on the task-level damage caused by compression rather than on domain mismatch. If compression preserves the target capability, changing the calibration corpus has little effect. If compression causes large losses, task-formatted calibration can recover part of the loss. We test this hypothesis across two model families, six compression configurations, three token-matched calibration corpora, and ten financial classification and numerical question-answering tasks. The results support this hypothesis. Quantization largely preserves task performance, and calibration choice has little effect in this case. Pruning reduces numerical QA accuracy by over 40 points. In these damaged settings, another generic corpus does not help, while FinMix, a mixture of financial task examples, recovers a large part of the loss. The link between damage and recovery holds across model families and scales. These findings support a practical rule. Measure task-specific compression damage first, and construct specialized calibration data only when the damage is large.

---

### ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap

Authors: Minhan Cho, Soyoung Park, Daejin Choi, Jinyoung Han
Published: 2026-08-12
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2609.26237v1

We present the ABAI submission to COLIEE 2026 Task 1, case law retrieval, together with a controlled study of why it underperformed. The task suppresses the cited passages themselves, which removes much of the lexical overlap a retriever would rely on. Our pipeline answers this with four independently trained stages: multi-view BM25 over citation-context windows with reciprocal rank fusion, neural reranking, graph-based features from entity communities and a graph attention network, and a LightGBM meta-learner over 34 features. Our best run reached F1=0.177 on the official test set, against a cross-validated 0.311, and we attributed that gap to a recall ceiling, temporal distribution shift, and threshold miscalibration. We then tested all three. Under leakage-free protocols threshold transfer costs 0.007 F1, decision quality is flat across chronological quartiles, and the official test queries are not measurably farther from the training manifold than training queries are from each other, in two independent embedding spaces. Decomposing the misses instead splits them exactly evenly between candidates never retrieved and candidates retrieved but ranked below the cut. Measuring the remedies for each half, BM25 length-normalisation tuning, an event-triple view, and full-content dense fusion lift top-200 recall by three to seven points, and citation-graph features add 0.014 F1 over eight seeds once own-citation leakage is removed, while per-query cutoff rules, a zero-shot reranker swap, and a date filter do not help. We also document four evaluation artifacts, each of which reversed a result once the protocol was corrected.

---

### High-Order Liquid Evidence Modeling for Continuous and Subtle GNSS Spoofing Detection in Autonomous Driving

Authors: Muhammad Ayub Sabir, Junbiao Pang, Fatima Ashraf
Published: 2026-08-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.26231v1

Continuous and subtle GNSS spoofing poses a serious threat to autonomous vehicles because forged positions may remain locally plausible while gradually becoming inconsistent with vehicle motion observed by non-GNSS onboard sensors. Existing AV-oriented detectors commonly rely on residual thresholds or feature-level classification and provide limited modeling of how weak GNSS--motion inconsistency develops and persists over time. This paper formulates subtle GNSS spoofing detection as a causal sequential evidence-modeling problem and proposes a high-order liquid evidence detector. The method first compares the displacement implied by consecutive GNSS positions with that inferred from independent onboard motion observations and converts their difference into uncertainty-normalized residual evidence. It then represents the current inconsistency, its local evolution, excess above the normal level, accumulated persistence, and displacement validity as causal weak evidence. These cues are mapped into instantaneous, evolutionary, and persistent latent states, aligned through a bounded Kirchhoff-inspired symmetric exchange, and combined through an explicit third-order interaction to capture their coordinated support for spoofing. To model how this coordinated evidence develops over time, second-order liquid dynamics track its memory and evolution to estimate causal spoofing probabilities, which are converted into confirmed alarms using validation-selected threshold and persistence parameters. Experiments on the AV--GPS dataset family demonstrate strong controlled and external generalization, together with clear sequential alarm behavior. On Dataset-1, the proposed detector achieves an AUROC of 0.9932 and an AUPRC of 0.9843, while obtaining the lowest false-positive rate among the learning-based baselines. Code: https://github.com/pangjunbiao/HO-LLN-Spoofing.

---

### Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation

Authors: Ashly Joseph
Published: 2026-08-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.26229v1

Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification, and knowledge retrieval. Still, they are prone to produce hallucinations, outputs that seem convincing but aren't based on context that limit their trustworthiness in high-end engineering applications where precision and compliance are crucial. The paper introduces CoVe-RAG+, a unified framework that integrates Chain-of-Verification (CoVe) with Retrieval-Augmented Generation (RAG) to mitigate hallucinations in the results generated by large language models (LLMs). CoVe-RAG+ supports LLM verification in external sources of authority, such as engineering standards, CAD information, and simulation reports, while applying an iterative self-verification process to validate important claims. CoVe-RAG+ is assessed on engineering activities such as CAD model documentation, standards compliance verification, and the reutilization of historical design data. Experimental findings indicate a 28% improvement in factual accuracy relative to baseline CoVe and RAG methodologies. Moreover, CoVe-RAG+ strengthens user confidence by providing elucidative verification reports and source traceability. The findings indicate that CoVe-RAG+ provides a scalable and reliable option for implementing LLMs in engineering design processes where factual accuracy is critical.

---

### Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

Authors: Mizanur Rahman, Huan Wu, Arash Asgari, Enamul Hoque Prince, Laleh Seyyed-Kalantari
Published: 2026-08-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.26210v1

Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. However, they may produce different narratives for the same chart when only the referenced social group changes, reinforcing stereotypes and misleading decisions. Despite these risks, no benchmark exists for systematically evaluating bias in chart interpretation across social dimensions. We introduce ChartBias, the first benchmark for auditing bias in VLM-based chart interpretation. ChartBias contains 820 manually curated real-world charts spanning six attributes: race, income, age, religion, immigration status, and gender, yielding 4,319 valid chart, attribute instances and 8,638 paired generations where the chart is fixed and only the group term is swapped. Across 12 proprietary and open-source VLMs, totaling 155,484 model responses, we find three widespread failure modes: narrative shift (same chart, different narratives), group hallucination (assigning a chart to a group without evidence), and preference polarity (favourable trends often linked to one group). We further propose a multi-agent mitigation framework that serves as a strong baseline by separating chart-grounded evidence extraction from group-conditioned generation and using a counterfactual judge to verify that group-driven differences are supported by the chart. The framework substantially reduces narrative shift while preserving chart-grounded reasoning. Our findings show that evaluating chart understanding requires measuring not only accuracy, but also fairness and consistency across social groups. We release ChartBias at https://github.com/vis-nlp/ChartBiasBench.

---

### Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation

Authors: Haoyu Zhang, Haowen Xu, Xiao Luo, Hanwen Liu, Yang Chen, Zijian Xiao, Yi Feng, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
Published: 2026-08-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.26176v2

Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often the model complied. A high refusal rate there is reported as safety, and it is equally consistent with a model that has stopped telling the request apart from anything else in the same format. We run the benign arm through the same transformation, and the two cases are far apart. Across four 7-8B models spanning three base families and four post-training recipes, refusal of harmful homoglyph-encoded prompts spans 0.08 while the same four span 0.57 on the identical requests in plaintext. What the encoding destroys is not refusal but the harm gap: on one model the gap between harmful and benign refusal falls from +0.82 in plaintext to exactly 0.00 under the encoding, and a benchmark reading only the harmful arm scores that model and one retaining a +0.61 gap identically. Running the cell such benchmarks leave out (plaintext content wearing the attack template, with nothing obfuscated) shows that on two of the four models the loss is caused by the protocol rather than by the character transformation, and on a third by the characters. Across a full SFT -> DPO -> RLVR pipeline the harm gap rises by +0.26 with a paired interval excluding zero while the standard harmful-arm metric registers no resolved change at all. We report twelve instrument defects, each with the control that caught it, including a binary jailbreak judge that fires on 0.61-0.70 of responses to plaintext benign prompts; six of the twelve inflate apparent safety, which is the direction a broken safety evaluation fails in by default.

---

### The Uncontrolled Variable: Vision-Language Refusal Is Conditioned on the Image-Attachment Interface, and Not Robust to Irrelevant Image Properties

Authors: Haoyu Zhang, Yi Feng, Hanwen Liu, Shibo Zheng, Zhuoxi Wang, Yang Chen, Haowen Xu, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
Published: 2026-08-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.26174v2

We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding everything the request asks fixed. Attaching a blank canvas, an image that cannot be read, cannot relate to the request, and is byte-identical across every prompt in its condition, shifts benign refusal by tens of points. The shift is not blanket caution but a threshold shift: genuinely neutral instructions are almost unaffected (<=2 percentage points on three of four hosted models) while borderline-benign prompts move +23 to +51 points, so the cost falls on sensitivity-adjacent traffic, meaning benign questions about privacy, self-harm, violence and illegal activity. There is a benign reading of such a threshold, namely that attachment correlates with risk in real traffic, and we take it seriously; a black-box study cannot measure that correlation and we do not claim to. What it can test is whether the response to attachment is robust to variation carrying no information about the request, and on four independent measurements it is not. It varies with canvas colour and pixel count. Its sign inverts across checkpoints. It survives an explicit instruction to disregard the image. And on one model it fires on a bare assertion that an attachment exists, with nothing attached and the modality word contributing none of it. Finally we price it. On a matched harmful set the same canvas does lower attack success, so the cue buys something. But the charge is decoupled from the purchase: the checkpoint with the least harmful headroom we measure, completing only 2% of plain harmful requests, still pays the benign cost in full, and across our models the harmful-side denominator falls as alignment improves while the benign cost does not track it down. Image presence is not a conservative default that a deployer chose and priced. It is an uncontrolled variable.

---

### NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers

Authors: Parsa Hassani Shariat Panahi, Amir Hossein Jalilvand, M. Hassan Najafi
Published: 2026-08-12
Categories: cs.AR, cs.CV
arXiv: https://arxiv.org/abs/2609.25022v1

Line-segment detection is fundamental to robotics, autonomous navigation, and industrial inspection. While transformer-based detectors achieve the highest accuracy, their deployment on microcontrollers remains impractical due to resource constraints. The STM32N6, with its Neural-ART NPU, promises to enable deep vision at the extreme edge. However, existing detectors rely on attention, grid-sampling, and normalization, operators that are unsupported by the convolution-oriented NPU. This architectural mismatch is characterized operator by operator: attention, grid-sampling, and normalization lack accelerator primitives, and the decoder's self-attention alone materializes a 39 MB score tensor that exceeds on-chip memory. To address this limitation, NPLSD is introduced as a pair of NPU-compatible line-segment detectors built from one design methodology. NPLSD-H retains the convolutional HGNetv2 backbone of LINEA and replaces the transformer head with a fully-convolutional feature pyramid and an F-Clip dense head. NPLSD-M adapts the M-LSD-tiny trunk to the supported operator set. Warm-started from ImageNet and trained on ShanghaiTech Wireframe, the 2.63M-parameter NPLSD-H reaches sAP^10=37.9 (35.9 int8); the 0.62M-parameter NPLSD-M reaches 41.9 (41.1 int8). A controlled ablation isolates the trunk as the only variable, and initialization alone accounts for 4.6 points.

---

### When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation

Authors: Anubhav Gupta, Mayara Costa Figueiredo, Leticia Santos Machado, Tanner Wright, Ivan Beschastnikh, Cleidson R. B. de Souza, Gema Rodríguez-Pérez
Published: 2026-08-12
Categories: cs.SE, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2609.22102v1

Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts the technical quality of generated code. We conduct a large-scale empirical study of persona-induced bias in LLM-based code generation, focusing a proprietary model (Gemini 2.5 Pro) and an open-weight model (GPT-OSS-120B). Using 18 demographic personas spanning nationality, gender, and experience level, we compare persona-induced prompts against a neutral baseline. Across 35,000+ generated programs, we analyze demographic marker leakage in reasoning and responses, as well as differences in functional correctness, maintainability, code style, and security. Our results show that demographic cues are frequently reflected in LLM reasoning and outputs. Demographic markers appear in up to 65% of responses and 70% of reasoning traces, despite being semantically irrelevant to the tasks. On LiveCodeBench, persona prompting were associated with lower correctness scores of the Gemini model by an average of 1.54 percentage points, with one persona exhibiting a decrease of 3.6% (odds ratio = 0.51). In contrast, the accuracy of the GPT-OSS model improved by 3.4 - 5.7% across all personas (odds ratios = 1.8 - 3.0). Maintainability and code style metrics show statistically significant but negligible effect sizes (all Cliff's δ < 0.15), and security vulnerabilities exhibit no systematic persona-specific patterns. Overall, our results show that the presence of demographic information about users is associated with measurable variation in LLM reasoning and code quality even in purely technical tasks, and that these effects hold across models. Our work highlights an under-examined risk in LLM-assisted software development.

---

### Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models

Authors: Meysam Ghaffari, Nina Fatehi, Bhaskar Sen, Nasim Sabetpour, Carlos Morato
Published: 2026-08-12
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.22101v1

Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We formulate this phenomenon, which we call context poisoning, as extreme-value interference in attention: the decisive-evidence score is upper-bounded, while the maximum score among effective distractors grows with their number. Under a softmax retrieval abstraction, we derive a finite-sample upper bound showing that maintaining a fixed accuracy target above base rate requires the evidence margin to scale as $Ω(\sqrt{\log N})$, where N denotes the effective distractor count rather than necessarily the raw context length. The analysis connects long-context degradation to score aliasing, positional aliasing, and softmax dilution. Controlled experiments show that retrieval accuracy decreases as total context grows in the presence of embedded hard negatives, that the same-format condition produces the largest observed accuracy drop among the tested distractor constructions at fixed context length, and that retrieval gating can improve evidence use while its net benefit depends on preserving evidence recall. These results motivate evidence bottlenecks, alias-resistant representations, retrieve-then-reason architectures, verifier-mediated memory, and contrastive anti-poison training.

---

### AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

Authors: Artem Sakhno, Grigorii Davydenko, Omar Zoloev, Julia Belikova, Andrey Savchenko, Maksim Makarenko
Published: 2026-08-12
Categories: cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2609.22100v1

Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce distracting information. Soft compression addresses this challenge by encoding passages as compact sequences of continuous memory embeddings before generation. However, existing methods typically assign each retained passage an identical number of memory embeddings, irrespective of its query-specific relevance. To address this, we propose AdaMem, a relevance-guided soft-compression framework that maps learned passage-relevance estimates to a query-dependent allocation of a fixed memory-token budget. A shared query-conditioned compressor produces both continuous passage memories and relevance scores in a single pass; a deterministic allocation rule assigns more memory tokens to higher-scoring passages and can omit low-scoring ones. Across six open-domain QA benchmarks, AdaMem consistently outperforms OSCAR (the closely matched soft-compression baseline that uses uniform allocation) as well as other soft-compression methods at matched memory budgets. Under standard 16$\times$ compression, AdaMem improves sub-string match by up to 3.2 points (5.5%) over uniform allocation baseline, with an average relative gain of 3.4%; under aggressive 64$\times$ compression the average relative gain grows to 14.6%, with a maximum of 9.8 points (19.7%) on PopQA. AdaMem matches the answer quality of the uncompressed at up to 4$\times$ lower inference latency than full context baseline. AdaMem retains an efficiency profile comparable to the uniform-compression baseline, while achieving up to $4\times$ lower inference latency than full-context inference. Thus, relevance-guided memory allocation is particularly effective when retrieval pools are large and the available memory budget is tight.

---

### A framework for recipe data structure with applications for culinary and nutritional insights

Authors: Mansi Goel, Sumit Bhagat, Saloni Srivastava, Malav Patel, Shlok Vinodkumar Mehroliya, Ganesh Bagler
Published: 2026-08-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.22099v1

Cooking is a complex process that transforms raw ingredients into delicious and nutritious dishes, yet the recipes that encode this process remain largely free text; readable by people but not directly computable. Existing recipe collections capture fragments of this information, but no shared representation links a recipe's structured ingredient composition, its geo-cultural provenance, and its nutritional profile within a single queryable schema. We address this representation gap by formalizing a framework for recipe data structure that decomposes each recipe into typed ingredient entities, grounds those entities in a reference nutritional database, and annotates them with geo-cultural and dietary context. We present RecipeDB2, a structured compilation of 128,942 recipes with 35,474 ingredients from 32 regions and 99 countries. Ingredient phrases are parsed into seven culinary attributes using a transformer-based named-entity model; ingredients are linked to the USDA reference tables through a BERT embedding strategy (F1 = 87.90 on a manually adjudicated set of the 200 most frequent ingredients), yielding 148 nutritional parameters per mapped ingredient; a Random Forest classifier propagates 34 ingredient categories across the full vocabulary; and a deterministic, conservative rule set assigns each recipe a dietary style. Through RecipeDB2 (https://cosylab.iiitd.edu.in/recipedb2/), we demonstrate a scalable framework for making recipes computable, turning culinary heritage (long treated as an artistic rather than a quantitative object) into a data-driven analysis.

---

### TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding

Authors: Huapeng Zhou, Huayu Wang, Xinyu Wang
Published: 2026-08-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.22098v1

Speculative decoding accelerates language-model inference by letting a cheap drafter propose tokens that the target model verifies in parallel. Recent block drafters make drafting nearly free: a single backbone pass emits an entire block of draft tokens. Draft trees promise a further gain -- several alternative continuations verified in one target forward -- but existing constructions rank candidates by per-position marginals that ignore which parent a candidate extends, so on semi-autoregressive drafters wider trees mostly add mis-ranked nodes; and a tree of fixed size ignores how much speculation each decoding round, and each serving load, can support. We introduce TreeSpark, which reads a parent-conditioned distribution from the drafter's existing Markov head at negligible cost, calibrates it into an edge-acceptance estimate, and lets path survival govern everything else: best-first expansion, per-round stopping, and a load-adaptive serving policy. Sampling siblings without replacement, with matching residuals in recursive rejection, keeps decoding lossless at any temperature. Adaptive trees improve on matched fixed budgets at every temperature; against a tuned chain on the same drafter, TreeSpark accepts 15-25% more draft tokens per round and decodes 8-14% faster in single-request wall-clock, and under rising load it gracefully shrinks the tree back to the chain. Code and artifacts: https://github.com/PopSoda2002/TreeSpark

---

### Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models

Authors: Junpeng Wang, Yuzhong Chen, Menghai Pan, Uday Singh Saini, Yiwei Cai
Published: 2026-08-12
Categories: cs.CL, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2609.22097v1

The evaluation of large language models (LLMs) on coding tasks has primarily focused on performance metrics such as pass@k. As LLMs continue to advance, many models now meet baseline performance requirements, reducing the discriminative power of performance-based evaluation alone. Yet a key question remains largely unexplored: how do LLMs differ in their coding behavior? We propose CLIC (Code Learning for Identification and Comparison), a visual analytics approach that characterizes LLM coding behavior through token-frequency analysis. CLIC represents each code sample as a feature vector of token frequencies and trains an interpretable decision tree to separate two LLMs' code sets. Beyond classification accuracy, we define two new metrics: robustness, which measures whether the two LLMs remain distinguishable as their most-discriminative tokens are progressively removed, and concentration, which measures whether the difference is driven by a few dominant tokens or spread across many. Interpreting numerous pairwise comparisons (across LLM pairs, tasks, and tokenization levels) and tracing the full analytical chain form an inherently multi-scale, hypothesis-driven exploration task. We therefore develop an interactive visual analytics system to navigate the comparison landscape, identify pairs of interest, and drill down into discriminative tokens and their code contexts. Case studies comparing 10 LLMs across 22 Kaggle ML tasks reveal actionable insights for LLM selection and prompt engineering.

---

### Function Lives Where Variance Doesn't: Task-Weighted Charts of a Language Model's Computation

Authors: Alexandre Quemy
Published: 2026-08-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.18989v1

How many dimensions does a language model's computation actually use? The question is ill-posed until one names a functional. Task-weighted charts make it well-posed: low-dimensional coordinate systems fit against a chosen functional of the representation, under the functional's own metric, turning distillation into plain least squares. Across six models from three families, spanning 70m to 7B parameters, next-token prediction needs 70--90% of the residual stream's width to stay within 5% of intact perplexity, a width consumed by the rare tail of language, and the variance profile predicts none of it: two directions carry 90% of GPT-2's activation variance and almost none of its function. Dimension is per-functional: the model's own uncertainty reads from six coordinates where the full predictive distribution needs hundreds; and it grows with depth. The dissociation is exploitable: when only a few dimensions can be kept, charts trained under the functional's metric preserve the model's predictions better than variance-based or optimal linear compression.

---

### Diagnosing Faults in Reinforcement Learning Simulators and World Models with Canonical Polynomial Invariants

Authors: Tesfay Zemuy Gebrekidan, Hadush Hailu Gebrerufael
Published: 2026-08-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.13194v1

A large literature builds physical structure into learned dynamics on the premise that models respecting the underlying physics predict better. We test that premise using exact polynomial invariants recovered from trajectories and canonicalised as reduced Gröbner bases over $\mathbb{Q}$. On Acrobot, exactness provides little benefit for prediction: a consistency regulariser reduces algebraic residual while leaving rollout fidelity essentially unchanged, and a shaping potential recovered from a system with a 100% mass error accelerates learning as effectively as the correct potential. Exact canonical invariants instead prove valuable for diagnosis. We develop two procedures: screening, which identifies the violated physical constraint, and attribution, which recovers the faulty invariant and identifies the responsible physical parameter. To enable this, we introduce normal-form deflation and quotient-space recovery. Across fifteen injected faults, screening localises every broken constraint with no false alarms, whereas observation-space baselines do not localise any; attribution recovers the responsible parameter on all seven parameter faults. Paired difference tests detect all faults, showing that the advantage is localisation rather than detection. Perturbing reference generators by $10^{-4}$ preserves 14--15/15 localisations, showing that screening does not require exactness, whereas ideal-equality decisions distinguish perturbations of only $10^{-12}$, showing that exactness is required for algebraic comparison. Applied to 350 release pairs across eleven RL environments, the diagnostic finds no evidence of changed simulator dynamics, instead revealing properties of the benchmark implementations themselves.

---

### Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching

Authors: Boldsaikhan Bolorkhuu, Tsogtgerel Gantumur
Published: 2026-08-12
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2609.11962v1

We study vector-valued binary affine refinement operators with finitely supported matrix masks and compactly supported continuous piecewise linear input and forcing data. We prove that every finite refinement iterate admits an exact ReLU realization of fixed width and depth linear in the number of iterations. No separation of the forcing profile from the binary cell seams is required. The main mechanism is universal reflection doubling. Pairing each residual profile with its reflection replaces the two binary transition matrices by one fixed block matrix together with a fixed swap involution. The cell-seam identity makes the two branch candidates agree at the tent fold, while their swap-odd component is bounded linearly by the distance to the fold. This permits exact branch selection by a fixed continuous piecewise linear cone switch, without multiplication by a variable selector. The resulting primal recursion requires the residual orbit in reverse order. We obtain exact backward replay from the residual memory controller developed previously for affine refinement, interpreted here through the reflection quotient of circle doubling. The construction propagates the full vectorized profiles rather than decomposing the input and forcing into reference atoms. We also treat stage-dependent forcing from a fixed finite-dimensional family and show that genuine reflection equivariance reduces the doubled cascade to a single parity sector.

---

### ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models

Authors: Zhengshu Zhang, Zhiyuan Li
Published: 2026-08-12
Categories: cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2609.05461v1

Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted future embedding lands closer to the goal embedding. This silently assumes that latent closeness is action-rankable, i.e., that ordering candidates by latent distance agrees with ordering them by true cost. We audit this assumption directly. We introduce ARC-Bench, a no-leak, fixed-candidate protocol that measures whether frozen JEPA-style objectives rank candidate actions correctly, and apply it to official released JEPA-WM checkpoints across navigation and manipulation-style control. The assumption fails, severely and structurally: on the official manipulation audits the top-scored candidate is almost always suboptimal, and the same inversion appears in the maze domains. A controlled visual-backbone extension shows that the defect persists when DINOv2 is replaced by video-pretrained V-JEPA 1 and V-JEPA 2 encoders at ViT-L/ViT-G scale. Provenance, undertraining, matched-budget backbone controls, and metric-circularity controls rule out trivial explanations. We then explain why this defect has stayed invisible: closed-loop replanning masks it. When we reduce the planner's replanning frequency, success collapses in both a navigation and a manipulation domain, and the episodes rescued by frequent replanning are enriched for severe first-plan ranking failures in the PointMaze first-plan diagnostic. Closed-loop success rates therefore systematically overstate the rankability of frozen latent representations. ARC-Bench supplies the measurement, and the masking mechanism the explanation, for methods that adapt, amortize, or replan around latent-space planners without directly auditing released JEPA-WM action rankability.

---

### Redesigning and Auditing Deep Research Writing for Faithful Reports

Authors: Hiroaki Hayashi, Pranav Narayanan Venkit, Prafulla Kumar Choubey, Chien-Sheng Wu
Published: 2026-08-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.28643v1

Rubric-based evaluations of deep-research (DR) systems often obscure fine-grained factual failures in generated reports. We introduce CLAIMPROBE, a claim-level audit that decomposes DR reports into claims and measures hallucination, misattribution, citation hygiene, and necessary-fact recall against retrieved evidence. Using CLAIMPROBE, we find that strong DR pipelines can omit key evidence and misattribute claims even when their rubric scores remain stable. We then propose CLAIMWRITER, a hierarchical claim-based writer that extracts source facts, maps them to a query-derived outline, and drafts each section from a source-linked claim representation. Across three prior DR frameworks, replacing only the report writer with CLAIMWRITER reduces hallucination by 2.6 to 4.5 times and improves necessary-fact recall by 1.2 to 1.7 times, while largely preserving overall report quality. CLAIMWRITER also enables localized revision: when sources change, it propagates changed source facts into revised reports at the highest rate among update methods, while also being more cost-effective.

---

### From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review

Authors: Pranav Bykampadi, Neel Mokaria, Vishesh Narayan, Faizan Wajid, Ashok Agrawala
Published: 2026-08-12
Categories: cs.AI, cs.CE, cs.DL, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2608.28642v1

Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admitted, or how it should be used downstream. We argue that reliable agentic knowledge systems require governance as an essential component of graph construction to bridge this gap. We propose MAGG, a principled multi-agent framework for constructing Governed Knowledge Graphs that introduces explicit governance decisions for reliable and trustworthy knowledge sharing. A domain classifier first induces entity and relation types directly from document content, enabling operation in open-world settings without fixed schemas. Candidate triples are assigned to domain owners, reviewed against supporting evidence, admitted through governance decisions, and stored with audit metadata. The same ownership structure is reused during question answering, where queries are routed to domain-specific graph experts rather than answered through undifferentiated retrieval. Our evaluation demonstrates MAGG's effectiveness: On SciERC, MAGG improves strict triple F1 by 47% and mapped triple F1 by 51% over flat insertion. A blinded review of 120 triples finds governed-only triples more often source-supported than flat-only ones, and revised triples supported in 100% of cases. Finally, on MuSiQue, MAGG outperforms Microsoft GraphRAG by 9.0 exact-match points and 11.2 token-F1 points.

---

### Operational digital twin clinics enable task-based evaluation of embodied AI

Authors: Xinyuan Wu, Jingrao Zhang, Mengdi Xu, Henry K. Chu, Mingguang He, Danli Shi
Published: 2026-08-12
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2608.21416v1

Embodied artificial intelligence (AI) must be tested in the clinical environments where it will operate, but building realistic, robot-testable settings is costly and difficult to scale. Here we show that routine clinic images can be transformed into operational digital twins for task-based evaluation of embodied AI. Using 39 ophthalmic clinic scenes, we converted single photographs into editable, simulator-ready environments and assessed reconstruction quality, room-scale geometry, mesh grounding, multi-robot feasibility, perturbation sensitivity and closed-loop policy performance. The reconstructed scenes preserved workspace structure, while local editing enabled controlled device reconfiguration. Device meshes, collision proxies and semantic anchors converted visual reconstructions into contact-aware simulation scenes. Across three robot embodiments, shared task targets showed different patterns of reachability and contact feasibility. Small device translations and rotations produced task-specific changes in contact margins that were not captured by visual similarity alone. Digital-twin trajectories also supported local policy learning and closed-loop evaluation. These findings establish operational validity as a key principle for clinical digital twins and provide an intermediate layer between offline development and physical deployment of embodied AI in healthcare.

---

### Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

Authors: Yisong Xiao, Aishan Liu, Yongxin Huang, Zonghao Ying, Shiji Zhao, Tianlin Li, Yong Han, Jian Yang, Xianglong Liu
Published: 2026-08-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.21415v1

Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debiasing approaches typically compare token probabilities between the original and biased generations during decoding, but they are fundamentally limited by their reliance on a single, stereotyped viewpoint and fail to account for the diversity of social perspectives. Inspired by the social science principle that diversity fosters fairness, we propose Counterfactual Ensemble Decoding (CED), a novel framework that constructs multi-group counterfactual perspectives within the visual representation space and integrates them during decoding to promote equitable model behavior. CED first performs counterfactual steering in the visual space by identifying semantic directions associated with each social group and generating counterfactual representations along these directions, thereby offering diverse perspectives that disrupt stereotypical narratives. During decoding, CED locates the decoder layer exhibiting the greatest divergence among these perspectives and ensembles their token distributions using uncertainty-aware weights, prioritizing high-confidence tokens from different groups to yield a more balanced probability distribution that guides fairer generation. Extensive experiments on three social bias evaluation benchmarks demonstrate that \tool achieves substantial improvements over leading baselines, reducing bias by up to 47.97% across scenarios involving occupations, descriptors, and persona traits. Moreover, CED also preserves the core capabilities of the original model with minimal degradation.

---

### RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification

Authors: Jingzheng Li, Yufei Ge, Qianren Mao, Zhijun Chen, Bing Li, Xingyu Peng, Baochang Zhang, Xianglong Liu
Published: 2026-08-12
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2608.21414v1

Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approaches typically predict scene-level accidents, infer risk objects indirectly from ego behavior, or apply geometric checks after trajectory forecasting, without directly using predicted ego--object relations for risk-source localization. We propose RiskWorld, an object-centric latent world model that identifies risk from the imagined evolution of each candidate relative to the ego vehicle. RiskWorld combines pretrained predictive video representations with structured ego--object histories, contextualizes observed interactions, and rolls relation-aware object states into the future using RSSM-style latent dynamics. It decodes the rollout into object-level risk scores, supported by auxiliary future-relation and temporal-risk predictions. Inference uses only observations up to the current time, while logged futures provide training supervision. On RiskBench, RiskWorld achieves the best overall F1 of 63.0\% and the lowest false-alarm rate of 2.1\%. Further analyses show that the learned rollout captures the evolution of object-level risk before critical events, while RiskWorld's selections preserve planning-critical information under filtered observation.

---

### Columnar-Embedder: A Biologically Inspired Cortical Architecture for Binary Sparse Distributed Graph Representations

Authors: Mohamed Abidalrekab, Dan Hammerstrom
Published: 2026-08-12
Categories: cs.NE
arXiv: https://arxiv.org/abs/2608.20408v1

Finding a representative description of graph entities that captures their structural roles and homophily is a challenging goal for graph embedding techniques due to the non-Euclidean nature of graphs. Traditionally, Graph embeddings achieve top performance via random-walk methods and graph neural networks. However, these methods are transductive and utilize an expensive global optimization via softmax or a dense representation trained in an end-to-end pipeline with gradient descent. Nonetheless, other variants of GNNs can map to unseen nodes; they still rely on iterative message passing and backpropagation, incurring high computational and memory costs. Conversely, the mammalian cortex solves structurally similar problems by learning to map its input stream of patterns into a compact representation for downstream regions. We present the biologically inspired Columnar-Embedder architecture for learning binary Sparse Distributed Representations (SDRs) of graph nodes. The learning is driven by a local Bienenstock-Cooper-Munro (BCM) Hebbian rule modulated by positive pointwise mutual information (PPMI) computed from online streams of random walks. Continuous learning from streaming random-walk pairs without labels, backpropagation, or supervision enables the architecture to exhibit natural resistance to catastrophic forgetting. Across five graph benchmarks, the performance of SDRs is competitive with that of real-valued dense embeddings on node classification and link prediction, while the architecture exhibits portability, resilience to noise, and robustness to data corruption.

---

### BASC : Behavior-Aligned Quantization and Pruning for Low-Bit Spiking Neural Networks

Authors: Linliang Chen, Yan Zhong, Xin Liu, Sai Li, Wang Kang
Published: 2026-08-12
Categories: cs.NE
arXiv: https://arxiv.org/abs/2608.19239v1

Spiking Neural Networks (SNNs) encode information through binary spikes and compute in an event-driven manner, offering an energy-efficient paradigm for machine intelligence. However, high-performance SNNs incur substantial memory and timestep-wise computation costs that hinder deployment on resource-constrained devices. Quantization and pruning provide complementary routes to reducing these costs, yet both make their decisions with local criteria that overlook temporal task feedback in quantization and inter-channel dependencies in pruning. Consequently, optimizing either criterion can still yield suboptimal compression performance. We refer to this discrepancy as criterion-behavior mismatch and propose Behavior-Aligned SNN Compression (BASC), a unified framework with two lightweight modules. For quantization, the scale is applied to synaptic current at every timestep and therefore shifts spike timing. Temporal-Behavior Scale Correction (TSC) makes the scale learnable under a temporal loss, allowing firing behavior to inform scale optimization. For pruning, channel importance depends on how channels jointly drive the membrane potential across the firing threshold. Boundary-Level Inter-Channel Correction (BIC) uses channelwise importance scores for initial selection and inter-channel information to re-evaluate only channels near the pruning threshold. Extensive experiments on static and neuromorphic benchmarks show that lower-bit BASC models match or outperform higher-bit baselines and retain this accuracy advantage after structured pruning, while further reducing model storage and synaptic operations.

---

### Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis

Authors: Moumita Sen Sarma, Pascal Hitzler, Eugene Y. Vasserman
Published: 2026-08-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.14729v1

Fake/synthetic images are increasingly prevalent, but it remains unclear whether Convolutional Neural Networks (CNNs) process real and fake images in the same internal manner. This work examines the hypothesis that CNNs represent real and fake images differently, such that fake images induce different hidden-layer activation patterns even when semantic content is preserved. The hypothesis is evaluated in scene recognition settings using trained CNN models. Dense-layer activations are extracted, and neurosymbolic methods assign semantic labels to selected neurons. For each real test image, corresponding fake images are generated with similar semantic content using object-label-guided text-to-image and image-to-image generation based on Stable Diffusion variants. Paired real-fake activation patterns are then compared statistically. Additional experiments with another dataset, CNN architecture, generative model, and JPEG/blur degradation analysis assess robustness. Results suggest that fake images evoke different hidden-neuron activations, and these differences are not explained only by simple image degradation. Overall, the findings indicate that real and fake images differ in CNN hidden-layer activation behavior at least in some settings, which opens the door for follow-up work on making use of this different behavior to improve fake image detection.

---

### Tail-Aware Top-$k$ On-Policy Distillation

Authors: Huipeng Huang, Hongxin Wei
Published: 2026-08-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.14728v1

On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories. To provide dense supervision at tractable cost, many works minimize the reverse Kullback-Leibler (KL) divergence between the student and teacher's normalized distributions over the teacher's top-$k$ tokens. However, this normalized objective discards the information about tail probability: the total probability outside the teacher's top-$k$ tokens. As a result, the optimization can steadily increase the student's tail probability and entropy, empirically degrading downstream accuracy. To address this issue, we propose Tail-Aware Top-$k$ OPD (\textbf{TA-OPD}), a novel distillation method that restores the missing tail probability signal. In particular, TA-OPD minimizes the reverse KL divergence over the top-$k$ tokens plus a tail token that carries the tail probability. In effect, TA-OPD better aligns the student's next-token distribution with the teacher's, preventing the increase in tail probability and entropy caused by top-$k$ normalization. Extensive experiments demonstrate the superiority of TA-OPD, improving Avg@8 by up to 8.05 points on common benchmarks. Our code is available at https://github.com/HuipengHuang/TA-OPD.

---

### Low Cost Two-Stage Fabric Defect Detection at the Edge

Authors: Rasel Hossen, Diptajoy Mistry, Mosaddek Hossain Kamal
Published: 2026-08-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.14727v1

Fabric inspection in the garment industries of low-income economies remains largely manual, and commercial vision systems are priced beyond most small and medium mills. Because defects are sparse under controlled production, a natural response is a cascade: screen every frame with a cheap anomaly detector and invoke a full detector only on suspicious frames. We build such a cascade for four knit-fabric defect classes and deploy it end-to-end on an NVIDIA Jetson Nano with TensorRT FP16. Stage 1 is a compact convolutional autoencoder with decoder attention gates, an edge-weighted reconstruction loss, and feature-level distillation from a frozen YOLOv5n teacher; Stage 2 is YOLOv5n, invoked only on flagged frames. On a 249-image benchmark disjoint from detector training (20 defective, 229 non-defective), Stage 1 at a recall-prioritised threshold flags all 20 defective images (95% CI 0.83-1.00) at a false-positive rate of 49.3% (113/229), reducing false positives by 19.3% relative to a plain autoencoder (p=0.011). The parallel pipeline reaches 13.45 FPS against 9.86 FPS for a sequential YOLO-only loop. Our central finding comes from decomposing that 1.36x: 91% of it is attributable to overlapping JPEG decode with inference rather than to the cascade, which contributes only a 5.1% inference reduction at the measured forwarding rate p = 0.534. We further show that forwarding here is false-positive-limited rather than prevalence-limited - 85% of forwarded frames are false alarms - and quantify the 29-45% inference reduction attainable under tighter calibration. We report this as a caution for cascade speedups measured without controlling the data path, and position the system as AI-assisted triage rather than autonomous acceptance.

---