Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
medRxiv (Medicine) 2026-06-15

Mucosal and Systemic Antibodies Associated with Clinical Protection in a Pertussis Controlled Human Infection Model

Background The engagement of mucosal and systemic immunity in preventing Bordetella pertussis colonization and infection in humans, the impact of prior vaccination on host immunity and protective outcomes, and the dynamics of the host response following exposure remain poorly understood. Methods Healthy adults were challenged with increasing colony-forming units (CFUs) doses, 106-108, of B. pertussis D420 intranasally (NCT05136599). Shedding (PCR and culturing) and symptom development were monitored up to 21 days post-challenge. Serum and nasal wash IgA and IgG were measured before challenge (baseline) and up to 6 months post-challenge. Findings Antibodies increased post-challenge only in infected individuals, primarily nasal IgA. Participants who remained uninfected had higher baseline levels of filamentous hemagglutinin (FHA)- specific mucosal IgA and IgG, and higher serum IgA against fimbriae 2/3 (FIM). FHA was negatively associated with bacterial load and was a key discriminator between shedders and non-shedders, up to one week post-challenge. By day 14 post-challenge, pertussis toxin (PT) IgG and FIM IgA in both serum and mucosal samples were negatively associated with bacterial colonization. The majority (96.7%) of acellular pertussis (aP) vaccine recipients (n=23, median age 2.0 years) became infected, compared to 69.4% of those who received whole-cell pertussis vaccine (n=36; median age 32.0 years), and their antibody responses remained distinct following infection. Interpretation Nasal FHA antibodies emerged as early predictors of protection against pertussis infection, while PT IgG and FIM IgA antibodies may reflect clearance after infection. aP-primed individuals were more susceptible to infection, despite their younger age and more recent vaccination. Funding CDC Contract #75D30122C15467 and CDC IPA Agreement #24IPA2417512 Disclaimer: The findings and conclusions in this report are those of the authors and do not necessarily represent the official position of the Centers for Disease Control and Prevention, US Department of Health and Human Services.

02.
medRxiv (Medicine) 2026-06-16

Validation of a Smartphone-Image-Based Computer-Vision Model for Lean Mass and Body Fat Estimation Against Dual-Energy X-ray Absorptiometry

Introduction Body composition, rather than body weight alone, is an increasingly important health metric, and preservation of lean mass has become a central concern in obesity treatment, aging, and chronic disease management. Dual-energy X-ray absorptiometry (DXA) provides accurate assessment of fat and lean tissue, but its cost and logistical requirements limit repeated measurement. Computer-vision approaches show promise for estimating adiposity from smartphone images, but lean-mass estimation remains less established. Methods We evaluated a computer-vision body composition model, applied to consumer-grade smartphone photographs, against DXA in a held-out validation sample of 195 adults from an ongoing cross-sectional study. Body fat percentage and total lean mass percentage were co-primary outcomes; for total lean mass percentage, an image-only configuration (no added covariates) was pre-specified as primary. Agreement was quantified using Lin's concordance correlation coefficient (CCC) as the lead statistic, with Pearson correlation, mean absolute error, root mean square error, mean bias, and Bland-Altman limits of agreement. In secondary analyses, appendicular lean mass and total lean mass percentage were each estimated with and without routine anthropometric and demographic inputs (body weight, height, age, and sex). Results Total lean mass percentage agreed with DXA from image features alone (CCC 0.916). Body fat percentage, estimated with routine inputs added, agreed at least as closely (CCC 0.930). Adding routine inputs barely changed agreement for total lean mass percentage but markedly improved it for appendicular lean mass, an absolute quantity that scales with body size. Conclusions A smartphone-image-based model estimated both body fat and lean mass with strong agreement to DXA, with lean mass percentage from image features alone. The approach needs no fixed equipment or ionizing radiation. Whether it can track change over time, including in incretin-based weight loss where lean mass preservation is a concern, was not assessed in this cross-sectional study.

03.
arXiv (CS.CL) 2026-06-19

Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality. We test this practice on a 28-quant cohort of Qwen3.6-35B-A3B and a 41-quant cohort of Devstral-Small-2-24B, evaluated across a suite of downstream benchmarks. We find that KLD is strongly correlated with benchmark score over the full cohort ($\rho=-0.72$ on Qwen and $\rho=-0.86$ on Devstral, both with $p

04.
arXiv (quant-ph) 2026-06-11

Towards the implementation of a quantum classifier

arXiv:2606.10150v2 Announce Type: replace Abstract: In this work, we investigate the use of a quantum circuit as a binary classification model in the context of quantum machine learning. We call this model, binary quantum classifier. First, we describe fundamental concepts of quantum computing and introduce the computational tool used: Qibo, an open-source framework for efficient quantum simulations and quantum hardware control. Then, we describe how to design a binary quantum classifier for the classification of images and small arrays of variables by showing how to input data in the circuit, defining a quantum circuit model Ansatz with trainable parameters and a loss function, and implementing multiple minimizers. We test our quantum classifier with two data sets. The first one is the MNIST data set which is composed of handwritten digits (reduced to only handwritten zeros and handwritten ones for binary classification). We study the behavior of different minimizers by increasing the number of layers of the Ansatz. The second data set represents two different high energy collisions that can occur at colliders such as LHC (CERN). Due to in-time proton-proton interactions known as pile-up, we distinguish two different data sets: "without pile-up" and "with pile-up". These collisions can be represented by images of size 32x32 or by six high-level variables that we call features. By increasing the size of the training data set and the number of layers of the Ansatz, we search for the best minimizer. Splitting the data set in training set and test set, we compute: ROC curve, AUC score, confusion matrices and test set accuracy. For "with pile-up" images, we compare the results obtained with the quantum classifier with a small convolutional neural network. We conclude that is possible to build a binary quantum classifier with a quantum circuit and we highlight its performances and limitations in comparison with classical technologies.

05.
arXiv (CS.CL) 2026-06-11

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges. Community registries have emerged to distribute these skills, but the security implications remain unstudied due to the absence of labeled threat data. This paper presents a systematic security analysis of 98,380 skills collected from two major registries. Through a combination of static pattern matching and dynamic behavioral verification, we identify 157 skills exhibiting confirmed malicious behavior, encompassing 632 distinct vulnerabilities across 13 attack techniques. Our analysis reveals that these threats are deliberate rather than accidental: each malicious skill contains an average of 4.03 vulnerabilities spanning multiple attack phases. We identify two dominant attack strategies with statistically significant negative correlation – credential theft via remote code execution, and agent manipulation through adversarial instructions embedded in documentation. Over half of all confirmed cases originate from a single threat actor employing templated brand impersonation at scale. We further observe that attack sophistication correlates with concealment investment, with advanced skills universally employing undocumented capabilities while also exploiting platform-native trust mechanisms. Following responsible disclosure, registry maintainers removed all 157 (100%) of the reported skills. Our dataset and detection pipeline are publicly available to facilitate future research on securing LLM agent ecosystems.

06.
arXiv (CS.LG) 2026-06-15

Can Machine Learning Forecast Rice Yields in Data-Constrained Settings? Satellite Climate Data, National Crop Statistics, and Lessons from Sierra Leone

arXiv:2606.13959v1 Announce Type: new Abstract: Sierra Leone's agriculture operates with almost no data-driven decision support, and no published machine learning study has examined the country's crop yields. We ask whether rice yield can be forecast from data Sierra Leone currently has. Using 25 years of FAOSTAT production data (2000-2024) for nine major crops, we train XGBoost, Gradient Boosting, and Random Forest under a strict anti-leakage protocol with expanding-window walk-forward evaluation across seven held-out years, benchmarked against naive persistence. No model trained on crop statistics alone outperforms persistence. Augmenting with free satellite climate data (CHIRPS rainfall, NASA POWER temperature) reverses this result: a climate-only XGBoost reduces forecast error by one third (RMSE 284 vs 428 kg/ha), a gain that holds for a linear model and is robust to excluding the anomalous 2018 season. Early-season (May-June) rainfall is the dominant predictor, implying seasonal yield risk is observable months before harvest. No model anticipated the 2018 collapse, whose origins were institutional rather than climatic. We translate the findings into policy recommendations for Sierra Leone's Feed Salone Strategy, with a fully open-source pipeline.

07.
arXiv (CS.LG) 2026-06-19

Towards Graph-Based Deep Learning for Map Generalization: Insights from Building Footprints Simplification and Aggregation

arXiv:2606.19956v1 Announce Type: new Abstract: Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-based deep learning to both tasks, reformulating simplification as node movement prediction and aggregation as link prediction within a unified graph learning framework. We evaluate representative graph neural network architectures (GCN, GAT, and GraphSAGE) on multi-scale building datasets, showing that GraphSAGE demonstrates relative strengths in link prediction accuracy, while also revealing persistent challenges in precise node movement prediction. Beyond quantitative performance, the results highlight that aggregation poses greater complexity and challenges than simplification, underscoring the difficulty of capturing higher-level spatial relationships in map generalization with current deep learning approaches. Although limitations such as data imbalance and the need for post-processing remain, the study provides valuable insights and methodological directions for advancing automated map generalization with deep learning approaches.

08.
medRxiv (Medicine) 2026-06-23

Acute Ischemic Stroke Detection on Non-Contrast CT: A Deep Learning Approach

Acute ischemic stroke (AIS) is a leading cause of disability and death while effective treatment requires quick and accurate diagnosis. Non-contrast CT (NCCT) is widely used in the initial screening of AIS, but stroke detection is challenging because early changes on NCCT are subtle or indistinguishable. Using hyperacute NCCTs as inputs and diffusion-weighted MRI as ground truth, we trained a deep learning algorithm to classify patients with AIS and segment the stroke lesions. We hypothesized that this approach would accurately detect hyperacute tissue density changes on NCCT. For the classification task, our ResNet50 model delivered the best performance (with 98.5% accuracy, 97.4% precision, and 100% recall on an evaluation set). Classification performance remained strong when restricted to lesions smaller than 5 mL, which constituted the majority of our evaluation cases. For the segmentation task accomplished using a range of U-Net architectures, performance was acceptable for large lesions and declined sharply for smaller lesions. Together, these findings demonstrate the feasibility of deep learning for AIS detection and represent a step towards faster triage and treatment for stroke patients.

09.
arXiv (CS.CL) 2026-06-15

Creative Integration: A Decidable Criterion of Creativity

"Integrative" solutions are widely praised but rarely defined: we lack an operational way to tell a genuine integration – one that makes the world cheaper to describe – from a tidy re-description. Building on the lineage that treats creativity and intelligence as compression, we give such a criterion for creative integration (CI): the resolution of a real conflict between A and B is CI if and only if, under a fixed description language, the description length strictly shrinks (C = L_pre/L_post > 1), with the reduction located in the conflict itself. We make the judgment decidable through four binary, conjunctive gates, and we fix its extension through a taxonomy of pseudo-integration that names and rejects the look-alikes. We back the criterion with a curated, multi-domain corpus and – crucially – validate it not by human inter-rater agreement but by four falsifiable tests it could fail: an independent computational check, discrimination against hard negatives, out-of-sample prediction, and description-language robustness; all pass with margin. The contribution is not "creativity is compression" but its decidability, discrimination, and corpus: on this account, what makes a move genuinely creative – rather than merely novel – is that it compresses a conflict, with novelty and value as downstream symptoms; whether all creativity is so constituted we state as an explicit conjecture. We claim only the sign of C-1; we judge, not generate. The result is a citable primitive for a broader program.

10.
arXiv (math.PR) 2026-06-11

Continuous stochastic flows driven by white noise and their duals

作者:

arXiv:2606.12143v1 Announce Type: new Abstract: We study a class of continuous stochastic flows driven by a space-time white noise and characterize their dual flows by explicit stochastic differential equations. A key ingredient of the proof is the convergence of solutions under coefficient approximations. As an application, we derive the dual flows in two illustrative examples, the squared Bessel flow and the Jacobi flow. We also introduce a new model of polynomially self-repelling (PSR) flow and show that it enjoys a self-duality property.

11.
arXiv (CS.LG) 2026-06-16

Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders

arXiv:2606.14999v1 Announce Type: new Abstract: Scientific user facilities generate X-ray scattering data faster than traditional workflows can process them. We address this challenge across two settings, offline dataset exploration and live on-the-fly analysis. We train a domain-specific attention-based Convolutional Variational Autoencoder (C-VAE) on 1.5 million X-ray scattering images to learn low-dimensional representations capturing structural variation across diverse experimental conditions. The learned latent space reveals well-organized clusters and smooth trajectories reflecting experimental progression. It further supports controlled synthetic scattering image generation across diverse structural states. When deployed without retraining, the model organizes time-resolved film formation experiments at two synchrotron facilities into interpretable latent structures. Benchmarking against DINOv3 (ViT-7B), a general-purpose vision foundation model, demonstrates that domain-specific training yields more interpretable latent organization for scattering data. Both workflows are integrated within Latent Space Explorer, a component of the MLExchange platform, supporting interactive structural exploration across archived datasets and live experiments.

12.
arXiv (CS.AI) 2026-06-16

LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization

arXiv:2606.15349v1 Announce Type: cross Abstract: Standardized examinations are typically treated as uniform syllabus coverage problems. We argue they are better understood as adversarial systems with stable latent cognitive structures diverging systematically from official syllabi. We introduce LearnOpt, which recovers this structure from historical question papers and generates personalized, time-bounded study plans. Applied to nine years of NEET questions (2016-2024, n=1,496), LearnOpt builds an exam knowledge graph from LLM-tagged questions, extracts a five-category latent skill distribution, and formulates study planning as a knapsack-variant optimization over prerequisite-aware subgraphs with Bayesian Knowledge Tracing. Central finding: NEET's latent skill distribution is stable within a syllabus regime (consecutive-year KL divergence 0.004-0.032 for 2016-2021, non-significant under permutation testing) but shifts significantly with NCERT's 2023 syllabus rationalization: pooling 2016-2021 (n=1,072) vs 2023-2024 (n=392) gives KL=0.040 (p=0.0005), with Elimination/Negation questions rising from ~20-29% to ~31-35%. Latent structure, while not permanently stationary, is piecewise stable, with shifts detectable and attributable to curricular events. Within either regime, subject predicts skill profile more strongly than year. An optimization evaluation, using one real and two synthetic mastery profiles, shows the skill-weighted objective produces a modest but real reordering of recommended topics over a mastery-conditioned frequency baseline. Applying the pipeline to JEE Advanced reveals a profile dominated by Multi-concept Integration (80.9% vs. 33.3% for NEET), with a JEE-vs-NEET divergence (KL=0.505) exceeding NEET's largest cross-subject divergence: exam tier shapes latent cognitive structure more than subject, which shapes it more than time within a regime. Code, knowledge graph, and annotated dataset are released publicly.

13.
arXiv (CS.AI) 2026-06-15

Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization

arXiv:2606.13925v1 Announce Type: new Abstract: Large language models can often close proof gaps in interactive theorem provers, but a verified theorem is not the same thing as a reusable library contribution. We study this distinction through a detailed case study: a semi-autonomous formalization of Grothendieck's vanishing theorem. The initial version compiles with no sorries, but an expert review found serious problems in definitions, theorem generality, file organization, and the API. We then ran a review-driven refactor and compression process and obtained a second expert review. The before-and-after comparison shows a sharp split: agents adapted well to local, mechanically checkable feedback, but remained weak at choosing definitions and designing APIs. We argue that autoformalization should be evaluated not only by closed sorries, but by whether the resulting formalization survives expert review.

14.
arXiv (CS.LG) 2026-06-16

Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare

arXiv:2605.01961v2 Announce Type: replace Abstract: Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents. However, in most scenarios, the model is trained on the average preference of all human evaluators, which, under large variations of preferences, can be unfair to minority groups. In this work, we consider fairness in dueling bandits, a standard framework for online learning from preference data. We assume that each user has a (potentially distinct) Condorcet winner, which is an arm preferred to every other arm. Using these user-specific Condorcet winners as reference points, we evaluate and score arms according to their performance relative to the corresponding winner. To promote fairness across heterogeneous users, we adopt the well-established Nash Social Welfare objective, which maximizes the product of user utilities, thereby inherently penalizing inequality and preventing the marginalization of any single user. Within this framework, we construct a hard instance to establish a regret lower bound of $\Omega(T^{2/3}\min(K,D)^\frac{1}{3})$ for a time horizon $T$, $K$ arms, and $D$ users, which, to the best of our knowledge, is the first result quantifying the cost of fairness in dueling bandits with heterogeneous preferences. We then present the Fair-Explore-Then-Commit and Fair-$\epsilon$-Greedy algorithms with a Condorcet winner identification phase. We further derive their regret upper bounds that match the lower-bound dependence on $T$ up to logarithmic factors.

15.
arXiv (CS.CL) 2026-06-12

Rigel: Reverse-Engineering the Metal 4.1 Tensor Compute Path on the Apple M4 Max GPU

Apple's Metal 4.1 exposes a tensor compute path: the Metal Performance Primitives (MPP) matmul2d operation over cooperative_tensor fragments, whose interface is documented but whose hardware behavior is deliberately hidden. The specification states which data-type rows are supported, never whether they are hardware-accelerated, where the operation physically executes, what its accumulator width is, or how it partitions matrix fragments across threads. We present Rigel, an empirical characterization of this path on a single Apple M4 Max (a pre-neural-accelerator generation). Using a checksum-gated, provenance-tracked microbenchmark harness, Rigel recovers eleven facts the v4.1 specification hides or contradicts. The headline finding: the Metal 4.1 fp8 (E4M3) matmul2d is emulated, not accelerated: it sustains 0.94x the throughput of fp16 despite reading half the operand bytes, so on M4 it is a memory-footprint feature, not a performance feature. We further show, via a three-signal triangulation (throughput ceiling, comparison against simdgroup_matrix, and per-rail power attribution), that matmul2d executes entirely on the GPU shader cores with no dedicated matrix datapath and no evidence of Apple Neural Engine routing; that it accumulates in >=fp32; and we reconstruct the opaque 8x8 cooperative_tensor fragment layout Apple documents nowhere. Acting on the characterization, a hand-fused GEMM + bias + GELU kernel beats the decomposed path by +6.5-12.9% in the cache-resident regime. All findings are reproducible from committed MIT-licensed code and per-cell CSVs.

16.
arXiv (CS.CL) 2026-06-11

Automated Scoring of Arabic Text Using Large Language Models: A Literature Review

In modern educational systems, Automatic Text Scoring (ATS) plays a central role by enabling scalable and consistent evaluation of learner responses without human intervention. Recently, the increased accessibility of LLMs and Arabic-specific datasets has sparked renewed interest in this area. In this work, we investigate LLM-Based approaches for the automated evaluation of Arabic texts, focusing on both short answer grading (ASAG) and essay scoring (AES). We further introduce a structured taxonomy comprising five dimensions: application domain, feedback generation capability, LLM architecture deployed, alignment with competency referential frameworks, and prompt engineering strategy. By applying this taxonomy, we conduct a comparative analysis of existing studies, examining their methodological approaches, datasets, evaluation metrics, and reported performance. The findings highlight the need for sustained and pedagogically grounded research efforts in Arabic ATS, given its significance for improving educational quality across Arabic-speaking communities.

17.
arXiv (CS.CV) 2026-06-18

Physics-IQ Verified

Video generative models ( VGMs) have become a new frontier that can be used not just for video generation but for a multitude of downstream tasks, including world modeling. To advance these tasks, a good video model must understand the physical reality of the world. Evaluating this understanding is an emerging field and has led to the Physics-IQ benchmark, which quantifies this explicitly by comparing model-generated videos to real-world videos of physical experiments. In this work, we present a systematic audit of the Physics-IQ benchmark, expose shortcomings and propose three solutions that sharpen how we can measure physical understanding of VGMs. Specifically, we improve prompt and ground-truth quality to reduce the influence of confounding factors and further introduce a sample-level scoring system that weights each sample and metric equally. Our resulting benchmark, Physics-IQ Verified, refines 57.6\% of all samples and improves over 34.8\% of prompts. In a comparison study using six image-to-video generative models, we observe moderate but meaningful ranking changes (Kendall's $\tau = 0.46$). We hope Physics-IQ Verified advances the community by providing a more reliable signal toward physically accurate VGMs. The code for the benchmark can be accessed at https://github.com/google-deepmind/physics-iq-benchmark

18.
arXiv (CS.CL) 2026-06-16

A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction

As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic work. We address this challenge by presenting a scalable pipeline for automating grammatical annotation in voluminous corpora using large language models (LLMs). Unlike previous supervised and iterative approaches, our method employs a four-phase workflow: prompt engineering, pre-hoc evaluation, automated batch processing, and post-hoc validation. We demonstrate the pipeline's accessibility and effectiveness through a diachronic case study of variation in the English evaluative consider construction (consider X as/to be/{\O} Y). We annotate 143,933 'consider' concordance lines from the Corpus of Historical American English (COHA) via the OpenAI API in under 60 hours, achieving 98%+ accuracy on two sophisticated annotation procedures. A Bayesian multinomial GAM fitted to 44,527 true positives of the evaluative construction reveals previously undocumented genre-specific trajectories of change, enabling us to advance new hypotheses about the relationship between register formality and competing pressures of morphosyntactic reduction and enhancement. Our results suggest that LLMs can perform a range of data preparation tasks at scale with minimal human intervention, unlocking substantive research questions previously beyond practical reach, though implementation requires attention to costs, licensing, and other ethical considerations.

19.
arXiv (CS.CL) 2026-06-15

The Linguistics Olympiads: Towards a New Corpus for Linguistics Research?

Linguistics olympiad problems (LOPs) are a category of self-sufficient puzzles consisting of a scaled-down corpus representative of certain linguistic phenomena, from which the solver must deduce a primitive set of rules of the language and then translate a new set of elements. The linguistics olympiads (LOs) have become a worldwide phenomenon with 43 different territories taking part in the International Linguistics Olympiad (IOL) 2025. While the typology and solving strategies of LOPs have been analysed, their scientific facet and connections to academic linguistics have yet to be explored. LOPs are directly connected to many linguistic fields, e.g., linguistic typology, linguistic relativity, and linguistics fieldwork. Recently, LOPs have become a research focus as benchmarks for large language models, thus highlighting their usefulness in computational linguistics. Nevertheless, they have not yet been integrated into mainstream linguistics research. This paper attempts to open new directions of including this particular type of puzzle in academic research by offering a structured evaluation of LOPs as linguistic data sources and proposes criteria for their responsible use in academic research. Starting from a set of over 1800 LOPs, this study critically examines the potential of LOPs as a novel corpus for linguistics research by discussing their strengths and limitations as tools, as well as the areas of linguistics into which these problems could fit. This work forms the foundation for a broader initiative aimed at bridging the gap between LOs and academic linguistics, by establishing a robust theoretical framework for LOPs.

20.
arXiv (CS.AI) 2026-06-19

Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models

arXiv:2606.19932v1 Announce Type: cross Abstract: Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a severe performance collapse. We attribute this degradation to the spatially agnostic nature of existing reduction methods, which violate the two-dimensional structural premise required by the selective scanning mechanism. In this work, we propose STORM, a spatial-aware token reduction framework designed to maintain structural integrity throughout the compression process. STORM reformulates reduction into a structured operation on spatial units, enforcing localized constraints to maintain both grid topology and neighborhood coherence. As a plug-and-play module, STORM equips existing reduction pipelines with explicit spatial awareness without any training. Empirical results demonstrate that STORM achieves state-of-the-art pruning accuracy across diverse vision Mamba backbones under training-free settings. Notably, STORM delivers a substantial accuracy recovery on VMamba, outperforming prior methods by up to 63.3\% in top-1 accuracy. Meanwhile, STORM incurs only a 1.0\% accuracy drop on PlainMamba, achieving performance comparable to ViT.

21.
arXiv (CS.CL) 2026-06-16

Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering

作者:

Aggregate accuracy benchmarks conceal a systematic structure in how large language models fail at electronic health record (EHR) question answering: questions requiring more inferential steps produce disproportionately more errors. Motivated by theoretical results on transformer compositionality limits, we introduce a pre-specified hop-count taxonomy – the number of distinct reasoning steps required to answer a clinical question from an EHR – as a principled predictor of model failure. We annotate 313 clinician-generated MedAlign EHR question-answer pairs across four hop levels and evaluate 301 questions in a within-model ablation (claude-sonnet-4-6, zero-shot vs. extended thinking) and cross-architecture replications (gpt-4o and gpt-5.4-2026-03-05, zero-shot). All three models, spanning two providers and two OpenAI generations (GPT-4 and GPT-5), show monotone accuracy decline with hop count: Claude Sonnet zero-shot falls from 30.6% (hop=1) to 17.6% (hop=4) (Cochran-Armitage z=-2.30, p=0.011; OR per hop 0.72, 95% CI [0.56,0.92], p=0.008); GPT-4o replicates this (37.8% to 14.7%; OR 0.58 [0.45,0.75], p

22.
arXiv (CS.CV) 2026-06-16

Trusting Right Predictions for Wrong Reasons: A LIME Based Analysis of Deep Learning Interpretability in Lung Cancer Diagnosis

Lung cancer is the leading cause of cancer-related mortality, with approximately 2.5 million new cases and 1.8 million deaths annually, making reliable diagnosis a clinical priority. Although deep learning models have achieved strong performance in lung cancer classification, evaluation has largely focused on predictive accuracy, leaving their decision-making processes insufficiently examined. This study compares three architecturally distinct models: a Convolutional Neural Network (CNN), a pretrained ResNet50, and a Vision Transformer (ViT), trained on the IQ-OTH/NCCD lung cancer CT dataset. Local Interpretable Model-Agnostic Explanations (LIME) were applied to investigate model reasoning. In addition to standard performance metrics, a dual-correlation framework was introduced to measure both prediction agreement and explanation agreement across model pairs. All three models achieved strong classification performance, with ResNet50 attaining 98.61% accuracy, CNN 97.91%, and ViT 93.75%, while all achieved ROC-AUC scores of 0.99. Prediction correlations exceeded 0.99 across all model pairs, indicating highly consistent outputs. However, LIME explanation correlations remained below 0.26, revealing substantial differences in the image regions used to reach those predictions. Analysis of misclassified samples further identified a consistent spatial pattern: incorrect predictions were associated with attention outside the lung parenchyma, whereas correct predictions focused primarily within lung regions. These findings demonstrate that prediction agreement is a poor proxy for reasoning consistency, and that interpretability evaluation must be treated as an independent validation criterion alongside predictive performance in clinical AI systems.

23.
arXiv (CS.CL) 2026-06-11

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

When a language model processes a hallucinated response, its attention routing tends to fail in one of two shapes: over-concentrating on a narrow set of positions, or spreading so diffusely that relevance is diluted, and the shape of the failure carries diagnostic signal. We study these shapes as a diagnostic characterization, computed from attention matrices under forced scoring of benchmark-labeled responses rather than during live generation. A widely used family of spectral methods analyzes the symmetric component of the degree-normalized attention operator, which governs transport capacity; we prove that every transpose-invariant spectral diagnostic of this operator is structurally orientation-blind (it cannot distinguish an operator from its transpose, and therefore cannot detect information-flow direction), with a converse to the blindness theorem bounding any Lipschitz diagnostic's transpose sensitivity by the asymmetry coefficient $G$. Pairing this with a closed-form bipartite-Cheeger landscape for canonical causal architectures, we show that uniform causal attention satisfies an $n$-independent floor $\phi \ge 1/5$, while window attention pierces the floor as $O(w/n)$; failure modes are shape-different, not just value-different. This floor is an idealized-architecture benchmark, not an empirical attractor: the fraction of real attention heads that pierce it is itself an architectural signature. The resulting two-axis diagnostic ($\phi$ for capacity, $G$ for direction) yields a falsifiable polarity prediction: bottleneck- and diffuse-dominated benchmarks should exhibit opposite polarity. Under length-controlled evaluation, transport features retain interpretable signal (0.62-0.84 LC-AUROC) across the tested decoder-only, encoder-only, and encoder-decoder models, with polarity reversing as predicted between HaluEval and MedHallu.

24.
arXiv (CS.CL) 2026-06-16

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot tell whether they do. Refusal benchmarks for malicious code are fragmented: they mix requests for executable software with requests for harmful security knowledge and report refusal rates over non-comparable corpora. This paper's central result is that the CODE-versus-KNOWLEDGE classification axis established in a prior four-corpus release remains stable under a substantially expanded corpus pool and an independently refreshed judge panel, evidence that it measures a real construct rather than an artifact of the prompts or judges. Eight corpora spanning diverse elicitation paradigms (direct, jailbreak-decorated, indirect, and agent/interpreter: ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2Prompt) are classified under a five-judge consensus protocol (6,675 prompts x 5 judges = 33,375 calls), reaching Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"). Critically, the panel shares no judge with the prior release (five paid commercial APIs replaced by five open-weight models from five vendors), yet the two panels agree on 94.45% of the 3,133 shared prompts and reach Cohen's kappa = 0.952 [0.942, 0.963] on the 3,031-prompt binary overlap: the axis survives near-total panel replacement. The released bank comprises 4,748 consensus-CODE and 1,923 consensus-KNOWLEDGE prompts, a reliability-quantified benchmark whose central classification axis is shown stable across corpus expansion and judge-panel replacement.

25.
arXiv (CS.CL) 2026-06-16

Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning

Automatic text summarization (ATS) is an emerging technology to assist clinicians in providing continuous and coordinated care. This study presents an approach to summarize doctor-patient dialogues using generative large language models (LLMs). We developed prompt-tuning algorithms to instruct generative LLMs to summarize clinical text. We examined the prompt-tuning strategies, the size of soft prompts, and the few-short learning ability of GatorTronGPT, a generative clinical LLM developed using 277 billion clinical and general English words with up to 20 billion parameters. We compared GatorTronGPT with a previous solution based on fine-tuning of a widely used T5 model, using a clinical benchmark dataset MTS-DIALOG. The experimental results show that the GatorTronGPT- 20B model achieved the best performance on all evaluation metrics. The proposed solution has a low computing cost as the LLM parameters are not updated during prompt-tuning. This study demonstrates the efficiency of generative clinical LLMs for clinical ATS through prompt tuning.