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.
arXiv (quant-ph) 2026-06-19

Steady-state entanglement of spin qubits mediated by nonreciprocal and chiral magnons

arXiv:2509.13094v3 Announce Type: replace Abstract: We propose a hybrid quantum system in which a magnet supporting non-reciprocal magnons, chiral magnons, or both mediates the dissipative and unidirectional coupling of spin qubits. By driving the qubits, the steady state of this qubit-qubit coupling scheme becomes the maximally entangled Bell state. We devise a protocol where the system converges to this entangled state and benchmark it including qubit decay and dephasing. The protocol is numerically tested on a hybrid system consisting of nitrogen-vacancy (NV) centers coupled to magnon surface modes of an yttrium iron garnet (YIG) film. We show that the dephasing time of the NV centers forms the bottleneck for achieving the entanglement of NV centers separated by a distance within the magnon coherence length. Our findings identify the key technological requirements and demonstrate a viable route toward steady-state entanglement of solid-state spins over distances of several microns using magnonic quantum networks, expanding the toolbox of magnonics for quantum information purposes.

02.
arXiv (CS.CV) 2026-06-11

CoVEBench: Can Video Editing Models Handle Complex Instructions?

While recent text-guided video editing models excel at elementary tasks (e.g., style transfer, object insertion), real-world user requests are highly compositional. A single prompt often demands multiple coupled edits, such as modifying subjects, actions, and camera views, while strictly preserving unrelated spatiotemporal content. Existing benchmarks, heavily constrained by isolated edits and coarse global metrics, fail to diagnose how models handle such complex workflows. To address this gap, we introduce CoVEBench, a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items. Covering diverse editing dimensions, CoVEBench evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality. Extensive experiments reveal that compositional editing remains a profound challenge: current models frequently omit edits, violate preservation constraints, or introduce artifacts when handling multiple operations simultaneously. CoVEBench provides a challenging, diagnostic testbed to advance video editing toward realistic user workflows.

03.
arXiv (CS.CV) 2026-06-16

Multi-Modal Attention for Automated Disaster Damage Assessment Using Remote Sensing Imagery and Deep Learning

Timely and accurate disaster damage assessment is crucial for effective emergency response, resource allocation, and recovery. Traditional methods, which often rely on manual inspections or sparse data, are typically slow and error-prone. This paper introduces a novel framework leveraging remote sensing imagery and deep learning to automate building damage classification. Using pre- and post-disaster satellite imagery, our model categorizes buildings into four damage levels: no damage, minor damage, major damage, and destroyed. The core innovation is a multi-modal attention mechanism that fuses bi-temporal features to explicitly detect and assess structural changes. We employ a lightweight ConvNeXT-Tiny backbone to ensure efficient processing without compromising performance. Key contributions include: (1) a cross-attention module for multi-modal data fusion, (2) an optimized preprocessing pipeline for large-scale datasets, and (3) robust data augmentation techniques. Experiments on a large-scale disaster dataset demonstrate an overall classification accuracy of 94.90%. The model effectively discriminates between damage categories and remains resilient to incomplete data. This system significantly improves assessment speed and accuracy, aiding emergency responders in prioritizing interventions. This work advances automated disaster damage detection by integrating multi-temporal imagery with deep learning, offering a scalable solution for real-time response.

04.
arXiv (CS.CV) 2026-06-16

SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly decomposed pipelines that entangle many factors at once and demand extensive scene-level supervision, limiting their generalization to complex real-world environments. We propose a multi-agent orchestration framework that decomposes single-image 3D scene generation into three structured stages: scene initialization, environment construction, and multi-agent refinement. The initialization stage extracts image-derived object masks, builds object-level 3D representations, and predicts an initial spatial layout to form a coarse 3D scene. The environment-construction stage then leverages this initialization together with point-map geometry to build an environmental scaffold of supporting surfaces, room boundaries, materials, and illumination. Finally, in the refinement stage, a planner agent identifies structural and visual inconsistencies, applies simple corrections directly, and dispatches specialist agents for complex localized revisions that are reintegrated into the global scene. To provide reliable structural initialization while reducing reliance on scene-level annotations, we further introduce a geometry-aware layout predictor supervised by sparse geometric priors derived from point maps. Unlike fully supervised layout generators, the predictor can be trained from segmentation-level data and generalizes robustly to diverse real-world scenes. Extensive experiments on benchmark datasets show that our method consistently outperforms prior approaches in geometric accuracy, spatial consistency, and perceptual realism.

05.
arXiv (CS.CL) 2026-06-19

REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection

Benchmark infrastructure for personally identifiable information (PII) detection remains limited: existing corpora cover few entity types, use ad hoc generation conditions, and do not show which surface conditions cause detector failures. We present REDACT, a systematically controlled multilingual PII benchmark with 13,427 records, 324,078 entity annotations, 51 entity types, 4,127 surface-form patterns, and 25 languages across 9 scripts. A strength-2 covering-array sampler controls nine generation axes: domain, format, difficulty, length, density, code-switching, language, adjacency, and co-occurrence. Three entity-level metadata fields (disclosure status, disclosure form, and a GDPR-aligned sensitivity tier) enable stratified evaluation beyond aggregate or per-type F1. From the full benchmark, we evaluate five detectors (Presidio, GLiNER, the OpenAI Privacy Filter, GPT-4.1, and Claude Sonnet 4.6) on a locked, language-stratified sample of 1,000 records. Aggregate F1 masks an architecture-dependent failure structure: the rule-based detector performs poorly on the highest-stakes data, including HIGH-sensitivity categories (recall 0.07) and non-verbatim disclosure forms, while the LLM detectors remain more robust, with the HIGH tier as their strongest sensitivity slice. A three-model reference-free LLM-as-judge assessment corroborates that sensitivity-tier assignment is the task's hardest axis. We release the benchmark, schema, prompts, and stratified evaluation harness.

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

When Similar Means Different: Evaluating LLMs on Arabic–Hebrew Cognates

Arabic and Hebrew, as closely related Semitic languages, share a substantial lexicon of true cognates, misleading false friends, and modern loanwords. This overlap poses a challenge for cross-lingual semantic understanding in large language models (LLMs). To evaluate this capability, we introduce SemCog Bench, a curated benchmark of 1,858 Arabic–Hebrew word pairs with sentence-level annotations for cognate identification and semantic disambiguation. We evaluate open-source and commercial LLMs across multiple input representations (raw, diacritized, Romanized, and phonetic) and reveal a critical gap in cross-lingual reasoning. While models achieve high accuracy on true cognates, performance drops sharply on false friends and loanwords, reflecting a strong reliance on surface-form similarity. Furthermore, sentence-level context yields only modest improvements, suggesting that contextual cues alone are insufficient to overcome misleading form-based signals. These findings reveal a fundamental limitation of current LLMs in resolving cross-lingual form–meaning conflicts and establish SemCog Bench as a rigorous benchmark for multilingual semantic reasoning. Our code and data are publicly available.

07.
arXiv (CS.LG) 2026-06-15

FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

arXiv:2505.16319v4 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobserved demand creates systemic policy biases. Existing datasets lack the temporal resolution and annotations needed to address this censoring effect. To fill this gap, we present FreshRetailNet-50K, the first large-scale benchmark for censored demand estimation. It comprises 50,000 store-product time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 863 perishable SKUs meticulously annotated for stockout events. The hourly stock status records unique to this dataset, combined with rich contextual covariates, including promotional discounts, precipitation, and temporal features, enable innovative research beyond existing solutions. We demonstrate one such use case of two-stage demand modeling: first, we reconstruct the latent demand during stockouts using precise hourly annotations. We then leverage the recovered demand to train robust demand forecasting models in the second stage. Experimental results show that this approach achieves a 2.73% improvement in prediction accuracy while reducing the systematic demand underestimation from 7.37% to near-zero bias. With unprecedented temporal granularity and comprehensive real-world information, FreshRetailNet-50K opens new research directions in demand imputation, perishable inventory optimization, and causal retail analytics. The unique annotation quality and scale of the dataset address long-standing limitations in retail AI, providing immediate solutions and a platform for future methodological innovation. The data (https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K) and code (https://github.com/Dingdong-Inc/frn-50k-baseline}) are openly released.

08.
arXiv (CS.CL) 2026-06-12

Reasoning Models Know What's Important, and Encode It in Their Activations

Language models often solve complex tasks by generating long reasoning chains, consisting of many steps with varying importance. While some steps are crucial for generating the final answer, others are removable. Determining which steps matter most, and why, remains an open question central to understanding how models process reasoning. We investigate if this question is best approached through model internals or through tokens of the reasoning chain itself. We find that model activations contain more information than tokens for identifying important reasoning steps. Crucially, by training probes on model activations to predict importance, we show that models encode an internal representation of step importance, even prior to the generation of subsequent steps. The internal representations of importance in different models yield high agreement on which steps are important. The representation is distributed across layers, and does not correlate with surface-level features, such as a step's relative position or its length. Our findings suggest that analyzing activations can reveal aspects of reasoning that surface-level approaches fundamentally miss, indicating that reasoning analyses should look into model internals.

09.
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.

10.
arXiv (CS.LG) 2026-06-16

On the Role of Computation in Reinforcement Learning

arXiv:2602.05999v3 Announce Type: replace Abstract: How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a language to answer these questions formally. Empirically, deep RL policies are often parameterized as neural networks with static architectures, conflating the amount of compute and the number of parameters. In this paper, we formalize compute bounded policies and prove that policies which use more compute can solve problems and generalize to longer-horizon tasks that are outside the scope of policies with less compute. Building on prior work in algorithmic learning and model-free planning, we propose a minimal architecture that can use a variable amount of compute. Our experiments complement our theory. On a set 31 different tasks spanning online and offline RL, we show that $(1)$ this architecture achieves stronger performance simply by using more compute, and $(2)$ stronger generalization on longer-horizon test tasks compared to standard feedforward networks or deep residual network using up to 5 times more parameters.

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

Semantic Reasoning in Medicine: The Role of Knowledge Graphs Across Five Key Domains

arXiv:2606.15155v1 Announce Type: new Abstract: Knowledge graphs (KGs) have emerged as a promising solution for integrating and reasoning over complex biomedical and clinical data in healthcare. By representing structured relationships among entities such as diseases, drugs, symptoms, and patient records, KGs provide a semantic backbone for decision-making, prediction, recommendation, and personalized care. Recent advances have demonstrated their utility across diverse medical applications–including clinical decision support systems, disease and treatment outcome prediction, health recommender systems, precision medicine, and medical question answering–where KGs often enhance interpretability, semantic coherence, and patient-specific reasoning. In parallel, a growing body of work focuses on medical KG generation itself, proposing frameworks that construct graphs from EHRs, clinical narratives, biomedical literature, and web resources using ontologies, semantic web technologies, deep-learning-based information extraction, and hybrid neuro-symbolic pipelines. Despite this progress, significant challenges remain, including limited and fragmented knowledge coverage, difficulties in aligning heterogeneous data sources, the fragility of current reasoning and representation-learning methods on dense multi-relational graphs, and unresolved issues related to privacy, bias, and accountability. This survey reviews and categorizes current research on KGs in medicine along both application-oriented and methodology-oriented dimensions, discusses their benefits and technical foundations, and outlines key limitations and open research directions. By analyzing trends, architectures, and evaluation practices, this work aims to guide future developments in KG-driven medical AI systems and support their safe and effective integration into healthcare environments.

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

Ranking Abuse via Strategic Pairwise Data Perturbations

arXiv:2604.17805v2 Announce Type: replace-cross Abstract: Pairwise ranking systems based on Maximum Likelihood Estimation (MLE), such as the Bradley-Terry model, are widely used to aggregate preferences from pairwise comparisons. However, their robustness under strategic data manipulation remains insufficiently understood. In this paper, we study the vulnerability of MLE-based ranking systems to adversarial perturbations. We formulate the manipulation task as a constrained combinatorial optimization problem and propose an Adaptive Subset Selection Attack (ASSA) to efficiently identify high-impact perturbations. Experimental results on both synthetic data and real-world election datasets show that MLE-based rankings exhibit a sharp phase-transition behavior: beyond a small perturbation budget, a limited number of strategic voters can significantly alter the global ranking. In particular, our method consistently outperforms random and greedy baselines under constrained budgets. These findings reveal a fundamental sensitivity of MLE-based ranking mechanisms to structured perturbations and highlight the need for more robust aggregation methods in collective decision-making systems.

13.
arXiv (CS.LG) 2026-06-19

SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with Application to GPU Data

arXiv:2606.20451v1 Announce Type: cross Abstract: Competing risks are commonly observed in engineering fields and can bring challenges to time-to-event data modeling when the application scenarios are complicated. Recently, deep neural networks have received great attention for prediction with competing risks, due to their flexibility and high learning capability. However, the complexity of neural network structure brings extra difficulty in hyperparameter tuning based on different data inputs. Additionally, when an engineered system has complex physical structures with multiple hierarchical levels, treating all structural levels as a single group of inputs may fail to capture critical information. To address the issues, we propose a Structured Segmented Hazard Deep Neural Network (SSH-Net) for failure time prediction under cause-specific competing risks framework. Our approach associates neural network structure with data structures, and allows different covariate groups to impact the failure prediction through separate sub-networks. The neural network is constructed based on a cause-specific competing risks model. The SSH-Net outputs cause-specific hazard functions, and utilizes the penalized log-likelihood as the loss function. The prediction accuracy of SSH-Net is validated through simulation studies by evaluating the Brier score, the area under receiver operating characteristic curves (AUC), and the root mean square error (RMSE) of the predicted cause-specific cumulative incident function. We further demonstrate the model's ability to predict failure time distribution functions using the Titan GPU failure time data.

14.
arXiv (CS.CL) 2026-06-11

Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?

Large language models (LLMs) in medicine are mainly evaluated using multiple-choice question answering (MCQA), which can overestimate real clinical ability due to guessing strategies and answer biases. To address these limitations, we introduce an expanded and more challenging benchmark based on Polish medical exams, adding over 15,000 questions, two new domains, and four structural modifications that reduce MCQA-specific artifacts and better test reasoning. We evaluate 21 LLMs and show that evaluation design strongly affects results. Under our harder setup, the best model (Qwen3.5-122B) drops by 28.4 and 31 pp on English and Polish exams, respectively. Despite low evidence of data contamination, standard MCQA scores do not reliably reflect true medical competence. To facilitate further research, we make our benchmark publicly available.

15.
PLOS Computational Biology 2026-05-29

A prototype-augmented graph representation learning framework for identifying brain disorder-associated genes and facilitating drug repurposing

作者:

by Jiafang Li, Yifei Li, Siying Lin, Jiahua Rao, Huiying Zhao Many genetic loci were identified as associated with neuropsychiatric disorders and neurodegenerative disorders by Genome-wide association studies (GWAS). How these loci impact these diseases is unclear. Advances in deep-learning approaches and multi-omics data have the potential to link GWAS findings with disease mechanisms. Here, we proposed the Multi-omics Graph Transformer Network (MOGT), a semi-supervised graph neural network that leverages graph representation learning to model biological networks derived from multi-omics data to predict disease-associated genes. MOGT outperforms the current approaches in disease gene prediction for two psychiatric disorders and three neurodegenerative/neurological diseases. High-risk genes (HRGs) for Parkinson’s disease (PD) predicted by MOGT were used to drug discovery by integrating with the CMAP database. Finally, 10 drugs were identified as potential candidates. Among them, the effect of drug UK-356618 was experimentally verified in a primary neuron model, showing that UK-356618 reversed the abnormal expression of PD-associated genes and improved the cell-level phenotypes of PD. Together, these results indicate that MOGT can be used to identify HRGs for brain disorders, and these predicted HRGs provide high-level insights into the mechanisms and treatments of brain disorders.

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

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

arXiv:2606.11357v1 Announce Type: cross Abstract: With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. However, practical LLM deployment on current client NPUs remains difficult: widely used quantization formats such as AWQ do not map cleanly onto many existing NPU software stacks, which are often proprietary and expose limited low-level control. In this work, we present TileFuse, a close-to-metal mixed-precision kernel library for AMD XDNA2 NPUs that targets transformer linear layers in quantized LLM inference. TileFuse brings practical low-bit formats such as AWQ-style W4A16 and W8A16 directly onto XDNA2, rather than forcing the model to be reshaped around an NPU-specific quantization scheme. TileFuse co-designs weight layout, metadata placement, mixed-precision microkernels, and array-level dataflow. Specifically, it fuses unpacking, dequantization, and GEMM/GEMV execution into a single kernel flow, introduces an interleaved pre-tiling layout that supports GEMM dimensions up to 32K, and redesigns GEMV dataflow to utilize the full 4x8 AIE array. Across kernel-level evaluations, TileFuse improves performance by up to 121.6% for GEMM and 281% for GEMV over full-precision baselines, while delivering more than 2x performance and energy-efficiency gains over strong iGPU baselines on GEMM. In end-to-end LLM experiments on Ryzen AI laptops, TileFuse achieves up to 2.0x lower prefilling latency with more than 64.6% lower energy consumption. Together, these results show that XDNA2 is a practical target for AWQ-style edge LLM inference and that native NPU support for off-the-shelf quantization can make NPUs substantially more usable in real client deployments.

17.
arXiv (CS.CL) 2026-06-16

Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale

Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned transformers and LLM-as-a-judge pipelines. These approaches impose significant per-query latency and infrastructure cost. Very little research has asked whether CPU-based classifiers, such as support vector machines and gradient-boosted trees trained on TF-IDF features, can match their accuracy across the conditions that production deployments encounter. We evaluate five CPU classifier families, Mamba-130M as an SSM-based GPU classifier, and transformer-based GPU models (DeBERTa-v3 and Gemma-2B with LoRA) across nine jailbreak sources and three regimes: in-distribution (D1), out-of-distribution (D2), and adversarially obfuscated (D3). On D1, the best CPU classifier matches the best transformer GPU model at roughly one-fifth the deployment cost. On D2, CPU classifiers fail via confident miscalibration, producing high-confidence false negatives that bypass escalation entirely. On D3, CPU classifiers outperform transformer GPU models by more than 26 percentage points in F1. Based on these complementary failure modes, we design GuardChain, a three-stage safety pipeline (Regex -> CPU -> GPU) that routes each prompt to the cheapest stage capable of a confident decision. The CPU stage alone resolves 80\% of in-distribution prompts at near-peak accuracy, and the GPU stage recovers the out-of-distribution failures. For practitioners deploying LLM safety at scale, this work provides evidence that GPU-class infrastructure is unnecessary for the majority of traffic.

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

Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation

Speech-to-speech translation (S2ST) systems have achieved impressive progress in semantic accuracy and speech naturalness. However, the cross-lingual transfer of lexical stress, a vital cue for emphasis and speaker intent, remains heavily underexplored, compounded by a lack of reliable automatic evaluation metrics for tonal languages like Chinese. We investigate English-to-Chinese S2ST stress transfer by constructing a stress-annotated Chinese dataset and an XLS-R-based Mandarin stress detector. Integrating this with the English EmphAssess system, we propose a novel objective metric for cross-lingual stress evaluation. Furthermore, we fine-tune CosyVoice3 to build a stress-aware S2ST system. Experiments demonstrate that our proposed S2ST architecture significantly outperforms existing systems in stress translation capability while maintaining competitive translation quality. Furthermore, our evaluation metric exhibits a strong correlation with human subjective judgments.

19.
arXiv (CS.AI) 2026-06-17

SEAGym: An Evaluation Environment for Self-Evolving LLM Agents

arXiv:2606.17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop. Existing evaluations often reduce this process to isolated task scores or a single sequential curve, obscuring whether an update produces reusable improvement, overfits recent tasks, increases cost, or harms older behavior. We introduce SEAGym, an evaluation environment for measuring agent harness updates across training, validation, test, replay, and cost records. SEAGym turns Harbor-compatible benchmarks into dynamic self-evolution task sources with train batches, frozen update-validation, held-out ID and OOD transfer views, replay diagnostics, and saved snapshot and metric records. Instantiating SEAGym on Terminal-Bench 2.0 and HLE, we compare ACE, TF-GRPO, and AHE under a shared epoch/batch protocol. The results show that these evaluation views provide complementary signals about the evolution process: frequent updates may fail to improve held-out performance, useful intermediate snapshots may collapse later, and source diversity and model backend can affect harness reliability.

20.
arXiv (CS.LG) 2026-06-16

Model Stealing Through the Lens of Model Multiplicity

arXiv:2606.15493v1 Announce Type: new Abstract: Model stealing attacks, where adversaries create high-fidelity surrogate models, are a significant threat to the intellectual property of machine learning services. Conventional wisdom suggests these surrogates could provide adversaries with economic leverage comparable to the original service providers. This paper challenges this assumption by evaluating model stealing attacks beyond mere fidelity to the target model. Because query-based extraction provides only partial supervision of the target's input-output behavior, the surrogate is not uniquely identified: many near-optimal surrogates can achieve comparable fidelity while differing in deployment-relevant properties. Instead of performing a classic learning-based model stealing attack, we compute the Rashomon Set (i.e., the set of almost-equally-accurate models) of surrogate models, and evaluate its diversity using multiplicity metrics (ambiguity, discrepancy, and Rashomon Capacity) and group fairness metrics. Across tabular, medical imaging, and NLP tasks, our experiments on real-world datasets reveal that despite exhibiting similar fidelity to the target model, surrogate models can display significant variances in other critical performance metrics. These findings cast doubt on the presumed equivalence between high-fidelity surrogates and the target model in practical deployment scenarios.

21.
arXiv (CS.CL) 2026-06-15

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19–0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise–pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% ($\kappa = 0.51$), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

22.
arXiv (CS.AI) 2026-06-12

Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage

arXiv:2606.12767v1 Announce Type: new Abstract: Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system is expected to use. We study how TMK-based question generation strategies affect dataset quality for procedural and multi-hop reasoning. We compare three strategies: strict generation from Task-Method-Knowledge (TMK) models, transcript-first generation with post-hoc TMK filtering, and TMK-aware generation that combines transcripts with structured guidance. To evaluate generated items, we introduce a grounding validation framework based on closed-set evidence units extracted from TMK models. The framework measures whether answers are supported by the underlying representation, whether questions are self-contained, and whether they target multi-hop procedural reasoning. Across 23 instructional topics and 690 generated question-answer pairs, strict TMK generation achieves the strongest overall quality, with 96.5% grounded questions and 92.6% usable questions. Transcript-first generation produces more learner-like questions but more context-dependent or weakly grounded items, while TMK-aware generation yields high raw multi-hop coverage but lower grounding. These results show that procedural richness and natural phrasing do not guarantee representational grounding, motivating explicit representation-aware validation for evaluation datasets in AI-supported learning.

23.
arXiv (CS.LG) 2026-06-16

Quantization Robustness of Monotone Operator Equilibrium Networks

arXiv:2603.10562v2 Announce Type: replace-cross Abstract: Monotone operator equilibrium networks are implicit-layer models whose output is the unique equilibrium of a monotone operator, guaranteeing existence, uniqueness, and convergence. When deployed on low-precision hardware, weights are quantized, potentially destroying these guarantees. We analyze weight quantization as a spectral perturbation of the underlying monotone inclusion. Convergence of the quantized solver is guaranteed whenever the spectral-norm weight perturbation is smaller than the monotonicity margin; the displacement between quantized and full-precision equilibria is bounded in terms of the perturbation size and margin; and a condition number characterizing the ratio of the operator norm to the margin links quantization precision to forward error. MNIST experiments confirm a phase transition at the predicted threshold: three- and four-bit post-training quantization diverge, while five-bit and above converge. The backward-pass guarantee enables quantization-aware training, which recovers provable convergence at four bits.

24.
arXiv (CS.LG) 2026-06-17

Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates

arXiv:2606.17529v1 Announce Type: cross Abstract: Scientific machine-learning (SciML) surrogates approximate expensive simulations, but exact expected outputs for arbitrary inputs are unavailable (the oracle problem). Metamorphic testing checks relations across executions, yet a candidate relation is not automatically valid: its preconditions, output mapping, and the numerical floor of the scoring operator determine whether a violation is meaningful. We study how candidate metamorphic relations (MRs) can be screened for domain validity and turned into executable, oracle-free test assets for SciML surrogates. We propose (i) a domain-validity rubric that admits a candidate only when its tolerance dominates the operator's numerical floor and its preconditions hold; (ii) an MR-card executable-asset format recording source cases, transformations, metrics, tolerances, and typed relation-level verdicts; and (iii) a case-study protocol on MeshGraphNets cylinder-flow surrogates, with a claim ledger binding every result to a tracked artifact. On a MeshGraphNets checkpoint, node permutation holds to machine precision, mirror-y is a bounded out-of-distribution stress finding rather than an exact symmetry, and absolute conservation stays deferred while a reference-relative guard passes. The same readings hold across held-out trajectories, a checkpoint roster, three further architectures, and PhysicsNeMo. On a second CFD task (compressible airfoil) the predicate instead rejects incompressible continuity on physical grounds, showing it reasons about domain validity rather than running a fixed checklist. On a second PDE family, FNO Burgers and heat surrogates run full admit/reject/execute verdicts. The evidence spans two CFD tasks and a second PDE family, supporting a validity-aware bridge from candidate MRs to auditable SciML test assets that separates model-level violations from out-of-domain applications.

25.
arXiv (quant-ph) 2026-06-12

Geometric Algebra Quantum Gate Decomposition

arXiv:2606.12480v1 Announce Type: new Abstract: Quantum gates are usually described through matrix and tensor-product formalisms that often obscure their geometric structure. In this work, we formulate the Pauli and Clifford groups within the complex Geometric Algebra (GA) framework. We show that the Pauli group is naturally identified with the group of blades up to a global phase, thereby providing a geometric interpretation of Pauli operators and their commutation relations in terms of oriented subspaces. We further prove that Clifford operators are generated by products of {\pi}/4-Pauli rotors and introduce a greedy Pauli rotor decomposition algorithm whose empirical behavior suggests unexpectedly compact decompositions for Clifford operators. Finally, we show that Clifford+T universality admits a natural geometric interpretation through {\pi}/8-rotors within this framework.