探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11786

Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay

作者:

Joanito Agili Lopo↗Yunita Sari↗Guntur Budi Herwanto↗

Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation, we propose an approach for fine-tuning LLMs on a low-resource language, Kupang Malay. Our approach involves designing a set of instructions by leveraging explicit lexical and semantic features from a bilingual dictionary, and introducing Continual Instruction Tuning (CIT), a training paradigm that enables iterative instruction-based training. Experimental results demonstrate that our model, named Lius, yields notable improvements over standard instruction-tuned models by outperforming 4-6 points, and surpassing both Neural Machine Translation (NMT) and Multilingual LLM models by 10-13 points on several evaluation metrics. These findings highlight the potential of our approach to mitigate the reliance on large-scale parallel data in low-resource language translation.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2512.20043

Discovering Symmetry Groups with Flow Matching

作者:

Yuxuan Chen↗Jung Yeon Park↗Floor Eijkelboom↗Jianke Yang↗Jan-Willem van de Meent↗Lawson L. S. Wong↗Robin Walters↗

arXiv:2512.20043v3 Announce Type: replace Abstract: Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data, yet discovering these symmetries automatically is challenging. We propose LieFlow, a novel framework that reframes symmetry discovery as a distribution learning problem on Lie groups. Instead of searching for the symmetry generators, our approach operates directly in group space, modeling a symmetry distribution over a large hypothesis group $G$. The support of the learned distribution reveals the underlying symmetry group $H \subseteq G$. Unlike previous works, LieFlow can discover both continuous and discrete symmetries within a unified framework, without assuming a fixed Lie algebra basis or a specific distribution over the group elements. Experiments on synthetic 2D and 3D point clouds, ModelNet10 and a real-world MI-Motion dataset show that LieFlow accurately discovers continuous and discrete subgroups, significantly outperforming a state-of-the-art baseline, LieGAN, in identifying discrete symmetries.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2512.11982

Semantic search for 100M+ galaxy images using AI-generated captions

作者:

Nolan Koblischke↗Liam Parker↗Francois Lanusse↗Jo Bovy↗Irina Espejo↗Shirley Ho↗

Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes. In this work, we develop a pipeline to create a semantic search engine from completely unlabeled image data. Our method leverages Vision-Language Models (VLMs) to generate descriptions for galaxy images, then contrastively aligns a pre-trained astronomy foundation model with these embedded descriptions to produce searchable embeddings at scale. We find that current VLMs provide descriptions that are sufficiently informative to train a semantic search model that outperforms direct image similarity search. Our model, AION-Search, achieves state-of-the-art zero-shot performance on finding rare phenomena despite training on randomly selected images with no deliberate curation for rare cases. Furthermore, we introduce a VLM-based re-ranking method that nearly doubles the recall for our most challenging targets in the top-100 results. For the first time, AION-Search enables flexible semantic search for over 100 million galaxy images, enabling discovery from previously infeasible searches, including the identification of 36 new extragalactic stellar stream candidates. More broadly, our work provides an approach for making large, unlabeled scientific image archives semantically searchable, expanding data exploration capabilities in fields from Earth observation to microscopy. The code, data, and app are publicly available at https://github.com/NolanKoblischke/AION-Search

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2505.00571

Discovery and inference beyond linearity for epidemiological data by integrating Bayesian regression, tree ensembles and Shapley values

作者:

Giorgio Spadaccini↗Marjolein Fokkema↗Mark A. van de Wiel↗

arXiv:2505.00571v3 Announce Type: replace-cross Abstract: Machine Learning (ML) is gaining popularity in epidemiology and healthcare studies for hypothesis-free discovery of risk and protective factors. ML is strong at discovering nonlinearities and interactions, but this power is compromised by a lack of reliable inference. Although Shapley values provide local measures of features' effects, valid uncertainty quantification for these effects is typically lacking, thus precluding statistical inference. We propose RuleSHAP, a framework that addresses this limitation by combining a dedicated Bayesian sparse regression model with an improved tree-based rule generator and Shapley value attribution. RuleSHAP provides detection of nonlinear and interaction effects, with uncertainty quantification at the individual level as a key contribution. We derive an efficient formula for computing marginal Shapley values within this framework. We apply RuleSHAP to data from an epidemiological cohort to detect and infer several effects for high cholesterol and blood pressure, such as nonlinear interaction effects between features like age, sex, ethnicity, BMI and glucose level. To conclude, we demonstrate the validity of our framework on simulated data.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19386

Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence

作者:

Manvendra Modgil↗

arXiv:2606.19386v1 Announce Type: cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench debugging agents (Modgil 2026). A post-release audit found the engine received dt=0 between actions, so its exponential decay never operated: the published trap is a pure-accumulator result. We correct the record (erratum, v2) and treat the flaw as an experiment. The key variable it exposes is whether a monitor's dynamics are calibrated in sample time (per observation, as in CUSUM) or wall-clock time (half-lives in seconds, as in affect models and EMA baselines). On fixed-rate streams these coincide; on agent streams, where inter-action time varies by orders of magnitude, they do not. A pre-registered sweep over uniform intervals (dt in {0..600}s) on 20 trajectories shows the wall-clock level trigger has two regimes: at dt=60s silent. Every critical dt lies in (1,30]s. Real agent runs measure latency at median 1.53s (p90 2.33s); real coding cadence sits inside the trap regime, vindicating the empirical finding under a corrected mechanism. The structure is a property of the calibration class, not the engine: a minimal wall-clock accumulator over the raw error stream reproduces the same cliff, while a sample-time CUSUM over the identical stream is exactly dt-invariant (20/20). A rising-edge trigger with hysteresis fires 0-3 times per trajectory in every condition. We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams; transition detection escapes the trap at every cadence, but does not recover human intervention timing.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12917

Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function

作者:

Atharva Gupta↗Dhruv Kumar↗Murari Mandal↗Saurabh Deshpande↗

arXiv:2606.12917v1 Announce Type: new Abstract: We present the first causal mechanistic analysis of a tabular foundation model, investigating how TabPFN 2.5's feature wise attention heads distribute computation across layers. Using activation patching, ablation, and attention entropy across two synthetic regression datasets, we find clear temporal specialisation: one head's causal necessity dominates that of the others by 2 to 5 times at peak layer, with its dominant layer shifting across tasks of different complexity, while the remaining heads exhibit symmetric late layer profiles. Attention entropy and patching provide convergent evidence for the computationally active layers of the dominant head. We additionally investigate inference time steerability via contrastive activation steering, which fails to transfer across samples. We attribute this result to TabPFN's in context learning mechanism, which encodes task structure through context dependent attention rather than the stable parametric directions that make steering tractable in language models.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17092

Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

作者:

Kyle Gao↗Pranavi Kotta↗Linlin Xu↗Jonathan Li↗David A. Clausi↗

Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.

阅读与讨论 → 访问原文 →

08.

arXiv (math.PR) 2026-06-12 DOI: arXiv:2606.07516

Counterintuitive problems in discrete probability

作者:

Luca Avena↗Gianmarco Bet↗Bernardo Busoni↗

arXiv:2606.07516v2 Announce Type: replace Abstract: This manuscript contains a collection of counterintuitive problems in discrete probability, together with detailed solutions. The dataset was constructed as part of a broader research project investigating the capabilities of the latest-generation Large Language Models (LLMs) in solving discrete probability problems, in order to assess whether LLMs tend to make systematic reasoning errors associated with known cognitive biases. The problems collected here are specifically designed to challenge heuristic reasoning strategies that often lead to intuitively appealing but mathematically incorrect conclusions. The dataset combines several types of problems. Some are adapted from classical probabilistic paradoxes and cognitive-bias literature, while others originate from recreational mathematics sources or were developed by ourselves following similar principles. The primary purpose of this document is to provide a transparent and publicly accessible reference for the problems used in our experimental evaluation of language models, as well as providing detailed human-made solutions. At the same time, we believe that this collection may also prove useful for future research on probabilistic reasoning, cognitive biases, and the evaluation of reasoning capabilities in artificial intelligence systems.

阅读与讨论 → 访问原文 →

09.

medRxiv (Medicine) 2026-06-15 DOI: HASH:0efee22e896d007187f998cdafed6089

Socioeconomic inequalities in smoking prevalence and intensity in Germany: A repeated cross-sectional analysis from 1998 to 2024

作者:

Emmert-Fees↗K. M. F↗Meyer↗Laxy↗Hanselmann↗

Background: Smoking inequalities by socioeconomic status have widened consistently in Germany, but sex-specific trends after 2013 and inequalities in daily cigarette consumption among smokers (intensity) are unknown. We analyzed trends in absolute and relative socioeconomic inequalities in smoking prevalence and intensity among German adults across three decades. Methods: We used 14 waves (1998-2024) of population-representative cross-sectional data from the German Socio-Economic Panel to estimate sex-specific trends in smoking prevalence and intensity in adults aged 25-64. Inequalities were quantified across strata of education, occupation, and equivalized household income using the absolute and relative concentration index with 95% bootstrap confidence intervals. Results: Overall smoking prevalence declined from 35.05% (CI: [33.90%, 36.20%] in 1998 to 22.19% (CI: [21.15%, 23.24%]) in 2024, and mean intensity from 17.49 (CI: [17.09,17.90]) to 13.33 (CI: [12.88, 13.79]) cigarettes/day. Over this period sex-differences in both outcomes narrowed almost completely. Absolute and relative inequalities in smoking prevalence widened across all SES dimensions, particularly for education and occupation. By 2024, inequalities were larger among women than men driven by a stagnating or rising smoking prevalence among low-SES women at least until 2018 alongside continued declines in higher-SES women and for men. Inequalities in smoking intensity, particularly related to income, were generally smaller than those in prevalence. Conclusion: Socioeconomic smoking inequalities in Germany widened from 1998 to 2024 primarily driven by reductions among higher-SES groups and increases in low-SES women. However, recent reductions in low-SES women may indicate a new phase in the smoking epidemic. Health equity considerations should be integrated into a targeted German tobacco control strategy.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2508.04888

Retrieval-Augmented Foundation Models for Water Level Prediction in the Everglades

作者:

Rahuul Rangaraj↗Jimeng Shi↗Rajendra Paudel↗Giri Narasimhan↗Yanzhao Wu↗

arXiv:2508.04888v2 Announce Type: replace Abstract: Accurate water level forecasting in the Everglades is essential for flood mitigation, drought management, water resource planning, and biodiversity conservation. While recent time-series foundation models have shown strong performance on generic tasks (represented in their pre-training), their effectiveness in domain-specific applications remains insufficiently understood. In this work, we curate a domain-specific dataset for water-level forecasting in the Everglades and observe that the performance of current state-of-the-art models remains limited. To address this gap, we leverage a retrieval-augmented mechanism that retrieves analogous multivariate hydrological episodes from an external archive of historical observations to enrich the input context of those pre-trained models. We study two retrieval strategies, statistical similarity-based retrieval and mutual information-based retrieval, and analyze how incorporating retrieved historical contexts affects predictive performance. Extensive experiments show that retrieval augmentation consistently improves long-horizon water level forecasts and yields disproportionately larger gains during extreme events, which is particularly critical for environmental decision-making. Our study provides empirical evidence that analog-based retrieval can benefit pretrained time-series foundation models in environmental science, offering practical insights into their strengths, limitations, and failure modes when applied to hydrological forecasting in the Everglades. Although evaluated in the Everglades, the proposed framework is general and can be applied to other hydrological systems given time series data. The code and data have been made publicly available at https://github.com/rahuul2992000/WaterRAF.

阅读与讨论 → 访问原文 →

11.

bioRxiv (Bioinfo) 2026-06-12 DOI: HASH:9535bd6fe6e1cfc9ccdb8eb9823119e1

ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts

作者:

Ku↗Kim↗Park↗Seok↗

Proteins are inherently dynamic, with biological functions often emerging from transitions between multiple conformational states. While recent breakthroughs have largely addressed the static structure prediction problem, no systematic benchmark exists to demonstrate how well current models capture functionally relevant dynamics. We introduce ProMiSE, the first benchmark that provides both a dataset and an evaluation scheme, based on native biological assemblies and integrating major conformational change mechanisms - intrinsic, ligand-induced, and protein-induced - within a single curated dataset. We conducted a comprehensive evaluation of state-of-the-art structure prediction models, including AlphaFold3 and recent generative approaches. Our findings reveal that current models exhibit a limited ability to sample intrinsic multi-states and are often insensitive to biological context in induced scenarios. Internal representation analysis suggests that training-data exposure can shift predictions toward dominant conformational states over alternative biologically relevant states, primarily at the structure module. In contrast, results from BioEmu indicate that reducing decoding-stage bias can substantially improve multi-state sampling without major changes to upstream pair representations.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19787

ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?

作者:

Jiajun Li↗Mingshu Cai↗Yixuan Li↗Yu Ding↗Ran Hou↗Guanyu Nie↗Xiongwei Han↗Wanyuan Wang↗

arXiv:2606.19787v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear. Existing OR evaluations often decouple modeling from solving, rely on pre-formalized or text-only instances, and rarely test the full workflow from operational artifacts to validated decisions. In this work, we introduce ORAgentBench, an execution-grounded benchmark for evaluating autonomous agents on challenging end-to-end operations research tasks. It contains 107 human-reviewed tasks across diverse operational scenarios, each packaged in an isolated environment with a natural-language brief, multi-file data, configuration artifacts, and a required submission schema. Agents must write and run solution code, and their submissions are evaluated by hidden validators for schema validity, hard-constraint feasibility, and normalized objective quality. Experiments with fourteen frontier agent-model configurations show that current agents remain far from reliable OR practice. The best agent passes only 35.51% of all tasks and 20.59% of hard tasks, and many feasible submissions still fall below the required quality threshold. Failure analysis further shows that errors are dominated by strategic weaknesses, including missed operational rules, brittle formulations, weak feasible-solution construction, and insufficient solution improvement. OR-specific procedural skills increase hard-task feasibility, but do not reliably improve solution quality or pass rate. These results suggest that progress in OR agents requires moving beyond plausible optimization code toward dependable, high-quality operational decision-making.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16794

LLM-Based Visual Explanation Evaluation Framework for Assessing the Explainability of Facial Skin Disease Classification Models

作者:

Gyuyeon Na↗

This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing Grad-CAM explanations in facial skin disease diagnosis models. While previous studies have primarily focused on improving classification performance through data augmentation techniques, relatively few studies have systematically examined whether model explanations are grounded in clinically relevant lesion regions. In this study, geometric augmentation, color-based augmentation, and mixed augmentation strategies were applied to facial skin disease classification models based on EfficientNet-B0, MobileNetV3, and ResNet18. Grad-CAM was employed to generate visual explanations representing the models' decision-making processes. Furthermore, an LLM-as-a-Judge evaluation framework was designed using GPT-5.5, Gemini 3.5 Flash, and Claude Sonnet 4.6 to assess Grad-CAM explanations from the perspectives of lesion localization and explanation trustworthiness. To improve evaluation consistency and clinical grounding, a progressive prompt engineering strategy was introduced, incorporating evaluation rubrics, clinical knowledge, penalty rules, and structured output formats.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17553

SpatioTemporal Causal Network Diagnostics for Geographic Tipping Point Early Warning

作者:

Zhaoyuan Yu↗Zhangyong Liang↗

arXiv:2606.17553v1 Announce Type: new Abstract: Geographic tipping points in ecosystems, climate subsystems, or ice sheets pose severe challenges for localized early warning. Classical spatial indicators such as Moran's I summarize global spatial structure, but they struggle with three issues: spatial dilution, Euclidean assumptions, and correlated noise. This paper introduces SpatioTemporal Causal Network Diagnostics (ST-CND), a framework that addresses these three issues by representing the geographic field as a time-evolving directed causal network. The core workflow is as follows: (1) infer which spatial nodes help predict other nodes via transfer entropy, replacing fixed Euclidean neighborhoods with data-driven information-flow topology; (2) estimate local recovery rates within each candidate subnetwork via dynamic mode decomposition; and (3) identify the most vulnerable subnetwork by combining three signals, namely high internal fluctuation, high internal synchronization, and low external coupling, thereby suppressing false alarms from spatially correlated noise. Validated on synthetic bifurcations and two observational sea-surface temperature benchmarks, namely Indo-Pacific SST and North Atlantic AMOC, ST-CND delivers localized and interpretable warnings. On the AMOC task, it achieves an AUROC of 0.783 and a critical-subnetwork IoU of 0.378, outperforming recurrence-network and lambda-AR1 baselines. The framework provides an interpretable and scalable pipeline for spatial early warning in Earth system science.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16923

MA-SBI: Misspecification-Aware Simulation-Based Inference via Side-Channel Guidance

作者:

Arunkumar V↗Manoranjan Gandhudi↗Gangadharan G. R↗Arun Prakash↗S. Senthilkumar↗

arXiv:2606.16923v1 Announce Type: new Abstract: Simulation-based inference (SBI) of latent parameters is often hindered by simulator misspecification, the mismatch between simulated and real-world observations caused by inherent modeling simplifications. RoPE, the recent state-of-the-art for robust SBI, addresses this through optimal transport between learned representations of real and simulated observations, but requires ground-truth parameter calibration pairs that are typically unavailable in the very settings where SBI is needed. What practitioners do have is unstructured side-information such as regime labels, instruction text, and policy bulletins. We propose Misspecification-Aware Simulation-Based Inference (MA-SBI), a calibration-free framework that turns this side-channel into a posterior correction. A learned corrector maps side-channel text to an observation-space shift applied before any pre-trained amortized posterior, requiring no retraining and no parameter ground-truth. Our main theorem bounds achievable bias reduction by the mutual information between misspecification and side-channel, with a non-vacuous constant that extends to all sub-Gaussian noise via Donsker-Varadhan. On hide-the-calibration benchmarks, MA-SBI with text alone matches the oracle posterior across 10 seeds and two backbones (TOST equivalence), while RoPE given more data does not. The two approaches are complementary: where misspecification is structural and recoverable from parameter pairs, RoPE dominates, as the theory predicts. A stochastic variant improves posterior-predictive log-likelihood on real COVID and OxCGRT epidemiological data, and correctly leaves the posterior unchanged on a well-specified cognitive-science corpus.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13221

From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation

作者:

Bora Kargi↗David Salinas↗

arXiv:2606.13221v1 Announce Type: new Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale. LLM-as-a-judge offers a cheaper alternative, but judge scores carry systematic errors - such as position bias, self-preference, or intransitivity - that can strongly miscalibrate the resulting rankings. We quantify the resulting judge-human disagreement at two complementary levels. At the local level, we estimate per-battle uncertainty from the judge's own score differences by propagating calibrated win probabilities rather than hard labels into the Bradley-Terry procedure. This alone provides a drastic improvement to Elo estimation accuracy, bringing LLM-derived ratings within 17.9 Elo MAE of human-derived ones when averaged over 55 held-out models on LMArena. At the global level, we apply split conformal prediction to the residual gap between LLM-derived and human-derived Elo ratings across held-out models, producing prediction intervals with distribution-free marginal coverage guarantees that account for irreducible LLM-human disagreement. Together, these two layers yield a low-cost evaluation tool that provides developers with calibrated Elo estimates and honest uncertainty bounds, without access to large-scale human annotations.To facilitate reproducibility, we release our code at https://github.com/kargibora/SoftElo .

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16786

We Need Explanation Cards to Connect Explanation Algorithms to the Real World

作者:

Eric G\"unther↗Bal\'azs Szabados↗Kristof Meding↗Gunnar K\"onig↗Sebastian Bordt↗Ulrike von Luxburg↗

arXiv:2606.16786v1 Announce Type: new Abstract: Algorithmic explanations are intended to help stakeholders understand opaque algorithmic decisions, but in practice, they often fall short. First, the meaning of algorithmic explanations is often not what one might intuitively expect, so expert knowledge is required to interpret them correctly. Second, recent work has shown that popular explanation algorithms are uninformative about the behavior of complex decision functions. Together, these issues create a gap between what explanations appear to convey and what they actually provide. In this work, we propose Explanation Cards for Explanation Algorithms, which augment standard explanations with complementary information about robustness and validity, as well as clear instructions for interpretation. The complementary information can render otherwise uninformative explanations practically useful, while also helping to detect cases where they are not. Importantly, the interpretation instructions in explanation cards shift responsibility from users to providers: Rather than expecting users to recognize what can and cannot be concluded from an explanation, providers must make this explicit upfront. Using counterfactual explanations and SHAP as examples, we demonstrate how providers can construct explanation cards and that these cards provide users with the guidance needed for sound interpretation. We further argue that explanation cards offer a practical means of operationalising the explainability provisions of the EU AI Act. Overall, explanation cards are a significant step toward making explanation algorithms fit for real-world use cases.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.28734

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

作者:

Richard J. Young↗Gregory D. Moody↗

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.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11662

TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search

作者:

Zhuofan Shi↗Mingzhe Ma↗Lu Wang↗Fangkai Yang↗Pu Zhao↗Yiming Guan↗Youling Huang↗Wei Zhang↗Qingwei Lin↗Dongmei Zhang↗Saravan Rajmohan↗

arXiv:2606.11662v1 Announce Type: new Abstract: Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge is deciding how to search when several directions look plausible but only some will later lead to reliable evidence. If an agent greedily follows the current best-looking direction, it may keep extending a weak continuation. If it explores without discipline, it may waste budget on disconnected trials. We propose TreeSeeker, an inference-time framework for controlled trial-and-error in deep search. TreeSeeker organizes search as branch-and-return search over tree-structured states, where each branch is a tentative direction for a sub-goal. At each round, TreeSearch reads all sub-goal trees, identifies active goals, and uses textual UCB signals of value, uncertainty, and risk to select among exploiting a promising branch, exploring an uncertain alternative, or pruning an unproductive continuation and returning to an earlier branch point. TreeMem supports this control loop by keeping evidence, uncertainty, conflicts, progress, and failure cues attached to the branches that produced them, so trial outcomes can guide later decisions. Experiments on XBench-DeepSearch, BrowseComp, and BrowseComp-ZH show that TreeSeeker consistently outperforms strong open-source baselines, suggesting that explicit branch-and-return control complements stronger reasoning and tool execution.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18548

Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction

作者:

Yongkyung Oh↗Lynn Talton↗Alex Bui↗

arXiv:2606.18548v1 Announce Type: cross Abstract: Adaptive AI ethics instruction in graduate research training benefits from intake measures that reflect differences in prior LLM experience. Prior coursework or workshop attendance is an obvious candidate, but it is not clear whether it is associated with pre-instruction ratings on key AI perception items. We compare three candidate intake features, self-reported usage frequency, self-rated LLM familiarity, and prior AI education, across five baseline perception outcomes in 93 bioscience graduate and postdoctoral trainees enrolled in a required research ethics course. Usage frequency shows Holm-corrected associations with all five outcomes, self-rated familiarity with three, and prior AI education with none. A threshold-like pattern at the lower end of the scale is most visible for training interest and accuracy trust rather than appearing as a uniform gradient across all five outcomes. In a short intake survey, reported LLM use is more consistently associated with these perceptions than prior coursework or workshops, with self-rated familiarity serving as a secondary indicator. These results suggest that simple pre-instruction behavioral signals can inform lightweight intake profiling for adaptive AI ethics education.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.15435

On the Stability of Growth in Structural Plasticity

作者:

Lute Lillo↗Nick Cheney↗

arXiv:2605.15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization. In contrast, a model can also be adapted by editing its structure during training, for example by pruning existing hidden-neuron units or growing new ones. Although growth is appealing for adaptive and continual systems, we show that it is not simply the inverse of pruning. Pruning selects among units that have participated in training from the start, whereas growth inserts new units into an already specialized optimization trajectory. We isolate this insertion problem and show that newborn units are often forward-active but backward-starved: they participate in the forward computation, yet receive much weaker gradient signal than incumbent units. This disadvantage is minor in small MLP benchmarks, but becomes clear in harder image-classification settings with a convolutional trunk. In these settings, \textsc{Grow} can achieve high final accuracy during the structural-editing procedure, while \textsc{Prune} is stronger when performance is averaged over the training trajectory or when the final sparse network is retrained from scratch. Interventions targeting optimizer state, insertion, selection, and trainability show that improving the integration of newborn units can improve adaptive performance, but does not automatically produce better final subnetworks. In continual-learning benchmarks stressing plasticity loss, \textsc{Grow} becomes competitive mainly when new units have enough time to integrate. Together, these results suggest that \textsc{Grow} should be evaluated not only as an architecture-search operator, but as a time-sensitive optimization process whose success depends on insertion stability.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2603.03485

Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion

作者:

Haoran Lu↗Shang Wu↗Songling Liu↗Jianshu Zhang↗Maojiang Su↗Guo Ye↗Chenwei Xu↗Lie Lu↗Pranav Maneriker↗Fan Du↗Manling Li↗Zhaoran Wang↗…

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time. In this work, we present Phys4D, a pipeline for learning physics-consistent 4D world representations from video diffusion models. Phys4D adopts a three-stage training paradigm that progressively lifts appearance-driven video diffusion models into physics-consistent 4D world representations. We first bootstrap robust geometry and motion representations through large-scale pseudo-supervised pretraining, establishing a foundation for 4D scene modeling. We then perform physics-grounded supervised fine-tuning using simulation-generated data, enforcing temporally consistent 4D dynamics. Finally, we apply simulation-grounded reinforcement learning to correct residual physical violations that are difficult to capture through explicit supervision. To evaluate fine-grained physical consistency beyond appearance-based metrics, we introduce a set of 4D world consistency evaluation that probe geometric coherence, motion stability, and long-horizon physical plausibility. Experimental results demonstrate that Phys4D substantially improves fine-grained spatiotemporal and physical consistency compared to appearance-driven baselines, while maintaining strong generative performance. Our project page is available at https://sensational-brioche-7657e7.netlify.app/

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-15 DOI: HASH:fa74f08787365ac64b197ad5bc53cf33

Validating Field-Feasible Measures of Recent Khat Use: A Diagnostic Accuracy Study Comparing Amphetamine Immunoassay and Assisted Self-Report Against HPLC in an Ethiopian Male Cohort

作者:

Atkinson↗H. F↗Mekonnen↗Suleman↗Oetzel↗Soboka↗Widmann↗Toennes↗S. W↗Tesfaye↗Stewart↗S. A↗…

Background: Khat (Catha edulis) is a widely consumed natural amphetamine-analog used across East Africa and the Arabian Peninsula. Accurate field-feasible measurement of recent khat use is a prerequisite for large-scale epidemiological research; yet no validated alternatives to laboratory reference methods have been identified in the scientific literature. This nested validation study evaluated the diagnostic accuracy of two point-of-care measures, a commercial amphetamine immunoassay and a Timeline Followback (TLFB) Assisted Self-Report (ASR), against high-performance liquid chromatography (HPLC) quantification of urinary norephedrine (NE), while additionally assessing agreement between the two field measures. Methods: A prospective, random sub-sample of 119 male participants aged 18-40 years from the Gilgel Gibe Field Research Center (GGFRC) longitudinal cohort, Ethiopia (validation timepoint T2, 2015), was used. Three index-reference comparisons were conducted: (1) amphetamine immunoassay (nal von minden, Drug-Screen AMP test, 300 ng/mL cutoff) vs. HPLC; (2) binary ASR (past-week use) vs. HPLC; and (3) binary ASR vs. immunoassay. Sensitivity (positive percent agreement, PPA), specificity (negative percent agreement, NPA), positive predictive value (PPV), negative predictive value (NPV), overall accuracy (overall percent agreement, OPA), and Cohen's kappa were calculated with 95% confidence intervals. Pre-specified secondary analyses applied three pharmacokinetically-informed recall windows (0-2, 3-5, and 6-7 days prior to interview) to ASR. Results: Against HPLC (77 positive, 42 negative), the immunoassay showed perfect specificity (1.0 [0.916-1.0]) and PPV (1.0 [0.91-1.0]) but low sensitivity (0.52 [0.40-0.64]), NPV (0.53 [0.42-0.65]), overall accuracy (0.69 [0.60-0.77]), and weak kappa (0.43 [0.34-0.52]). Binary ASR showed high sensitivity (0.96 [0.89-0.99]), specificity of 0.60 [0.433-0.74], PPV (0.81 [0.72-0.89]), NPV (0.89 [0.72-0.98]), with overall accuracy 0.83 [0.75-0.89] and moderate kappa (0.60 [0.51,0.69]). Restricting ASR to use within 0-2 days improved specificity to 0.69 [0.52-0.84], PPV to 0.86 [0.77-0.93], overall accuracy to 0.87 [0.79-0.93], and kappa to 0.69 [0.61-0.78] (moderate), while sensitivity (0.96 [0.89-0.99]) and NPV (0.89 [0.72-0.98]) remained stable. Against the immunoassay, ASR achieved high PPA of (1.0 [0.91-1.0]), NPA of 0.35 [0.25-0.47], OPA of 0.57 [0.48-0.66], and minimal kappa (0.27 [0.19-0.35]). Conclusions: Time-stratified ASR (0-2 days) is a valid, scalable alternative to biological testing for recent khat use in resource-limited settings. The immunoassay's 300 ng/mL cutoff functions as a marker of heavy or recent high-dose khat use rather than any-use detection. Its perfect specificity and PPV make it valuable as a confirmatory test for substantial exposure, while its lower sensitivity reflects calibration to amphetamine rather than to khat-derived cathinone metabolite. Keywords: khat; Catha edulis; diagnostic accuracy; STARD; self-report; immunoassay; HPLC; Ethiopia; substance use measurement

阅读与讨论 → 访问原文 →

24.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2605.15233

Measuring Control-Plane Openness in Near-Term Quantum Computing: A Rubric, Its Validation, and an Application to Thirteen Vendor Stacks

作者:

Rylan Malarchick↗

arXiv:2605.15233v2 Announce Type: replace Abstract: Public access to pulse-level and control-electronics interfaces in commercial quantum computing has bifurcated. This paper proposes a six-axis rubric for measuring control-plane openness, the layer between gate-level circuit specification and physical control electronics, defined operationally so that the same evidence produces the same grade across vendors. The rubric is validated three ways: a blinded re-grading pass, thirty-nine days after the evidence cutoff, that tests whether the cited evidence and the level definitions alone reproduce the recorded grades; a boundary-case methodology that fixes where each level begins and ends; and a published grading protocol that lets others reproduce and contest any cell. We establish that the rubric measures change rather than describing a snapshot by comparing the catalog against the documented control plane before the February 2025 removal of pulse-level access from IBM hardware, and reporting the cells that moved. The rubric is applied to thirteen commercial vendors across superconducting, trapped-ion, neutral-atom, and photonic modalities as of May 1, 2026, as its first application, and one of the three harms the rubric is designed to detect is demonstrated through a reproduction-access audit of five pre-2025 IBM Qiskit Pulse experiments against the access available on current hardware, carried through to a client-side structural port of the audit's selected target to Rigetti Quil-T. The catalog ships as a separate machine-readable artifact under CC-BY-4.0 with per-cell source URLs (https://doi.org/10.5281/zenodo.20163276). The catalog readings will change as vendor policies shift; the rubric is the contribution that survives them.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13135

Cascade Classification of Dermoscopic Images of Skin Neoplasms with Controllable Sensitivity and External Clinical Validation

作者:

Elena S. Kozachok↗Sergey S. Seregin↗Aleksandr V. Kozachok↗Ilya P. Latyshev↗Oleg I. Samovarov↗

Purpose. To compare deep learning architectures and classification schemes for dermoscopic images of skin neoplasms and assess their generalization on transfer from open international datasets to independent clinical datasets of Russian practice. Methods. Four architectures (ViT-B/16, Swin-S, ConvNeXt-S, EfficientNetV2-S) were compared in three schemes: binary (malignant/benign), single-stage four-class (benign, MEL, SCC, BCC), and a two-stage cascade (binary triage, then three-class differentiation MEL/SCC/BCC). All models used ImageNet-pretrained weights and a single augmentation protocol on aggregated open ISIC Archive data, and were evaluated on an internal held-out sample and two clinical datasets (Melanoscope AI mobile system; Sechenov University). Results. Internally the binary stage attains ROC-AUC 0.952-0.966; on Sechenov University it drops to 0.797-0.893, sensitivity to 0.53-0.67, and ECE rises from 0.02 to 0.27-0.39 with underestimation of malignancy, quantifying a generalization gap in ranking and calibration. Paired tests confirm one inter-architecture result on clinical data: the deficit of ViT-B/16 at the binary stage (p

阅读与讨论 → 访问原文 →