Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.

In settings where ML models are used to inform the allocation of resources, agents affected by the allocation decisions might have an incentive to strategically change their features to secure better outcomes. While prior work has studied strategic responses broadly, disentangling misreporting from genuine modification remains a fundamental challenge. In this paper, we propose a causally-motivated approach to identify and quantify how much an agent misreports on average by distinguishing deceptive changes in their features from genuine modification. Our key insight is that, unlike genuine modification, misreported features do not causally affect downstream variables (i.e., causal descendants). We exploit this asymmetry by comparing the causal effect of misreported features on their causal descendants as derived from manipulated datasets against those from unmanipulated datasets. We formally prove identifiability of the misreporting rate and characterize the variance of our estimator. We empirically validate our theoretical results using a semi-synthetic and real Medicare dataset with misreported data, demonstrating that our approach can be employed to identify misreporting in real-world scenarios.

Large Language Models are widely used for content moderation but often misclassify benign comments as toxic, leading to over-sensitivity. While previous research attributes this issue primarily to the presence of offensive terms, we reveal a potential cause beyond token level: LLMs exhibit systematic topic biases in their implicit associations. Inspired by cognitive psychology's implicit association tests, we introduce Topic Association Analysis, a semantic-level approach to quantify how LLMs associate certain topics with toxicity. By prompting LLMs to generate free-form scenario imagination for misclassified benign comments and analyzing their topic amplification levels, we find that more advanced models (e.g., GPT-4 Turbo) demonstrate stronger topic stereotype despite lower overall false positive rates. These biases suggest that LLMs do not merely react to explicit, offensive language but rely on learned topic associations, shaping their moderation decisions. Our findings highlight the need for refinement beyond keyword-based filtering, providing insights into the underlying mechanisms driving LLM over-sensitivity.

Weaknesses: - I could not follow the motivation for the simplified estimation procedure (and subsequent theoretical analysis in 3.1) that ignores timestamps (using event counts to estimate the branching ratio). It would be helpful if the authors could explain what advantages this approach brings compared to a "standard" block model inference in networks with a weighted adjacency matrix and the assumption that "event counts" (i.e. For instance, how do the results for the misclustering error rate compare to existing works on dectectability limits in the (weighted) block model? I would guess that there is a difference due to the use of the variance of event counts within blocks, which is not used for parameter estimation in some of the simpler block modelling approaches. However, this simpler version of the model is not included in the experimental evaluation.

Brain network analysis plays a crucial role in diagnosing and monitoring neurodegenerative disorders such as Alzheimer's disease (AD). Existing approaches for constructing structural brain networks from diffusion tensor imaging (DTI) often rely on specialized toolkits that suffer from inherent limitations: operator subjectivity, labor-intensive workflows, and restricted capacity to capture complex topological features and disease-specific biomarkers. To overcome these challenges and advance computational neuroimaging instrumentation, ConnectomeDiffuser is proposed as a novel diffusion-based framework for automated end-to-end brain network construction from DTI. The proposed model combines three key components: (1) a Template Network that extracts topological features from 3D DTI scans using Riemannian geometric principles, (2) a diffusion model that generates comprehensive brain networks with enhanced topological fidelity, and (3) a Graph Convolutional Network classifier that incorporates disease-specific markers to improve diagnostic accuracy. ConnectomeDiffuser demonstrates superior performance by capturing a broader range of structural connectivity and pathology-related information, enabling more sensitive analysis of individual variations in brain networks. Experimental validation on datasets representing two distinct neurodegenerative conditions demonstrates significant performance improvements over other brain network methods. This work contributes to the advancement of instrumentation in the context of neurological disorders, providing clinicians and researchers with a robust, generalizable measurement framework that facilitates more accurate diagnosis, deeper mechanistic understanding, and improved therapeutic monitoring of neurodegenerative diseases such as AD.

In connected and autonomous vehicles, machine learning for safety message classification has become critical for detecting malicious or anomalous behavior. However, conventional approaches that rely on centralized data collection or purely local training face limitations due to the large scale, high mobility, and heterogeneous data distributions inherent in inter-vehicle networks. To overcome these challenges, this paper explores Distributed Federated Learning (DFL), whereby vehicles collaboratively train deep learning models by exchanging model updates among one-hop neighbors and propagating models over multiple hops. Using the Vehicular Reference Misbehavior (VeReMi) Extension Dataset, we show that DFL can significantly improve classification accuracy across all vehicles compared to learning strictly with local data. Notably, vehicles with low individual accuracy see substantial accuracy gains through DFL, illustrating the benefit of knowledge sharing across the network. We further show that local training data size and time-varying network connectivity correlate strongly with the model's overall accuracy. We investigate DFL's resilience and vulnerabilities under attacks in multiple domains, namely wireless jamming and training data poisoning attacks. Our results reveal important insights into the vulnerabilities of DFL when confronted with multi-domain attacks, underlining the need for more robust strategies to secure DFL in vehicular networks.

Integrating structured information has long improved the quality of abstractive summarization, particularly in retaining salient content. In this work, we focus on a specific form of structure: argument roles, which are crucial for summarizing documents in high-stakes domains such as law. We investigate whether instruction-tuned large language models (LLMs) adequately preserve this information. To this end, we introduce Argument Representation Coverage (ARC), a framework for measuring how well LLM-generated summaries capture salient arguments. Using ARC, we analyze summaries produced by three open-weight LLMs in two domains where argument roles are central: long legal opinions and scientific articles. Our results show that while LLMs cover salient argument roles to some extent, critical information is often omitted in generated summaries, particularly when arguments are sparsely distributed throughout the input. Further, we use ARC to uncover behavioral patterns -- specifically, how the positional bias of LLM context windows and role-specific preferences impact the coverage of key arguments in generated summaries, emphasizing the need for more argument-aware summarization strategies.

Multi-Modal Learning (MML) integrates information from diverse modalities to improve predictive accuracy. However, existing methods mainly aggregate gradients with fixed weights and treat all dimensions equally, overlooking the intrinsic gradient uncertainty of each modality. This may lead to (i) excessive updates in sensitive dimensions, degrading performance, and (ii) insufficient updates in less sensitive dimensions, hindering learning. To address this issue, we propose BOGC-MML, a Bayesian-Oriented Gradient Calibration method for MML to explicitly model the gradient uncertainty and guide the model optimization towards the optimal direction. Specifically, we first model each modality's gradient as a random variable and derive its probability distribution, capturing the full uncertainty in the gradient space. Then, we propose an effective method that converts the precision (inverse variance) of each gradient distribution into a scalar evidence. This evidence quantifies the confidence of each modality in every gradient dimension. Using these evidences, we explicitly quantify per-dimension uncertainties and fuse them via a reduced Dempster-Shafer rule. The resulting uncertainty-weighted aggregation produces a calibrated update direction that balances sensitivity and conservatism across dimensions. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness and advantages of the proposed method.

Background Sepsis is a life - threatening condition affecting over 48.9 million people globally and causing 11 million deaths annually. Despite medical advancements, predicting sepsis remains a challenge due to non - specific symptoms and complex pathophysiology. The SXI++ LNM model is a machine learning - based scoring system that refines sepsis prediction by leveraging multiple algorithms and deep neural networks. The COMPOSER model, a de ep learning framework utilizing conformal prediction, aims to improve robustness in clinical applications. This study compares the predictive performance of SXI++ LNM and COMPOSER for sepsis prediction. Methods A dataset containing 1,552,210 rows with 43 columns was cleaned and refined to 964,355 rows and 14 key features for sepsis prediction. Data were sourced from ICU patients across three separate hospital systems, including two publicly available datasets fro m Kaggle and the Early Prediction of Sepsis from Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019.