arXiv subjects

Weijing Wang

Publications and source records attributed to Weijing Wang.

5 recordsLinked to original sources

arXiv2026

KernelDiag: Agent-Based Root Cause Diagnosis for Kernel Crashes

The Linux kernel is one of the most complex software systems, where automated fuzzing continuously exposes thousands of crashes, yet root-cause diagnosis remains a manual and time-consuming bottleneck. Existing LLM-based root cause analysis (RCA) techniques, effective for distributed systems, do not readily generalize to kernel debugging due to sparse low-level artifacts, heterogeneous diagnostic evidence (e.g., syscalls, logs, and crash reports), and complex non-linear fault propagation that demands fine-grained method-level reasoning. To address these challenges, we propose KernelDiag, an agent-based framework for kernel root-cause diagnosis via structured causal reasoning. KernelDiag first aligns heterogeneous diagnostic artifacts through log-to-code mapping, and then employs artifact-specialized agents to iteratively reason over source-level program semantics and crash-specific kernel configurations. The inferred causal dependencies are incrementally organized into structured Evidence Graphs, enabling accurate faulty-method localization and causal explanations. We evaluate KernelDiag on the real-world KGYM benchmark. KernelDiag consistently outperforms state-of-the-art localization approaches at both file and method levels, achieving significant improvements in Top@k accuracy, including up to 4x and 2x gains in challenging settings without explicit hints. Furthermore, both human and LLM-assisted evaluations show that KernelDiag generates accurate, coherent, and actionable diagnostic explanations. Overall, this work lays the foundation for automated kernel root-cause diagnosis by bridging low-level diagnostic evidence with source-level causal reasoning.

cs.SE↗

arXiv2026

A Milestone-Based Framework for Characterizing Time-Varying Treatment Effects in Immunotherapy Trials

Immune checkpoint inhibitor--based therapies often produce heterogeneous survival responses, including early risk, delayed treatment benefit, and durable long-term survival in a subset of patients. In these settings, conventional summary measures such as the hazard ratio may not adequately describe how treatment effects evolve over follow-up. We propose a milestone-based framework that separates long-term survival beyond a clinically meaningful time point from earlier outcomes and provides a practical way to characterize patient heterogeneity in treatment response. The framework summarizes treatment differences through milestone survival probabilities and, among patients who do not reach the milestone, characterizes short-term treatment ordering over time using a tau-based summary that helps identify hazard reversal. We illustrate the approach using reconstructed individual-level data from three landmark phase III trials: CheckMate~067, CheckMate~227, and CLEAR. Across these examples, the framework captures patterns that are difficult to summarize with conventional measures, including settings in which early disadvantage coexists with later durable benefit. It also helps clarify when treatment benefit begins to emerge and how short-term and long-term effects differ within the same trial. This approach provides a clinically interpretable and statistically principled way to evaluate heterogeneous and time-varying treatment effects in oncology trials with nonproportional hazards.

stat.ME↗

arXiv2024

Estimand-based Inference in Presence of Long-Term Survivors

In this article, we develop nonparametric inference methods for comparing survival data across two samples, which are beneficial for clinical trials of novel cancer therapies where long-term survival is a critical outcome. These therapies, including immunotherapies or other advanced treatments, aim to establish durable effects. They often exhibit distinct survival patterns such as crossing or delayed separation and potentially leveling-off at the tails of survival curves, clearly violating the proportional hazards assumption and rendering the hazard ratio inappropriate for measuring treatment effects. The proposed methodology utilizes the mixture cure framework to separately analyze the cure rates of long-term survivors and the survival functions of susceptible individuals. We evaluate a nonparametric estimator for the susceptible survival function in the one-sample setting. Under sufficient follow-up, it is expressed as a location-scale-shift variant of the Kaplan-Meier (KM) estimator. It retains several desirable features of the KM estimator, including inverse-probability-censoring weighting, product-limit estimation, self-consistency, and nonparametric efficiency. In scenarios of insufficient follow-up, it can easily be adapted by incorporating a suitable cure rate estimator. In the two-sample setting, besides using the difference in cure rates to measure the long-term effect, we propose a graphical estimand to compare the relative treatment effects on susceptible subgroups. This process, inspired by Kendall's tau, compares the order of survival times among susceptible individuals. The proposed methods' large-sample properties are derived for further inference, and the finite-sample properties are examined through extensive simulation studies. The proposed methodology is applied to analyze the digitized data from the CheckMate 067 immunotherapy clinical trial.

stat.ME↗

arXiv2024

On the Evaluation of Large Language Models in Unit Test Generation

Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.

cs.SE↗

arXiv2022

Kendall's Tau for Two-Sample Inference Problems

We consider a Kendall's tau measure between a binary group indicator and the continuous variable under investigation to develop a thorough two-sample comparison procedure. The measure serves as a useful alternative to the hazard ratio whose applicability depends on the proportional hazards assumption. For right censored data, we propose a weighted log-rank statistic with weights adapted to the censoring distributions and develop theoretical properties of the derived estimators. In absence of censoring, the proposed estimator reduces to the WMW statistic. The proposed methodology is applied to analyze several data examples.

stat.ME↗