Selected work

Representative Papers

GitReq: A Gold Standard Dataset for Software Quality Requirements

Jun 19, 2026

This work addresses the scarcity of fine-grained, expert-annotated non-functional requirement (NFR) samples in existing public GitHub datasets by introducing GitReq—the first large-scale GitHub-based quality requirements dataset aligned with the ISO/IEC 25010 standard. GitReq comprises 6,302 expert-validated requirements extracted from 4,080 repositories, spanning all eight quality characteristics defined in the standard. The construction methodology employs category-specific tri-signal mining, a preprocessing step to separate functional from non-functional requirements, and a rigorous manual annotation protocol, achieving a Fleiss’ Kappa inter-annotator agreement of 0.72. Experimental evaluation demonstrates that GPT-5.2 attains a macro-averaged F1 score of 0.641 under zero-shot settings, confirming both the dataset’s validity and its inherent challenge for current language models.

0 citationsRead paper

REStack: A Large-Scale Dataset of Reverse Engineering Discussions from Stack Exchange

Jun 03, 2026

This study addresses the scarcity of systematic, large-scale empirical data from real-world reverse engineering (RE) practice, which has hindered rigorous analysis of practitioners’ core challenges and knowledge gaps. To bridge this gap, we introduce and publicly release REStack—a novel dataset comprising over 12,000 RE-related question-answer pairs collected across 15 years from Stack Overflow and Reverse Engineering Stack Exchange. By integrating a genetic algorithm–optimized LDA topic model, manual annotation, and community interaction signals (e.g., unanswered question rates and response times), we identify 23 semantic topics grouped into six high-level categories. Our analysis reveals that debugging, decompilation, and system-level analysis dominate current discourse, whereas memory, firmware, and file format analysis are notably more difficult and exhibit lower resolution rates. REStack provides a foundational resource for developing AI-assisted RE tools, improving education, and enabling reproducible empirical research.

0 citationsRead paper

STMutants: A Mutation Testing Dataset for Structured Text Programs in Industrial Automation

Jun 03, 2026

This study addresses the lack of publicly available mutation testing benchmarks for IEC 61131-3 Structured Text (ST) programs widely used in industrial automation, which has hindered reproducible testing research. The authors present STMutants, the first mutation testing dataset specifically designed for PLC ST programs, incorporating seven mutation operators tailored to industrial control domains. Through a rigorous four-stage pipeline—syntactic transformation, compilation validation, manual equivalence screening (with inter-rater agreement κ = 0.87), and observability filtering—the dataset retains 108 high-quality, non-equivalent mutants. This benchmark facilitates research in automated test generation, fault localization, and AI-assisted quality assurance. Leveraging STMutants, the study evaluates three large language models, achieving mutation detection accuracies of 86.1%, 94.4%, and 86.1%, respectively, with statistical analysis confirming significant performance differences among them.

0 citationsRead paper

AI-Augmented OTDR Fault Localization Framework for Resilient Rural Fiber Networks in the United States

Jun 03, 2025

Conventional OTDR threshold-based methods suffer from high false-alarm rates and poor fault localization accuracy in U.S. rural fiber networks, where operational resources—including computational capacity and skilled personnel—are severely constrained. Method: This paper proposes a lightweight AI-enhanced OTDR diagnostic framework integrating time-series signal feature extraction with a CNN-LSTM hybrid model. It employs synthetic-data-driven transfer learning and embedded edge inference optimization to enable proactive, robust fault detection under low-compute conditions. Contribution/Results: To our knowledge, this is the first work to deeply couple deep learning with OTDR signal analysis—specifically tailored for mid- and last-mile rural fiber links. Experimental evaluation demonstrates a 32.7% improvement in fault localization accuracy and a 68.4% reduction in false alarms. The framework has been validated in real-world ISP deployments and is production-ready, directly supporting the BEAD program’s goal of building resilient rural broadband infrastructure.

0 citationsRead paper

A Survey on Heterogeneous Computing Using SmartNICs and Emerging Data Processing Units (Expanded Preprint)

Mar 03, 2025arXiv.org

This paper addresses key challenges in building heterogeneous computing systems through DPU/SmartNIC–CPU co-design. We conduct a systematic survey of over 100 representative works published between 2018 and 2024. Methodologically, we propose the first comprehensive taxonomy for DPU–CPU collaborative computing, categorizing research along three dimensions: hardware architectures (e.g., NVIDIA BlueField, Pensando), programming models (e.g., eBPF, DPDK, SPDK), and offloading mechanisms with coordinated scheduling techniques. Our analysis identifies driving forces behind technological evolution, fundamental bottlenecks—including memory consistency, inter-device communication latency, and software stack fragmentation—and emerging trends toward tighter hardware–software integration. As a result, we construct a domain knowledge graph spanning architectural principles, software stacks, and application scenarios (e.g., AI/ML acceleration, cloud data centers). This work establishes an authoritative benchmark and methodological foundation for co-designed DPU hardware/software development, performance modeling, and domain-specific adaptation.

0 citationsRead paper

Recent publications

Latest Papers

GitReq: A Gold Standard Dataset for Software Quality Requirements

Jun 19, 2026

This work addresses the scarcity of fine-grained, expert-annotated non-functional requirement (NFR) samples in existing public GitHub datasets by introducing GitReq—the first large-scale GitHub-based quality requirements dataset aligned with the ISO/IEC 25010 standard. GitReq comprises 6,302 expert-validated requirements extracted from 4,080 repositories, spanning all eight quality characteristics defined in the standard. The construction methodology employs category-specific tri-signal mining, a preprocessing step to separate functional from non-functional requirements, and a rigorous manual annotation protocol, achieving a Fleiss’ Kappa inter-annotator agreement of 0.72. Experimental evaluation demonstrates that GPT-5.2 attains a macro-averaged F1 score of 0.641 under zero-shot settings, confirming both the dataset’s validity and its inherent challenge for current language models.

0 citationsRead paper

REStack: A Large-Scale Dataset of Reverse Engineering Discussions from Stack Exchange

Jun 03, 2026

This study addresses the scarcity of systematic, large-scale empirical data from real-world reverse engineering (RE) practice, which has hindered rigorous analysis of practitioners’ core challenges and knowledge gaps. To bridge this gap, we introduce and publicly release REStack—a novel dataset comprising over 12,000 RE-related question-answer pairs collected across 15 years from Stack Overflow and Reverse Engineering Stack Exchange. By integrating a genetic algorithm–optimized LDA topic model, manual annotation, and community interaction signals (e.g., unanswered question rates and response times), we identify 23 semantic topics grouped into six high-level categories. Our analysis reveals that debugging, decompilation, and system-level analysis dominate current discourse, whereas memory, firmware, and file format analysis are notably more difficult and exhibit lower resolution rates. REStack provides a foundational resource for developing AI-assisted RE tools, improving education, and enabling reproducible empirical research.

0 citationsRead paper

STMutants: A Mutation Testing Dataset for Structured Text Programs in Industrial Automation

Jun 03, 2026

This study addresses the lack of publicly available mutation testing benchmarks for IEC 61131-3 Structured Text (ST) programs widely used in industrial automation, which has hindered reproducible testing research. The authors present STMutants, the first mutation testing dataset specifically designed for PLC ST programs, incorporating seven mutation operators tailored to industrial control domains. Through a rigorous four-stage pipeline—syntactic transformation, compilation validation, manual equivalence screening (with inter-rater agreement κ = 0.87), and observability filtering—the dataset retains 108 high-quality, non-equivalent mutants. This benchmark facilitates research in automated test generation, fault localization, and AI-assisted quality assurance. Leveraging STMutants, the study evaluates three large language models, achieving mutation detection accuracies of 86.1%, 94.4%, and 86.1%, respectively, with statistical analysis confirming significant performance differences among them.

0 citationsRead paper

AI-Augmented OTDR Fault Localization Framework for Resilient Rural Fiber Networks in the United States

Jun 03, 2025

Conventional OTDR threshold-based methods suffer from high false-alarm rates and poor fault localization accuracy in U.S. rural fiber networks, where operational resources—including computational capacity and skilled personnel—are severely constrained. Method: This paper proposes a lightweight AI-enhanced OTDR diagnostic framework integrating time-series signal feature extraction with a CNN-LSTM hybrid model. It employs synthetic-data-driven transfer learning and embedded edge inference optimization to enable proactive, robust fault detection under low-compute conditions. Contribution/Results: To our knowledge, this is the first work to deeply couple deep learning with OTDR signal analysis—specifically tailored for mid- and last-mile rural fiber links. Experimental evaluation demonstrates a 32.7% improvement in fault localization accuracy and a 68.4% reduction in false alarms. The framework has been validated in real-world ISP deployments and is production-ready, directly supporting the BEAD program’s goal of building resilient rural broadband infrastructure.

0 citationsRead paper

A Survey on Heterogeneous Computing Using SmartNICs and Emerging Data Processing Units (Expanded Preprint)

Mar 03, 2025arXiv.org

This paper addresses key challenges in building heterogeneous computing systems through DPU/SmartNIC–CPU co-design. We conduct a systematic survey of over 100 representative works published between 2018 and 2024. Methodologically, we propose the first comprehensive taxonomy for DPU–CPU collaborative computing, categorizing research along three dimensions: hardware architectures (e.g., NVIDIA BlueField, Pensando), programming models (e.g., eBPF, DPDK, SPDK), and offloading mechanisms with coordinated scheduling techniques. Our analysis identifies driving forces behind technological evolution, fundamental bottlenecks—including memory consistency, inter-device communication latency, and software stack fragmentation—and emerging trends toward tighter hardware–software integration. As a result, we construct a domain knowledge graph spanning architectural principles, software stacks, and application scenarios (e.g., AI/ML acceleration, cloud data centers). This work establishes an authoritative benchmark and methodological foundation for co-designed DPU hardware/software development, performance modeling, and domain-specific adaptation.

0 citationsRead paper