arXiv subjects

Justin Shi

Publications and source records attributed to Justin Shi.

3 recordsLinked to original sources

arXiv2025

PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints

Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework that constrains reasoning to single-step inferences while preserving natural language formulations. Each output explicitly specifies premises, rules, and conclusions, thereby enabling verification against a target logic. This mechanism mitigates trustworthiness concerns by supporting chain-level validation even in black-box settings. Moreover, PCRLLM facilitates systematic multi-LLM collaboration, allowing intermediate steps to be compared and integrated under formal rules. Finally, we introduce a benchmark schema for generating large-scale step-level reasoning data, combining natural language expressiveness with formal rigor.

cs.CL↗

arXiv2014

Standing Together for Reproducibility in Large-Scale Computing: Report on reproducibility@XSEDE

This is the final report on reproducibility@xsede, a one-day workshop held in conjunction with XSEDE14, the annual conference of the Extreme Science and Engineering Discovery Environment (XSEDE). The workshop's discussion-oriented agenda focused on reproducibility in large-scale computational research. Two important themes capture the spirit of the workshop submissions and discussions: (1) organizational stakeholders, especially supercomputer centers, are in a unique position to promote, enable, and support reproducible research; and (2) individual researchers should conduct each experiment as though someone will replicate that experiment. Participants documented numerous issues, questions, technologies, practices, and potentially promising initiatives emerging from the discussion, but also highlighted four areas of particular interest to XSEDE: (1) documentation and training that promotes reproducible research; (2) system-level tools that provide build- and run-time information at the level of the individual job; (3) the need to model best practices in research collaborations involving XSEDE staff; and (4) continued work on gateways and related technologies. In addition, an intriguing question emerged from the day's interactions: would there be value in establishing an annual award for excellence in reproducible research?

cs.DC↗

arXiv2014

Seeking the Principles of Sustainable Software Engineering

Like other engineering disciplines, software engineering should also have principles to guide the construction of sustainable computer applications. Tangible properties include a) unlimited scalability, b) maximal reproducibility, and c) optimizable energy efficiency. In practice, we expect a sustainable scientific application should be written once and execute many times on multiple different processing platforms of different scales with optimized performance and energy efficiency. For more than two decades, explicit parallel programming/processing paradigms only focused on performance. Practices showed that the rigid program-data binding prohibited dynamic runtime resource optimization and fault isolation, making it difficult to reproduce applications in scale. This paper reports our practice and experiences in search of the first principles of sustainable software engineering for compute and data intensive applications. Specifically, we report our practice and experiences using implicit parallel programming/processing paradigms.

cs.DC↗