Neuro-Symbolic Approach to Certified Scientific Software Synthesis
Scientific software development demands robust solutions to meet the complexities of modern scientific systems. In response, we propose a paradigm-shifting Neuro-Symbolic Approach to Certified Scientific Software Synthesis. This innovative framework integrates large language models (LLMs) with formal methods, facilitating automated synthesis of complex scientific software while ensuring verifiability and correctness. Through a combination of technologies including a Scientific and Satisfiability-Aided Large Language Model (SaSLLM), a Scientific Domain Specific Language (DSL), and Generalized Planning for Abstract Reasoning, our approach transforms scientific concepts into certified software solutions. By leveraging advanced reasoning techniques, our framework streamlines the development process, allowing scientists to focus on design and exploration. This approach represents a significant step towards automated, certified-by-design scientific software synthesis, revolutionizing the landscape of scientific research and discovery.
Tue 16 JulDisplayed time zone: Brasilia, Distrito Federal, Brazil change
09:00 - 10:30 | Opening Day2 + Keynote2 + AIware for Domain-specific ApplicationsLate Breaking Arxiv Track / Main Track at Mandacaru Chair(s): Jie M. Zhang King's College London | ||
09:00 5mDay opening | Opening for day 2 Main Track | ||
09:05 45mKeynote | Semantic-Aware AI: Elevating the Future of Software Development Main Track Baishakhi Ray Columbia University, New York; AWS AI Lab | ||
09:50 10mPaper | SolMover: Smart Contract Code Translation Based on Concepts Main Track Rabimba Karanjai University of Houston, Lei Xu Kent State University, Weidong Shi University of Houston DOI | ||
10:00 5mPaper | The Art of Programming: Challenges in Generating Code for Creative Applications Main Track Michael Cook King’s College London DOI | ||
10:05 5mPaper | Neuro-Symbolic Approach to Certified Scientific Software Synthesis Main Track Hamid Bagheri University of Nebraska-Lincoln, Mehdi Mirakhorli Rochester Institute of Technology, Mohamad Fazelnia University of Hawaii at Manoa, Ibrahim Mujhid University of Hawaii at Manoa, Md Rashedul Hasan University of Nebraska-Lincoln DOI | ||
10:10 5mPaper | LLMs in the Heart of Differential Testing: A Case Study on a Medical Rule Engine Late Breaking Arxiv Track Erblin Isaku Simula Research Laboratory, and University of Oslo (UiO), Christoph Laaber Simula Research Laboratory, Hassan Sartaj Simula Research Laboratory, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University, Thomas Schwitalla Cancer Registry of Norway, Jan F. Nygård Cancer Registry of Norway Pre-print | ||
10:15 15mLive Q&A | Session Q&A and topic discussions Main Track | ||