Project Grant 2220991

Award Date 10/1/22
Completion Date 9/30/25
Dollars Obligated $1M
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
MIDDLE CITY EAST, PA 19102, USA
Similar Awards
This National Science Foundation (NSF) $900,000 "COLLABORATIVE RESEARCH: SHF: MEDIUM: NATURAL LANGUAGE MODELS WITH EXECUTION DATA FOR SOFTWARE TESTING" Project Grant, awarded under the Computer and Information Science and Engineering program (CFDA 47.070), aims to develop natural language processing (NLP) models to simplify the development and maintenance of software tests. Key objectives include test generation, completion, update, and migration across programming languages, targeting...
This Project Grant award from the National Science Foundation (NSF) Division of Computing and Communication Foundations, under CFDA Program #47.070 "Computer and Information Science and Engineering", provides $300,000 to the University of Illinois to develop natural language processing (NLP) models that can simplify the development and maintenance of software tests (NLP4TEST). The key objectives are to create NLP models for tasks such as test generation, completion, update, and...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) is providing $400,000 to the University of Delaware to develop tools that help developers easily verify and find defects in scientific software. The project aims to create a modular approach to specifying program components using mathematical abstractions, automated methods to verify program adherence to specifications, and apply these techniques to...
This $875,000 Project Grant was awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) to the University of California, San Diego (UCSD). The project aims to develop new techniques for aligning large language models (LLMs) with formal specifications in order to generate high-quality computer code that provably matches user intent. Specifically, the project will: (1) develop grammar-aligned decoding...
This $600,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to enable developers to perform fine-grained software testing, thereby increasing software quality. The research project will: (1) develop a language and framework for expressing and using fine-grained tests; (2) automatically generate fine-grained tests from code or existing tests; (3) adapt fine-grained tests to software evolution and...
This $439,112 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program will support research to enable practical dynamic program reasoning across language boundaries in multi-language software systems. The award will fund the development of new foundations for dynamic analysis and application tools to diagnose cross-language correctness and security issues, helping to produce multi-language systems of...
This $600,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to enable developers to perform fine-grained software testing, thereby increasing software quality. The key objectives are to: (1) develop a language and framework for expressing and using fine-grained tests; (2) automatically generate fine-grained tests from code or existing tests; (3) adapt fine-grained tests to software evolution and...
This three-year Project Grant from the National Science Foundation Division of Computing and Communication Foundations provides $499,821 to Virginia Polytechnic Institute & State University under the Computer and Information Science and Engineering program (CFDA 47.070) from October 2021 through September 2024. The funding supports research to develop hybrid natural language processing and formal techniques for synthesizing assertions and identifying ambiguities from English text. The work...
This National Science Foundation (NSF) Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program provides $195,000 to Seton Hall University to explore the development of teaching language progressions for embedded domain-specific languages (EDSLs). The project aims to make programming more accessible to novice learners by simplifying EDSLs into starter versions and gradually introducing complexity. The research will create two tailored teaching EDSLs (TEDSLs)...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) provides USD 174,999 to the University of Central Missouri to develop a unified, large language model (LLM)-empowered framework to systematically address software performance challenges. The key products and services to be delivered under this 2-year award include: 1) Advancing automation in performance testing, issue localization, and...

This three-year National Science Foundation Project Grant of $1,048,850 will fund the development of new techniques for translating English language specifications into formal specifications accepted by software quality tools. Drexel University will receive the funding under the Computer and Information Science and Engineering program (CFDA 47.070) to pursue approaches connecting natural language software behavior descriptions to semi-formal specifications used in property-based testing frameworks, proof assistants, and temporal logic tools. The project aims to address gaps in current practice where manual translation of specifications leaves room for misunderstandings or mistakes. Key products will include new methods for translating English sentences to property-based tests, proof assistant specifications in dependent type theory, and multiple temporal logics. An open-source prototype system and tools for domain-specific lexicon learning from examples will also be delivered.

Generated 1/6/24, 10:54 PM