4 papers
Automated Testing and Repair for Verified Compilers Generated by a Coding Agent
Martin Rinard
We present an agent based automated testing and repair system for verified compilers that contain four kinds of code: verified code, checked code, unverified code, and specificatio…
Incremental Computation for Efficient Programmable Inference in Probabilistic Programs
Fabian Zaiser, Jack Czenszak, Martin C. Rinard +2
Inference in probabilistic programs generally requires evaluating many possible program executions to find those of high posterior density. To scale inference to large datasets, it…
Lexo: Eliminating Stealthy Supply-Chain Attacks via LLM-Assisted Program Regeneration
Evangelos Lamprou, Julian Dai, Grigoris Ntousakis +2
Software supply-chain attacks are an important and ongoing concern in the open source software ecosystem. These attacks maintain the standard functionality that a component impleme…
Probing the Design Space: Parallel Versions for Exploratory Programming
Tom Beckmann, Joana Bergsiek, Eva Krebs +4
Exploratory programming involves open-ended tasks. To evaluate their progress on these, programmers require frequent feedback and means to tell if the feedback they observe is brin…