Reproduce “MELT: Mining Effective Lightweight Transformations from Pull Requests” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Daniel Ramos, Hailie Mitchell, Inês Lynce, Vasco Manquinho, Ruben Martins, Claire Le Goues
MELT mines library pull requests for API changes and converts before-and-after code examples into syntax-based search-and-replace rules for Python. It generalizes rules by relaxing surrounding context and argument details. In a sample of 15 rules, generalized rules matched 1,469 code locations versus 162 for original rules, a 9.07-fold increase; these matches are not verified safe migrations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.