A diff-reading foundation-model oracle detects behavior-changing Python refactorings with 91% recall and surfaced 13 Rope bugs, 12 accepted by maintainers.
Basili, Gianluigi Caldiera, and H
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Detecting Behavioral Changes in Python Refactoring Implementations with Foundation Models
A diff-reading foundation-model oracle detects behavior-changing Python refactorings with 91% recall and surfaced 13 Rope bugs, 12 accepted by maintainers.