AnyPoC introduces a multi-agent system for generating and validating PoC tests from LLM bug reports, producing 1.3x more valid PoCs, rejecting 9.8x more false positives, and discovering 122 new bugs across 12 major projects.
On the naturalness of software,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2representative citing papers
A methodology mines 62,965 real Python syntax errors and fixes from Stack Overflow posts, releases the dataset publicly, and shows these errors differ from student or randomly mutated ones.
citing papers explorer
-
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
AnyPoC introduces a multi-agent system for generating and validating PoC tests from LLM bug reports, producing 1.3x more valid PoCs, rejecting 9.8x more false positives, and discovering 122 new bugs across 12 major projects.
-
Syntax and Stack Overflow: A methodology for extracting a corpus of syntax errors and fixes
A methodology mines 62,965 real Python syntax errors and fixes from Stack Overflow posts, releases the dataset publicly, and shows these errors differ from student or randomly mutated ones.