SWE-bench reveals that even top language models like Claude 2 resolve only 1.96% of 2,294 real-world GitHub issues, highlighting a gap in practical coding capabilities.
Learning to represent programs with graphs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Controlled experiments show PLM-GNN hybrids improve code tasks over GNN-only baselines, with PLM source having larger impact than GNN backbone.
citing papers explorer
-
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
SWE-bench reveals that even top language models like Claude 2 resolve only 1.96% of 2,294 real-world GitHub issues, highlighting a gap in practical coding capabilities.
-
PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection
Controlled experiments show PLM-GNN hybrids improve code tasks over GNN-only baselines, with PLM source having larger impact than GNN backbone.