DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
Hunting for bugs in code coverage tools via randomized differential testing
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
AFGNN detects API misuses in Java code more effectively than prior methods by representing usage as graphs and clustering learned embeddings from self-supervised training.
Model-checking stateless quantum pushdown systems against PCTL is undecidable while against bPCTL it is decidable and NP-hard.
citing papers explorer
-
Code Generation by Differential Test Time Scaling
DiffCodeGen clusters code candidates by behavioral similarity from fuzzing-synthesized inputs and selects the largest cluster's medoid, matching or exceeding prior test-time scaling methods with far less token and time cost.
-
AFGNN: API Misuse Detection using Graph Neural Networks and Clustering
AFGNN detects API misuses in Java code more effectively than prior methods by representing usage as graphs and clustering learned embeddings from self-supervised training.
-
Computational Complexity of Model-Checking Quantum Pushdown Systems
Model-checking stateless quantum pushdown systems against PCTL is undecidable while against bPCTL it is decidable and NP-hard.