DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding
DeepDiscovery is presented, a task-level repository-understanding method for large industrial codebases that uses a two-stage \textit{Location--Inference} framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints.
Jia-Wei He, Wei-Song Sun, Mengyu Shi et al.
· 1 citation