Two recent arXiv papers explore the concept of Self-Admitted Technical Debt (SATD) in software development. The first paper introduces PRESTI, a BERT- and TextCNN-based model for predicting the effort required to repay SATD, finding that code/design and requirement debts are most costly. The second paper provides a decade-long systematic review of SATD detection approaches, noting the shift from heuristic methods to advanced ML, DL, and Transformer models, while highlighting ongoing challenges in generalizability and industrial adoption. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Improved methods for predicting and detecting software development debt could streamline maintenance and resource allocation.
RANK_REASON The cluster contains two academic papers published on arXiv, detailing new models and systematic reviews related to software development.