Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This qualitative study investigates how GenAI tools contribute to "Comprehension Debt" (CD) – the gap between a team's codebase knowledge and required understanding – in undergraduate software engineering projects. Analyzing 621 reflective diaries from 207 students, the research identifies four CD accumulation patterns (e.g., AI-as-black-box code acceptance, context-mismatch debt) and one mitigating pattern (GenAI as a comprehension scaffold). The study distinguishes CD from technical debt by highlighting its socio-cognitive nature, residing in the team's collective cognition.
Using GenAI tools in software engineering can create a "Comprehension Debt" where developers understand less about their code than they need to, even when the code works.
Generative Artificial Intelligence (GenAI) tools (e.g., ChatGPT, Calude) have rapidly become integral to software development. These tools are especially attractive to students, as they can reduce cognitive load. However, their adoption also introduces a socio-cognitive risk: the accumulation of Comprehension Debt (CD). CD refers to the growing gap between what a development team knows about its codebase and what it actually needs to understand in order to maintain and modify it effectively. This qualitative study investigate how GenAI tools contribute to CD in the context of an undergraduate software engineering project. Our study is based on 621 reflective diaries from 207 students over eight weeks. We identify four CD accumulation patterns and one mitigating pattern in students'use of GenAI tools. The four accumulation patterns include: (1) AI-as-black-box code acceptance, (2) context-mismatch debt, (3) dependency-induced atrophy, and (4) verification-bypass. In contrast, the mitigating pattern involves students using GenAI as a comprehension scaffold, allowing them to build a deeper understanding of the code. We argue that CD is distinct from traditional technical debt because it resides in the collective cognition of development teams rather than in the codebase itself. Our findings highlight the need for explicit pedagogical strategies to mitigate CD in software engineering education, emphasizing verification practices, structured retrospectives, and active learning assessments.