🤖 AI Summary
This study introduces and defines the concept of “comprehension debt,” denoting the gap between a development team’s current understanding of a codebase and the knowledge required for its effective maintenance, thereby revealing its nature as a collective cognitive deficit distinct from traditional technical debt. Drawing on qualitative analysis of 621 reflective logs submitted by 207 undergraduate students over eight weeks, the research identifies four behavioral patterns that contribute to the accumulation of comprehension debt—such as black-box acceptance and contextual mismatch—as well as one mitigating pattern: the use of generative AI as a cognitive scaffold for understanding. The findings inform targeted pedagogical strategies in software engineering education, including validation practices and structured retrospectives, to address the cognitive risks introduced by generative AI.
📝 Abstract
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.