# Characterizing Technical Debt and Antipatterns in AI-Based Systems: A Systematic Mapping Study arXiv: https://arxiv.org/abs/2103.09783 ยท HTML: https://mlsanity.com/paper/2103.09783/ ## Key facts - Cited by 21 papers in the map (data through 14 Oct 2026). - Builds on 13 of its 55 references that are in the map. - First posted on arXiv 17 Mar 2021. ## Builds on (most cited first, 13 of 13) - [Taxonomy of Real Faults in Deep Learning Systems](https://mlsanity.com/paper/1910.11015/) (2019) - [Software Engineering Challenges of Deep Learning](https://mlsanity.com/paper/1810.12034/) (2018) - [Engineering AI Systems: A Research Agenda](https://mlsanity.com/paper/2001.07522/) (2020) - [Adoption and Effects of Software Engineering Best Practices in Machine Learning](https://mlsanity.com/paper/2007.14130/) (2020) - [Studying Software Engineering Patterns for Designing Machine Learning Systems](https://mlsanity.com/paper/1910.04736/) (2019) - [Requirements Engineering Challenges in Building AI-Based Complex Systems](https://mlsanity.com/paper/1908.11791/) (2019) - [Quality Assurance for AI-based Systems: Overview and Challenges](https://mlsanity.com/paper/2102.05351/) (2021) - [Towards Guidelines for Assessing Qualities of Machine Learning Systems](https://mlsanity.com/paper/2008.11007/) (2020) - [Machine Learning Software Engineering in Practice: An Industrial Case Study](https://mlsanity.com/paper/1906.07154/) (2019) - [Quality Management of Machine Learning Systems](https://mlsanity.com/paper/2006.09529/) (2020) - [Technical Debt in Data-Intensive Software Systems](https://mlsanity.com/paper/1905.13455/) (2019) - [Component Mismatches Are a Critical Bottleneck to Fielding AI-Enabled Systems in the Public Sector](https://mlsanity.com/paper/1910.06136/) (2019) - [Prioritizing Technical Debt in Database Normalization Using Portfolio Theory and Data Quality Metrics](https://mlsanity.com/paper/1801.06989/) (2018) ## Built on by (most cited first, 21 of 21) - [Analyzing the Evolution and Maintenance of ML Models on Hugging Face](https://mlsanity.com/paper/2311.13380/) (2023) - [Vibe Coding as a Reconfiguration of Intent Mediation in Software Development: Definition, Implications, and Research Agenda](https://mlsanity.com/paper/2507.21928/) (2025) - [Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2](https://mlsanity.com/paper/2208.05056/) (2022) - [Quality issues in Machine Learning Software Systems](https://mlsanity.com/paper/2208.08982/) (2022) - [Maintainability Challenges in ML: A Systematic Literature Review](https://mlsanity.com/paper/2408.09196/) (2024) - [Data Smells: Categories, Causes and Consequences, and Detection of Suspicious Data in AI-based Systems](https://mlsanity.com/paper/2203.10384/) (2022) - [Design Patterns for AI-based Systems: A Multivocal Literature Review and Pattern Repository](https://mlsanity.com/paper/2303.13173/) (2023) - [System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games](https://mlsanity.com/paper/2212.04603/) (2022) - [Towards green AI-based software systems: an architecture-centric approach (GAISSA)](https://mlsanity.com/paper/2307.09964/) (2023) - [How do Machine Learning Models Change?](https://mlsanity.com/paper/2411.09645/) (2024) - ["Project smells" -- Experiences in Analysing the Software Quality of ML Projects with mllint](https://mlsanity.com/paper/2201.08246/) (2022) - [Assessing the Quality of Computational Notebooks for a Frictionless Transition from Exploration to Production](https://mlsanity.com/paper/2205.11941/) (2022) - [How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model Integration](https://mlsanity.com/paper/2502.00429/) (2025) - [Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures](https://mlsanity.com/paper/2601.03988/) (2026) - [A Case Study on AI Engineering Practices: Developing an Autonomous Stock Trading System](https://mlsanity.com/paper/2303.13216/) (2023) - [Quality Issues in Machine Learning Software Systems](https://mlsanity.com/paper/2306.15007/) (2023) - [The Impact of Environment Configurations on the Stability of AI-Enabled Systems](https://mlsanity.com/paper/2408.02825/) (2024) - [RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems](https://mlsanity.com/paper/2603.28735/) (2026) - [Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics](https://mlsanity.com/paper/2606.09957/) (2026) - [From AI Technical Debt to Agentic Technical Debt: A Systematic Mapping of Root Causes and Manifestations in Agentic AI Systems](https://mlsanity.com/paper/2608.01001/) (2026) - [Studying, Identifying, and Fixing Hidden Technical Debt in AI-Intensive Cyber-Physical Systems](https://mlsanity.com/paper/2608.02638/) (2026) ## Abstract (arXiv) Background: With the rising popularity of Artificial Intelligence (AI), there is a growing need to build large and complex AI-based systems in a cost-effective and manageable way. Like with traditional software, Technical Debt (TD) will emerge naturally over time in these systems, therefore leading to challenges and risks if not managed appropriately. The influence of data science and the stochastic nature of AI-based systems may also lead to new types of TD or antipatterns, which are not yet fully understood by researchers and practitioners. Objective: The goal of our study is to provide a clear overview and characterization of the types of TD (both established and new ones) that appear in AI-based systems, as well as the antipatterns and related solutions that have been proposed. Method: Following the process of a systematic mapping study, 21 primary studies are identified and analyzed. Results: Our results show that (i) established TD types, variations of them, and four new TD types (data, model, configuration, and ethics debt) are present in AI-based systems, (ii) 72 antipatterns are discussed in the literature, the majority related to data and model deficiencies, and (iii) 46 solutions have been proposed, either to address specific TD types, antipatterns, or TD in general. Conclusions: Our results can support AI professionals with reasoning about and communicating aspects of TD present in their systems. Additionally, they can serve as a foundation for future research to further our understanding of TD in AI-based systems.