# Debugging Machine Learning Pipelines

arXiv: https://arxiv.org/abs/2002.04640 · HTML: https://mlsanity.com/paper/2002.04640/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [Explanation-Based Human Debugging of NLP Models: A Survey](https://mlsanity.com/paper/2104.15135/) (2021)
- [Interpretable Data-Based Explanations for Fairness Debugging](https://mlsanity.com/paper/2112.09745/) (2021)
- [Preventing Machine Learning Poisoning Attacks Using Authentication and Provenance](https://mlsanity.com/paper/2105.10051/) (2021)

## Abstract (arXiv)

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce incorrect results. Inferring the root cause of failures and unexpected behavior is challenging, usually requiring much human thought, and is both time-consuming and error-prone. We propose a new approach that makes use of iteration and provenance to automatically infer the root causes and derive succinct explanations of failures. Through a detailed experimental evaluation, we assess the cost, precision, and recall of our approach compared to the state of the art. Our source code and experimental data will be available for reproducibility and enhancement.