1. A benchmark for interpretability methods in deep neural networks;hooker;arXiv preprint arXiv 1806 10976,2018
2. Hidden technical debt in machine learning systems;sculley;Advances in neural information processing systems,2015
3. Troubling trends in machine learning scholarship;lipton;arXiv preprint arXiv 1807 03341,2018
4. Underspecification presents challenges for credibility in modern machine learning;d’amour;arXiv preprint arXiv 2011 00177,2020
5. Using multiple models to understand data;patel;Twenty-Second International Joint Conference on Artificial Intelligence,2011