# Prescriptive and Descriptive Approaches to Machine-Learning Transparency

arXiv: https://arxiv.org/abs/2204.13582 · HTML: https://mlsanity.com/paper/2204.13582/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 27 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards](https://mlsanity.com/paper/1805.03677/) (2018)
- [A Step Toward Quantifying Independently Reproducible Machine Learning Research](https://mlsanity.com/paper/1909.06674/) (2019)
- [On Aliased Resizing and Surprising Subtleties in GAN Evaluation](https://mlsanity.com/paper/2104.11222/) (2021)
- [Mind the Pad -- CNNs can Develop Blind Spots](https://mlsanity.com/paper/2010.02178/) (2020)
- [The Dataset Nutrition Label (2nd Gen): Leveraging Context to Mitigate Harms in Artificial Intelligence](https://mlsanity.com/paper/2201.03954/) (2022)
- [Studying Software Engineering Patterns for Designing Machine Learning Systems](https://mlsanity.com/paper/1910.04736/) (2019)
- [Experiences with Improving the Transparency of AI Models and Services](https://mlsanity.com/paper/1911.08293/) (2019)
- [ABOUT ML: Annotation and Benchmarking on Understanding and Transparency of Machine Learning Lifecycles](https://mlsanity.com/paper/1912.06166/) (2019)
- [Perspectives on Machine Learning from Psychology's Reproducibility Crisis](https://mlsanity.com/paper/2104.08878/) (2021)

## Built on by (most cited first, 7 of 7)

- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering](https://mlsanity.com/paper/2209.04963/) (2022)
- [Use case cards: a use case reporting framework inspired by the European AI Act](https://mlsanity.com/paper/2306.13701/) (2023)
- [Saliency Cards: A Framework to Characterize and Compare Saliency Methods](https://mlsanity.com/paper/2206.02958/) (2022)
- [Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain](https://mlsanity.com/paper/2406.14758/) (2024)
- [Ex-Ante Assessment of Discrimination in Dataset](https://mlsanity.com/paper/2208.07918/) (2022)
- [AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation](https://mlsanity.com/paper/2604.09617/) (2026)

## Abstract (arXiv)

Specialized documentation techniques have been developed to communicate key facts about machine-learning (ML) systems and the datasets and models they rely on. Techniques such as Datasheets, FactSheets, and Model Cards have taken a mainly descriptive approach, providing various details about the system components. While the above information is essential for product developers and external experts to assess whether the ML system meets their requirements, other stakeholders might find it less actionable. In particular, ML engineers need guidance on how to mitigate potential shortcomings in order to fix bugs or improve the system's performance. We survey approaches that aim to provide such guidance in a prescriptive way. We further propose a preliminary approach, called Method Cards, which aims to increase the transparency and reproducibility of ML systems by providing prescriptive documentation of commonly-used ML methods and techniques. We showcase our proposal with an example in small object detection, and demonstrate how Method Cards can communicate key considerations for model developers. We further highlight avenues for improving the user experience of ML engineers based on Method Cards.