# Providing Assurance and Scrutability on Shared Data and Machine Learning Models with Verifiable Credentials

arXiv: https://arxiv.org/abs/2105.06370 · HTML: https://mlsanity.com/paper/2105.06370/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 64 references that are in the map.
- First posted on arXiv 13 May 2021.

## Builds on (most cited first, 16 of 16)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims](https://mlsanity.com/paper/2004.07213/) (2020)
- [Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure](https://mlsanity.com/paper/2010.13561/) (2020)
- [Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?](https://mlsanity.com/paper/1912.08320/) (2019)
- [Privacy and Trust Redefined in Federated Machine Learning](https://mlsanity.com/paper/2103.15753/) (2021)
- [Towards Traceability in Data Ecosystems using a Bill of Materials Model](https://mlsanity.com/paper/1904.04253/) (2019)
- [Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform](https://mlsanity.com/paper/1810.07159/) (2018)
- [A framework for fostering transparency in shared artificial intelligence models by increasing visibility of contributions](https://mlsanity.com/paper/2103.03610/) (2021)
- [Defending against Sybil Devices in Crowdsourced Mapping Services](https://mlsanity.com/paper/1508.00837/) (2015)
- [Measurement in AI Policy: Opportunities and Challenges](https://mlsanity.com/paper/2009.09071/) (2020)
- [Certifying Provenance of Scientific Datasets with Self-sovereign Identity and Verifiable Credentials](https://mlsanity.com/paper/2004.02796/) (2020)
- [Full-text Search for Verifiable Credential Metadata on Distributed Ledgers](https://mlsanity.com/paper/1909.02895/) (2019)

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

- [Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering](https://mlsanity.com/paper/2209.04963/) (2022)
- [An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Face](https://mlsanity.com/paper/2502.04484/) (2025)
- [Responsible-AI-by-Design: a Pattern Collection for Designing Responsible AI Systems](https://mlsanity.com/paper/2203.00905/) (2022)

## Abstract (arXiv)

Adopting shared data resources requires scientists to place trust in the originators of the data. When shared data is later used in the development of artificial intelligence (AI) systems or machine learning (ML) models, the trust lineage extends to the users of the system, typically practitioners in fields such as healthcare and finance. Practitioners rely on AI developers to have used relevant, trustworthy data, but may have limited insight and recourse. This paper introduces a software architecture and implementation of a system based on design patterns from the field of self-sovereign identity. Scientists can issue signed credentials attesting to qualities of their data resources. Data contributions to ML models are recorded in a bill of materials (BOM), which is stored with the model as a verifiable credential. The BOM provides a traceable record of the supply chain for an AI system, which facilitates on-going scrutiny of the qualities of the contributing components. The verified BOM, and its linkage to certified data qualities, is used in the AI Scrutineer, a web-based tool designed to offer practitioners insight into ML model constituents and highlight any problems with adopted datasets, should they be found to have biased data or be otherwise discredited.