Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

OverviewToolsMetricsAbout the catalogue
Contribute to the catalogue
Contribute to the catalogue

Beta Shapley

18717 citations of this metric
Github
Website
Beta Shapley is a unified data valuation framework that naturally arises from Data Shapley by relaxing the efficiency axiom. The Beta(α, β)-Shapley value considers the pair of hyperparameters (α, β) which decides the weight distribution on [n]. Beta(1,1)-Shapley is the original data Shapley.

Trustworthy AI Relevance

This metric addresses Explainability and Transparency by quantifying relevant system properties. Beta Shapley assigns per-example contribution scores that make the role of specific training data explicit, directly supporting Transparency by revealing which records drive model behavior and enabling interpretable data influence summaries. Those same per-example valuations support Data Governance & Traceability because they enable audit trails (which records affected outcomes), identification/removal of problematic or high-leverage records, and evidence for provenance-based decisions (e.g., paying contributors, enforcing retention/deletion).

About the metric

You can click on the links to see the associated metrics

Objective(s):

Purpose(s):

Lifecycle stage(s):

Target users:

Risk management stage(s):

Github stars:

  • 11500

Github forks:

  • 1800

Modify this metric

catalogue Logos

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.