Metadata preservation

metric

ML-A2-01M: Metadata remains available even if the ML model is no longer available. Test: 1) Programmatic assessment of the preservation of metadata of a data object can only be tested if the object is deleted or replaced. So, this test is only applicable for deleted, replaced or obsolete objects. *Note: Use automatic tool to assess this metric and enter the result here.*

Principle: A

Rationale: This metric determines if the metadata will be preserved even when the ML models they represent are no longer available, replaced or lost. The metric applies at a repository rather than the level of an individual research object (ML model). See the FAIR assessment specification for more details.

FAIR Metrics: A2

View Assessments

Associated Rubrics (1)

FAIR for Machine Learning Models

This rubric consists of assessment metrics that evaluate the FAIR maturity of ML models. The metrics...

FAIR machine learning model FAIR assessment NFDI4DataScience