Linking provenance and its metadata for an AI-based computation using CPM and RO-Crate

<p>This dataset is a prototype implementation of a mechanism for linking provenance information and its metadata, also called provenance of provenance or meta-provenance. This dataset is an <a href="https://www.researchobject.org/ro-crate/">RO-Crate</a> that bundles artifacts of an AI-based computational pipeline. The resulting RO-Crate contains (directly or by a reference) artifacts of the pipeline execution, such as input dataset, intermediate and final results, configuration files, pipeline implementation, log files, or provenance files. The RO-Crate is based on the <a href="https://w3id.org/cpm/ro-crate/0.2">CPM RO-Crate profile</a>, which integrates the <a href="https://doi.org/10.1038/s41597-022-01537-6">Common Provenance Model</a> (CPM) and <a href="https://w3id.org/ro/wfrun/process/0.2">Process Run Crate profile</a>.&nbsp;The description of the AI pipeline and an explanation of how the CPM RO-Crate profile is applied to bundle the pipeline execution artifacts is provided in our <a href="https://doi.org/10.5281/zenodo.7676924">previous work</a>.</p> <p>As this dataset aims to demonstrate the mechanism for linking provenance and meta-provenance, the input dataset used for the AI model training and testing is reduced only to a few images, as the size of the input dataset does not affect the mechanism. The images used in the input are from the <a href="http://gigadb.org/dataset/100439">Camelyon16 dataset</a>.</p> <p>&nbsp;</p>