Yadage and Packtivity - analysis preservation using parametrized workflows
arXiv:1706.01878 · doi:10.1088/1742-6596/898/10/102019
Abstract
Preserving data analyses produced by the collaborations at LHC in a parametrized fashion is crucial in order to maintain reproducibility and re-usability. We argue for a declarative description in terms of individual processing steps - packtivities - linked through a dynamic directed acyclic graph (DAG) and present an initial set of JSON schemas for such a description and an implementation - yadage - capable of executing workflows of analysis preserved via Linux containers.
9 pages