@ARTICLE{Barga2008,
  author = {Roger S. Barga and Luciano A. Digiampietri},
  title = {Automatic Capture and Efficient Storage of eScience Experiment Provenance},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2008},
  volume = {20},
  pages = {419-429},
  number = {5},
  abstract = {Workflow is playing an increasingly important role in conducting e-Science
	experiments, but most commercial systems lack the necessary support
	for the collection and management of provenance data. We argue that
	eScience provenance data should be automatically generated by the
	workflow enactment engine and managed over time by an underlying
	storage service. In this paper, we introduce a layered model for
	workflow execution provenance, which allows navigation from an abstract
	model of the experiment to instance data collected during a specific
	experiment run. We outline modest extensions to a commercial workflow
	engine so it will automatically capture this provenance data at runtime.
	We then present an approach to store this provenance data in a relational
	database engine. Finally, we identify important properties of provenance
	data captured by our model that can significantly reduce the amount
	of storage required, and demonstrate we can reduce the size of provenance
	data captured from an actual experiment to 0.4\% of the original
	size, with modest performance overhead.},
  doi = {http://dx.doi.org/10.1002/cpe.1235},

}