Publication

The current state of the art for provenance in data stream management systems (DSMS) is to provide provenance at a high level of abstraction (such as, from which sensors in a sensor network an aggregated value is derived from). This limitation was imposed by high-throughput requirements and an anticipated lack of application demand for more detailed provenance information. In this work, we first demonstrate by means of well-chosen use cases that this is a misconception, i.e., coarse-grained provenance is in fact insufficient for many application domains. We then analyze the requirements and challenges involved in integrating support for fine-grained provenance into a streaming system and outline a scalable solution for supporting tuple-level provenance in DSMS.

@inproceedings{abc,
	abstract = {The current state of the art for provenance in data stream management
systems (DSMS) is to provide provenance at a high level of abstraction (such as, from
which sensors in a sensor network an aggregated value is derived from). This limitation
was imposed by high-throughput requirements and an anticipated lack of application
demand for more detailed provenance information. In this work, we first demonstrate 
by means of well-chosen use cases that this is a misconception, i.e., coarse-grained
provenance is in fact insufficient for many application domains. We then analyze the
requirements and challenges involved in integrating support for fine-grained provenance
into a streaming system and outline a scalable solution for supporting tuple-level
provenance in DSMS.},
	author = {Boris Glavic and Peter M. Fischer and Nesime Tatbul and Kyumars Sheykh Esmaili},
	booktitle = {Proceedings of the Data Streams and Event Processing Workshop (co-located with BTW 2011), Kaiserslautern, Germany},
	title = {The Case for Fine-Grained Stream Provenance},
	year = {2011}
}