Publications by Boris Glavic

@inproceedings{abc,
	author = {Boris Glavic and Kyumars Sheykh Esmaili and Peter M. Fischer and Nesime Tatbul},
	booktitle = {The 7th ACM International Conference on Distributed Event-Based Systems, DEBS {\textquoteright}13, Arlington, TX},
	title = {Ariadne: managing fine-grained provenance on data streams.},
	url = {http://doi.acm.org/10.1145/2488222.2488256},
	year = {2013}
}

@inproceedings{abc,
	author = {Boris Glavic and Ren{\'e}e J. Miller and Gustavo Alonso},
	booktitle = {In Search of Elegance in the Theory and Practice of Computation - Essays Dedicated to Peter Buneman},
	title = {Using SQL for Efficient Generation and Querying of Provenance Information.},
	url = {http://dx.doi.org/10.1007/978-3-642-41660-6_16},
	year = {2013}
}

@techreport{abc,
	author = {Boris Glavic and Kyumars Sheykh Esmaili and Peter M. Fischer and Nesime Tatbul},
	title = {Ariadne: Managing Fine-Grained Provenance on Data Streams},
	year = {2012}
}

@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}
}

@inproceedings{abc,
	author = {Boris Glavic and Jiang Du and Ren{\'e}e J. Miller and Gustavo Alonso and Laura M. Haas},
	booktitle = {PVLDB},
	title = {Debugging Data Exchange with Vagabond.},
	url = {http://www.vldb.org/pvldb/vol4/p1383-glavic.pdf},
	year = {2011}
}

@article{abc,
	author = {Boris Glavic and Gustavo Alonso and Ren{\'e}e Miller and Laura M. Haas},
	journal = {PVLDB},
	title = {TRAMP: Understanding the Behavior of Schema Mappings through Provenance.},
	year = {2010}
}

@inproceedings{abc,
	abstract = {In this demonstration we present the Perm provenance management system (PMS). Perm is capable of computing, storing and querying provenance information for the relational data model. Provenance is computed by using query rewriting techniques to annotate tuples with provenance information. Thus, provenance data and provenance computations are represented as relational data and queries and hence can be queried, stored and optimized using standard relational database techniques. This demo will show the complete Perm system and let attendants examine in detail the process of query rewriting and provenance retrieval on what is today the most complete data provenance system available.},
	author = {Boris Glavic and Gustavo Alonso},
	booktitle = {Demo},
	title = {The Perm Provenance Management System in Action},
	url = {http://doi.acm.org/10.1145/1559845.1559980},
	year = {2009}
}

@inproceedings{abc,
	abstract = {
        Data provenance is essential in applications such as scientific
        computing, curated databases, and data warehouses. Several
        systems have been developed that provide provenance
        functionality for the relational data model. These systems
        support only a small subset of SQL, a severe limitation in
        practice since most of the application domains that benefit from
        provenance information use complex queries. Such queries
        typically involve nested subqueries, aggregation and/or user
        defined functions. Without support for these constructs, a
        provenance management system is of limited use.

        In this paper we address this limitation by exploring the
        problem of provenance derivation when complex queries are
        involved. More precisely, we demonstrate that the widely used
        definition of Why-provenance fails in the presence of nested
        subqueries, and show how the definition can be modified to
        produce meaningful results for nested subqueries. We further
        present query rewrite rules to transform an SQL query into a
        query propagating provenance. The solution introduced in this
        paper allows us to track provenance information for a far wider
        subset of SQL than any of the existing approaches. We have
        incorporated these ideas into the Perm provenance management
        system engine and used it to evaluate the feasibility and
        performance of our approach.
      },
	author = {Boris Glavic and Gustavo Alonso},
	booktitle = {Research},
	title = {Provenance for nested subqueries},
	url = {http://doi.acm.org/10.1145/1516360.1516472},
	year = {2009}
}

@inproceedings{abc,
	author = {Boris Glavic and Gustavo Alonso},
	booktitle = {Proceedings of the 25th International Conference on Data Engineering, ICDE 2009},
	title = {Perm: Processing Provenance and Data on the Same Data Model through Query Rewriting.},
	url = {http://dx.doi.org/10.1109/ICDE.2009.15},
	venue = {Shanghai, China},
	year = {2009}
}