lm2009.bib

@COMMENT{{This file has been generated by bib2bib 1.66}}

@COMMENT{{Command line: bib2bib -oc lm2009.keys -ob lm2009.bib -c 'export = "yes" and year=2009' ../lm.bib ../euprovenance.bib ../ops.bib}}

@ARTICLE{Groth:TOIT09,
  AUTHOR = {Paul Groth and Simon Miles and Luc Moreau},
  TITLE = {{A Model of Process Documentation to Determine Provenance in Mash-ups}},
  PASOA = {yes},
  EXPORT = {yes},
  JOURNAL = {Transactions on Internet Technology (TOIT)},
  URL = {http://www.ecs.soton.ac.uk/~lavm/papers/toit09.pdf},
  YEAR = {2009},
  OPTKEY = {},
  VOLUME = {9},
  NUMBER = {1},
  DOI = {http://doi.acm.org/10.1145/1462159.1462162},
  ISSN = {1533-5399},
  PAGES = {1--31},
  PUBLISHER = {ACM},
  ADDRESS = {New York, NY, USA},
  OPTNOTE = {},
  OPTANNOTE = {},
  ABSTRACT = {Through technologies such as RSS (Really Simple Syndication), Web
            Services, and AJAX (Asynchronous JavaScript And XML), the Internet
            has facilitated the emergence of applications that are composed
            from a variety of services and data sources. Through tools such as
            Yahoo Pipes, these ``mash-ups'' can be composed in a dynamic,
            just-in-time manner from components provided by multiple
            institutions (i.e. Google, Amazon, your neighbour). However, when
            using these applications, it is not apparent where data comes from
            or how it is processed. Thus, to inspire trust and confidence in
            mash-ups, it is critical to be able to analyse their processes
            after the fact. These trailing analyses, in particular the
            determination of the provenance of a result (i.e. the process that
            led to it), are enabled by process documentation, which is
            documentation of an application's past process created by the
            components of that application at execution time. In this paper, we
            define a generic conceptual data model that supports the autonomous
            creation of attributable, factual process documentation for dynamic
            multi-institutional applications. The data model is instantiated
            using two Internet formats, OWL and XML, and is evaluated with
            respect to questions about the provenance of results generated by a
            complex bioinformatics mash-up.}
}

@ARTICLE{Groth:TPDS09,
  AUTHOR = {Paul Groth and Luc Moreau},
  TITLE = {Recording Process Documentation for Provenance},
  JOURNAL = {IEEE Transactions on Parallel and Distributed Systems},
  YEAR = {2009},
  PASOA = {yes},
  EXPORT = {yes},
  VOLUME = {In publication},
  PUBLISHER = {IEEE Computer Society},
  ADDRESS = {Los Alamitos, CA, USA},
  DOI = {http://doi.ieeecomputersociety.org/10.1109/TPDS.2008.215},
  URL = {http://www.ecs.soton.ac.uk/~lavm/papers/tpds09.pdf},
  ISSN = {1045-9219},
  OPTKEY = {},
  OPTVOLUME = {},
  OPTNUMBER = {},
  OPTPAGES = {},
  MONTH = SEP,
  OPTNOTE = {},
  OPTANNOTE = {},
  ABSTRACT = {Scientific and business communities are adopting large scale distributed systems as a means to solve a wide range of resource intensive tasks. These communities also have requirements in terms of provenance. We define the provenance of a result produced by a distributed system as the process that led to that result. This paper describes a protocol for recording documentation of a distributed system's execution. The distributed protocol guarantees that documentation with characteristics suitable for accurately determining the provenance of results is recorded. These characteristics are confirmed through a number of proofs based on an abstract state machine formalisation.}
}

@ARTICLE{Miles:TOSEM09,
  AUTHOR = {Simon Miles and Paul Groth and Steve Munroe and Luc Moreau},
  TITLE = {PrIMe: A Methodology for Developing Provenance-Aware Applications},
  JOURNAL = {ACM Transactions on Software Engineering and Methodology},
  YEAR = {2009},
  OPTKEY = {},
  OPTVOLUME = {},
  OPTNUMBER = {},
  URL = {http://eprints.ecs.soton.ac.uk/17450/},
  EXPORT = {yes},
  OPTPAGES = {},
  MONTH = JUN,
  OPTNOTE = {},
  OPTANNOTE = {},
  ABSTRACT = {Provenance refers to the past processes that brought about a given (version of an) object, item or
entity. By knowing the provenance of data, users can often better understand, trust, reproduce,
and validate it. A provenance-aware application has the functionality to answer questions regard-
ing the provenance of the data it produces, by using documentation of past processes. PrIMe is a
software engineering technique for adapting application designs to enable them to interact with a
provenance middleware layer, thereby making them provenance-aware. In this article, we specify
the steps involved in applying PrIMe, analyse its effectiveness, and illustrate its use with two case
studies, in bioinformatics and medicine.}
}

@UNPUBLISHED{ecs17282,
  MONTH = {April},
  TITLE = {The Foundations of the Open Provenance Model},
  AUTHOR = {Luc Moreau and Natalia Kwasnikowska and Jan Van den Bussche},
  YEAR = {2009},
  EXPORT = {yes},
  URL = {http://eprints.ecs.soton.ac.uk/17282/},
  ABSTRACT = {The Open Provenance Model (OPM) is a community-driven data model for Provenance that is designed to support inter-operability of provenance technology. Underpinning OPM, is a notion of directed acyclic graph, used to represent data products and processes involved in past computations, and causal dependencies between these.  The Open Provenance Model was derived following two ``Provenance Challenges'', international, multi-disciplinary activities trying to investigate how to exchange information between multiple systems supporting provenance and how to query it.  The OPM design was mostly driven by practical and pragmatic considerations, and is being tested in a third Provenance Challenge, which has just started. The purpose of this paper is to investigate the theoretical foundations of this data model. The formalisation consists of a set-theoretic definition of the data model, a definition of the inferences by transitive closure that are permitted, a formal description of how the model can be used to express dependencies in past computations, and finally, a description of the kind of time-based inferences that are supported. A novel element that OPM introduces is the concept of an account, by which multiple descriptions of a same execution are allowed to co-exist in a same graph. Our formalisation gives a precise meaning to such accounts and associated notions of alternate and refinement.}
}