lm2009.bib
@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -oc lm2009.keys -ob lm2009.bib -c 'export = "yes" and year=2009' lm.bib ../euprovenance.bib ../ops.bib}}
@comment{{This file has been generated by bib2bib 1.99}}
@comment{{Command line: bib2bib -ob lm.bib -oc lm.keys -c 'export = "yes"' ../lm.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)},
doi = {10.1145/1462159.1462162},
eprints = {https://eprints.soton.ac.uk/270861/},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/toit09.pdf},
year = {2009},
optkey = {},
volume = {9},
number = {1},
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},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
doi = {10.1109/TPDS.2008.215},
eprints = {https://eprints.soton.ac.uk/267309/},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/tpds09.pdf},
issn = {1045-9219},
optkey = {},
volume = {20},
number = {9},
pages = {1246--1259},
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.}
}
@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},
eprints = {https://eprints.soton.ac.uk/267282/},
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.}
}
@misc{Moreau:GOV09,
key = {Governance},
author = {Luc Moreau and Juliana Freire and Joe Futrelle and Jim Myers and Patrick Paulson},
title = {Governance of the Open Provenance Model},
opthowpublished = {},
month = jun,
year = {2009},
optnote = {},
optannote = {},
url = {http://twiki.ipaw.info/pub/OPM/WebHome/governance.pdf},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/governance.pdf},
export = {yes},
abstract = {The Open Provenance Model (OPM) was originally crafted by the five
authors in a meeting held in Salt Lake City in August 2007. OPM v1.00 [1] was
released to the community in December 2007. The first OPM workshop in June 2008
involved some twenty participants discussing issues related this specification, and led
to a revised specification, referred to as OPM v1.01. From the outset, the original authors' intent has been to define a data model that
is open from an inter-operability viewpoint but also with respect to the community
of its contributors, reviewers and users. The early public release of v1.00, the first
OPM workshop and the revised specification v1.01 are testimony of the community
focus that is intended for OPM. So far, our approach to discuss changes and agree on
revisions has been adhoc. The purpose of this document is to outline a governance
model for OPM.}
}
@misc{groth:collections09,
key = {groth:collections},
author = {Paul Groth and Simon Miles and Paolo Missier and Luc Moreau},
title = {A Proposal for Handling Collections in the Open Provenance Model},
opthowpublished = {},
month = jun,
year = {2009},
optnote = {},
optannote = {},
export = {yes},
url = {http://mailman.ecs.soton.ac.uk/pipermail/provenance-challenge-ipaw-info/2009-June/000120.html},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/collections-opm09.pdf}
}
@misc{miles:dc09,
optkey = {miles:dc},
author = {Simon Miles and Luc Moreau and Joe Futrelle},
title = {OPM Profile for Dublin Core Terms (Draft)},
opthowpublished = {},
month = jun,
year = {2009},
optnote = {},
optannote = {},
export = {yes},
url = {http://mailman.ecs.soton.ac.uk/pipermail/provenance-challenge-ipaw-info/2009-June/000124.html},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/dc-opm09.pdf}
}
@inproceedings{EwaDeelman:2009,
author = {{Ewa Deelman} and {Bruce Berriman} and {Ann Chervenak} and {Oscar Corcho} and {Paul Groth} and {Luc Moreau}},
booktitle = {Scientific Data Management},
isbn = {978-1-4200-6980-8},
month = dec,
publisher = {Chapman and Hall/CRC},
series = {Chapman \& Hall/CRC Computational Science},
title = {{Metadata and Provenance Management}},
doi = {10.1201/9781420069815-c12},
year = {2009},
export = {yes},
eprints = {https://arxiv.org/pdf/1005.2643v1.pdf},
local = {https://nms.kcl.ac.uk/luc.moreau/papers/deelman-sdm09.pdf},
abstract = {Scientists today collect, analyze, and generate TeraBytes and PetaBytes of data. These data are often
shared and further processed and analyzed among collaborators. In order to facilitate sharing and data
interpretations, data need to carry with it metadata about how the data was collected or generated, and
provenance information about how the data was processed. This chapter describes metadata and
provenance in the context of the data lifecycle. It also gives an overview of the approaches to metadata
and provenance management, followed by examples of how applications use metadata and provenance in
their scientific processes.}
}