lm2007.bib
@COMMENT{{This file has been generated by bib2bib 1.66}}
@COMMENT{{Command line: bib2bib -oc lm2007.keys -ob lm2007.bib -c 'export = "yes" and year=2007' ../lm.bib ../euprovenance.bib ../ops.bib}}
@ARTICLE{Miles:JOGC06,
AUTHOR = {Simon Miles and Paul Groth and Miguel Branco and Luc Moreau},
TITLE = {The requirements of recording and using provenance in e-Science
experiments},
JOURNAL = {Journal of Grid Computing},
EXPORT = {yes},
PROVENANCE = {yes},
PASOA = {yes},
URL = {http://eprints.ecs.soton.ac.uk/10269/},
DOI = {10.1007/s10723-006-9055-3},
VOLUME = {5},
NUMBER = {1},
PAGES = {1--25},
YEAR = {2007},
ABSTRACT = {In e-Science experiments, it is vital to record the experimental process for later use such as in interpreting results, verifying that the correct process took place or tracing where data came from. The documentation of a process that led to some data is called the provenance of that data, and a provenance architecture is the software architecture for a system that will provide the necessary functionality to record, store and use provenance data. However, there has been little principled analysis of what is actually required of a provenance architecture, so it is impossible to determine the functionality they would ideally support. In this paper, we present use cases for a provenance architecture from current experiments in biology, chemistry, physics and computer science, and analyse the use cases to determine the technical requirements of a generic, application-independent architecture. We propose an architecture that meets these requirements and evaluate a preliminary implementation by attempting to realise one of the use cases.}
}
@PROCEEDINGS{Moreau-Ludaescher:Challenge06,
TITLE = {{Special Issue on the First Provenance Challenge}},
YEAR = {2007},
OPTKEY = {},
BOOKTITLE = {Concurrency and Computation: Practice and Experience},
EDITOR = {Luc Moreau and Bertram Ludaescher},
EUPUB = {yes},
EXPORT = {yes},
VOLUME = {20},
NUMBER = {5},
OPTSERIES = {},
OPTADDRESS = {},
MONTH = APR,
OPTORGANIZATION = {},
PUBLISHER = {Wiley},
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {The first Provenance Challenge was set up in order to provide a
forum for the community to help understand the capabilities
of different provenance systems and the expressiveness of
their provenance representations. To this end, a Functional
Magnetic Resonance Imaging workflow was defined, which
participants had to either simulate or run in order to
produce some provenance representation, from which a set of
identified queries had to be implemented and executed. This
special issue contains the contributions of the sixteen teams
who responded to the challenge, and submitted their inputs. }
}
@ARTICLE{Miles:WEBSEM07,
AUTHOR = {Simon Miles and Sylvia C. Wong and Weijian Fang and Paul
Groth and Klaus-Peter Zauner and Luc Moreau},
TITLE = {Provenance-Based Validation of e-Science Experiments},
JOURNAL = {Web Semantics: Science, Services and Agents
on the World Wide Web},
YEAR = {2007},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/WEBSEM07.pdf},
EXPORT = {yes},
PROVENANCE = {yes},
PASOA = {yes},
MYGRID = {yes},
GRIMOIRES = {yes},
SD = {yes},
OPTKEY = {},
VOLUME = {5},
NUMBER = {1},
ISSN = {1570-8268},
PAGES = {28--38},
DOI = {doi:10.1016/j.websem.2006.11.003},
OPTMONTH = {},
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {E-science experiments typically involve many distributed services maintained by different organisations. After an experiment has been executed,
it is useful for a scientist to verify that the execution was performed correctly or is compatible with some existing experimental criteria or standards,
not necessarily anticipated prior to execution. Scientists may also want to review and verify experiments performed by their colleagues. There are
no existing frameworks for validating such experiments in today's e-science systems. Users therefore have to rely on error checking performed
by the services, or adopt other ad hoc methods. This paper introduces a platform-independent framework for validating workflow executions.
The validation relies on reasoning over the documented provenance of experiment results and semantic descriptions of services advertised in a
registry. This validation process ensures experiments are performed correctly, and thus results generated are meaningful. The framework is tested
in a bioinformatics application that performs protein compressibility analysis.}
}
@ARTICLE{Editorial:Challenge06,
AUTHOR = {Luc Moreau and
Bertram Lud\"ascher and
Ilkay Altintas and
Roger S. Barga and
Shawn Bowers and
Steven Callahan and
George {Chin Jr.} and
Ben Clifford and
Shirley Cohen and
Sarah Cohen-Boulakia and
Susan Davidson and
Ewa Deelman and
Luciano Digiampietri and
Ian Foster and
Juliana Freire and
James Frew and
Joe Futrelle and
Tara Gibson and
Yolanda Gil and
Carole Goble and
Jennifer Golbeck and
Paul Groth and
David A. Holland and
Sheng Jiang and
Jihie Kim and
David Koop and
Ales Krenek and
Timothy McPhillips and
Gaurang Mehta and
Simon Miles and
Dominic Metzger and
Steve Munroe and
Jim Myers and
Beth Plale and
Norbert Podhorszki and
Varun Ratnakar and
Emanuele Santos and
Carlos Scheidegger and
Karen Schuchardt and
Margo Seltzer and
Yogesh L. Simmhan and
Claudio Silva and
Peter Slaughter and
Eric Stephan and
Robert Stevens and
Daniele Turi and
Huy Vo and
Mike Wilde and
Jun Zhao and
Yong Zhao
},
TITLE = {{The First Provenance Challenge}},
JOURNAL = {Concurrency and Computation: Practice and Experience},
YEAR = {2007},
EUPUB = {yes},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/challenge-editorial.pdf},
PASOA = {yes},
EXPORT = {yes},
OPTKEY = {},
VOLUME = {20},
NUMBER = {5},
PAGES = {409--418},
MONTH = APR,
OPTNOTE = {},
DOI = {DOI: 10.1002/cpe.1233},
OPTANNOTE = {},
SOCA = {yes},
ABSTRACT = {The first Provenance Challenge was set up in order to provide a forum for the community to help understand the capabilities of different provenance systems
and the expressiveness of their provenance representations.
To this end, a Functional
Magnetic Resonance Imaging workflow was defined, which participants
had to either simulate or run in order to produce some provenance
representation, from which a set of identified queries had to be
implemented and executed. Sixteen teams responded to the
challenge, and submitted their inputs. In this paper, we present
the challenge workflow and queries, and summarise the participants
contributions.}
}
@ARTICLE{OPA:Challenge06,
AUTHOR = {Simon Miles and Paul Groth and Steve Munroe and Sheng Jiang
and Thibaut Assandri and Luc Moreau},
TITLE = {{Extracting Causal Graphs from an Open Provenance Data Model}},
JOURNAL = {Concurrency and Computation: Practice and Experience},
YEAR = {2007},
EUPUB = {yes},
PASOA = {yes},
EXPORT = {yes},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/miles-ccpe07.pdf},
OPTKEY = {},
VOLUME = {20},
NUMBER = {5},
PAGES = {577--586},
MONTH = APR,
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {The open provenance architecture (OPA) approach to the challenge
was distinct in several regards. In particular, it is based on an
open, well-defined data model and architecture, allowing different
components of the challenge workflow to independently record
documentation, and for the workflow to be executed in any
environment. Another noticeable feature is that we distinguish
between the data recorded about what has occurred, \emph{process
documentation}, and the \emph{provenance} of a data item, which is
all that caused the data item to be as it is and is obtained as the
result of a query over process documentation. This distinction
allows us to tailor the system to separately best address the
requirements of recording and querying documentation. Other
notable features include the explicit recording of causal
relationships between both events and data items, an
interaction-based world model, intensional definition of data items
in queries rather than relying on explicit naming mechanisms, and
\emph{styling} of documentation to support non-functional
application requirements such as reducing storage costs or ensuring
privacy of data. In this paper we describe how each of these
features aid us in answering the challenge provenance queries.}
}
@ARTICLE{Fang:CCPE07,
AUTHOR = {Weijian Fang and Simon Miles and Luc Moreau},
TITLE = {Performance Analysis of a Semantics-Enabled Service Registry},
JOURNAL = {Concurrency and Computation: Practice and Experience},
YEAR = 2007,
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/grimoires-ccpe07.pdf},
VOLUME = 20,
NUMBER = 3,
PAGES = {207--224},
MONTH = MAR,
EXPORT = {yes},
DOI = {DOI: 10.1002/cpe.1204},
ABSTRACT = {Service discovery is a critical task in service-oriented
architectures. In this paper, we study grimoires, the
semantics-enabled service registry of the OMII software
distribution, from a performance perspective. We study the
scalability of grimoires against the amount of information that
has been published into it. The methodology we use and the data we
present are helpful for researchers to understand the performance
characteristics of the registry and, more generally, of
semantics-enabled service discovery. Based on this
experimentation, we claim that grimoires is an efficient
semantics-aware service discovery engine.}
}
@INPROCEEDINGS{Miles:AAMAS07,
AUTHOR = {Simon Miles and Steve Munroe and Michael Luck and Luc Moreau},
TITLE = {Modelling the Provenance of Data in Autonomous Systems},
OPTCROSSREF = {},
OPTKEY = {},
BOOKTITLE = {Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS'07)},
OPTPAGES = {},
YEAR = {2007},
PASOA = {yes},
EXPORT = {yes},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/aamas07.pdf},
OPTEDITOR = {},
OPTVOLUME = {},
OPTNUMBER = {},
OPTSERIES = {},
OPTADDRESS = {},
OPTMONTH = {},
OPTORGANIZATION = {},
OPTPUBLISHER = {},
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {Determining the provenance of data, i.e. the process that led to
that
data, is vital in many disciplines. For example, in science, the process
that produced a given result must be demonstrably rigorous for
the result to be deemed reliable. A provenance system supports applications
in recording adequate documentation about process executions
to answer queries regarding provenance, and provides functionality
to perform those queries. Several provenance systems are
being developed, but all focus on systems in which the components
are reactive, for example Web Services that act on the basis
of a request, job submission system, etc. This limitation means that
questions regarding the motives of autonomous actors, or agents, in
such systems remain unanswerable in the general case. Such questions
include: who was ultimately responsible for a given effect,
what was their reason for initiating the process and does the effect
of a process match what was intended to occur by those initiating
the process? In this paper, we address this limitation by integrating
two solutions: a generic, re-usable framework for representing
the provenance of data in service-oriented architectures and a
model for describing the goal-oriented delegation and engagement
of agents in multi-agent systems. Using these solutions, we present
algorithms to answer common questions regarding responsibility
and success of a process and evaluate the approach with a simulated
healthcare example.}
}
@INPROCEEDINGS{Miles:Methodo07,
AUTHOR = {Simon Miles and Paul Groth and Steve Munroe and Michael Luck and
Luc Moreau},
TITLE = {{AgentPrIMe: Adapting MAS Designs to Build Confidence}},
OPTCROSSREF = {},
OPTKEY = {},
BOOKTITLE = {Agent-Oriented Software Engineering (AOSE'07)},
OPTPAGES = {},
YEAR = {2007},
PASOA = {yes},
EXPORT = {yes},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/aose07.pdf},
OPTEDITOR = {},
OPTVOLUME = {},
OPTNUMBER = {},
OPTSERIES = {},
OPTADDRESS = {},
OPTMONTH = {},
OPTORGANIZATION = {},
OPTPUBLISHER = {},
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {The products of systems cannot always be judged at face value: the
process by which they were obtained is also important. For
instance, the rigour of a scientific experiment, the ethics with
which an item was manufactured and the use of services with
particular licens- ing all affect how the results of those
processes are valued. However, in systems of autonomous agents, and
particularly those with multiple independent contributory
organisations, the ability of agents to choose how their goals or
responsibilities are achieved can hide such process qualities from
users. The issue of ensuring that users are able to check these
process qualities is a software engineering one: the developer must
decide to ensure that adequate data is recorded regarding processes
and safeguards implemented to ensure accuracy. In this paper, we
describe AgentPrIMe, an adjunct to existing agent-oriented
methodologies that allows system designs to be adapted to give
users confidence in the results they produce. It does this by
adaptations to the design for documenta- tion, corroboration,
independent storage and accountability.}
}
@INPROCEEDINGS{Miles:eScience07,
AUTHOR = {Simon Miles and Ewa Deelman and Paul Groth and Karan Vahi and
Gaurang Mehta and Luc Moreau},
TITLE = {Connecting Scientific Data to Scientific Experiments with
Provenance},
OPTCROSSREF = {},
OPTKEY = {},
BOOKTITLE = {Proceedings of the third IEEE International Conference on
e-Science and Grid Computing (e-Science'07)},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/escience07.pdf},
YEAR = {2007},
OPTEDITOR = {},
OPTVOLUME = {},
OPTNUMBER = {},
OPTSERIES = {},
ADDRESS = {Bangalore, India},
PUBLISHER = {IEEE Computer Society},
MONTH = DEC,
PAGES = {179--186},
DOI = {http://dx.doi.org/10.1109/E-SCIENCE.2007.22},
OPTNOTE = {},
OPTANNOTE = {},
EXPORT = {yes},
SOCA = {yes},
PASOA = {yes},
ABSTRACT = {As scientific workflows, and the data they operate on, grow in size and complexity, the task of defining how those workflows should execute (which resources they should use, where those resources should be in preparation for processing etc.) becomes proportionally more difficult. While `workflow compilers', such as Pegasus, aid greatly in reducing this burden, a further problem arises: as specifying the details of execution is now automatic, a workflow's results are harder to interpret, as they are in part due to the specifics of execution. By automating the steps between the original experiment design and its results, we lose the connection between them, making results harder to interpret. To reconnect the scientific data with the original experiment, we argue that scientists should have access to the full provenance of their data, including not only parameters, input data and intermediary results, but also the abstract experiment, refined into a concrete execution by the `workflow compiler'. In this paper, we describe our preliminary work on adapting Pegasus to capture the process of workflow refinement in the PASOA provenance system.}
}
@TECHREPORT{opm:2007,
AUTHOR = {Luc Moreau and Juliana Freire and Joe Futrelle
and Robert E. McGrath and Jim Myers
and Patrick Paulson},
TITLE = {The Open Provenance Model (v1.00)},
INSTITUTION = {University of Southampton},
YEAR = {2007},
PASOA = {yes},
EXPORT = {yes},
URL = {http://eprints.ecs.soton.ac.uk/14979/1/opm.pdf},
OPTKEY = {},
OPTTYPE = {},
OPTNUMBER = {},
OPTADDRESS = {},
MONTH = DEC,
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {In this paper, we introduce the Open Provenance Model , a model for
provenance which meets the following requirements: (1) To
allow provenance information to be exchanged between systems,
by means of a compatibility layer based on a shared
provenance model. (2) To allow developers to build and share
tools that operate on such provenance model. (3) To define
the model in a precise, technology-agnostic manner. (4) To
support a digital representation of provenance for any
``thing'', whether produced by computer systems or not. (5)
To define a core set of rules that identify the valid
inferences that can be made on provenance graphs.}
}
@ARTICLE{Gil-Deelman:IEEE07,
AUTHOR = {Yolanda Gil and Ewa Deelman and Mark Ellisman and Thomas
Fahringer and Geoffrey Fox and Dennis Gannon and Carole Goble
and Miron Livny and Luc Moreau and Jim Myers},
TITLE = {Examining the Challenges of Scientific Workflows},
JOURNAL = {IEEE Computer},
YEAR = {2007},
EXPORT = {yes},
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/computer07.pdf},
OPTKEY = {},
VOLUME = {40},
NUMBER = {12},
PAGES = {26--34},
MONTH = DEC,
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {Workflows have recently emerged as a paradigm
for representing and managing complex distributed
scientific computations and therefore accelerate the
pace of scientific progress. A recent workshop on the
Challenges of Scientific Workflows, sponsored by the
National Science Foundation and held on May 1-2,
2006, brought together domain scientists, computer
scientists, and social scientists to discuss requirements
of future scientific applications and the challenges that
they present to current workflow technologies. This
paper reports on the discussions and recommendations
of the workshop, the full report can be found at
http://www.isi.edu/nsf-workflows06.}
}
@INBOOK{Vazquez:book07,
AUTHOR = {J. V\'azquez-Salceda and S. Alvarez and T. Kifor and
L. Z. Varga and S. Miles and L. Moreau and S. Willmott},
ALTEDITOR = {},
TITLE = {In R. Annicchiarico, U. Cort\'es, C. Urdiales (eds.) Agent
Technology and E-Health},
CHAPTER = {EU PROVENANCE Project: An Open Provenance Architecture for
Distributed Applications},
PUBLISHER = {Birkh\"auser Verlag AG},
YEAR = {2007},
EXPORT = {yes},
OPTKEY = {},
OPTVOLUME = {},
OPTNUMBER = {},
SERIES = {Whitestein Series in Software Agent Technologies and Autonomic
Computing.},
OPTTYPE = {},
ADDRESS = {Switzerland},
OPTEDITION = {},
ISBN = {ISBN 978-3-7643-85546-0},
MONTH = DEC,
URL = {http://www.ecs.soton.ac.uk/~lavm/papers/healthbook07.pdf},
OPTPAGES = {},
OPTNOTE = {},
OPTANNOTE = {},
ABSTRACT = {The concept of provenance is already well understood in the study
of fine art where it refers to the trusted, documented
history of some work of art. Given that documented history,
the object attains an authority that allows scholars to
understand and appreciate its importance and context relative
to other works of art. This same concept of provenance may
also be applied to data and information generated within a
computer system; particularly when the information is subject
to regulatory control over an extended period of
time. Today’s distributed architectures (not only Agent
technologies, but alsoWeb Services’ and GRID architectures)
suffer from limitations, such as lack of mechanisms to trace
results. Provenance enables users to trace how a particular
result has been arrived at by identifying the individual and
aggregated services that produced a particular output. In
this chapter we present the main results of the EU PROVENANCE
project and how these can be valuable in agent-mediated
healthcare applications. For the latter we describe the Organ
Transplant Management Application (OTMA), one of the
demonstrator applications developed.}
}