@article{Sahoo2011,
author = {Sahoo, Satya S and Zhao, Jun and Missier, Paolo},
file = {:Users/paolo/Dropbox/Janus/paper-IC2010/response-to-review/SemanticProvenance\_July28\_Satya.pdf:pdf},
journal = {Internet Computing, special issue on Provenance in Web Applications},
title = {{Extending Semantic provenance into the Web of Data}},
volume = {to appear},
year = {2011},
urlpaper={http://www.mendeley.com/download/public/212462/3524567501/eb427e75759297a4bf9e8073ddbc28f7f3518ccc/dl.pdf}
}

@article{Missier2011,
abstract = {The Open Provenance Model is designed to capture relationships amongst data values, and amongst processors that produce or consume those values. While OPM graphs are able to describe aspects of a workflow execution, capturing the structure of the workflows themselves is understandably beyond the scope of the OPM specification, since the graphs may be generated by a broad variety of processes, which may not be formal workflows at all. \% In particular, OPM does not address two questions: firstly, whether for any OPM graph there exists a $\backslash$textit\{plausible\} workflow, in some model, which could have generated the graph. And secondly, which information should be captured as part of an OPM graph that is derived from the execution of some known type of workflow, so that the workflow structure and the execution trace can both be inferred back from the graph. \% Motivated by the need to address the $\backslash$textit\{Third Provenance Challenge\} using Taverna workflows and provenance, in this paper we explore such notion of $\backslash$textit\{lossless-ness\} of OPM graphs relative to Taverna workflows. \% For the first question, we show that Taverna is a suitable model for representing plausible OPM-generating processes. For the second question, we show how augmenting OPM with two types of annotations makes it lossless with respect to Taverna. We support this claim by presenting a two-way mapping between OPM graphs and Taverna workflows.},
author = {Missier, Paolo and Goble, Carole},
doi = {http://dx.doi.org/10.1016/j.future.2010.10.012},
file = {:Users/paolo/Library/Application Support/Mendeley Desktop/Downloaded/Missier, Goble - 2011 - Workflows to Open Provenance Graphs, round-trip.pdf:pdf},
journal = {Future Generation Computer Systems (FGCS)},
keywords = {\#OPM,\#provenance,OPM},
mendeley-tags = {\#OPM,\#provenance},
publisher = {Elsevier},
title = {{Workflows to Open Provenance Graphs, round-trip}},
volume = {in press},
year = {2011}
}

The Open Provenance Model is designed to capture relationships amongst data values, and amongst processors that produce or consume those values. While OPM graphs are able to describe aspects of a workflow execution, capturing the structure of the workflows themselves is understandably beyond the scope of the OPM specification, since the graphs may be generated by a broad variety of processes, which may not be formal workflows at all. % In particular, OPM does not address two questions: firstly, whether for any OPM graph there exists a $\$textit\plausible\ workflow, in some model, which could have generated the graph. And secondly, which information should be captured as part of an OPM graph that is derived from the execution of some known type of workflow, so that the workflow structure and the execution trace can both be inferred back from the graph. % Motivated by the need to address the $\$textit\Third Provenance Challenge\ using Taverna workflows and provenance, in this paper we explore such notion of $\$textit\lossless-ness\ of OPM graphs relative to Taverna workflows. % For the first question, we show that Taverna is a suitable model for representing plausible OPM-generating processes. For the second question, we show how augmenting OPM with two types of annotations makes it lossless with respect to Taverna. We support this claim by presenting a two-way mapping between OPM graphs and Taverna workflows.

@inproceedings{Missier2010a,
address = {Lausanne, Switzerland},
author = {Missier, P. and Paton, N. and Belhajjame, K.},
booktitle = {Procs. EDBT},
file = {:Users/paolo/Library/Application Support/Mendeley Desktop/Downloaded/Missier, Paton, Belhajjame - 2010 - Fine-grained and efficient lineage querying of collection-based workflow provenance.pdf:pdf},
title = {{Fine-grained and efficient lineage querying of collection-based workflow provenance}},
urlpaper={http://www.mendeley.com/download/public/212462/1436102841/a3435cce7917d1995fdb70485b20efa0d3ffdf81/dl.pdf},
year = {2010}
}

@inproceedings{Missier2010c,
address = {Troy, NY},
author = {Missier, Paolo and Sahoo, Satya S and Zhao, Jun and Sheth, Amit and Goble, Carole},
booktitle = {Procs. IPAW 2010},
file = {:Users/paolo/Dropbox/Janus/paper-IPAW2010/SP-IPAW10.pdf:pdf},
keywords = {provenance Taverna LOD RDF semantics},
title = {{Janus: from Workflows to Semantic Provenance and Linked Open Data}},
urlpaper={http://www.mendeley.com/download/public/212462/2928549431/f166661dce9df21dd0c321fbffb0fb6eb4c85cd1/dl.pdf},
year = {2010}
}

@inproceedings{Altintas2010a,
address = {Troy, NY},
author = {Altintas, Ilkay and Anand, Manish Kumar and Crawl, Daniel and Belloum, Adam and Missier, Paolo and Goble, Carole and Sloot, Peter},
booktitle = {Procs. IPAW 2010},
file = {:Users/paolo/Documents/myGRID/refs/IPAW2010-CP.pdf:pdf},
keywords = {provenance interoperability},
title = {{Understanding Collaborative Studies Through Interoperable Workflow Provenance}},
urlpaper={http://www.mendeley.com/download/public/212462/2928549401/bcae9fcd73771e1d2dde11d3123f475178aca3fa/dl.pdf},
year = {2010}
}

@article{Moreau2010a,
author = {Moreau, Luc and Clifford, Ben and Freire, Juliana and Futrelle, Joe and Gil, Yolanda and Groth, Paul and Kwasnikowska, Natalia and Miles, Simon and Missier, Paolo and Myers, Jim and Plale, Beth and Simmhan, Yogesh and Stephan, Eric and {Van Den Bussche}, Jan},
doi = {http://dx.doi.org/10.1016/j.future.2010.07.005},
file = {:Users/paolo/Documents/myGRID/refs/opm.pdf:pdf},
journal = {Future Generation Computer Systems},
title = {{The Open Provenance Model --- Core Specification (v1.1)}},
urlpaper={http://www.mendeley.com/download/public/212462/3464695141/849c7a26f20b3fa9338bc8d6ab292b6c8332cf8d/dl.pdf},
year = {2010}
}

@inproceedings{Missier2010e,
abstract = {Scientific collaboration increasingly involves data sharing between separate groups. We consider a scenario where data products of scientific workflows are published and then used by other researchers as inputs to their workflows. For proper interpretation, shared data must be complemented by descriptive metadata. We focus on provenance traces, a prime example of such metadata which describes the genesis and processing history of data products in terms of the computational workflow steps. Through the reuse of published data, virtual, implicitly collaborative experiments emerge, making it desirable to compose the independently generated traces into global ones that describe the combined executions as single, seamless experiments. We present a model for provenance sharing that realizes this holistic view by overcoming the various interoperability problems that emerge from the heterogeneity of workflow systems, data formats, and provenance models. At the heart lie (i) an abstract workflow and provenance model in which (ii) data sharing becomes itself part of the combined workflow. We then describe an implementation of our model that we developed in the context of the Data Observation Network for Earth (DataONE) project and that can “stitch together” traces from different Kepler and Taverna workflow runs. It provides a prototypical framework for seamless cross-system, collaborative provenance management and can be easily extended to include other systems. Our approach also opens the door to new ways of workflow interoperability not only through often elusive workflow standards but through shared provenance information from public repositories.},
author = {Missier, Paolo and Ludascher, Bertram and Bowers, Shawn and Anand, Manish Kumar and Altintas, Ilkay and Dey, Saumen and Sarkar, Anandarup and Shrestha, Biva and Goble, Carole},
booktitle = {Proc.s 5th Workshop on Workflows in Support of Large-Scale Science (WORKS)},
file = {:Users/paolo/Library/Application Support/Mendeley Desktop/Downloaded/Missier et al. - 2010 - Linking Multiple Workflow Provenance Traces for Interoperable Collaborative Science.pdf:pdf},
title = {{Linking Multiple Workflow Provenance Traces for Interoperable Collaborative Science}},
year = {2010},
urlpaper={http://www.mendeley.com/download/public/212462/3556889201/ee6f03ee10bd5455aa1335d8898d2938631eb295/dl.pdf}
}

Scientific collaboration increasingly involves data sharing between separate groups. We consider a scenario where data products of scientific workflows are published and then used by other researchers as inputs to their workflows. For proper interpretation, shared data must be complemented by descriptive metadata. We focus on provenance traces, a prime example of such metadata which describes the genesis and processing history of data products in terms of the computational workflow steps. Through the reuse of published data, virtual, implicitly collaborative experiments emerge, making it desirable to compose the independently generated traces into global ones that describe the combined executions as single, seamless experiments. We present a model for provenance sharing that realizes this holistic view by overcoming the various interoperability problems that emerge from the heterogeneity of workflow systems, data formats, and provenance models. At the heart lie (i) an abstract workflow and provenance model in which (ii) data sharing becomes itself part of the combined workflow. We then describe an implementation of our model that we developed in the context of the Data Observation Network for Earth (DataONE) project and that can “stitch together” traces from different Kepler and Taverna workflow runs. It provides a prototypical framework for seamless cross-system, collaborative provenance management and can be easily extended to include other systems. Our approach also opens the door to new ways of workflow interoperability not only through often elusive workflow standards but through shared provenance information from public repositories.

@inproceedings{Missier2010d,
address = {San Francisco, CA, USA},
author = {Missier, Paolo and Ludascher, Bertram and Bowers, Shawn and Anand, Manish Kumar and Altintas, Ilkay and Dey, Saumen and Sarkar, Anandarup and Shrestha, Biva and Goble, Carole},
booktitle = {AGU Fall Meeting},
file = {:Users/paolo/Documents/DataONE/AGU 2010 abstracts/AGU-IN02 submission.pdf:pdf},
title = {{Seamless Provenance Representation and Use in Collaborative Science Scenarios (Abstract)}},
year = {2010},
urlpaper = {http://www.mendeley.com/download/public/212462/1436102841/a3435cce7917d1995fdb70485b20efa0d3ffdf81/dl.pdf}
}

@inproceedings{Bin2009,
author = {Cao, B and Plale, B and Subramanian, G and Missier, P and Goble, C and Simmhan, Y},
booktitle = {1st International Workshop on the Role of Semantic Web in Provenance Management},
editor = {Freire, Juliana and Missier, Paolo and Sahoo, Satya S.},
file = {:Users/paolo/Library/Application Support/Mendeley Desktop/Downloaded/Cao et al. - 2009 - Semantically Annotated Provenance in the Life Science Grid(2).pdf:pdf},
keywords = {\#provxg \#provenance,semantics provenance},
mendeley-tags = {\#provxg \#provenance},
publisher = {CEUR Proceedings},
title = {{Semantically Annotated Provenance in the Life Science Grid}},
url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-526/},
urlpaper={http://www.mendeley.com/download/public/212462/982701542/3a8950b4a6495a57e59ccc5166f84737f8dc9c4a/dl.pdf},
year = {2009}
}

@inbook{Khalid-Belhajjame:2009ix,
annote = {chapter},
author = {Belhajjame, Khalid and Missier, Paolo and Goble, Carole},
booktitle = {Handbook of Research on Computational Grid Technologies for Life Sciences, Biomedicine, and Healthcare},
keywords = {"Workflow Management",Provenance},
publisher = {IGI Global},
title = {{Data Provenance in Scientific Workflows}},
year = {2009}
}