[ { "key": "X35FP52P", "version": 17, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/X35FP52P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/X35FP52P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Marwick et al.", "parsedDate": "2018-01-02", "numChildren": 0 }, "data": { "key": "X35FP52P", "version": 17, "itemType": "journalArticle", "title": "Packaging Data Analytical Work Reproducibly Using R (and Friends)", "creators": [ { "creatorType": "author", "firstName": "Ben", "lastName": "Marwick" }, { "creatorType": "author", "firstName": "Carl", "lastName": "Boettiger" }, { "creatorType": "author", "firstName": "Lincoln", "lastName": "Mullen" } ], "abstractNote": "Computers are a central tool in the research process, enabling complex and large-scale data analysis. As computer-based research has increased in complexity, so have the challenges of ensuring that this research is reproducible. To address this challenge, we review the concept of the research compendium as a solution for providing a standard and easily recognizable way for organizing the digital materials of a research project to enable other researchers to inspect, reproduce, and extend the research. We investigate how the structure and tooling of software packages of the R programming language are being used to produce research compendia in a variety of disciplines. We also describe how software engineering tools and services are being used by researchers to streamline working with research compendia. Using real-world examples, we show how researchers can improve the reproducibility of their work using research compendia based on R packages and related tools.", "publicationTitle": "The American Statistician", "publisher": "", "place": "", "date": "January 2, 2018", "volume": "72", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "80-88", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1080/00031305.2017.1375986", "citationKey": "", "url": "https://doi.org/10.1080/00031305.2017.1375986", "accessDate": "2019-02-14T22:39:28Z", "PMID": "", "PMCID": "", "ISSN": "0003-1305", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Taylor and Francis+NEJM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computational science", "type": 1 }, { "tag": "Data science", "type": 1 }, { "tag": "Open source software", "type": 1 }, { "tag": "Reproducible research", "type": 1 }, { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-02-14T22:40:51Z", "dateModified": "2019-02-14T22:40:51Z" } }, { "key": "VBNV88AC", "version": 19, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/VBNV88AC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/VBNV88AC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "lastModifiedByUser": { "id": 241131, "username": "tmcphillips", "name": "Timothy McPhillips", "links": { "alternate": { "href": "https://www.zotero.org/tmcphillips", "type": "text/html" } } }, "creatorSummary": "Farah Zaib Khan et al.", "parsedDate": "2018-12-04", "numChildren": 1 }, "data": { "key": "VBNV88AC", "version": 19, "itemType": "report", "title": "Sharing interoperable workflow provenance: A review of best practices and their practical application in CWLProv", "creators": [ { "creatorType": "author", "firstName": "", "lastName": "Farah Zaib Khan" }, { "creatorType": "author", "firstName": "", "lastName": "Stian Soiland-Reyes" }, { "creatorType": "author", "firstName": "", "lastName": "Richard O. Sinnott" }, { "creatorType": "author", "firstName": "", "lastName": "Andrew Lonie" }, { "creatorType": "author", "firstName": "", "lastName": "Carole Goble" }, { "creatorType": "author", "firstName": "", "lastName": "Michael R. Crusoe" } ], "abstractNote": "Background: The automation of data analysis in the form of scientific workflows has become a widely adopted practice in many fields of research. Computationally driven data-intensive experiments using workflows enable Automation, Scaling, Adaption and Provenance support (ASAP). However, there are still several challenges associated with the effective sharing, publication and reproducibility of such workflows due to the incomplete capture of provenance and lack of interoperability between different technical (software) platforms. Results: Based on best practice recommendations identified from literature on workflow design, sharing and publishing, we define a hierarchical provenance framework to achieve uniformity in the provenance and support comprehensive and fully re-executable workflows equipped with domain-specific information. To realise this framework, we present CWLProv, a standard-based format to represent any workflow-based computational analysis to produce workflow output artefacts that satisfy the various levels of provenance. We utilise open source community-driven standards; interoperable workflow definitions in Common Workflow Language (CWL), structured provenance representation using the W3C PROV model, and resource aggregation and sharing as workflow-centric Research Objects (RO) generated along with the final outputs of a given workflow enactment. We demonstrate the utility of this approach through a practical implementation of CWLProv and evaluation using real-life genomic workflows developed by independent groups. Conclusions: The underlying principles of the standards utilised by CWLProv enable semantically-rich and executable Research Objects that capture computational workflows with retrospective provenance such that any platform supporting CWL will be able to understand the analysis, re-use the methods for partial re-runs, or reproduce the analysis to validate the published findings.", "reportNumber": "", "reportType": "", "institution": "Zenodo", "place": "", "date": "2018-12-04", "seriesTitle": "", "seriesNumber": "", "pages": "", "DOI": "10.5281/zenodo.1966881", "ISBN": "", "citationKey": "", "url": "https://zenodo.org/record/1966881", "accessDate": "2019-02-02T02:19:28Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Sharing interoperable workflow provenance", "language": "", "libraryCatalog": "Zenodo", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "BagIt", "type": 1 }, { "tag": "CWL", "type": 1 }, { "tag": "Common Workflow Language", "type": 1 }, { "tag": "Containers", "type": 1 }, { "tag": "Interoperability", "type": 1 }, { "tag": "Provenance", "type": 1 }, { "tag": "RO", "type": 1 }, { "tag": "Research Object", "type": 1 }, { "tag": "Scientific Workflows", "type": 1 }, { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-02-02T02:22:48Z", "dateModified": "2019-02-02T02:22:48Z" } }, { "key": "AX5RPVK4", "version": 14, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/AX5RPVK4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/AX5RPVK4", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/724819/items/VBNV88AC", "type": "application/json" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "AX5RPVK4", "version": 14, "parentItem": "VBNV88AC", "itemType": "note", "note": "Submitted to GigaScience (GIGA-D-18-00483)", "tags": [], "relations": {}, "dateAdded": "2019-02-02T02:22:48Z", "dateModified": "2019-02-02T02:22:48Z" } }, { "key": "K8UVXPUE", "version": 13, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/K8UVXPUE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/K8UVXPUE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1014164, "username": "victoriastodden", "name": "Victoria Stodden", "links": { "alternate": { "href": "https://www.zotero.org/victoriastodden", "type": "text/html" } } }, "lastModifiedByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Donoho et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "K8UVXPUE", "version": 13, "itemType": "journalArticle", "title": "Reproducible Research in Computational Harmonic Analysis", "creators": [ { "creatorType": "author", "firstName": "David L.", "lastName": "Donoho" }, { "creatorType": "author", "firstName": "Arian", "lastName": "Maleki" }, { "creatorType": "author", "firstName": "Inam Ur", "lastName": "Rahman" }, { "creatorType": "author", "firstName": "Morteza", "lastName": "Shahram" }, { "creatorType": "author", "firstName": "Victoria", "lastName": "Stodden" } ], "abstractNote": "", "publicationTitle": "Computing in Science & Engineering", "publisher": "", "place": "", "date": "1/2009", "volume": "11", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "8-18", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1109/MCSE.2009.15", "citationKey": "", "url": "http://ieeexplore.ieee.org/document/4720218/", "accessDate": "2016-10-03T13:57:27Z", "PMID": "", "PMCID": "", "ISSN": "1521-9615", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": { "dc:replaces": "http://zotero.org/groups/724819/items/NJMK9HUT" }, "dateAdded": "2016-10-03T13:57:27Z", "dateModified": "2019-01-15T18:33:38Z" } }, { "key": "7I8WE2JC", "version": 11, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/7I8WE2JC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/7I8WE2JC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1014164, "username": "victoriastodden", "name": "Victoria Stodden", "links": { "alternate": { "href": "https://www.zotero.org/victoriastodden", "type": "text/html" } } }, "lastModifiedByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Sandve et al.", "parsedDate": "2013-10-24", "numChildren": 0 }, "data": { "key": "7I8WE2JC", "version": 11, "itemType": "journalArticle", "title": "Ten Simple Rules for Reproducible Computational Research", "creators": [ { "creatorType": "author", "firstName": "Geir Kjetil", "lastName": "Sandve" }, { "creatorType": "author", "firstName": "Anton", "lastName": "Nekrutenko" }, { "creatorType": "author", "firstName": "James", "lastName": "Taylor" }, { "creatorType": "author", "firstName": "Eivind", "lastName": "Hovig" }, { "creatorType": "editor", "firstName": "Philip E.", "lastName": "Bourne" } ], "abstractNote": "", "publicationTitle": "PLoS Computational Biology", "publisher": "", "place": "", "date": "2013-10-24", "volume": "9", "issue": "10", "section": "", "partNumber": "", "partTitle": "", "pages": "e1003285", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1371/journal.pcbi.1003285", "citationKey": "", "url": "http://dx.plos.org/10.1371/journal.pcbi.1003285", "accessDate": "2016-10-03T13:57:27Z", "PMID": "", "PMCID": "", "ISSN": "1553-7358", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": { "dc:replaces": "http://zotero.org/groups/724819/items/2VVVEHVU" }, "dateAdded": "2016-10-03T13:57:27Z", "dateModified": "2019-01-15T18:32:19Z" } }, { "key": "YD776TBG", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/YD776TBG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/YD776TBG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Cao et al.", "parsedDate": "2016", "numChildren": 0 }, "data": { "key": "YD776TBG", "version": 10, "itemType": "bookSection", "title": "DataONE: A Data Federation with Provenance Support", "creators": [ { "creatorType": "editor", "firstName": "Marta", "lastName": "Mattoso" }, { "creatorType": "editor", "firstName": "Boris", "lastName": "Glavic" }, { "creatorType": "author", "firstName": "Yang", "lastName": "Cao" }, { "creatorType": "author", "firstName": "Christopher", "lastName": "Jones" }, { "creatorType": "author", "firstName": "Víctor", "lastName": "Cuevas-Vicenttín" }, { "creatorType": "author", "firstName": "Matthew B.", "lastName": "Jones" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Timothy", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" }, { "creatorType": "author", "firstName": "Christopher", "lastName": "Schwalm" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Slaughter" }, { "creatorType": "author", "firstName": "Dave", "lastName": "Vieglais" }, { "creatorType": "author", "firstName": "Lauren", "lastName": "Walker" }, { "creatorType": "author", "firstName": "Yaxing", "lastName": "Wei" } ], "abstractNote": "", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "", "seriesNumber": "", "volume": "9672", "numberOfVolumes": "", "edition": "", "date": "2016", "publisher": "Springer International Publishing", "place": "Cham", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "230-234", "ISBN": "978-3-319-40592-6 978-3-319-40593-3", "DOI": "", "citationKey": "", "url": "http://link.springer.com/10.1007/978-3-319-40593-3_28", "accessDate": "2016-11-04T23:14:03Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "DataONE", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "All rights reserved", "extra": "", "tags": [ { "tag": "ProvONE" }, { "tag": "provenance" } ], "collections": [], "relations": { "dc:replaces": "http://zotero.org/groups/724819/items/RHR4ZZTV" }, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:31:53Z" } }, { "key": "JU72VLHK", "version": 19, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/JU72VLHK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/JU72VLHK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "lastModifiedByUser": { "id": 241131, "username": "tmcphillips", "name": "Timothy McPhillips", "links": { "alternate": { "href": "https://www.zotero.org/tmcphillips", "type": "text/html" } } }, "creatorSummary": "Prabhune et al.", "parsedDate": "2016", "numChildren": 0 }, "data": { "key": "JU72VLHK", "version": 19, "itemType": "bookSection", "title": "Prov2ONE: An Algorithm for Automatically Constructing ProvONE Provenance Graphs", "creators": [ { "creatorType": "editor", "firstName": "Marta", "lastName": "Mattoso" }, { "creatorType": "editor", "firstName": "Boris", "lastName": "Glavic" }, { "creatorType": "author", "firstName": "Ajinkya", "lastName": "Prabhune" }, { "creatorType": "author", "firstName": "Aaron", "lastName": "Zweig" }, { "creatorType": "author", "firstName": "Rainer", "lastName": "Stotzka" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Gertz" }, { "creatorType": "author", "firstName": "Juergen", "lastName": "Hesser" } ], "abstractNote": "", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "", "seriesNumber": "", "volume": "9672", "numberOfVolumes": "", "edition": "", "date": "2016", "publisher": "Springer International Publishing", "place": "Cham", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "204-208", "ISBN": "978-3-319-40592-6 978-3-319-40593-3", "DOI": "10.1007/978-3-319-40593-3_22", "citationKey": "", "url": "http://link.springer.com/10.1007/978-3-319-40593-3_22", "accessDate": "2017-03-13T06:11:09Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Prov2ONE", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "365MVDR6", "version": 19, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/365MVDR6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/365MVDR6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "lastModifiedByUser": { "id": 241131, "username": "tmcphillips", "name": "Timothy McPhillips", "links": { "alternate": { "href": "https://www.zotero.org/tmcphillips", "type": "text/html" } } }, "creatorSummary": "Dey et al.", "parsedDate": "2015", "numChildren": 0 }, "data": { "key": "365MVDR6", "version": 19, "itemType": "bookSection", "title": "Computing Location-Based Lineage from Workflow Specifications to Optimize Provenance Queries", "creators": [ { "creatorType": "author", "firstName": "Saumen", "lastName": "Dey" }, { "creatorType": "author", "firstName": "Sven", "lastName": "Köhler" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "editor", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "editor", "firstName": "Beth", "lastName": "Plale" } ], "abstractNote": "", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "volume": "8628", "numberOfVolumes": "", "edition": "", "date": "2015", "publisher": "Springer International Publishing", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "180-193", "ISBN": "978-3-319-16461-8", "DOI": "10.1007/978-3-319-16462-5_14", "citationKey": "", "url": "http://dx.doi.org/10.1007/978-3-319-16462-5_14", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "L5ATQ8UP", "version": 19, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/L5ATQ8UP", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/L5ATQ8UP", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "lastModifiedByUser": { "id": 241131, "username": "tmcphillips", "name": "Timothy McPhillips", "links": { "alternate": { "href": "https://www.zotero.org/tmcphillips", "type": "text/html" } } }, "creatorSummary": "Cuevas-Vicenttín et al.", "parsedDate": "2015", "numChildren": 0 }, "data": { "key": "L5ATQ8UP", "version": 19, "itemType": "bookSection", "title": "Provenance Storage, Querying, and Visualization in PBase", "creators": [ { "creatorType": "author", "firstName": "Víctor", "lastName": "Cuevas-Vicenttín" }, { "creatorType": "author", "firstName": "Parisa", "lastName": "Kianmajd" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" }, { "creatorType": "author", "firstName": "Fernando", "lastName": "Chirigati" }, { "creatorType": "author", "firstName": "Yaxing", "lastName": "Wei" }, { "creatorType": "author", "firstName": "David", "lastName": "Koop" }, { "creatorType": "author", "firstName": "Saumen", "lastName": "Dey" } ], "abstractNote": "", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "", "seriesNumber": "Lecture Notes in Computer Science, Vol. 8628", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2015", "publisher": "Springer International Publishing", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "239-241", "ISBN": "978-3-319-16461-8", "DOI": "10.1007/978-3-319-16462-5", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "BSF39E3I", "version": 19, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/BSF39E3I", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/BSF39E3I", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "lastModifiedByUser": { "id": 241131, "username": "tmcphillips", "name": "Timothy McPhillips", "links": { "alternate": { "href": "https://www.zotero.org/tmcphillips", "type": "text/html" } } }, "creatorSummary": "Cuevas-Vicenttín et al.", "parsedDate": "2015", "numChildren": 0 }, "data": { "key": "BSF39E3I", "version": 19, "itemType": "bookSection", "title": "Provenance-Based Searching and Ranking for Scientific Workflows", "creators": [ { "creatorType": "author", "firstName": "Víctor", "lastName": "Cuevas-Vicenttín" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" } ], "abstractNote": "", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "", "seriesNumber": "Lecture Notes in Computer Science, Vol. 8628", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2015", "publisher": "Springer International Publishing", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "209-214", "ISBN": "978-3-319-16461-8", "DOI": "10.1007/978-3-319-16462-5_17", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "WZV3ZHY5", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/WZV3ZHY5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/WZV3ZHY5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Davidson et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "WZV3ZHY5", "version": 10, "itemType": "journalArticle", "title": "Provenance in Scientific Workflow Systems", "creators": [ { "creatorType": "author", "firstName": "S", "lastName": "Davidson" }, { "creatorType": "author", "firstName": "S", "lastName": "Cohen-Boulakia" }, { "creatorType": "author", "firstName": "A", "lastName": "Eyal" }, { "creatorType": "author", "firstName": "B", "lastName": "Ludascher" }, { "creatorType": "author", "firstName": "T", "lastName": "Mcphillips" }, { "creatorType": "author", "firstName": "S", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "M K", "lastName": "Anand" }, { "creatorType": "author", "firstName": "J", "lastName": "Freire" } ], "abstractNote": "The automated tracking and storage of provenance information promises to be a major advantage of scientific workflow systems. We discuss issues related to data and workflow provenance, and present techniques for focusing user attention on meaningful provenance through user views, for managing the provenance of nested scientific data, and for using information about the evolution of a workflow specification to understand the difference in the provenance of similar data products.", "publicationTitle": "Data Engineering Bulletin", "publisher": "", "place": "", "date": "2007", "volume": "30", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "1–7", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1145/1376616.1376772", "citationKey": "", "url": "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.5191&rep=rep1&type=pdf", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "EPCLE8A9", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/EPCLE8A9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/EPCLE8A9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Ellison et al.", "parsedDate": "2006-06", "numChildren": 0 }, "data": { "key": "EPCLE8A9", "version": 10, "itemType": "journalArticle", "title": "Analytic webs support the synthesis of ecological data sets.", "creators": [ { "creatorType": "author", "firstName": "Aaron M", "lastName": "Ellison" }, { "creatorType": "author", "firstName": "Leon J", "lastName": "Osterweil" }, { "creatorType": "author", "firstName": "Lori", "lastName": "Clarke" }, { "creatorType": "author", "firstName": "Julian L", "lastName": "Hadley" }, { "creatorType": "author", "firstName": "Alexander", "lastName": "Wise" }, { "creatorType": "author", "firstName": "Emery", "lastName": "Boose" }, { "creatorType": "author", "firstName": "David R", "lastName": "Foster" }, { "creatorType": "author", "firstName": "Allen", "lastName": "Hanson" }, { "creatorType": "author", "firstName": "David", "lastName": "Jensen" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Kuzeja" }, { "creatorType": "author", "firstName": "Edward", "lastName": "Riseman" }, { "creatorType": "author", "firstName": "Howard", "lastName": "Schultz" } ], "abstractNote": "A wide variety of data sets produced by individual investigators are now synthesized to address ecological questions that span a range of spatial and temporal scales. It is important to facilitate such syntheses so that \"consumers\" of data sets can be confident that both input data sets and synthetic products are reliable. Necessary documentation to ensure the reliability and validation of data sets includes both familiar descriptive metadata and formal documentation of the scientific processes used (i.e., process metadata) to produce usable data sets from collections of raw data. Such documentation is complex and difficult to construct, so it is important to help \"producers\" create reliable data sets and to facilitate their creation of required metadata. We describe a formal representation, an \"analytic web,\" that aids both producers and consumers of data sets by providing complete and precise definitions of scientific processes used to process raw and derived data sets. The formalisms used to define analytic webs are adaptations of those used in software engineering, and they provide a novel and effective support system for both the synthesis and the validation of ecological data sets. We illustrate the utility of an analytic web as an aid to producing synthetic data sets through a worked example: the synthesis of long-term measurements of whole-ecosystem carbon exchange. Analytic webs are also useful validation aids for consumers because they support the concurrent construction of a complete, Internet-accessible audit trail of the analytic processes used in the synthesis of the data sets. Finally we describe our early efforts to evaluate these ideas through the use of a prototype software tool, SciWalker. We indicate how this tool has been used to create analytic webs tailored to specific data-set synthesis and validation activities, and suggest extensions to it that will support additional forms of validation. The process metadata created by SciWalker is readily adapted for inclusion in Ecological Metadata Language (EML) files.", "publicationTitle": "Ecology", "publisher": "", "place": "", "date": "June 2006", "volume": "87", "issue": "6", "section": "", "partNumber": "", "partTitle": "", "pages": "1345–58", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://works.bepress.com/cgi/viewcontent.cgi?article=1018&context=leon_osterweil http://www.jstor.org/stable/20069083 http://www.ncbi.nlm.nih.gov/pubmed/16869408", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "0012-9658", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Data Collection" }, { "tag": "Data Collection: methods" }, { "tag": "Databases" }, { "tag": "Ecology" }, { "tag": "Ecology: methods" }, { "tag": "Factual" }, { "tag": "Internet" }, { "tag": "Software Design" }, { "tag": "User-Computer Interface" }, { "tag": "provenance" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "9K89R6G5", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/9K89R6G5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/9K89R6G5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Frew et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "9K89R6G5", "version": 10, "itemType": "journalArticle", "title": "Automatic capture and reconstruction of computational provenance", "creators": [ { "creatorType": "author", "firstName": "James", "lastName": "Frew" }, { "creatorType": "author", "firstName": "Dominic", "lastName": "Metzger" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Slaughter" } ], "abstractNote": "The Earth System Science Server (ES3) project is developing a local infrastructure for managing Earth science data products derived from satellite remote sensing. By ‘local,’ we mean the infrastructure that a scientist uses to manage the creation and dissemination of her own data products, particularly those that are constantly incorporating corrections or improvements based on the scientist’s own research. There- fore, in addition to being robust and capacious enough to support public access, ES3 is intended to be flexible enough to manage the idiosyncratic computing ensembles that typify scientific research. Instead of specifying provenance explicitly with a workflow model, ES3 extracts provenance information auto- matically from arbitrary applications by monitoring their interactions with their execution environment. These interactions (arguments, file I/O, system calls, etc.) are logged to the ES3 database, which assembles them into provenance graphs. These graphs resemble workflow specifications, but are really reports—they describe what actually happened, as opposed to what was requested. The ES3 database supports forward and backward navigation through provenance graphs (i.e. ancestor/descendant queries), as well as graph retrieval.", "publicationTitle": "Concurrency and Computation: Practice and Experience", "publisher": "", "place": "", "date": "2008", "volume": "20", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "485–496", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/cpe.1247", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "es3" }, { "tag": "instrumentation" }, { "tag": "lineage" }, { "tag": "passive" }, { "tag": "provenance" }, { "tag": "transparency" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "RZXG7XFL", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/RZXG7XFL", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/RZXG7XFL", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Jaeger-Frank et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "RZXG7XFL", "version": 10, "itemType": "journalArticle", "title": "A three tier architecture applied to LiDAR processing and monitoring", "creators": [ { "creatorType": "author", "firstName": "Efrat", "lastName": "Jaeger-Frank" }, { "creatorType": "author", "firstName": "Christopher J", "lastName": "Crosby" }, { "creatorType": "author", "firstName": "Ashraf", "lastName": "Memon" }, { "creatorType": "author", "firstName": "Viswanath", "lastName": "Nandigam" }, { "creatorType": "author", "firstName": "Jeffery", "lastName": "Conner" }, { "creatorType": "author", "firstName": "J Ramon", "lastName": "Arrowsmith" }, { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "Chaitan", "lastName": "Baru" } ], "abstractNote": "", "publicationTitle": "Sci Program", "publisher": "", "place": "", "date": "2006", "volume": "14", "issue": "3,4", "section": "", "partNumber": "", "partTitle": "", "pages": "185–194", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1376960.1376964", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "10589244", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "grid portals" }, { "tag": "grids" }, { "tag": "lidar" }, { "tag": "provenance" }, { "tag": "scientific worfklows" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "QFWBMW48", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/QFWBMW48", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/QFWBMW48", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Jones", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "QFWBMW48", "version": 10, "itemType": "journalArticle", "title": "Meta-information systems and ontologies A special feature from ISEI'06", "creators": [ { "creatorType": "author", "firstName": "Matthew B.", "lastName": "Jones" }, { "creatorType": "editor", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "editor", "firstName": "Louiqa", "lastName": "Raschid" } ], "abstractNote": "", "publicationTitle": "Ecological Informatics", "publisher": "", "place": "", "date": "2007", "volume": "2", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "193–194", "series": "Lecture Notes in Computer Science", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.ecoinf.2007.09.003", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Geospatial analysis" }, { "tag": "Knowledge representation" }, { "tag": "Metadata" }, { "tag": "data management" }, { "tag": "ontologies" }, { "tag": "provenance" }, { "tag": "scientific workflows" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "ZFEB3AQS", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/ZFEB3AQS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/ZFEB3AQS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Ludäscher et al.", "parsedDate": "2008-04", "numChildren": 0 }, "data": { "key": "ZFEB3AQS", "version": 10, "itemType": "journalArticle", "title": "From computation models to models of provenance: the RWS approach", "creators": [ { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Norbert", "lastName": "Podhorszki" }, { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Timothy", "lastName": "McPhillips" } ], "abstractNote": "Scientific workflows often benefit from or even require advanced modeling constructs, e.g., nesting of subworkflows, cycles for executing loops, data-dependent routing, and pipelined execution. In such settings, an often overlooked aspect of provenance takes center stage: A suitable model of provenance (MoP) for scientific workflow should be based upon the underlying model of computation (MoC) for executing workflows. We can derive an adequate MoP from a MoC such as Kahn’s dataflow process networks, by taking into account the assumptions that a MoC entails, and by recording the observables which it affords. In this way, a MoP captures or at least better approximates real data dependencies for workflows with advanced modeling constructs. As a specific instance, we elaborate on the Read-Write-ReSet (RWS) model, a simple and flexible MoP suitable for a number of different MoCs.", "publicationTitle": "Concurrency and Computation: Practice and Experience", "publisher": "", "place": "", "date": "April 2008", "volume": "20", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "507–518", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/cpe.1234", "citationKey": "", "url": "http://doi.wiley.com/10.1002/cpe.1234", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "15320626", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "kepler" }, { "tag": "provenance" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "EU2I6KUX", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/EU2I6KUX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/EU2I6KUX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Ma et al.", "parsedDate": "2014-06", "numChildren": 0 }, "data": { "key": "EU2I6KUX", "version": 10, "itemType": "journalArticle", "title": "Capturing provenance of global change information", "creators": [ { "creatorType": "author", "firstName": "Xiaogang", "lastName": "Ma" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Fox" }, { "creatorType": "author", "firstName": "Curt", "lastName": "Tilmes" }, { "creatorType": "author", "firstName": "Katharine", "lastName": "Jacobs" }, { "creatorType": "author", "firstName": "Anne", "lastName": "Waple" } ], "abstractNote": "Global change information demands access to data sources and well-documented provenance to provide the evidence needed to build confidence in scientific conclusions and decision making. A new generation of web technology, the Semantic Web, provides tools for that purpose.", "publicationTitle": "Nature Climate Change", "publisher": "", "place": "", "date": "June 2014", "volume": "4", "issue": "6", "section": "", "partNumber": "", "partTitle": "", "pages": "409-413", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nature Clim. Change", "DOI": "10.1038/nclimate2141", "citationKey": "", "url": "http://www.nature.com/nclimate/journal/v4/n6/full/nclimate2141.html#t1", "accessDate": "2015-01-21T04:38:14Z", "PMID": "", "PMCID": "", "ISSN": "1758-678X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "www.nature.com", "callNumber": "", "rights": "© 2014 Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "YH9VQ9XT", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/YH9VQ9XT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/YH9VQ9XT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Missier et al.", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "YH9VQ9XT", "version": 10, "itemType": "journalArticle", "title": "Golden Trail: Retrieving the Data History that Matters from a Comprehensive Provenance Repository", "creators": [ { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Saumen", "lastName": "Dey" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Wang" }, { "creatorType": "author", "firstName": "Tim", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Agun" }, { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" } ], "abstractNote": "", "publicationTitle": "International Journal of Digital Curation", "publisher": "", "place": "", "date": "03/2012", "volume": "7", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.2218/ijdc.v7i1.221", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "KDBT3YLH", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/KDBT3YLH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/KDBT3YLH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Altintas et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "KDBT3YLH", "version": 10, "itemType": "journalArticle", "title": "Understanding Collaborative Studies Through Interoperable Workflow Provenance", "creators": [ { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "Manish Kumar", "lastName": "Anand" }, { "creatorType": "author", "firstName": "Daniel", "lastName": "Crawl" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" }, { "creatorType": "author", "firstName": "Carole", "lastName": "Goble" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Sloot" }, { "creatorType": "editor", "firstName": "Deborah L", "lastName": "McGuinness" }, { "creatorType": "editor", "firstName": "James R", "lastName": "Michaelis" }, { "creatorType": "editor", "firstName": "Luc", "lastName": "Moreau" } ], "abstractNote": "Data provenance graphs are form of metadata that can be used to establish a variety of properties of data products that undergo sequences of transformations, typically specified as workflows. Their use- fulness for answering user provenance queries is limited, however, unless the graphs are enhanced with domain-specific annotations. In this paper we propose a model and architecture for semantic, domain-aware prove- nance, and demonstrate its usefulness in answering typical user queries. Furthermore, we discuss the additional benefits and the technical impli- cations of publishing provenance graphs as a form of Linked Data. A prototype implementation of the model is available for data produced by the Taverna workflow system.", "publicationTitle": "Computer", "publisher": "", "place": "", "date": "2010", "volume": "6378", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "42–58", "series": "Lecture Notes in Computer Science", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/978-3-642-17819-1_6", "citationKey": "", "url": "http://dx.doi.org/10.1007/978-3-642-17819-1_6", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "XRD3CP6N", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/XRD3CP6N", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/XRD3CP6N", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Altintas et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "XRD3CP6N", "version": 10, "itemType": "conferencePaper", "title": "Provenance Collection Support in the Kepler Scientific Workflow System", "creators": [ { "creatorType": "author", "firstName": "I", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "O", "lastName": "Barney" }, { "creatorType": "author", "firstName": "E", "lastName": "Jaeger-Frank" } ], "abstractNote": "", "proceedingsTitle": "IPAW", "conferenceName": "", "publisher": "Springer", "place": "", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "118–132", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/11890850_14", "ISBN": "", "citationKey": "", "url": "http://dx.doi.org/10.1007/11890850_14", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "kepler" }, { "tag": "provenance" }, { "tag": "scientific workflow" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "2PU6L7VC", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/2PU6L7VC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/2PU6L7VC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Bowers et al.", "parsedDate": "2008-04", "numChildren": 0 }, "data": { "key": "2PU6L7VC", "version": 10, "itemType": "journalArticle", "title": "Provenance in collection-oriented scientific workflows", "creators": [ { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Timothy M.", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" } ], "abstractNote": "", "publicationTitle": "Concurrency and Computation: Practice and Experience", "publisher": "", "place": "", "date": "April 2008", "volume": "20", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "519–529", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/cpe.1226", "citationKey": "", "url": "http://doi.wiley.com/10.1002/cpe.1226", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "15320626", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "collection-oriented scientific workflows" }, { "tag": "kepler" }, { "tag": "provenance" }, { "tag": "scientific data management" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "HRQXJNVV", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/HRQXJNVV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/HRQXJNVV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Duffy et al.", "parsedDate": "2012-06", "numChildren": 0 }, "data": { "key": "HRQXJNVV", "version": 10, "itemType": "journalArticle", "title": "Designing a road map for geoscience workflows", "creators": [ { "creatorType": "author", "firstName": "Christopher", "lastName": "Duffy" }, { "creatorType": "author", "firstName": "Yolanda", "lastName": "Gil" }, { "creatorType": "author", "firstName": "Ewa", "lastName": "Deelman" }, { "creatorType": "author", "firstName": "Suresh", "lastName": "Marru" }, { "creatorType": "author", "firstName": "Marlon", "lastName": "Pierce" }, { "creatorType": "author", "firstName": "Ibrahim", "lastName": "Demir" }, { "creatorType": "author", "firstName": "Gerry", "lastName": "Wiener" } ], "abstractNote": "Advances in geoscience research and discovery are fundamentally tied to data and computation, but formal strategies for managing the diversity of models and data resources in the Earth sciences have not yet been resolved or fully appreciated. The U.S. National Science Foundation (NSF) EarthCube initiative (http://earthcube.ning.com), which aims to support community-guided cyberinfrastructure to integrate data and information across the geosciences, recently funded four community development activities: Geoscience Workflows; Semantics and Ontologies; Data Discovery, Mining, and Integration; and Governance. The Geoscience Workflows working group, with broad participation from the geosciences, cyberinfrastructure, and other relevant communities, is formulating a workflows road map (http://sites.google.com/site/earthcubeworkflow/). The Geoscience Workflows team coordinates with each of the other community development groups given their direct relevance to workflows. Semantics and ontologies are mechanisms for describing workflows and the data they process.", "publicationTitle": "Eos, Transactions American Geophysical Union", "publisher": "", "place": "", "date": "June 2012", "volume": "93", "issue": "24", "section": "", "partNumber": "", "partTitle": "", "pages": "225", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1029/2012EO240002", "citationKey": "", "url": "http://www.agu.org/pubs/crossref/2012/2012EO240002.shtml", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "0096-3941", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "EarthCube" }, { "tag": "cyberinfrastructure." }, { "tag": "geoscience workflows" }, { "tag": "provenance" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "JBMCXD43", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/JBMCXD43", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/JBMCXD43", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Koop et al.", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "JBMCXD43", "version": 10, "itemType": "journalArticle", "title": "A Provenance-Based Infrastructure to Support the Life Cycle of Executable Papers", "creators": [ { "creatorType": "author", "firstName": "David", "lastName": "Koop" }, { "creatorType": "author", "firstName": "Emanuele", "lastName": "Santos" }, { "creatorType": "author", "firstName": "Phillip", "lastName": "Mates" }, { "creatorType": "author", "firstName": "Huy T", "lastName": "Vo" }, { "creatorType": "author", "firstName": "Philippe", "lastName": "Bonnet" }, { "creatorType": "author", "firstName": "Bela", "lastName": "Bauer" }, { "creatorType": "author", "firstName": "Brigitte", "lastName": "Surer" }, { "creatorType": "author", "firstName": "Matthias", "lastName": "Troyer" }, { "creatorType": "author", "firstName": "Dean N", "lastName": "Williams" }, { "creatorType": "author", "firstName": "Joel E", "lastName": "Tohline" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" }, { "creatorType": "author", "firstName": "Cláudio T", "lastName": "Silva" } ], "abstractNote": "As publishers establish a greater online presence as well as infrastructure to support the distribution of more varied information, the idea of an executable paper that enables greater interaction has developed. An executable paper provides more information for computational experiments and results than the text, tables, and figures of standard papers. Executable papers can bundle computational content that allow readers and reviewers to interact, validate, and explore experiments. By including such content, authors facilitate future discoveries by lowering the barrier to reproducing and extending results. We present an infrastructure for creating, disseminating, and maintaining executable papers. Our approach is rooted in provenance, the documentation of exactly how data, experiments, and results were generated. We seek to improve the experience for everyone involved in the life cycle of an executable paper. The automated capture of provenance information allows authors to easily integrate and update results into papers as they write, and also helps reviewers better evaluate approaches by enabling them to explore experimental results by varying parameters or data. With a provenance-based system, readers are able to examine exactly how a result was developed to better understand and extend published findings.", "publicationTitle": "Procedia CS", "publisher": "", "place": "", "date": "2011", "volume": "4", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "648–657", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.procs.2011.04.068", "citationKey": "", "url": "http://www.sciencedirect.com/science/article/pii/S1877050911001268", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "18770509", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "executable paper" }, { "tag": "provenance" }, { "tag": "reproducibility" }, { "tag": "scientific workflows" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "MP2F2AQM", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/MP2F2AQM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/MP2F2AQM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Moreau et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "MP2F2AQM", "version": 10, "itemType": "journalArticle", "title": "The Open Provenance Model core specification (v1.1)", "creators": [ { "creatorType": "author", "firstName": "Luc", "lastName": "Moreau" }, { "creatorType": "author", "firstName": "Ben", "lastName": "Clifford" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" }, { "creatorType": "author", "firstName": "Joe", "lastName": "Futrelle" }, { "creatorType": "author", "firstName": "Yolanda", "lastName": "Gil" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Groth" }, { "creatorType": "author", "firstName": "Natalia", "lastName": "Kwasnikowska" }, { "creatorType": "author", "firstName": "Simon", "lastName": "Miles" }, { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" }, { "creatorType": "author", "firstName": "Jim", "lastName": "Myers" }, { "creatorType": "author", "firstName": "Yogesh L", "lastName": "Simmhan" }, { "creatorType": "author", "firstName": "Eric", "lastName": "Stephan" }, { "creatorType": "author", "firstName": "Jan", "lastName": "Van Den Bussche" } ], "abstractNote": "The Open Provenance Model is a model of provenance that is designed to meet 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 a provenance model. (3) To define provenance 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 allow multiple levels of description to coexist. (6) To define a core set of rules that identify the valid inferences that can be made on provenance representation. This document contains the specification of the Open Provenance Model (v1.1) resulting from a community-effort to achieve inter-operability in the Provenance Challenge series.", "publicationTitle": "Future Generation Computer Systems", "publisher": "", "place": "", "date": "2010", "volume": "27", "issue": "August 2007", "section": "", "partNumber": "", "partTitle": "", "pages": "743–756", "series": "1.1", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://dx.doi.org/10.1016/j.future.2010.07.005", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "inter operability" }, { "tag": "provenance" }, { "tag": "representation" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } }, { "key": "5XDAVBUA", "version": 10, "library": { "type": "group", "id": 724819, "name": "whole_tale", "links": { "alternate": { "href": "https://www.zotero.org/groups/whole_tale", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/724819/items/5XDAVBUA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/whole_tale/items/5XDAVBUA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1280008, "username": "mbjones", "name": "Matthew Jones", "links": { "alternate": { "href": "https://www.zotero.org/mbjones", "type": "text/html" } } }, "creatorSummary": "Mouallem et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "5XDAVBUA", "version": 10, "itemType": "conferencePaper", "title": "Tracking Files in the Kepler Provenance Framework", "creators": [ { "creatorType": "author", "firstName": "Pierre", "lastName": "Mouallem" }, { "creatorType": "author", "firstName": "Roselyne", "lastName": "Barreto" }, { "creatorType": "author", "firstName": "Scott", "lastName": "Klasky" }, { "creatorType": "author", "firstName": "Norbert", "lastName": "Podhorszki" }, { "creatorType": "author", "firstName": "Mladen", "lastName": "Vouk" }, { "creatorType": "author", "firstName": "Marianne", "lastName": "Winslett" }, { "creatorType": "editor", "firstName": "Marianne", "lastName": "Winslett" } ], "abstractNote": "Workflow Management Systems (WFMS), such as Kepler, are prov- ing to be an important tool in scientific problem solving. They can automate and manage complex processes and huge amounts of data produced by petas- cale simulations. Typically, the produced data need to be properly visualized and analyzed by scientists in order to achieve the desired scientific goals. Both run-time and post analysis may benefit from, even require, additional meta-data – provenance information. One of the challenges in this context is the tracking of the data files that can be produced in very large numbers during stages of the workflow, such as visualizations. The Kepler provenance framework collects all or part of the raw information flowing through the workflow graph. This infor- mation then needs to be further parsed to extract meta-data of interest. This can be done through add-on tools and algorithms. We show how to automate track- ing specific information such as data files locations.", "proceedingsTitle": "Scientific and Statistical Database Management", "conferenceName": "", "publisher": "Springer Berlin Heidelberg", "place": "Berlin, Heidelberg", "date": "2009", "eventPlace": "", "volume": "5566", "issue": "", "numberOfVolumes": "", "pages": "273–282", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-642-02279-1", "ISBN": "978-3-642-02278-4", "citationKey": "", "url": "http://www.springerlink.com/content/5026156h31361133/ http://www.springerlink.com/index/10.1007/978-3-642-02279-1", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computer Science" }, { "tag": "kepler" }, { "tag": "provenance" }, { "tag": "scientific workflow" }, { "tag": "workflow" } ], "collections": [], "relations": {}, "dateAdded": "2019-01-15T18:30:37Z", "dateModified": "2019-01-15T18:30:37Z" } } ]