[ { "key": "4I567TVJ", "version": 94, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/4I567TVJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/4I567TVJ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Loibl et al.", "parsedDate": "2020", "numChildren": 0 }, "data": { "key": "4I567TVJ", "version": 94, "itemType": "journalArticle", "title": "Procedure for the transfer of standards into machine-actionability", "creators": [ { "creatorType": "author", "firstName": "André", "lastName": "Loibl" }, { "creatorType": "author", "firstName": "Thivakar", "lastName": "Manoharan" }, { "creatorType": "author", "firstName": "Arun", "lastName": "Nagarajah" } ], "abstractNote": "", "publicationTitle": "Journal of Advanced Mechanical Design, Systems, and Manufacturing", "publisher": "", "place": "", "date": "2020", "volume": "14", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "JAMDSM0022-JAMDSM0022", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "JAMDSM", "DOI": "10.1299/jamdsm.2020jamdsm0022", "citationKey": "", "url": "https://www.jstage.jst.go.jp/article/jamdsm/14/2/14_2020jamdsm0022/_article", "accessDate": "2021-02-03T15:06:09Z", "PMID": "", "PMCID": "", "ISSN": "1881-3054", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "DOI.org (Crossref)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "MNJSXVEH" ], "relations": {}, "dateAdded": "2021-02-03T15:06:09Z", "dateModified": "2021-02-03T15:06:09Z" } }, { "key": "WNKJD5VH", "version": 90, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/WNKJD5VH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/WNKJD5VH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Tan", "parsedDate": "2004", "numChildren": 0 }, "data": { "key": "WNKJD5VH", "version": 90, "itemType": "journalArticle", "title": "Research Problems in Data Provenance", "creators": [ { "creatorType": "author", "firstName": "Wang-Chiew", "lastName": "Tan" } ], "abstractNote": "The problem of tracing the provenance (also known as lineage) of data is an ubiquitous problem that is frequently encountered in databases that are the result of many transformation steps. Scientific databases and data warehouses are some examples of such databases. However, contributions from the database research community towards this problem have been somewhat limited. In this paper, we motivate the problem of supporting data provenance in scientific database applications and provide some background on previous research. We also briefly describe the DBNotes prototype developed at UC Santa Cruz that can be used to “eagerly” trace the provenance and flow of relational data and describe some directions for further research.", "publicationTitle": "IEEE Data Engineering Bulletin", "publisher": "", "place": "", "date": "2004", "volume": "27", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "45–52", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "ftp://ftp.research.microsoft.com/pub/debull/A04dec/tan.ps", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Relational Database" } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/ZAYPT3L3" }, "dateAdded": "2013-11-13T14:07:41Z", "dateModified": "2020-07-29T13:39:01Z" } }, { "key": "S2RURABI", "version": 91, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/S2RURABI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/S2RURABI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Miles et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "S2RURABI", "version": 91, "itemType": "journalArticle", "title": "The Requirements of Using Provenance in e-Science Experiments", "creators": [ { "creatorType": "author", "firstName": "Simon", "lastName": "Miles" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Groth" }, { "creatorType": "author", "firstName": "Miguel", "lastName": "Branco" }, { "creatorType": "author", "firstName": "Luc", "lastName": "Moreau" } ], "abstractNote": "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 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 process documentation to determine the provenance of data items. 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, technology and application-independent architecture. We propose an architecture that meets these requirements, analyse its features compared with other approaches and evaluate a preliminary implementation by attempting to realise two of the use cases.", "publicationTitle": "Journal of Grid Computing", "publisher": "", "place": "", "date": "2007", "volume": "5", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "1-25", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/s10723-006-9055-3", "citationKey": "", "url": "http://dx.doi.org/10.1007/s10723-006-9055-3", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1570-7873", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Grid" }, { "tag": "Provenance" }, { "tag": "e-Science" }, { "tag": "provenance", "type": 1 }, { "tag": "requirements" }, { "tag": "use case" }, { "tag": "workflow" } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/F25CYB9F" }, "dateAdded": "2013-11-13T14:07:41Z", "dateModified": "2020-07-29T13:38:54Z" } }, { "key": "HT534YJ3", "version": 91, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/HT534YJ3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/HT534YJ3", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/231441/items/M4IVCAXZ", "type": "application/json" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "HT534YJ3", "version": 91, "parentItem": "M4IVCAXZ", "itemType": "note", "note": "Comment: Partial manuscript; figures down-sampled", "tags": [], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-07-29T13:38:51Z" } }, { "key": "M4IVCAXZ", "version": 90, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/M4IVCAXZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/M4IVCAXZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Franz et al.", "parsedDate": "2014-12", "numChildren": 1 }, "data": { "key": "M4IVCAXZ", "version": 90, "itemType": "journalArticle", "title": "Taxonomic Provenance: Two Influential Primate Classifications Logically Aligned", "creators": [ { "creatorType": "author", "firstName": "N. M.", "lastName": "Franz" }, { "creatorType": "author", "firstName": "N. M.", "lastName": "Pier" }, { "creatorType": "author", "firstName": "D. M.", "lastName": "Reeder" }, { "creatorType": "author", "firstName": "M.", "lastName": "Chen" }, { "creatorType": "author", "firstName": "S.", "lastName": "Yu" }, { "creatorType": "author", "firstName": "P.", "lastName": "Kianmajd" }, { "creatorType": "author", "firstName": "S.", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "B.", "lastName": "Ludaescher" } ], "abstractNote": "", "publicationTitle": "ArXiv e-prints", "publisher": "", "place": "", "date": "December 2014", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Quantitative Biology - Genomics" }, { "tag": "Quantitative Biology - Populations and Evolution" } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/ZS7UF64B" }, "dateAdded": "2015-03-27T15:53:37Z", "dateModified": "2020-07-29T13:38:51Z" } }, { "key": "4EQIZKT6", "version": 90, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/4EQIZKT6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/4EQIZKT6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Sahoo et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "4EQIZKT6", "version": 90, "itemType": "journalArticle", "title": "Semantic Provenance for eScience: Managing the Deluge of Scientific Data", "creators": [ { "creatorType": "author", "firstName": "S.S.", "lastName": "Sahoo" }, { "creatorType": "author", "firstName": "A.", "lastName": "Sheth" }, { "creatorType": "author", "firstName": "C.", "lastName": "Henson" } ], "abstractNote": "Provenance information in eScience is metadata that's critical to effectively manage the exponentially increasing volumes of scientific data from industrial-scale experiment protocols. Semantic provenance, based on domain-specific provenance ontologies, lets software applications unambiguously interpret data in the correct context. The semantic provenance framework for eScience data comprises expressive provenance information and domain-specific provenance ontologies and applies this information to data management. The authors' \"two degrees of separation\" approach advocates the creation of high-quality provenance information using specialized services. In contrast to workflow engines generating provenance information as a core functionality, the specialized provenance services are integrated into a scientific workflow on demand. This article describes an implementation of the semantic provenance framework for glycoproteomics.", "publicationTitle": "Internet Computing, IEEE", "publisher": "", "place": "", "date": "2008", "volume": "12", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "46-54", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1109/MIC.2008.86", "citationKey": "", "url": "http://dx.doi.org/10.1109/MIC.2008.86", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1089-7801", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Application software", "type": 1 }, { "tag": "Cities and towns", "type": 1 }, { "tag": "Computer industry", "type": 1 }, { "tag": "Engines", "type": 1 }, { "tag": "Grid" }, { "tag": "Information management", "type": 1 }, { "tag": "Ontologies", "type": 1 }, { "tag": "Proteomics", "type": 1 }, { "tag": "Protocols", "type": 1 }, { "tag": "Semantic provenance" }, { "tag": "Software tools", "type": 1 }, { "tag": "Spade", "type": 1 }, { "tag": "Throughput", "type": 1 }, { "tag": "cyberinfrastructure", "type": 1 }, { "tag": "data management", "type": 1 }, { "tag": "e-Science" }, { "tag": "eScience", "type": 1 }, { "tag": "industrial-scale experiment protocols", "type": 1 }, { "tag": "information management", "type": 1 }, { "tag": "meta data", "type": 1 }, { "tag": "metadata", "type": 1 }, { "tag": "natural sciences computing", "type": 1 }, { "tag": "provenance", "type": 1 }, { "tag": "provenance information", "type": 1 }, { "tag": "provenance ontologies", "type": 1 }, { "tag": "scientific data", "type": 1 }, { "tag": "semantic provenance", "type": 1 }, { "tag": "software applications", "type": 1 }, { "tag": "workflow" } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": [ "http://zotero.org/groups/231441/items/8XHWGU82", "http://zotero.org/groups/231441/items/PQC6PY9W" ] }, "dateAdded": "2013-11-13T14:07:41Z", "dateModified": "2020-07-29T13:38:48Z" } }, { "key": "94PD98GI", "version": 90, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/94PD98GI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/94PD98GI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Moreau et al.", "parsedDate": "2008-04-10", "numChildren": 0 }, "data": { "key": "94PD98GI", "version": 90, "itemType": "journalArticle", "title": "Special Issue: The First Provenance Challenge", "creators": [ { "creatorType": "author", "firstName": "Luc", "lastName": "Moreau" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "Roger S.", "lastName": "Barga" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Steven", "lastName": "Callahan" }, { "creatorType": "author", "firstName": "George", "lastName": "Chin" }, { "creatorType": "author", "firstName": "Ben", "lastName": "Clifford" }, { "creatorType": "author", "firstName": "Shirley", "lastName": "Cohen" }, { "creatorType": "author", "firstName": "Sarah", "lastName": "Cohen-Boulakia" }, { "creatorType": "author", "firstName": "Susan", "lastName": "Davidson" }, { "creatorType": "author", "firstName": "Ewa", "lastName": "Deelman" }, { "creatorType": "author", "firstName": "Luciano", "lastName": "Digiampietri" }, { "creatorType": "author", "firstName": "Ian", "lastName": "Foster" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" }, { "creatorType": "author", "firstName": "James", "lastName": "Frew" }, { "creatorType": "author", "firstName": "Joe", "lastName": "Futrelle" }, { "creatorType": "author", "firstName": "Tara", "lastName": "Gibson" }, { "creatorType": "author", "firstName": "Yolanda", "lastName": "Gil" }, { "creatorType": "author", "firstName": "Carole", "lastName": "Goble" }, { "creatorType": "author", "firstName": "Jennifer", "lastName": "Golbeck" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Groth" }, { "creatorType": "author", "firstName": "David A.", "lastName": "Holland" }, { "creatorType": "author", "firstName": "Sheng", "lastName": "Jiang" }, { "creatorType": "author", "firstName": "Jihie", "lastName": "Kim" }, { "creatorType": "author", "firstName": "David", "lastName": "Koop" }, { "creatorType": "author", "firstName": "Ales", "lastName": "Krenek" }, { "creatorType": "author", "firstName": "Timothy", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "Gaurang", "lastName": "Mehta" }, { "creatorType": "author", "firstName": "Simon", "lastName": "Miles" }, { "creatorType": "author", "firstName": "Dominic", "lastName": "Metzger" }, { "creatorType": "author", "firstName": "Steve", "lastName": "Munroe" }, { "creatorType": "author", "firstName": "Jim", "lastName": "Myers" }, { "creatorType": "author", "firstName": "Beth", "lastName": "Plale" }, { "creatorType": "author", "firstName": "Norbert", "lastName": "Podhorszki" }, { "creatorType": "author", "firstName": "Varun", "lastName": "Ratnakar" }, { "creatorType": "author", "firstName": "Emanuele", "lastName": "Santos" }, { "creatorType": "author", "firstName": "Carlos", "lastName": "Scheidegger" }, { "creatorType": "author", "firstName": "Karen", "lastName": "Schuchardt" }, { "creatorType": "author", "firstName": "Margo", "lastName": "Seltzer" }, { "creatorType": "author", "firstName": "Yogesh L.", "lastName": "Simmhan" }, { "creatorType": "author", "firstName": "Claudio", "lastName": "Silva" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Slaughter" }, { "creatorType": "author", "firstName": "Eric", "lastName": "Stephan" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Stevens" }, { "creatorType": "author", "firstName": "Daniele", "lastName": "Turi" }, { "creatorType": "author", "firstName": "Huy", "lastName": "Vo" }, { "creatorType": "author", "firstName": "Mike", "lastName": "Wilde" }, { "creatorType": "author", "firstName": "Jun", "lastName": "Zhao" }, { "creatorType": "author", "firstName": "Yong", "lastName": "Zhao" } ], "abstractNote": "", "publicationTitle": "Concurrency and Computation: Practice and Experience", "publisher": "", "place": "", "date": "April 10, 2008", "volume": "20", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "409-418", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Concurrency Computat.: Pract. Exper.", "DOI": "10.1002/cpe.1233", "citationKey": "", "url": "http://dx.doi.org/10.1002/cpe.1233", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1532-0634", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/UWCJ2Q4J" }, "dateAdded": "2015-05-12T00:35:44Z", "dateModified": "2020-07-29T13:38:41Z" } }, { "key": "9CCKNKPN", "version": 89, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/9CCKNKPN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/9CCKNKPN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 809173, "username": "ddubin", "name": "Dave Dubin", "links": { "alternate": { "href": "https://www.zotero.org/ddubin", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Alper et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "9CCKNKPN", "version": 89, "itemType": "conferencePaper", "title": "Enhancing and Abstracting Scientific Workflow Provenance for Data Publishing", "creators": [ { "creatorType": "author", "firstName": "Pinar", "lastName": "Alper" }, { "creatorType": "author", "firstName": "Khalid", "lastName": "Belhajjame" }, { "creatorType": "author", "firstName": "Carole A.", "lastName": "Goble" }, { "creatorType": "author", "firstName": "Pinar", "lastName": "Karagoz" } ], "abstractNote": "Many scientists are using workflows to systematically design and run computational experiments. Once the workflow is executed, the scientist may want to publish the dataset generated as a result, to be, e.g., reused by other scientists as input to their experiments. In doing so, the scientist needs to curate such dataset by specifying metadata information that describes it, e.g. its derivation history, origins and ownership. To assist the scientist in this task, we explore in this paper the use of provenance traces collected by workflow management systems when enacting workflows. Specifically, we identify the shortcomings of such raw provenance traces in supporting the data publishing task, and propose an approach whereby distilled, yet more informative, provenance traces that are fit for the data publishing task can be derived.", "proceedingsTitle": "Proceedings of the Joint EDBT/ICDT 2013 Workshops", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "313–318", "series": "EDBT '13", "seriesNumber": "", "DOI": "10.1145/2457317.2457370", "ISBN": "978-1-4503-1599-9", "citationKey": "", "url": "http://dx.doi.org/10.1145/2457317.2457370", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Provenance" }, { "tag": "data publishing" }, { "tag": "provenance", "type": 1 }, { "tag": "scientific workflows" } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/W4V5BM5T" }, "dateAdded": "2015-05-12T00:35:44Z", "dateModified": "2020-07-29T13:38:14Z" } }, { "key": "4UNVXW2P", "version": 95, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/4UNVXW2P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/4UNVXW2P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Soldatova and King", "parsedDate": "2006-12-22", "numChildren": 0 }, "data": { "key": "4UNVXW2P", "version": 95, "itemType": "journalArticle", "title": "An ontology of scientific experiments", "creators": [ { "creatorType": "author", "firstName": "Larisa N", "lastName": "Soldatova" }, { "creatorType": "author", "firstName": "Ross D", "lastName": "King" } ], "abstractNote": "The formal description of experiments for efficient analysis, annotation and sharing of results is a fundamental part of the practice of science. Ontologies are required to achieve this objective. A few subject-specific ontologies of experiments currently exist. However, despite the unity of scientific experimentation, no general ontology of experiments exists. We propose the ontology EXPO to meet this need. EXPO links the SUMO (the Suggested Upper Merged Ontology) with subject-specific ontologies of experiments by formalizing the generic concepts of experimental design, methodology and results representation. EXPO is expressed in the W3C standard ontology language OWL-DL. We demonstrate the utility of EXPO and its ability to describe different experimental domains, by applying it to two experiments: one in high-energy physics and the other in phylogenetics. The use of EXPO made the goals and structure of these experiments more explicit, revealed ambiguities, and highlighted an unexpected similarity. We conclude that, EXPO is of general value in describing experiments and a step towards the formalization of science.", "publicationTitle": "Journal of the Royal Society Interface", "publisher": "", "place": "", "date": "2006-12-22", "volume": "3", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "795-803", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "J R Soc Interface", "DOI": "10.1098/rsif.2006.0134", "citationKey": "", "url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1885356/", "accessDate": "2018-08-09T07:44:05Z", "PMID": "17015305", "PMCID": "PMC1885356", "ISSN": "1742-5689", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "PubMed Central", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/B9MSCXWK" }, "dateAdded": "2018-08-09T07:44:05Z", "dateModified": "2020-07-29T13:38:03Z" } }, { "key": "ZDMENPHR", "version": 88, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/ZDMENPHR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/ZDMENPHR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Zhao et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "ZDMENPHR", "version": 88, "itemType": "conferencePaper", "title": "Applying the Virtual Data Provenance Model", "creators": [ { "creatorType": "author", "firstName": "Yong", "lastName": "Zhao" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Wilde" }, { "creatorType": "author", "firstName": "Ian", "lastName": "Foster" }, { "creatorType": "editor", "firstName": "Luc", "lastName": "Moreau" }, { "creatorType": "editor", "firstName": "Ian", "lastName": "Foster" } ], "abstractNote": "In many domains of science, engineering, and commerce, data analysis systems are employed to derive new data (and ultimately, one hopes, knowledge) from datasets describing experimental results or simulated phenomena. To support such analyses, we have developed a “virtual data system” that allows users first to define, then to invoke, and finally explore the provenance of procedures (and workflows comprising multiple procedure calls) that perform such data derivations. The underlying execution model is “functional” in the sense that procedures read (but do not modify) their input and produce output via deterministic computations. This property makes it straightforward for the virtual data system to record not only the recipe for producing any given data object but also sufficient information about the environment in which the recipe has been executed, all with sufficient fidelity that the steps used to create a data object can be re-executed to reproduce the data object at a later time or a different location. The virtual data system maintains this information in an integrated schema alongside semantic annotations, and thus enables a powerful query capability in which the rich semantic information implied by knowledge of the structure of data derivation procedures can be exploited to provide an information environment that fuses recipe, history, and application-specific semantics. We provide here an overview of this integration, the queries and transformations that it enables, and examples of how these capabilities can serve scientific processes.", "proceedingsTitle": "Provenance and Annotation of Data", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "148-161", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/11890850_16", "ISBN": "978-3-540-46303-0", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Argument Model", "type": 1 }, { "tag": "Procedure Call", "type": 1 }, { "tag": "Procedure Definition", "type": 1 }, { "tag": "Provenance Information", "type": 1 }, { "tag": "Virtual Data", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/AAVGTJLY" }, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-07-29T13:37:36Z" } }, { "key": "2PBL89XS", "version": 87, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/2PBL89XS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/2PBL89XS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Khan et al.", "parsedDate": "2019-11-01", "numChildren": 0 }, "data": { "key": "2PBL89XS", "version": 87, "itemType": "journalArticle", "title": "Sharing interoperable workflow provenance: A review of best practices and their practical application in CWLProv", "creators": [ { "creatorType": "author", "firstName": "Farah Zaib", "lastName": "Khan" }, { "creatorType": "author", "firstName": "Stian", "lastName": "Soiland-Reyes" }, { "creatorType": "author", "firstName": "Richard O.", "lastName": "Sinnott" }, { "creatorType": "author", "firstName": "Andrew", "lastName": "Lonie" }, { "creatorType": "author", "firstName": "Carole", "lastName": "Goble" }, { "creatorType": "author", "firstName": "Michael R.", "lastName": "Crusoe" } ], "abstractNote": "AbstractBackground. The automation of data analysis in the form of scientific workflows has become a widely adopted practice in many fields of research. Comput", "publicationTitle": "GigaScience", "publisher": "", "place": "", "date": "2019/11/01", "volume": "8", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Gigascience", "DOI": "10.1093/gigascience/giz095", "citationKey": "", "url": "https://academic.oup.com/gigascience/article/8/11/giz095/5611001", "accessDate": "2020-04-08T12:01:51Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Sharing interoperable workflow provenance", "language": "en", "libraryCatalog": "academic.oup.com", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": { "dc:replaces": "http://zotero.org/groups/231441/items/BL49H684" }, "dateAdded": "2020-04-08T12:01:51Z", "dateModified": "2020-07-29T13:37:18Z" } }, { "key": "JQUBCA8Y", "version": 95, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/JQUBCA8Y", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/JQUBCA8Y", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Lebo et al.", "parsedDate": "2015", "numChildren": 0 }, "data": { "key": "JQUBCA8Y", "version": 95, "itemType": "bookSection", "title": "Walking into the Future with PROV Pingback: An Application to OPeNDAP Using Prizms", "creators": [ { "creatorType": "editor", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "editor", "firstName": "Beth", "lastName": "Plale" }, { "creatorType": "author", "firstName": "Timothy", "lastName": "Lebo" }, { "creatorType": "author", "firstName": "Patrick", "lastName": "West" }, { "creatorType": "author", "firstName": "Deborah L.", "lastName": "McGuinness" } ], "abstractNote": "Adding provenance to existing systems can benefit users, but comes at an expense that may be di cult for some to justify. This tradeo↵ can be overcome by increasing the value of provenance, by decreasing the cost to add it – or by doing both. This paper o↵ers a contribution for each. First, we develop further the W3C PROV pingback technique so that it may reach its potential to interconnect provenance records that would traditionally sit in isolation, thus increasing their value. Second, we reduce the expense to publish the provenance of existing host systems by using minimal coupling to the Prizms Linked Data platform. Using an Earth Sciences scenario and the OPeNDAP data transport architecture as an example host system, we investigate how PROV pingback could work in practice, demonstrate its potential, and identify outstanding issues that must be addressed before it can be widely adopted.", "bookTitle": "Provenance and Annotation of Data and Processes", "series": "", "seriesNumber": "", "volume": "8628", "numberOfVolumes": "", "edition": "", "date": "2015", "publisher": "Springer International Publishing", "place": "Cham", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "31-43", "ISBN": "978-3-319-16461-8 978-3-319-16462-5", "DOI": "10.1007/978-3-319-16462-5_3", "citationKey": "", "url": "http://link.springer.com/10.1007/978-3-319-16462-5_3", "accessDate": "2020-07-11T11:29:19Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Walking into the Future with PROV Pingback", "language": "en", "libraryCatalog": "DOI.org (Crossref)", "callNumber": "", "rights": "", "extra": "Series Title: Lecture Notes in Computer Science", "tags": [], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-07-11T11:29:39Z", "dateModified": "2020-07-11T11:29:39Z" } }, { "key": "8CK39RJ5", "version": 78, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/8CK39RJ5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/8CK39RJ5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/231441/items/2L5HDY55", "type": "application/json" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } } }, "data": { "key": "8CK39RJ5", "version": 78, "parentItem": "2L5HDY55", "itemType": "attachment", "linkMode": "linked_url", "title": "Semantic Scholar Link", "accessDate": "2020-02-05T10:11:17Z", "url": "https://www.semanticscholar.org/paper/A-survey-of-data-provenance-techniques-Simmhan-Plale/54c2b2f2a709f5c14d0f46265729a06e69f1955f", "note": "", "contentType": "text/html", "charset": "", "tags": [], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "JWFM9ILD", "version": 78, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/JWFM9ILD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/JWFM9ILD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Buneman et al.", "parsedDate": "2001", "numChildren": 0 }, "data": { "key": "JWFM9ILD", "version": 78, "itemType": "conferencePaper", "title": "Why and Where: A Characterization of Data Provenance", "creators": [ { "creatorType": "author", "firstName": "Peter", "lastName": "Buneman" }, { "creatorType": "author", "firstName": "Sanjeev", "lastName": "Khanna" }, { "creatorType": "author", "firstName": "Tan", "lastName": "Wang-Chiew" }, { "creatorType": "editor", "firstName": "Jan", "lastName": "Van den Bussche" }, { "creatorType": "editor", "firstName": "Victor", "lastName": "Vianu" } ], "abstractNote": "With the proliferation of database views and curated data- bases, the issue of data provenance - where a piece of data came from and the process by which it arrived in the database - is becoming increasingly important, especially in scientific databases where understanding provenance is crucial to the accuracy and currency of data. In this paper we describe an approach to computing provenance when the data of interest has been created by a database query. We adopt a syntactic approach and present results for a general data model that applies to relational databases as well as to hierarchical data such as XML. A novel aspect of our work is a distinction between “why” provenance (refers to the source data that had some influence on the existence of the data) and “where” provenance (refers to the location(s) in the source databases from which the data was extracted).Supported in part by an Alfred P. Sloan Research Fellowship.", "proceedingsTitle": "Database Theory — ICDT 2001", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2001", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "316-330", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/3-540-44503-X_20", "ISBN": "978-3-540-44503-6", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Why and Where", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Derivation Basis", "type": 1 }, { "tag": "Edge Label", "type": 1 }, { "tag": "Normal Form", "type": 1 }, { "tag": "Output Expression", "type": 1 }, { "tag": "Query Language", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "3P4Z4KQE", "version": 78, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/3P4Z4KQE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/3P4Z4KQE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Ram and Liu", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "3P4Z4KQE", "version": 78, "itemType": "conferencePaper", "title": "Understanding the Semantics of Data Provenance to Support Active Conceptual Modeling", "creators": [ { "creatorType": "author", "firstName": "Sudha", "lastName": "Ram" }, { "creatorType": "author", "firstName": "Jun", "lastName": "Liu" }, { "creatorType": "editor", "firstName": "Peter P.", "lastName": "Chen" }, { "creatorType": "editor", "firstName": "Leah Y.", "lastName": "Wong" } ], "abstractNote": "Data Provenance refers to the lineage of data including its origin, key events that occur over the course of its lifecycle, and other details associated with data creation, processing, and archiving. We believe that tracking provenance enables users to share, discover, and reuse the data, thus streamlining collaborative activities, reducing the possibility of repeating dead ends, and facilitating learning. It also provides a mechanism to transition from static to active conceptual modeling. The primary goal of our research is to investigate the semantics or meaning of data provenance. We describe the W7 model that represents different components of provenance and their relationships to each other. We conceptualize provenance as a combination of seven interconnected elements including “what”, “when”, “where”, “how”, “who”, “which” and “why”. Each of these components may be used to track events that affect data during its lifetime. A homeland security example illustrates how current conceptual models can be extended to embed provenance.", "proceedingsTitle": "Active Conceptual Modeling of Learning", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "17-29", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-540-77503-4_3", "ISBN": "978-3-540-77503-4", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "UP34S6CK", "version": 78, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/UP34S6CK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/UP34S6CK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Cohen et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "UP34S6CK", "version": 78, "itemType": "conferencePaper", "title": "Towards a Model of Provenance and User Views in Scientific Workflows", "creators": [ { "creatorType": "author", "firstName": "Shirley", "lastName": "Cohen" }, { "creatorType": "author", "firstName": "Sarah", "lastName": "Cohen-Boulakia" }, { "creatorType": "author", "firstName": "Susan", "lastName": "Davidson" }, { "creatorType": "editor", "firstName": "Ulf", "lastName": "Leser" }, { "creatorType": "editor", "firstName": "Felix", "lastName": "Naumann" }, { "creatorType": "editor", "firstName": "Barbara", "lastName": "Eckman" } ], "abstractNote": "Scientific experiments are becoming increasingly large and complex, with a commensurate increase in the amount and complexity of data generated. Data, both intermediate and final results, is derived by chaining and nesting together multiple database searches and analytical tools. In many cases, the means by which the data are produced is not known, making the data difficult to interpret and the experiment impossible to reproduce. Provenance in scientific workflows is thus of paramount importance.In this paper, we provide a formal model of provenance for scientific workflows which is general (i.e. can be used with existing workflow systems, such as Kepler, myGrid and Chimera) and sufficiently expressive to answer the provenance queries we encountered in a number of case studies. Interestingly, our model not only takes into account the chained and nested structure of scientific workflows, but allows asks for provenance at different levels of abstraction (user views).", "proceedingsTitle": "Data Integration in the Life Sciences", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "264-279", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/11799511_24", "ISBN": "978-3-540-36595-2", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Data Object", "type": 1 }, { "tag": "Data Provenance", "type": 1 }, { "tag": "Provenance Information", "type": 1 }, { "tag": "Service Invocation", "type": 1 }, { "tag": "Transitive Closure", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "U6ICZLKS", "version": 78, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/U6ICZLKS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/U6ICZLKS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Asghar et al.", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "U6ICZLKS", "version": 78, "itemType": "conferencePaper", "title": "Securing Data Provenance in the Cloud", "creators": [ { "creatorType": "author", "firstName": "Muhammad Rizwan", "lastName": "Asghar" }, { "creatorType": "author", "firstName": "Mihaela", "lastName": "Ion" }, { "creatorType": "author", "firstName": "Giovanni", "lastName": "Russello" }, { "creatorType": "author", "firstName": "Bruno", "lastName": "Crispo" }, { "creatorType": "editor", "firstName": "Jan", "lastName": "Camenisch" }, { "creatorType": "editor", "firstName": "Dogan", "lastName": "Kesdogan" } ], "abstractNote": "Cloud storage offers the flexibility of accessing data from anywhere at any time while providing economical benefits and scalability. However, cloud stores lack the ability to manage data provenance. Data provenance describes how a particular piece of data has been produced. It is vital for a post-incident investigation, widely used in healthcare, scientific collaboration, forensic analysis and legal proceedings. Data provenance needs to be secured since it may reveal private information about the sensitive data while the cloud service provider does not guarantee confidentiality of the data stored in dispersed geographical locations. This paper proposes a scheme to secure data provenance in the cloud while offering the encrypted search.", "proceedingsTitle": "Open Problems in Network Security", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "145-160", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-642-27585-2_12", "ISBN": "978-3-642-27585-2", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Encrypted Cloud Storage", "type": 1 }, { "tag": "Privacy", "type": 1 }, { "tag": "Secure Data Provenance", "type": 1 }, { "tag": "Security", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "NBQZVHWV", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/NBQZVHWV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/NBQZVHWV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Szomszor and Moreau", "parsedDate": "2003", "numChildren": 0 }, "data": { "key": "NBQZVHWV", "version": 77, "itemType": "conferencePaper", "title": "Recording and Reasoning over Data Provenance in Web and Grid Services", "creators": [ { "creatorType": "author", "firstName": "Martin", "lastName": "Szomszor" }, { "creatorType": "author", "firstName": "Luc", "lastName": "Moreau" }, { "creatorType": "editor", "firstName": "Robert", "lastName": "Meersman" }, { "creatorType": "editor", "firstName": "Zahir", "lastName": "Tari" }, { "creatorType": "editor", "firstName": "Douglas C.", "lastName": "Schmidt" } ], "abstractNote": "Large-scale, dynamic and open environments such as the Grid and Web Services build upon existing computing infrastructures to supply dependable and consistent large-scale computational systems. This kind of architecture has been adopted by the business and scientific communities allowing them to exploit extensive and diverse computing resources to perform complex data processing tasks. In such systems, results are often derived by composing multiple, geographically distributed, heterogeneous services as specified by intricate workflow management. This leads to the undesirable situation where the results are known, but the means by which they were achieved is not. With both scientific experiments and business transactions, the notion of lineage and dataset derivation is of paramount importance since without it, information is potentially worthless. We address the issue of data provenance, the description of the origin of a piece of data, in these environments showing the requirements, uses and implementation difficulties. We propose an infrastructure level support for a provenance recording capability for service-oriented architectures such as the Grid and Web Services. We also offer services to view and retrieve provenance and we provide a mechanism by which provenance is used to determine whether previous computed results are still up to date.", "proceedingsTitle": "On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2003", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "603-620", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-540-39964-3_39", "ISBN": "978-3-540-39964-3", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Business Process Execution Language", "type": 1 }, { "tag": "Data Provenance", "type": 1 }, { "tag": "Grid Service", "type": 1 }, { "tag": "Open Grid Service Architecture", "type": 1 }, { "tag": "Provenance Information", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "9QWJQT73", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/9QWJQT73", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/9QWJQT73", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Hartig", "numChildren": 0 }, "data": { "key": "9QWJQT73", "version": 77, "itemType": "journalArticle", "title": "Provenance Information in the Web of Data", "creators": [ { "creatorType": "author", "firstName": "Olaf", "lastName": "Hartig" } ], "abstractNote": "The openness of the Web and the ease to combine linked data from different sources creates new challenges. Systems that consume linked data must evaluate quality and trustworthiness of the data. A common approach for data quality assessment is the analysis of provenance information. For this reason, this paper discusses provenance of data on the Web and proposes a suitable provenance model. While traditional provenance research usually addresses the creation of data, our provenance model also represents data access, a dimension of provenance that is particularly relevant in the context of Web data. Based on our model we identify options to obtain provenance information and we raise open questions concerning the publication of provenance-related metadata for linked data on the Web.", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "9", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "3NKJJEX3", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/3NKJJEX3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/3NKJJEX3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Cheney et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "3NKJJEX3", "version": 77, "itemType": "conferencePaper", "title": "Provenance as Dependency Analysis", "creators": [ { "creatorType": "author", "firstName": "James", "lastName": "Cheney" }, { "creatorType": "author", "firstName": "Amal", "lastName": "Ahmed" }, { "creatorType": "author", "firstName": "Umut A.", "lastName": "Acar" }, { "creatorType": "editor", "firstName": "Marcelo", "lastName": "Arenas" }, { "creatorType": "editor", "firstName": "Michael I.", "lastName": "Schwartzbach" } ], "abstractNote": "Provenance is information recording the source, derivation, or history of some information. Provenance tracking has been studied in a variety of settings; however, although many design points have been explored, the mathematical or semantic foundations of data provenance have received comparatively little attention. In this paper, we argue that dependency analysis techniques familiar from program analysis and program slicing provide a formal foundation for forms of provenance that are intended to show how (part of) the output of a query depends on (parts of) its input. We introduce a semantic characterization of such dependency provenance, show that this form of provenance is not computable, and provide dynamic and static approximation techniques.", "proceedingsTitle": "Database Programming Languages", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "138-152", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-540-75987-4_10", "ISBN": "978-3-540-75987-4", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Collection Type", "type": 1 }, { "tag": "Data Provenance", "type": 1 }, { "tag": "Dependency Analysis", "type": 1 }, { "tag": "Semantic Characterization", "type": 1 }, { "tag": "Typing Judgment", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "RVUI3RZN", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/RVUI3RZN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/RVUI3RZN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Davidson and Freire", "numChildren": 0 }, "data": { "key": "RVUI3RZN", "version": 77, "itemType": "journalArticle", "title": "Provenance and Scientific Workflows: Challenges and Opportunities", "creators": [ { "creatorType": "author", "firstName": "Susan B", "lastName": "Davidson" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" } ], "abstractNote": "Provenance in the context of workflows, both for the data they derive and for their specification, is an essential component to allow for result reproducibility, sharing, and knowledge re-use in the scientific community. Several workshops have been held on the topic, and it has been the focus of many research projects and prototype systems. This tutorial provides an overview of research issues in provenance for scientific workflows, with a focus on recent literature and technology in this area. It is aimed at a general database research audience and at people who work with scientific data and workflows. We will (1) provide a general overview of scientific workflows, (2) describe research on provenance for scientific workflows and show in detail how provenance is supported in existing systems; (3) discuss emerging applications that are enabled by provenance; and (4) outline open problems and new directions for database-related research.", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "6", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "9Y9DFSCK", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/9Y9DFSCK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/9Y9DFSCK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Park and Heidemann", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "9Y9DFSCK", "version": 77, "itemType": "conferencePaper", "title": "Provenance in Sensornet Republishing", "creators": [ { "creatorType": "author", "firstName": "Unkyu", "lastName": "Park" }, { "creatorType": "author", "firstName": "John", "lastName": "Heidemann" }, { "creatorType": "editor", "firstName": "Juliana", "lastName": "Freire" }, { "creatorType": "editor", "firstName": "David", "lastName": "Koop" }, { "creatorType": "editor", "firstName": "Luc", "lastName": "Moreau" } ], "abstractNote": "Sensornets are being deployed and increasingly brought on-line to share data as it is collected. Sensornet republishing is the process of transforming on-line sensor data and sharing the filtered, aggregated, or improved data with others. We explore the need for data provenance in this system to allow users to understand how processed results are derived and detect and correct anomalies. We describe our sensornet provenance system, exploring design alternatives and quantifying storage trade-offs in the context of a city-sized temperature monitoring application. In that application, our link approach outperforms other alternatives on saving storage requirement and our incremental compression scheme save the storage further up to 83%.", "proceedingsTitle": "Provenance and Annotation of Data and Processes", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "280-292", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-540-89965-5_28", "ISBN": "978-3-540-89965-5", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "REVR6SZS", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/REVR6SZS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/REVR6SZS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Altintas et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "REVR6SZS", "version": 77, "itemType": "conferencePaper", "title": "Provenance Collection Support in the Kepler Scientific Workflow System", "creators": [ { "creatorType": "author", "firstName": "Ilkay", "lastName": "Altintas" }, { "creatorType": "author", "firstName": "Oscar", "lastName": "Barney" }, { "creatorType": "author", "firstName": "Efrat", "lastName": "Jaeger-Frank" }, { "creatorType": "editor", "firstName": "Luc", "lastName": "Moreau" }, { "creatorType": "editor", "firstName": "Ian", "lastName": "Foster" } ], "abstractNote": "In many data-driven applications, analysis needs to be performed on scientific information obtained from several sources and generated by computations on distributed resources. Systematic analysis of this scientific information unleashes a growing need for automated data-driven applications that also can keep track of the provenance of the data and processes with little user interaction and overhead. Such data analysis can be facilitated by the recent advancements in scientific workflow systems. A major profit when using scientific workflow systems is the ability to make provenance collection a part of the workflow. Specifically, provenance should include not only the standard data lineage information but also information about the context in which the workflow was used, execution that processed the data, and the evolution of the workflow design. In this paper we describe a complete framework for data and process provenance in the Kepler Scientific Workflow System. We outline the requirements and issues related to data and workflow provenance in a multi-disciplinary workflow system and introduce how generic provenance capture can be facilitated in Kepler’s actor-oriented workflow environment. We also describe the usage of the stored provenance information for efficient rerun of scientific workflows.", "proceedingsTitle": "Provenance and Annotation of Data", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "118-132", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/11890850_14", "ISBN": "978-3-540-46303-0", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Geographic Information System", "type": 1 }, { "tag": "Kepler System", "type": 1 }, { "tag": "Provenance Data", "type": 1 }, { "tag": "Provenance Information", "type": 1 }, { "tag": "Provenance Recorder", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "Q79P99QM", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/Q79P99QM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/Q79P99QM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Chapman and Jagadish", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "Q79P99QM", "version": 77, "itemType": "conferencePaper", "title": "Provenance and the Price of Identity", "creators": [ { "creatorType": "author", "firstName": "Adriane", "lastName": "Chapman" }, { "creatorType": "author", "firstName": "H. V.", "lastName": "Jagadish" }, { "creatorType": "editor", "firstName": "Juliana", "lastName": "Freire" }, { "creatorType": "editor", "firstName": "David", "lastName": "Koop" }, { "creatorType": "editor", "firstName": "Luc", "lastName": "Moreau" } ], "abstractNote": "As developers acknowledge that provenance is essential, more and more datasets are attempting to keep provenance records describing how they were created. Some of these datasets are constructed using workflows, others cobble together processes and applications to manipulate the data. While the provenance needs are the same, the inputs and set of processes used must be kept, the identity needs are very different. We outline several identification strategies that can be used for data manipulation outside of workflows. We evaluate these strategies in terms of time to create and store identity, and the space needed to keep this information. Additionally, we discuss the strengths and weaknesses of each strategy.", "proceedingsTitle": "Provenance and Annotation of Data and Processes", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "106-119", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-540-89965-5_12", "ISBN": "978-3-540-89965-5", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Data Item", "type": 1 }, { "tag": "Identity Strategy", "type": 1 }, { "tag": "Intermediate Data", "type": 1 }, { "tag": "Intermediate Result", "type": 1 }, { "tag": "Reverse Transformation", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } }, { "key": "F8MW5YVA", "version": 77, "library": { "type": "group", "id": 231441, "name": "Data Provenance", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_provenance", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/231441/items/F8MW5YVA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_provenance/items/F8MW5YVA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2016095, "username": "joerg.geiger", "name": "Jörg Geiger", "links": { "alternate": { "href": "https://www.zotero.org/joerg.geiger", "type": "text/html" } } }, "creatorSummary": "Sahoo et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "F8MW5YVA", "version": 77, "itemType": "conferencePaper", "title": "Ontology-Driven Provenance Management in eScience: An Application in Parasite Research", "creators": [ { "creatorType": "author", "firstName": "Satya S.", "lastName": "Sahoo" }, { "creatorType": "author", "firstName": "D. Brent", "lastName": "Weatherly" }, { "creatorType": "author", "firstName": "Raghava", "lastName": "Mutharaju" }, { "creatorType": "author", "firstName": "Pramod", "lastName": "Anantharam" }, { "creatorType": "author", "firstName": "Amit", "lastName": "Sheth" }, { "creatorType": "author", "firstName": "Rick L.", "lastName": "Tarleton" }, { "creatorType": "editor", "firstName": "Robert", "lastName": "Meersman" }, { "creatorType": "editor", "firstName": "Tharam", "lastName": "Dillon" }, { "creatorType": "editor", "firstName": "Pilar", "lastName": "Herrero" } ], "abstractNote": "Provenance, from the French word “provenir”, describes the lineage or history of a data entity. Provenance is critical information in scientific applications to verify experiment process, validate data quality and associate trust values with scientific results. Current industrial scale eScience projects require an end-to-end provenance management infrastructure. This infrastructure needs to be underpinned by formal semantics to enable analysis of large scale provenance information by software applications. Further, effective analysis of provenance information requires well-defined query mechanisms to support complex queries over large datasets. This paper introduces an ontology-driven provenance management infrastructure for biology experiment data, as part of the Semantic Problem Solving Environment (SPSE) for Trypanosoma cruzi (T.cruzi). This provenance infrastructure, called T.cruzi Provenance Management System (PMS), is underpinned by (a) a domain-specific provenance ontology called Parasite Experiment ontology, (b) specialized query operators for provenance analysis, and (c) a provenance query engine. The query engine uses a novel optimization technique based on materialized views called materialized provenance views (MPV) to scale with increasing data size and query complexity. This comprehensive ontology-driven provenance infrastructure not only allows effective tracking and management of ongoing experiments in the Tarleton Research Group at the Center for Tropical and Emerging Global Diseases (CTEGD), but also enables researchers to retrieve the complete provenance information of scientific results for publication in literature.", "proceedingsTitle": "On the Move to Meaningful Internet Systems: OTM 2009", "conferenceName": "", "publisher": "Springer", "place": "Berlin, Heidelberg", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "992-1009", "series": "Lecture Notes in Computer Science", "seriesNumber": "", "DOI": "10.1007/978-3-642-05151-7_18", "ISBN": "978-3-642-05151-7", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Ontology-Driven Provenance Management in eScience", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Bioinformatics", "type": 1 }, { "tag": "Parasite Experiment ontology", "type": 1 }, { "tag": "Provenance management framework", "type": 1 }, { "tag": "T.cruzi parasite research", "type": 1 }, { "tag": "eScience", "type": 1 }, { "tag": "provenance query engine", "type": 1 }, { "tag": "provenance query operators", "type": 1 }, { "tag": "provenir ontology", "type": 1 } ], "collections": [ "2BNCECP5" ], "relations": {}, "dateAdded": "2020-02-05T10:25:50Z", "dateModified": "2020-02-05T10:25:50Z" } } ]