Dear Wiki user, You have subscribed to a wiki page or wiki category on "Tika Wiki" for change notification.
The "GrobidJournalParser" page has been changed by ChrisMattmann: https://wiki.apache.org/tika/GrobidJournalParser?action=diff&rev1=4&rev2=5 Comment: - update example from Tika app "org.apache.tika.parser.CompositeParser", "org.apache.tika.parser.journal.JournalParser" ], - "X-TIKA:content": "<html xmlns=\"http://www.w3.org/1999/xhtml\";>\n<head>\n<meta name=\"access_permission:extract_for_accessibility\" content=\"true\" />\n<meta name=\"meta:save-date\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"access_permission:modify_annotations\" content=\"true\" />\n<meta name=\"Creation-Date\" content=\"2006-02-15T21:13:58Z\" />\n<meta name=\"grobid:header_Address\" content=\"Pasadena, CA 91109, USA Los Angeles, CA 90089, USA\" />\n<meta name=\"access_permission:fill_in_form\" content=\"true\" />\n<meta name=\"created\" content=\"Wed Feb 15 13:13:58 PST 2006\" />\n<meta name=\"grobid:header_FullAffiliations\" content=\"[Affiliation{name='null', url='null', institutions=[California Institute of Technology], departments=null, laboratories=[Jet Propulsion Laboratory], country='USA', postCode='91109', postBox='null', region='CA', settlement='Pasadena', addrLine='null', marker='1', addressString='null', affiliationString='null', failAffiliation=false}, Affiliation{name='null', url='null', institutions=[University of Southern California], departments=[Computer Science Department], laboratories=null, country='USA', postCode='90089', postBox='null', region='CA', settlement='Los Angeles', addrLine='null', marker='2', addressString='null', affiliationString='null',..snip..", + "X-TIKA:content": "<html xmlns=\"http://www.w3.org/1999/xhtml\";>\n<head>\n<meta name=\"access_permission:extract_for_accessibility\" content=\"true\" />\n<meta name=\"meta:save-date\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"grobid:header_Affiliation\" content=\"1 Jet Propulsion Laboratory California Institute of Technology; 2 Computer Science Department University of Southern California\" />\n<meta name=\"Content-Length\" content=\"200435\" />\n<meta name=\"dcterms:created\" content=\"2006-02-15T21:13:58Z\" />\n<meta name=\"Author\" content=\"End User Computing Services\" />\n<meta name=\"date\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"access_permission:can_modify\" content=\"true\" />\n<meta name=\"creator\" content=\"End User Computing Services\" />\n<meta name=\"access_permission:modify_annotations\" content=\"true\" />\n<meta name=\"Creation-Date\" content=\"2006-02-15T21:13:58Z\" />\n<meta name=\"grobid:header_Address\" content=\"Pasadena, CA 91109 USA Los Angeles, CA 90089 USA \" />\n<meta name=\"meta:author\" content=\"End User Computing Services\" />\n<meta name=\"created\" content=\"Wed Feb 15 13:13:58 PST 2006\" />\n<meta name=\"access_permission:fill_in_form\" content=\"true\" />\n<meta name=\"grobid:header_FullAffiliations\" content=\"[Affiliation {orgName=Jet Propulsion Laboratory California Institute of Technology , address=Pasadena, CA 91109 USA},Affiliation {orgName=Computer Science Department University of Southern California , address=Los Angeles, CA 90089 USA}[Affiliation {orgName=Jet Propulsion Laboratory California Institute of Technology , address=Pasadena, CA 91109 USA},Affiliation {orgName=Computer Science Department University of Southern California , address=Los Angeles, CA 90089 USA}]\" />\n<meta name=\"grobid:header_Class\" content=\"org.apache.tika.metadata.Metadata\" />\n<meta name=\"dc:format\" content=\"application/pdf; version=1.4\" />\n<meta name=\"access_permission:can_print\" content=\"true\" />\n<meta name=\"Company\" content=\"ACM\" />\n<meta name=\"xmp:CreatorTool\" content=\"Acrobat PDFMaker 6.0 for Word\" />\n<meta name=\"resourceName\" content=\"ICSE06.pdf\" />\n<meta name=\"Last-Save-Date\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"dc:title\" content=\"Proceedings Template - WORD\" />\n<meta name=\"grobid:header_TEIJSONSource\" content=\"{"TEI":{"text":{"xml:lang":"en"},"teiHeader":{"fileDesc":{"titleStmt":{"title":{"content":"A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications","level":"a","type":"main"}},"sourceDesc":{"biblStruct":{"analytic":{"author":[{"persName":{"forename":[{"content":"Chris","type":"first"},{"content":"A","type":"middle"}],"surname":"Mattmann"},"affiliation":[{"address":{"region":"CA","postCode":91109,"settlement":"Pasadena","country":{"content":"USA","key":"US"}},"orgName":[{"content":"Jet Propulsion Laboratory","type":"laboratory"},{"content":"California Institute of Technology","type":"institution"}]},{"address":{"region":"CA","postCode":90089,"settlement":"Los Angeles","country":{"content":"USA","key":"US"}},"orgName":[{"content":"Computer Science Department","type":"department"},{"content":"University of Southern California","type":"institution"}]}]},{"persName":{"forename":[{"content":"Daniel","type":"first"},{"content":"J","type":"middle"}],"surname":"Crichton"},"affiliation":{"address":{"region":"CA","postCode":91109,"settlement":"Pasadena","country":{"content":"USA","key":"US"}},"orgName":[{"content":"Jet Propulsion Laboratory","type":"laboratory"},{"content":"California Institute of Technology","type":"institution"}]}},{"persName":{"forename":{"content":"Nenad","type":"first"},"surname":"Medvidovic"},"affiliation":{"address":{"region":"CA","postCode":90089,"settlement":"Los Angeles","country":{"content":"USA","key":"US"}},"orgName":[{"content":"Computer Science Department","type":"department"},{"content":"University of Southern California","type":"institution"}]}},{"persName":{"forename":{"content":"Steve","type":"first"},"surname":"Hughes"},"affiliation":{"address":{"region":"CA","postCode":91109,"settlement":"Pasadena","country":{"content":"USA","key":"US"}},"orgName":[{"content":"Jet Propulsion Laboratory","type":"laboratory"},{"content":"California Institute of Technology","type":"institution"}]}}],"title":{"content":"A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications","level":"a","type":"main"}},"monogr":{"imprint":{"date":""}}}},"publicationStmt":{"availability":{"licence":"","status":"unknown"},"publisher":""}},"profileDesc":{"abstract":{"p":"Modern scientific research is increasingly conducted by virtual communities of scientists distributed around the world. The data volumes created by these communities are extremely large, and growing rapidly. The management of the resulting highly distributed, virtual data systems is a complex task, characterized by a number of formidable technical challenges, many of which are of a software engineering nature. In this paper we describe our experience over the past seven years in constructing and deploying OODT, a software framework that supports large, distributed, virtual scientific communities. We outline the key software engineering challenges that we faced, and addressed, along the way. We argue that a major contributor to the success of OODT was its explicit focus on software architecture. We describe several large-scale, real-world deployments of OODT, and the manner in which OODT helped us to address the domain-specific challenges induced by each deployment."},"textClass":{"keywords":{"term":["D2 Software Engineering, D211 Domain Specific Architectures","Keywords","OODT, Data Management, Software Architecture"]}}},"xml:lang":"en"},"xmlns":"http://www.tei-c.org/ns/1.0"}}\"; />\n<meta name=\"access_permission:assemble_document\" content=\"true\" />\n<meta name=\"dcterms:modified\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"meta:creation-date\" content=\"2006-02-15T21:13:58Z\" />\n<meta name=\"dc:creator\" content=\"End User Computing Services\" />\n<meta name=\"pdf:PDFVersion\" content=\"1.4\" />\n<meta name=\"Last-Modified\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"SourceModified\" content=\"D:20060215211344\" />\n<meta name=\"X-Parsed-By\" content=\"org.apache.tika.parser.CompositeParser\" />\n<meta name=\"X-Parsed-By\" content=\"org.apache.tika.parser.journal.JournalParser\" />\n<meta name=\"modified\" content=\"2006-02-15T21:16:01Z\" />\n<meta name=\"access_permission:can_print_degraded\" content=\"true\" />\n<meta name=\"xmpTPg:NPages\" content=\"10\" />\n<meta name=\"pdf:encrypted\" content=\"false\" />\n<meta name=\"access_permission:extract_content\" content=\"true\" />\n<meta name=\"grobid:header_Keyword\" content=\""D2 Software Engineering, D211 Domain Specific Architectures"\" />\n<meta name=\"producer\" content=\"Acrobat Distiller 6.0 (Windows)\" />\n<meta name=\"grobid:header_Title\" content=\"A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications\" />\n<meta name=\"grobid:header_TEIXMLSource\" content=\"<?xml version="1.0" encoding="UTF-8"?>\n<?xml-model href="file:///Users/mattmann/git/grobid/grobid-home/schemas/rng/Grobid.rng" schematypens="http://relaxng.org/ns/structure/1.0"?>\n<TEI xmlns="http://www.tei-c.org/ns/1.0">\n\t<teiHeader xml:lang="en">\n\t\t<fileDesc>\n\t\t\t<titleStmt>\n\t\t\t\t<title level="a" type="main">A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications</title>\n\t\t\t</titleStmt>\n\t\t\t<publicationStmt>\n\t\t\t\t<publisher/>\n\t\t\t\t<availability status="unknown"><licence/></availability>\n\t\t\t</publicationStmt>\n\t\t\t<sourceDesc>\n\t\t\t\t<biblStruct>\n\t\t\t\t\t<analytic>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type="first">Chris</forename>\n\t\t\t\t\t\t\t\t<forename type="middle">A</forename>\n\t\t\t\t\t\t\t\t<surname>Mattmann</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type="laboratory">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type="institution">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key="US">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type="department">Computer Science Department</orgName>\n\t\t\t\t\t\t\t\t<orgName type="institution">University of Southern California</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>90089</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Los Angeles</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key="US">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type="first">Daniel</forename>\n\t\t\t\t\t\t\t\t<forename type="middle">J</forename>\n\t\t\t\t\t\t\t\t<surname>Crichton</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type="laboratory">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type="institution">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key="US">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type="first">Nenad</forename>\n\t\t\t\t\t\t\t\t<surname>Medvidovic</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type="department">Computer Science Department</orgName>\n\t\t\t\t\t\t\t\t<orgName type="institution">University of Southern California</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>90089</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Los Angeles</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key="US">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type="first">Steve</forename>\n\t\t\t\t\t\t\t\t<surname>Hughes</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type="laboratory">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type="institution">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key="US">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<title level="a" type="main">A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications</title>\n\t\t\t\t\t</analytic>\n\t\t\t\t\t<monogr>\n\t\t\t\t\t\t<imprint>\n\t\t\t\t\t\t\t<date/>\n\t\t\t\t\t\t</imprint>\n\t\t\t\t\t</monogr>\n\t\t\t\t</biblStruct>\n\t\t\t</sourceDesc>\n\t\t</fileDesc>\n\t\t<profileDesc>\n\t\t\t<textClass>\n\t\t\t\t<keywords>\n\t\t\t\t\t<term>D2 Software Engineering, D211 Domain Specific Architectures</term>\n\t\t\t\t\t<term>Keywords</term>\n\t\t\t\t\t<term>OODT, Data Management, Software Architecture</term>\n\t\t\t\t</keywords>\n\t\t\t</textClass>\n\t\t\t<abstract>\n\t\t\t\t<p>Modern scientific research is increasingly conducted by virtual communities of scientists distributed around the world. The data volumes created by these communities are extremely large, and growing rapidly. The management of the resulting highly distributed, virtual data systems is a complex task, characterized by a number of formidable technical challenges, many of which are of a software engineering nature. In this paper we describe our experience over the past seven years in constructing and deploying OODT, a software framework that supports large, distributed, virtual scientific communities. We outline the key software engineering challenges that we faced, and addressed, along the way. We argue that a major contributor to the success of OODT was its explicit focus on software architecture. We describe several large-scale, real-world deployments of OODT, and the manner in which OODT helped us to address the domain-specific challenges induced by each deployment.</p>\n\t\t\t</abstract>\n\t\t</profileDesc>\n\t</teiHeader>\n\t<text xml:lang="en">\n\t</text>\n</TEI>\n\" />\n<meta name=\"Content-Type\" content=\"application/pdf\" />\n<meta name=\"grobid:header_Authors\" content=\"Chris A Mattmann 1,2 Daniel J Crichton 1 Nenad Medvidovic 2 Steve Hughes 1 \" />\n<title>Proceedings Template - WORD</title>\n</head>\n<body><div class=\"page\"><p />\n<p>A Software Architecture-Based Framework for Highly \nDistributed and Data Intensive Scientific Applications \n</p>\n<p> \nChris A. Mattmann1, 2 Daniel J. Crichton1 Nenad Medvidovic2 Steve Hughes1 \n</p>\n<p> \n1Jet Propulsion Laboratory \n</p>\n<p>California Institute of Technology \nPasadena, CA 91109, USA \n</p>\n<p>{dan.crichton,mattmann,steve.hughes}@jpl.nasa.gov \n</p>\n<p>2Computer Science Department \nUniversity of Southern California \n</p>\n<p>Los Angeles, CA 90089, USA \n{mattmann,neno}@usc.edu \n</p>\n<p> \nABSTRACT \nModern scientific research is increasingly conducted by virtual \ncommunities of scientists distributed around the world. The data \nvolumes created by these communities are extremely large, and \ngrowing rapidly. The management of the resulting highly \ndistributed, virtual data systems is a..snip", - "X-TIKA:parse_time_millis": "11529", + "X-TIKA:parse_time_millis": "4302", "access_permission:assemble_document": "true", "access_permission:can_modify": "true", "access_permission:can_print": "true", @@ -84, +84 @@ "dc:title": "Proceedings Template - WORD", "dcterms:created": "2006-02-15T21:13:58Z", "dcterms:modified": "2006-02-15T21:16:01Z", - "grobid:header_Abstract": "Modern scientific research is increasingly conducted by virtual communities of scientists distributed around the world. The data volumes created by these communities are extremely large, and growing rapidly. The management of the resulting highly distributed, virtual data systems is a complex task, characterized by a number of formidable technical challenges, many of which are of a software engineering nature. In this paper we describe our experience over the past seven years in constructing and deploying OODT, a software framework that supports large, distributed, virtual scientific communities. We outline the key software engineering challenges that we faced, and addressed, along the way. We argue that a major contributor to the success of OODT was its explicit focus on software architecture. We describe several large-scale, real-world deployments of OODT, and the manner in which OODT helped us to address the domain-specific challenges induced by each deployment.", - "grobid:header_AbstractHeader": "ABSTRACT", - "grobid:header_Address": "Pasadena, CA 91109, USA Los Angeles, CA 90089, USA", + "grobid:header_Address": "Pasadena, CA 91109 USA Los Angeles, CA 90089 USA ", - "grobid:header_Affiliation": "1 Jet Propulsion Laboratory California Institute of Technology ; 2 Computer Science Department University of Southern California", + "grobid:header_Affiliation": "1 Jet Propulsion Laboratory California Institute of Technology; 2 Computer Science Department University of Southern California", - "grobid:header_Authors": "Chris A. Mattmann 1, 2 Daniel J. Crichton 1 Nenad Medvidovic 2 Steve Hughes 1", + "grobid:header_Authors": "Chris A Mattmann 1,2 Daniel J Crichton 1 Nenad Medvidovic 2 Steve Hughes 1 ", + "grobid:header_Class": "org.apache.tika.metadata.Metadata", + "grobid:header_FullAffiliations": "[Affiliation {orgName=Jet Propulsion Laboratory California Institute of Technology , address=Pasadena, CA 91109 USA},Affiliation {orgName=Computer Science Department University of Southern California , address=Los Angeles, CA 90089 USA}[Affiliation {orgName=Jet Propulsion Laboratory California Institute of Technology , address=Pasadena, CA 91109 USA},Affiliation {orgName=Computer Science Department University of Southern California , address=Los Angeles, CA 90089 USA}]", + "grobid:header_Keyword": "\"D2 Software Engineering, D211 Domain Specific Architectures\"", + "grobid:header_TEIJSONSource": "{\"TEI\":{\"text\":{\"xml:lang\":\"en\"},\"teiHeader\":{\"fileDesc\":{\"titleStmt\":{\"title\":{\"content\":\"A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications\",\"level\":\"a\",\"type\":\"main\"}},\"sourceDesc\":{\"biblStruct\":{\"analytic\":{\"author\":[{\"persName\":{\"forename\":[{\"content\":\"Chris\",\"type\":\"first\"},{\"content\":\"A\",\"type\":\"middle\"}],\"surname\":\"Mattmann\"},\"affiliation\":[{\"address\":{\"region\":\"CA\",\"postCode\":91109,\"settlement\":\"Pasadena\",\"country\":{\"content\":\"USA\",\"key\":\"US\"}},\"orgName\":[{\"content\":\"Jet Propulsion Laboratory\",\"type\":\"laboratory\"},{\"content\":\"California Institute of Technology\",\"type\":\"institution\"}]},{\"address\":{\"region\":\"CA\",\"postCode\":90089,\"settlement\":\"Los Angeles\",\"country\":{\"content\":\"USA\",\"key\":\"US\"}},\"orgName\":[{\"content\":\"Computer Science Department\",\"type\":\"department\"},{\"content\":\"University of Southern California\",\"type\":\"institution\"}]}]},{\"persName\":{\"forename\":[{\"content\":\"Daniel\",\"type\":\"first\"},{\"content\":\"J\",\"type\":\"middle\"}],\"surname\":\"Crichton\"},\"affiliation\":{\"address\":{\"region\":\"CA\",\"postCode\":91109,\"settlement\":\"Pasadena\",\"country\":{\"content\":\"USA\",\"key\":\"US\"}},\"orgName\":[{\"content\":\"Jet Propulsion Laboratory\",\"type\":\"laboratory\"},{\"content\":\"California Institute of Technology\",\"type\":\"institution\"}]}},{\"persName\":{\"forename\":{\"content\":\"Nenad\",\"type\":\"first\"},\"surname\":\"Medvidovic\"},\"affiliation\":{\"address\":{\"region\":\"CA\",\"postCode\":90089,\"settlement\":\"Los Angeles\",\"country\":{\"content\":\"USA\",\"key\":\"US\"}},\"orgName\":[{\"content\":\"Computer Science Department\",\"type\":\"department\"},{\"content\":\"University of Southern California\",\"type\":\"institution\"}]}},{\"persName\":{\"forename\":{\"content\":\"Steve\",\"type\":\"first\"},\"surname\":\"Hughes\"},\"affiliation\":{\"address\":{\"region\":\"CA\",\"postCode\":91109,\"settlement\":\"Pasadena\",\"country\":{\"content\":\"USA\",\"key\":\"US\"}},\"orgName\":[{\"content\":\"Jet Propulsion Laboratory\",\"type\":\"laboratory\"},{\"content\":\"California Institute of Technology\",\"type\":\"institution\"}]}}],\"title\":{\"content\":\"A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications\",\"level\":\"a\",\"type\":\"main\"}},\"monogr\":{\"imprint\":{\"date\":\"\"}}}},\"publicationStmt\":{\"availability\":{\"licence\":\"\",\"status\":\"unknown\"},\"publisher\":\"\"}},\"profileDesc\":{\"abstract\":{\"p\":\"Modern scientific research is increasingly conducted by virtual communities of scientists distributed around the world. The data volumes created by these communities are extremely large, and growing rapidly. The management of the resulting highly distributed, virtual data systems is a complex task, characterized by a number of formidable technical challenges, many of which are of a software engineering nature. In this paper we describe our experience over the past seven years in constructing and deploying OODT, a software framework that supports large, distributed, virtual scientific communities. We outline the key software engineering challenges that we faced, and addressed, along the way. We argue that a major contributor to the success of OODT was its explicit focus on software architecture. We describe several large-scale, real-world deployments of OODT, and the manner in which OODT helped us to address the domain-specific challenges induced by each deployment.\"},\"textClass\":{\"keywords\":{\"term\":[\"D2 Software Engineering, D211 Domain Specific Architectures\",\"Keywords\",\"OODT, Data Management, Software Architecture\"]}}},\"xml:lang\":\"en\"},\"xmlns\":\"http://www.tei-c.org/ns/1.0\"}}";, + "grobid:header_TEIXMLSource": "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<?xml-model href=\"file:///Users/mattmann/git/grobid/grobid-home/schemas/rng/Grobid.rng\" schematypens=\"http://relaxng.org/ns/structure/1.0\";?>\n<TEI xmlns=\"http://www.tei-c.org/ns/1.0\";>\n\t<teiHeader xml:lang=\"en\">\n\t\t<fileDesc>\n\t\t\t<titleStmt>\n\t\t\t\t<title level=\"a\" type=\"main\">A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications</title>\n\t\t\t</titleStmt>\n\t\t\t<publicationStmt>\n\t\t\t\t<publisher/>\n\t\t\t\t<availability status=\"unknown\"><licence/></availability>\n\t\t\t</publicationStmt>\n\t\t\t<sourceDesc>\n\t\t\t\t<biblStruct>\n\t\t\t\t\t<analytic>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type=\"first\">Chris</forename>\n\t\t\t\t\t\t\t\t<forename type=\"middle\">A</forename>\n\t\t\t\t\t\t\t\t<surname>Mattmann</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type=\"laboratory\">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type=\"institution\">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key=\"US\">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type=\"department\">Computer Science Department</orgName>\n\t\t\t\t\t\t\t\t<orgName type=\"institution\">University of Southern California</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>90089</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Los Angeles</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key=\"US\">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type=\"first\">Daniel</forename>\n\t\t\t\t\t\t\t\t<forename type=\"middle\">J</forename>\n\t\t\t\t\t\t\t\t<surname>Crichton</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type=\"laboratory\">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type=\"institution\">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key=\"US\">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type=\"first\">Nenad</forename>\n\t\t\t\t\t\t\t\t<surname>Medvidovic</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type=\"department\">Computer Science Department</orgName>\n\t\t\t\t\t\t\t\t<orgName type=\"institution\">University of Southern California</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>90089</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Los Angeles</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key=\"US\">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<author>\n\t\t\t\t\t\t\t<persName>\n\t\t\t\t\t\t\t\t<forename type=\"first\">Steve</forename>\n\t\t\t\t\t\t\t\t<surname>Hughes</surname>\n\t\t\t\t\t\t\t</persName>\n\t\t\t\t\t\t\t<affiliation>\n\t\t\t\t\t\t\t\t<orgName type=\"laboratory\">Jet Propulsion Laboratory</orgName>\n\t\t\t\t\t\t\t\t<orgName type=\"institution\">California Institute of Technology</orgName>\n\t\t\t\t\t\t\t\t<address>\n\t\t\t\t\t\t\t\t\t<postCode>91109</postCode>\n\t\t\t\t\t\t\t\t\t<settlement>Pasadena</settlement>\n\t\t\t\t\t\t\t\t\t<region>CA</region>\n\t\t\t\t\t\t\t\t\t<country key=\"US\">USA</country>\n\t\t\t\t\t\t\t\t</address>\n\t\t\t\t\t\t\t</affiliation>\n\t\t\t\t\t\t</author>\n\t\t\t\t\t\t<title level=\"a\" type=\"main\">A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications</title>\n\t\t\t\t\t</analytic>\n\t\t\t\t\t<monogr>\n\t\t\t\t\t\t<imprint>\n\t\t\t\t\t\t\t<date/>\n\t\t\t\t\t\t</imprint>\n\t\t\t\t\t</monogr>\n\t\t\t\t</biblStruct>\n\t\t\t</sourceDesc>\n\t\t</fileDesc>\n\t\t<profileDesc>\n\t\t\t<textClass>\n\t\t\t\t<keywords>\n\t\t\t\t\t<term>D2 Software Engineering, D211 Domain Specific Architectures</term>\n\t\t\t\t\t<term>Keywords</term>\n\t\t\t\t\t<term>OODT, Data Management, Software Architecture</term>\n\t\t\t\t</keywords>\n\t\t\t</textClass>\n\t\t\t<abstract>\n\t\t\t\t<p>Modern scientific research is increasingly conducted by virtual communities of scientists distributed around the world. The data volumes created by these communities are extremely large, and growing rapidly. The management of the resulting highly distributed, virtual data systems is a complex task, characterized by a number of formidable technical challenges, many of which are of a software engineering nature. In this paper we describe our experience over the past seven years in constructing and deploying OODT, a software framework that supports large, distributed, virtual scientific communities. We outline the key software engineering challenges that we faced, and addressed, along the way. We argue that a major contributor to the success of OODT was its explicit focus on software architecture. We describe several large-scale, real-world deployments of OODT, and the manner in which OODT helped us to address the domain-specific challenges induced by each deployment.</p>\n\t\t\t</abstract>\n\t\t</profileDesc>\n\t</teiHeader>\n\t<text xml:lang=\"en\">\n\t</text>\n</TEI>\n", - "grobid:header_BeginPage": "-1", - "grobid:header_Class": "class org.grobid.core.data.BiblioItem", - "grobid:header_Email": "{dan.crichton,mattmann,steve.hughes}@jpl.nasa.gov ; {mattmann,neno}@usc.edu", - "grobid:header_EndPage": "-1", - "grobid:header_Error": "true", - "grobid:header_FirstAuthorSurname": "Mattmann", - "grobid:header_FullAffiliations": "[Affiliation{name='null', url='null', institutions=[California Institute of Technology], departments=null, laboratories=[Jet Propulsion Laboratory], country='USA', postCode='91109', postBox='null', region='CA', settlement='Pasadena', addrLine='null', marker='1', addressString='null', affiliationString='null', failAffiliation=false}, Affiliation{name='null', url='null', institutions=[University of Southern California], departments=[Computer Science Department], laboratories=null, country='USA', postCode='90089', postBox='null', region='CA', settlement='Los Angeles', addrLine='null', marker='2', addressString='null', affiliationString='null', failAffiliation=false}]", - "grobid:header_FullAuthors": "[Chris A Mattmann, Daniel J Crichton, Nenad Medvidovic, Steve Hughes]", - "grobid:header_Item": "-1", - "grobid:header_Keyword": "Categories and Subject Descriptors D2 Software Engineering, D211 Domain Specific Architectures Keywords OODT, Data Management, Software Architecture", - "grobid:header_Keywords": "[D2 Software Engineering, D211 Domain Specific Architectures (type:subject-headers), Keywords (type:subject-headers), OODT, Data Management, Software Architecture (type:subject-headers)]", - "grobid:header_Language": "en", - "grobid:header_NbPages": "-1", - "grobid:header_OriginalAuthors": "Chris A. Mattmann 1, 2 Daniel J. Crichton 1 Nenad Medvidovic 2 Steve Hughes 1", "grobid:header_Title": "A Software Architecture-Based Framework for Highly Distributed and Data Intensive Scientific Applications", "meta:author": "End User Computing Services", "meta:creation-date": "2006-02-15T21:13:58Z",
