{"id":"https://openalex.org/W2134860894","doi":"https://doi.org/10.1109/icppw.2002.1039762","title":"Using high performance systems to build collections for a digital library","display_name":"Using high performance systems to build collections for a digital library","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2134860894","doi":"https://doi.org/10.1109/icppw.2002.1039762","mag":"2134860894"},"language":"en","primary_location":{"id":"doi:10.1109/icppw.2002.1039762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icppw.2002.1039762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. International Conference on Parallel Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058048844","display_name":"Donna Bergmark","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I41639379","display_name":"Association of Research Libraries","ror":"https://ror.org/053mpbz30","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I41639379"]},{"id":"https://openalex.org/I87424562","display_name":"Ithaca College","ror":"https://ror.org/01kw1gj07","country_code":"US","type":"education","lineage":["https://openalex.org/I87424562"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Bergmark","raw_affiliation_strings":["Cornell Digital Library Research Group, Ithaca, NY, USA","Comell Digital Libr. Res. Group, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell Digital Library Research Group, Ithaca, NY, USA","institution_ids":["https://openalex.org/I41639379","https://openalex.org/I205783295"]},{"raw_affiliation_string":"Comell Digital Libr. Res. Group, Ithaca, NY, USA","institution_ids":["https://openalex.org/I87424562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058048844"],"corresponding_institution_ids":["https://openalex.org/I205783295","https://openalex.org/I41639379","https://openalex.org/I87424562"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15246659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"431","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8304966688156128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819377183914185},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6744786500930786},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6719426512718201},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6681048274040222},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.6236452460289001},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5575133562088013},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5054323673248291},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5052149891853333},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.4825148284435272},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.279064416885376},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22727268934249878}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8304966688156128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819377183914185},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6744786500930786},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6719426512718201},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6681048274040222},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.6236452460289001},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5575133562088013},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5054323673248291},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5052149891853333},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.4825148284435272},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.279064416885376},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22727268934249878},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icppw.2002.1039762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icppw.2002.1039762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. International Conference on Parallel Processing Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.9033","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.9033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mercator.comm.nsdlib.org/CollectionBuilding/DCADL_bergmark.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.6734","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.6734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mercator.comm.nsdlib.org/CollectionBuilding/bergmarkd_collections.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.509.1659","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.509.1659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iicm.edu:8000/thesis/cguetl_diss/literatur/Kapitel07/References/Bergmark_2002/using-high-performance-systems.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1481372933","https://openalex.org/W1489992655","https://openalex.org/W1529322544","https://openalex.org/W1536700701","https://openalex.org/W1602667807","https://openalex.org/W1613836731","https://openalex.org/W2003754790","https://openalex.org/W2039976898","https://openalex.org/W2080571106","https://openalex.org/W2081094496","https://openalex.org/W2129620481","https://openalex.org/W2138621811","https://openalex.org/W2140279085","https://openalex.org/W2164542999","https://openalex.org/W2293546693","https://openalex.org/W4285719527","https://openalex.org/W6628707600","https://openalex.org/W6636119244","https://openalex.org/W6679117999","https://openalex.org/W6680536191"],"related_works":["https://openalex.org/W2626999804","https://openalex.org/W4250004941","https://openalex.org/W2736202444","https://openalex.org/W2097808084","https://openalex.org/W2049015391","https://openalex.org/W2137014442","https://openalex.org/W1533158771","https://openalex.org/W122082928","https://openalex.org/W2104288289","https://openalex.org/W2521397622"],"abstract_inverted_index":{"Nothing":[0],"is":[1,20],"more":[2],"distributed":[3],"than":[4],"the":[5,54],"Web,":[6],"with":[7,36],"its":[8],"content":[9],"spread":[10],"across":[11],"thousands":[12],"of":[13,29,50],"servers.":[14],"High":[15],"performance":[16],"hardware":[17],"and":[18,27],"software":[19],"essential":[21],"for":[22,53],"an":[23],"effective":[24],"download,":[25],"analysis,":[26],"organization":[28],"this":[30],"content.":[31],"We":[32],"describe":[33],"our":[34],"experience":[35],"a":[37],"highly":[38],"parallel":[39],"Web":[40],"crawling":[41],"system":[42],"(Mercator)":[43],"to":[44],"construct":[45],"-":[46,48],"automatically":[47],"collections":[49],"scientific":[51],"resources":[52],"National":[55],"Science":[56],"Digital":[57],"Library.":[58]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
