{"id":"https://openalex.org/W2464674082","doi":"https://doi.org/10.1007/s00799-016-0184-4","title":"Web archive profiling through CDX summarization","display_name":"Web archive profiling through CDX summarization","publication_year":2016,"publication_date":"2016-07-16","ids":{"openalex":"https://openalex.org/W2464674082","doi":"https://doi.org/10.1007/s00799-016-0184-4","mag":"2464674082"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-016-0184-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-016-0184-4","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-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/A5087503706","display_name":"Sawood Alam","orcid":"https://orcid.org/0000-0002-8267-3326"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sawood Alam","raw_affiliation_strings":["Computer Science Department, Old Dominion University, Norfolk, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8267-3326","affiliations":[{"raw_affiliation_string":"Computer Science Department, Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081811192","display_name":"Michael L. Nelson","orcid":"https://orcid.org/0000-0003-3749-8116"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Nelson","raw_affiliation_strings":["Computer Science Department, Old Dominion University, Norfolk, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Old Dominion University, Norfolk, VA, USA","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079585875","display_name":"Herbert Van de Sompel","orcid":"https://orcid.org/0000-0002-0715-6126"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herbert Van de Sompel","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027991610","display_name":"Lyudmila Balakireva","orcid":"https://orcid.org/0000-0002-3919-3634"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lyudmila L. Balakireva","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081021549","display_name":"Harihar Shankar","orcid":"https://orcid.org/0000-0003-4949-0728"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harihar Shankar","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062232872","display_name":"David S. H. Rosenthal","orcid":"https://orcid.org/0000-0002-3627-499X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David S. H. Rosenthal","raw_affiliation_strings":["Stanford University Libraries, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Libraries, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087503706"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":1.3811,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86398014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":"3","first_page":"223","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.9988999962806702,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7995628118515015},{"id":"https://openalex.org/keywords/news-aggregator","display_name":"News aggregator","score":0.7865937948226929},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7521505355834961},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7028874754905701},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6660533547401428},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6622523069381714},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5729533433914185},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5187940001487732},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.5060216784477234},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.48532336950302124},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4631238877773285},{"id":"https://openalex.org/keywords/scrolling","display_name":"Scrolling","score":0.4114293158054352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1505066454410553},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.11878952383995056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995628118515015},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.7865937948226929},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7521505355834961},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7028874754905701},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6660533547401428},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6622523069381714},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5729533433914185},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5187940001487732},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5060216784477234},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.48532336950302124},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4631238877773285},{"id":"https://openalex.org/C59046462","wikidata":"https://www.wikidata.org/wiki/Q181319","display_name":"Scrolling","level":2,"score":0.4114293158054352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1505066454410553},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.11878952383995056},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00799-016-0184-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-016-0184-4","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1777016212","https://openalex.org/W1863089320","https://openalex.org/W1922832738","https://openalex.org/W2006672970","https://openalex.org/W2023657004","https://openalex.org/W2036682342","https://openalex.org/W2043275333","https://openalex.org/W2058374187","https://openalex.org/W2082998226","https://openalex.org/W2122829781","https://openalex.org/W2143079043","https://openalex.org/W2218908741","https://openalex.org/W2293827470","https://openalex.org/W2401581791","https://openalex.org/W2417822008","https://openalex.org/W3100737583","https://openalex.org/W4241808895","https://openalex.org/W4247704254","https://openalex.org/W6673207825","https://openalex.org/W6911377709"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W4255854114"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
