{"id":"https://openalex.org/W2944152102","doi":"https://doi.org/10.48550/arxiv.1905.03836","title":"Collecting 16K archived web pages from 17 public web archives","display_name":"Collecting 16K archived web pages from 17 public web archives","publication_year":2019,"publication_date":"2019-05-09","ids":{"openalex":"https://openalex.org/W2944152102","doi":"https://doi.org/10.48550/arxiv.1905.03836","mag":"2944152102"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1905.03836","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03836","pdf_url":"https://arxiv.org/pdf/1905.03836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.03836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042654957","display_name":"Mohamed Aturban","orcid":"https://orcid.org/0000-0001-7648-9082","observed_orcids":["https://orcid.org/0000-0001-7648-9082"]},"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":"Aturban, Mohamed","raw_affiliation_strings":["Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"\u2021Old Dominion University","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","observed_orcids":["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":"Nelson, Michael L.","raw_affiliation_strings":["Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"\u2021Old Dominion University","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085719625","display_name":"Michele C. Weigle","orcid":"https://orcid.org/0000-0002-2787-7166","observed_orcids":["https://orcid.org/0000-0002-2787-7166","https://orcid.org/0000-0002-4372-870X"]},"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":"Weigle, Michele C.","raw_affiliation_strings":["Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computer Science , Old Dominion University , Norfolk , VA ( USA)","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"\u2021Old Dominion University","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073828706","display_name":"Martin Klein","orcid":"https://orcid.org/0000-0003-0130-2097","observed_orcids":["https://orcid.org/0000-0003-0130-2097"]},"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":"Klein, Martin","raw_affiliation_strings":["Research Library , Los Alamos National Laboratory , Los Alamos , NM ( USA","Los Alamos national Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Library , Los Alamos National Laboratory , Los Alamos , NM ( USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Los Alamos national Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079585875","display_name":"Herbert Van De Sompel A","orcid":"https://orcid.org/0000-0002-0715-6126","observed_orcids":["https://orcid.org/0000-0002-0715-6126"]},"institutions":[{"id":"https://openalex.org/I1322597698","display_name":"Royal Netherlands Academy of Arts and Sciences","ror":"https://ror.org/043c0p156","country_code":"NL","type":"government","lineage":["https://openalex.org/I1322597698"]},{"id":"https://openalex.org/I4210089348","display_name":"Data Archiving and Networked Services (DANS)","ror":"https://ror.org/008pnp284","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I2800991832","https://openalex.org/I4210089348"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Van de Sompel, Herbert","raw_affiliation_strings":["Data Archiving and Networked Services ( Netherlands","Royal Netherlands Academy of Arts and Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Archiving and Networked Services ( Netherlands","institution_ids":["https://openalex.org/I4210089348"]},{"raw_affiliation_string":"Royal Netherlands Academy of Arts and Sciences","institution_ids":["https://openalex.org/I1322597698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5160999894142151,"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":0.5160999894142151,"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.39329999685287476,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.018200000748038292,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-archiving","display_name":"web archiving","score":0.8970000147819519},{"id":"https://openalex.org/keywords/memento","display_name":"Memento","score":0.843999981880188},{"id":"https://openalex.org/keywords/dataset-collection","display_name":"dataset collection","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.8691222667694092},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6862743496894836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5730303525924683},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43297111988067627},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.42348015308380127}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1905.03836","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03836","pdf_url":"https://arxiv.org/pdf/1905.03836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2944152102","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.03836.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.03836","doi":"https://doi.org/10.48550/arxiv.1905.03836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.03836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.03836","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03836","pdf_url":"https://arxiv.org/pdf/1905.03836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G957578216","display_name":null,"funder_award_id":"11600663","funder_id":"https://openalex.org/F4320306146","funder_display_name":"Andrew W. Mellon Foundation"}],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944152102.pdf","grobid_xml":"https://content.openalex.org/works/W2944152102.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W257652643","https://openalex.org/W1510484544","https://openalex.org/W1553448964","https://openalex.org/W2346198741","https://openalex.org/W2411682725","https://openalex.org/W2417822008","https://openalex.org/W2772771410","https://openalex.org/W2806426301","https://openalex.org/W2917183366","https://openalex.org/W2947016226"],"related_works":["https://openalex.org/W3193697788","https://openalex.org/W4386919430","https://openalex.org/W7127106270","https://openalex.org/W2137187346","https://openalex.org/W4416838991","https://openalex.org/W7096141412","https://openalex.org/W2275303056","https://openalex.org/W2947410375","https://openalex.org/W3127736396","https://openalex.org/W7099086899"],"abstract_inverted_index":{"We":[0,29],"document":[1],"the":[2,36,41,63,68,76,81,93,137,148,154],"creation":[3],"of":[4,8,15,52,56,95,118,120,163,166],"a":[5,164],"data":[6],"set":[7,55],"16,627":[9,158],"archived":[10],"web":[11,19,27,114],"pages,":[12],"or":[13],"mementos,":[14],"3,698":[16],"unique":[17],"live":[18],"URIs":[20,57,91,100,119],"(Uniform":[21],"Resource":[22],"Identifiers)":[23],"from":[24,59,92,133,144,178],"17":[25],"public":[26],"archives.":[28],"used":[30,40,70,103],"four":[31,60],"different":[32],"methods":[33],"to":[34,49,104,157,160,174],"collect":[35,50],"dataset.":[37],"First,":[38],"we":[39,89,112,129,152],"Los":[42],"Alamos":[43],"National":[44],"Laboratory":[45],"(LANL)":[46],"Memento":[47,138,149],"Aggregator":[48],"mementos":[51,107,132,156,168,177],"an":[53],"initial":[54],"obtained":[58],"sources:":[61],"(a)":[62],"Moz":[64],"Top":[65],"500,":[66],"(b)":[67],"dataset":[69],"in":[71,108,181],"our":[72,161],"previous":[73],"study,":[74],"(c)":[75],"HTTP":[77],"Archive,":[78],"and":[79,124,171],"(d)":[80],"Web":[82],"Archives":[83],"for":[84],"Historical":[85],"Research":[86],"group.":[87],"Second,":[88],"extracted":[90],"HTML":[94],"already":[96],"collected":[97,130,155],"mementos.":[98,127],"These":[99],"were":[101],"then":[102],"look":[105],"up":[106],"LANL's":[109],"aggregator.":[110,150],"Third,":[111],"downloaded":[113],"archives'":[115],"published":[116],"lists":[117],"both":[121],"original":[122],"pages":[123],"their":[125],"associated":[126],"Fourth,":[128],"more":[131],"archives":[134],"that":[135],"support":[136],"protocol":[139],"by":[140],"requesting":[141],"TimeMaps":[142],"directly":[143],"archives,":[145],"not":[146],"through":[147],"Finally,":[151],"downsampled":[153],"due":[159],"constraints":[162],"maximum":[165],"1,600":[167],"per":[169],"archive":[170,180],"being":[172],"able":[173],"download":[175],"all":[176],"each":[179],"less":[182],"than":[183],"40":[184],"hours.":[185]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-05-16T00:00:00"}
