{"id":"https://openalex.org/W2947410375","doi":"https://doi.org/10.1109/jcdl.2019.00033","title":"MementoMap Framework for Flexible and Adaptive Web Archive Profiling","display_name":"MementoMap Framework for Flexible and Adaptive Web Archive Profiling","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2947410375","doi":"https://doi.org/10.1109/jcdl.2019.00033","mag":"2947410375"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2019.00033","doi":"https://doi.org/10.1109/jcdl.2019.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2019.00033","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.12607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087503706","display_name":"Sawood Alam","orcid":"https://orcid.org/0000-0002-8267-3326","observed_orcids":["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":false,"raw_author_name":"Sawood Alam","raw_affiliation_strings":["Department of Computer Science, Old Dominion University, Norfolk, Virginia, USA","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Old Dominion University, Norfolk, Virginia, 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":"Michele Weigle","raw_affiliation_strings":["Department of Computer Science, Old Dominion University, Norfolk, Virginia, USA","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Old Dominion University, Norfolk, Virginia, 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":"Michael Nelson","raw_affiliation_strings":["Department of Computer Science, Old Dominion University, Norfolk, Virginia, USA","\u2021Old Dominion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Old Dominion University, Norfolk, Virginia, USA","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"\u2021Old Dominion University","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fernando Melo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I7883018","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","ror":"https://ror.org/00snfqn58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210146676","https://openalex.org/I7883018"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Fernando Melo","raw_affiliation_strings":["FCT: Arquivo.pt, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FCT: Arquivo.pt, Lisbon, Portugal","institution_ids":["https://openalex.org/I7883018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041336942","display_name":"Daniel Bicho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I7883018","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","ror":"https://ror.org/00snfqn58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210146676","https://openalex.org/I7883018"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Daniel Bicho","raw_affiliation_strings":["FCT: Arquivo.pt, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FCT: Arquivo.pt, Lisbon, Portugal","institution_ids":["https://openalex.org/I7883018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037253095","display_name":"Daniel Gomes","orcid":"https://orcid.org/0000-0002-5447-4581","observed_orcids":["https://orcid.org/0000-0002-5447-4581"]},"institutions":[{"id":"https://openalex.org/I7883018","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","ror":"https://ror.org/00snfqn58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210146676","https://openalex.org/I7883018"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Daniel Gomes","raw_affiliation_strings":["FCT: Arquivo.pt, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FCT: Arquivo.pt, Lisbon, Portugal","institution_ids":["https://openalex.org/I7883018"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":39.4754,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.7656000256538391,"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"}},"topics":[{"id":"https://openalex.org/T11657","display_name":"Digital and Traditional Archives Management","score":0.7656000256538391,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.1354999989271164,"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/T12601","display_name":"Web Applications and Data Management","score":0.014700000174343586,"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":0.7540000081062317},{"id":"https://openalex.org/keywords/memento","display_name":"Memento","score":0.7950000166893005},{"id":"https://openalex.org/keywords/binary-search","display_name":"binary search","score":0.5950000286102295},{"id":"https://openalex.org/keywords/space-efficient-algorithms","display_name":"memory-efficient algorithms","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391232490539551},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.7203845977783203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6150930523872375},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5483282208442688},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5370442271232605},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5127550363540649},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5014252662658691},{"id":"https://openalex.org/C2779820595","wikidata":"https://www.wikidata.org/wiki/Q798505","display_name":"Listing (finance)","level":2,"score":0.4919302463531494},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.47729504108428955},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4490377604961395},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4147571921348572},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.4135821461677551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38963156938552856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3287360668182373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2074752151966095},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/jcdl.2019.00033","doi":"https://doi.org/10.1109/jcdl.2019.00033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2019.00033","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.12607","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.12607","pdf_url":"https://arxiv.org/pdf/1905.12607","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2947410375","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1905.12607","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.1905.12607","doi":"https://doi.org/10.48550/arxiv.1905.12607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.12607","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:1905.12607","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.12607","pdf_url":"https://arxiv.org/pdf/1905.12607","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/G4610856633","display_name":"III: Small: Increasing the Value of Existing Web Archives","funder_award_id":"1526700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947410375.pdf","grobid_xml":"https://content.openalex.org/works/W2947410375.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W153213769","https://openalex.org/W1587224754","https://openalex.org/W1922832738","https://openalex.org/W2000042664","https://openalex.org/W2006672970","https://openalex.org/W2019790506","https://openalex.org/W2023657004","https://openalex.org/W2023717017","https://openalex.org/W2036682342","https://openalex.org/W2043275333","https://openalex.org/W2143079043","https://openalex.org/W2218908741","https://openalex.org/W2401581791","https://openalex.org/W2411682725","https://openalex.org/W2417822008","https://openalex.org/W2464674082","https://openalex.org/W2528442590","https://openalex.org/W2528706266","https://openalex.org/W2730423384","https://openalex.org/W2739870517","https://openalex.org/W2810191764","https://openalex.org/W2947016226","https://openalex.org/W2971133053","https://openalex.org/W3103362336","https://openalex.org/W4241808895","https://openalex.org/W4245347511","https://openalex.org/W4247704254","https://openalex.org/W4253293330","https://openalex.org/W6728015546","https://openalex.org/W6752612253"],"related_works":["https://openalex.org/W3127736396","https://openalex.org/W3028945005","https://openalex.org/W3187246695","https://openalex.org/W7099086899","https://openalex.org/W7095629861","https://openalex.org/W1587224754","https://openalex.org/W4391281495","https://openalex.org/W2732945795","https://openalex.org/W2464674082","https://openalex.org/W3097155391"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,75],"proposed":[4],"MementoMap,":[5],"a":[6,15,21,77,85,89,140],"flexible":[7],"and":[8,48,80,92],"adaptive":[9],"framework":[10],"to":[11,44,83,113,150],"summarize":[12],"holdings":[13],"of":[14,35,50,59,71,107,118,142,154,167,169],"web":[16,42,121],"archive":[17,176],"efficiently.":[18],"We":[19,30,53,101,123,137],"described":[20],"simple,":[22],"yet":[23],"extensible,":[24],"file":[25],"format":[26],"suitable":[27],"for":[28,98],"MementoMap.":[29],"used":[31],"the":[32,36,46,115,151,156,163,170,174],"complete":[33],"index":[34],"Arquivo.pt":[37],"comprising":[38],"5B":[39],"mementos":[40],"(archived":[41],"pages/files)":[43],"understand":[45,114],"nature":[47],"shape":[49],"its":[51,62],"holdings.":[52],"generated":[54],"MementoMaps":[55,125],"with":[56],"varying":[57],"amount":[58],"detail":[60],"from":[61,134],"HTML":[63],"pages":[64],"that":[65,139],"have":[66],"an":[67,93],"HTTP":[68],"status":[69],"code":[70],"200":[72],"OK.":[73],"Additionally,":[74],"designed":[76],"single-pass,":[78],"memory-efficient,":[79],"parallelization-friendly":[81],"algorithm":[82],"compact":[84],"large":[86],"MementoMap":[87,141],"into":[88],"small":[90],"one":[91],"in-file":[94],"binary":[95],"search":[96],"method":[97],"efficient":[99],"lookup.":[100],"analyzed":[102],"more":[103],"than":[104,144],"three":[105],"years":[106],"MemGator":[108,135],"(a":[109],"Memento":[110],"aggregator)":[111],"logs":[112],"response":[116],"behavior":[117],"14":[119],"public":[120],"archives.":[122],"evaluated":[124],"by":[126],"measuring":[127],"their":[128],"Accuracy":[129],"using":[130],"3.3M":[131],"unique":[132,157],"URIs":[133,172],"logs.":[136],"found":[138],"less":[143],"1.5%":[145],"Relative":[146],"Cost":[147],"(as":[148],"compared":[149],"comprehensive":[152],"listing":[153],"all":[155],"original":[158],"URIs)":[159],"can":[160],"correctly":[161],"identify":[162],"presence":[164],"or":[165],"absence":[166],"60%":[168],"lookup":[171],"in":[173],"corresponding":[175],"while":[177],"maintaining":[178],"100%":[179],"Recall":[180],"(i.e.,":[181],"zero":[182],"false":[183],"negatives).":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-06-07T00:00:00"}
