{"id":"https://openalex.org/W4320024364","doi":"https://doi.org/10.1109/bigdata55660.2022.10020340","title":"Metadata Verification: A Workflow for Computational Archival Science","display_name":"Metadata Verification: A Workflow for Computational Archival Science","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024364","doi":"https://doi.org/10.1109/bigdata55660.2022.10020340"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045632528","display_name":"Joel Pepper","orcid":"https://orcid.org/0000-0002-1601-8729"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel Pepper","raw_affiliation_strings":["Drexel University,Department of Computer Science,Philadelphia,PA,USA","Department of Computer Science, Drexel University, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Computer Science,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Computer Science, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055464113","display_name":"Andrew Senin","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Senin","raw_affiliation_strings":["Drexel University,Department of Computer Science,Philadelphia,PA,USA","Department of Computer Science, Drexel University, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Computer Science,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Computer Science, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067009730","display_name":"Dom Jebbia","orcid":"https://orcid.org/0000-0002-9587-8718"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dom Jebbia","raw_affiliation_strings":["Drexel University,Department of Information Science,Philadelphia,PA,USA","Department of Information Science, Drexel University, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Information Science,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Information Science, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061644705","display_name":"David E. Breen","orcid":"https://orcid.org/0000-0002-1376-5008"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Breen","raw_affiliation_strings":["Drexel University,Department of Computer Science,Philadelphia,PA,USA","Department of Computer Science, Drexel University, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Computer Science,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Computer Science, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035913440","display_name":"Jane Greenberg","orcid":"https://orcid.org/0000-0001-7819-5360"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jane Greenberg","raw_affiliation_strings":["Drexel University,Department of Information Science,Philadelphia,PA,USA","Department of Information Science, Drexel University, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Information Science,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Information Science, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2565","last_page":"2571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9962999820709229,"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/T11937","display_name":"Research Data Management Practices","score":0.9962999820709229,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9783999919891357,"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/metadata","display_name":"Metadata","score":0.9262522459030151},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8778622150421143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.791872501373291},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6844286322593689},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49133816361427307},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.46811360120773315},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4491085410118103},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39710384607315063},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2326447069644928},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0844467282295227}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9262522459030151},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8778622150421143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791872501373291},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6844286322593689},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49133816361427307},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.46811360120773315},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4491085410118103},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39710384607315063},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2326447069644928},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0844467282295227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334028","display_name":"Illinois Natural History Survey","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W118398040","https://openalex.org/W1599771537","https://openalex.org/W1777661762","https://openalex.org/W1985157738","https://openalex.org/W2001496424","https://openalex.org/W2007967719","https://openalex.org/W2302501749","https://openalex.org/W2788008213","https://openalex.org/W2912055463","https://openalex.org/W2960364096","https://openalex.org/W2992806738","https://openalex.org/W2993427049","https://openalex.org/W2993670771","https://openalex.org/W3008344928","https://openalex.org/W3014939377","https://openalex.org/W3047402597","https://openalex.org/W3138514522","https://openalex.org/W3194498659","https://openalex.org/W4220988041","https://openalex.org/W4225771432","https://openalex.org/W4254111051","https://openalex.org/W4254421450","https://openalex.org/W4280554058","https://openalex.org/W4309878855","https://openalex.org/W6635847735","https://openalex.org/W6735463952","https://openalex.org/W6766351668","https://openalex.org/W6811636098"],"related_works":["https://openalex.org/W57267792","https://openalex.org/W1981250005","https://openalex.org/W2151972543","https://openalex.org/W756399425","https://openalex.org/W94963990","https://openalex.org/W1499447047","https://openalex.org/W130839190","https://openalex.org/W2361349944","https://openalex.org/W2381351160","https://openalex.org/W1998549824"],"abstract_inverted_index":{"Researchers":[0],"seeking":[1],"to":[2,9,136,157],"apply":[3],"computational":[4],"methods":[5],"are":[6],"increasingly":[7],"turning":[8],"scientific":[10,27,75,122],"digital":[11],"archives":[12],"containing":[13],"images":[14,169],"of":[15,26,45,52,57,91,127,152],"specimens.":[16],"Unfortunately,":[17],"metadata":[18,46,77,94,124,161],"errors":[19,47,125],"can":[20,170],"inhibit":[21],"the":[22,34,115,142,150],"discovery":[23],"and":[24,108,164],"use":[25],"archival":[28,168],"images.":[29],"One":[30],"such":[31],"case":[32],"is":[33,80],"NSF-sponsored":[35],"Biology":[36],"Guided":[37],"Neural":[38],"Network":[39],"(BGNN)":[40],"project,":[41],"where":[42],"an":[43],"abundance":[44],"has":[48],"significantly":[49],"delayed":[50],"development":[51],"a":[53,70,89,137],"proposed,":[54],"new":[55],"class":[56],"neural":[58],"networks.":[59],"This":[60],"paper":[61],"reports":[62],"on":[63,88],"research":[64],"addressing":[65],"this":[66],"challenge.":[67],"We":[68],"present":[69],"prototype":[71,116,147],"workflow":[72,102,117,148],"for":[73,141,162],"specimen":[74,92,133],"name":[76,93,123],"verification":[78],"that":[79],"grounded":[81],"in":[82,173],"Computational":[83],"Archival":[84],"Science":[85],"(CAS),":[86],"report":[87],"taxonomy":[90],"error":[95,139],"types":[96],"with":[97,114],"preliminary":[98],"solutions.":[99],"Our":[100],"3-phased":[101],"includes":[103],"tag":[104],"extraction,":[105],"text":[106],"processing,":[107],"interactive":[109],"assessment.":[110],"A":[111],"baseline":[112],"test":[113],"identified":[118],"at":[119],"least":[120],"15":[121],"out":[126],"857":[128],"manually":[129],"reviewed,":[130],"potentially":[131],"erroneous":[132],"images,":[134],"corresponding":[135],"\u223c0.2%":[138],"rate":[140],"full":[143],"image":[144],"dataset.":[145],"The":[146],"minimizes":[149],"amount":[151],"time":[153],"domain":[154],"experts":[155],"need":[156],"spend":[158],"reviewing":[159],"archive":[160],"correctness":[163],"AI-readiness":[165],"before":[166],"these":[167],"be":[171],"utilized":[172],"downstream":[174],"analysis.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}