{"id":"https://openalex.org/W4387005685","doi":"https://doi.org/10.1109/e-science58273.2023.10254801","title":"Can Automated Metadata Extraction Make Scientific Data More Navigable?","display_name":"Can Automated Metadata Extraction Make Scientific Data More Navigable?","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4387005685","doi":"https://doi.org/10.1109/e-science58273.2023.10254801"},"language":"en","primary_location":{"id":"doi:10.1109/e-science58273.2023.10254801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","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/A5079278437","display_name":"Tyler J. Skluzacek","orcid":"https://orcid.org/0000-0003-2242-4931"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler J. Skluzacek","raw_affiliation_strings":["National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN","Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN"],"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences,Oak Ridge National Lab,Oak Ridge,TN","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Lab, National Center for Computational Sciences, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago,Department of Computer Science,Chicago,IL","Data Science and Learning Division, Argonne National Lab, Lemont, IL","Department of Computer Science, University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Chicago,Department of Computer Science,Chicago,IL","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Lab, Lemont, IL","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["University of Chicago,Department of Computer Science,Chicago,IL","Data Science and Learning Division, Argonne National Lab, Lemont, IL","Department of Computer Science, University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Chicago,Department of Computer Science,Chicago,IL","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Data Science and Learning Division, Argonne National Lab, Lemont, IL","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Department of Computer Science, University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079278437"],"corresponding_institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4388482696"],"apc_list":null,"apc_paid":null,"fwci":1.8006,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8848283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9973999857902527,"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/T11719","display_name":"Data Quality and Management","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8974011540412903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8188512325286865},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7020161747932434},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6129205226898193},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5070436000823975},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.49732401967048645},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4898928999900818},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.4632035493850708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15690430998802185}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8974011540412903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188512325286865},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7020161747932434},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6129205226898193},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5070436000823975},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.49732401967048645},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4898928999900818},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.4632035493850708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15690430998802185},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science58273.2023.10254801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/e-science58273.2023.10254801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 19th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G2797879381","display_name":null,"funder_award_id":"70NANB19H005","funder_id":"https://openalex.org/F4320306111","funder_display_name":"U.S. Department of Commerce"},{"id":"https://openalex.org/G5129028721","display_name":null,"funder_award_id":"2004894","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306111","display_name":"U.S. Department of Commerce","ror":"https://ror.org/04chq2495"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W148271226","https://openalex.org/W153213769","https://openalex.org/W1120778379","https://openalex.org/W1485391494","https://openalex.org/W1912712249","https://openalex.org/W1995541717","https://openalex.org/W2023408138","https://openalex.org/W2125800352","https://openalex.org/W2165703420","https://openalex.org/W2302501749","https://openalex.org/W2583718094","https://openalex.org/W2611973536","https://openalex.org/W2794512438","https://openalex.org/W2875407561","https://openalex.org/W2901518007","https://openalex.org/W2906830849","https://openalex.org/W2964332384","https://openalex.org/W2984976594","https://openalex.org/W3005844845","https://openalex.org/W3024813357","https://openalex.org/W3121728796","https://openalex.org/W3170801192","https://openalex.org/W3173426902","https://openalex.org/W4200223120","https://openalex.org/W4309185501","https://openalex.org/W6606083523"],"related_works":["https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W1667647204","https://openalex.org/W3155196058","https://openalex.org/W4252960523","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W1529821365","https://openalex.org/W3046984657","https://openalex.org/W2053943328"],"abstract_inverted_index":{"FAIR":[0],"principles":[1],"require":[2],"that":[3,151,182],"scientific":[4],"data":[5,45,171],"be":[6],"findable,":[7],"discoverable,":[8],"and":[9,51,83,114,142,161,198,200],"reusable":[10],"by":[11,48,122],"users.":[12],"To":[13],"enable":[14],"FAIRness,":[15],"practioners":[16],"of":[17,28,133,158,184,196],"a":[18,24,74,98,219],"science":[19],"repository":[20],"will":[21],"often":[22],"construct":[23],"rich,":[25],"searchable":[26],"index":[27],"metadata":[29,36,72,90,126],"derived":[30],"from":[31,110],"the":[32,43,84,124,130,164,185],"data.":[33],"Unfortunately,":[34],"manual":[35,214],"annotation":[37],"methods":[38,212],"do":[39],"not":[40],"scale":[41],"to":[42,58,86,154,175],"many":[44,49],"files":[46],"generated":[47],"projects;":[50],"instead":[52],"automated":[53],"extraction":[54,127],"systems":[55],"are":[56],"needed":[57],"scalably":[59],"parse":[60],"these":[61],"files\u2014often":[62],"with":[63,103,193],"nonstandard":[64],"schema":[65],"requiring":[66],"specialized":[67],"parsing":[68],"strategies\u2014and":[69],"deposit":[70],"representative":[71],"into":[73],"search":[75],"index.":[76],"In":[77,129,163],"this":[78],"work,":[79],"we":[80,136],"evaluate":[81],"whether,":[82],"extent":[85],"which,":[87],"automatically":[88,121],"extracted":[89],"make":[91],"research":[92,119,170],"repositories":[93],"more":[94],"navigable.":[95],"We":[96,117,149,180],"present":[97],"two-part":[99],"user":[100],"study":[101],"conducted":[102],"scientists":[104],"at":[105],"two":[106],"U.S.":[107],"national":[108],"laboratories":[109],"projects":[111],"spanning":[112],"spectroscopy":[113],"battery":[115],"modeling.":[116],"constructed":[118],"indexes":[120],"using":[123],"Xtract":[125],"system.":[128],"first":[131],"part":[132],"our":[134],"study,":[135],"learned":[137],"about":[138],"each":[139],"user's":[140],"role":[141],"identified":[143],"key":[144],"navigation":[145,172,191],"concerns":[146],"for":[147,156],"scientists.":[148],"found":[150,181],"participants":[152,167,188],"wished":[153],"navigate":[155],"purposes":[157],"discovery,":[159],"retrieval,":[160],"organization.":[162],"second":[165],"part,":[166],"completed":[168],"simulated":[169],"tasks":[173,192],"crafted":[174],"reflect":[176],"real-world":[177],"navigability":[178],"concerns.":[179],"regardless":[183],"interface":[186],"used,":[187],"consistently":[189],"solved":[190],"high":[194],"degrees":[195],"confidence":[197],"correctness,":[199],"significantly":[201],"(":[202],"<tex":[203],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[204],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.2\\mathrm{X}-50\\times$</tex>":[205],")":[206],"faster":[207],"than":[208],"via":[209],"their":[210],"alternative":[211],"(e.g.,":[213],"directory":[215],"scans":[216],"or":[217],"designing":[218],"customized":[220],"navigational":[221],"tool).":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}