{"id":"https://openalex.org/W2583391637","doi":"https://doi.org/10.1109/bigdata.2016.7840957","title":"Automated schema extraction for PID information types","display_name":"Automated schema extraction for PID information types","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583391637","doi":"https://doi.org/10.1109/bigdata.2016.7840957","mag":"2583391637"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","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/A5018027277","display_name":"Ulrich Schwardmann","orcid":"https://orcid.org/0000-0001-6337-8674"},"institutions":[{"id":"https://openalex.org/I4210091733","display_name":"Gesellschaft f\u00fcr wissenschaftliche Datenverarbeitung mbH G\u00f6ttingen","ror":"https://ror.org/00cd95c65","country_code":"DE","type":"other","lineage":["https://openalex.org/I4210091733","https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ulrich Schwardmann","raw_affiliation_strings":["Gesellschaft f\u00fcr wissenschaftliche Datenverarbeitung mbH G\u00f6ttingen (GWDG), G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"Gesellschaft f\u00fcr wissenschaftliche Datenverarbeitung mbH G\u00f6ttingen (GWDG), G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210091733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018027277"],"corresponding_institution_ids":["https://openalex.org/I4210091733"],"apc_list":null,"apc_paid":null,"fwci":2.6588,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93206081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3036","last_page":"3044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9965000152587891,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9887999892234802,"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/T11719","display_name":"Data Quality and Management","score":0.977400004863739,"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/computer-science","display_name":"Computer science","score":0.8368449211120605},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.829984188079834},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7133233547210693},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.641035795211792},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5668537020683289},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.5480908155441284},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.5393938422203064},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.5336393117904663},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.49490517377853394},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.47479456663131714},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42667871713638306},{"id":"https://openalex.org/keywords/data-mapping","display_name":"Data mapping","score":0.4249919652938843},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4034826159477234},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3415486216545105},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28564006090164185},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20437833666801453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368449211120605},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.829984188079834},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7133233547210693},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.641035795211792},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5668537020683289},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.5480908155441284},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.5393938422203064},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.5336393117904663},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.49490517377853394},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.47479456663131714},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42667871713638306},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.4249919652938843},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4034826159477234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3415486216545105},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28564006090164185},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20437833666801453}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/F4320322035","display_name":"Rural Development Administration","ror":"https://ror.org/03xs9yg50"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1525293519","https://openalex.org/W1539626980","https://openalex.org/W2035516519","https://openalex.org/W2070812389","https://openalex.org/W2071908440","https://openalex.org/W6632156576","https://openalex.org/W7062618633"],"related_works":["https://openalex.org/W2183628870","https://openalex.org/W2379265733","https://openalex.org/W2347306054","https://openalex.org/W3016521766","https://openalex.org/W1503116306","https://openalex.org/W3199469221","https://openalex.org/W2545809202","https://openalex.org/W3084772717","https://openalex.org/W2362378919","https://openalex.org/W2981561176"],"abstract_inverted_index":{"Typing":[0],"is":[1,80,116],"a":[2,20,26,141,153],"well":[3],"known":[4,46],"concept":[5],"to":[6,19,44,55,74,120,131],"prepare":[7],"services":[8,98],"for":[9,12,23,49,109],"data":[10,51,61,76],"processing":[11,37],"instance":[13],"by":[14],"choosing":[15],"the":[16,69,75,86,89,122,146,149],"correct":[17],"service":[18],"mime":[21],"type":[22,90,138],"processing.":[24],"But":[25,85],"lot":[27],"more":[28],"metadata":[29,58,79],"elements,":[30],"like":[31],"availability":[32],"and":[33,144],"access":[34],"conditions,":[35],"provenance,":[36],"preconditions":[38],"or":[39],"integrity":[40],"parameters,":[41],"are":[42,99,107],"useful":[43],"be":[45,65],"in":[47,140,152],"advance":[48],"preprocessing":[50],"services.":[52],"In":[53],"order":[54],"expose":[56],"such":[57,111],"independently":[59],"from":[60,135],"access,":[62],"it":[63],"can":[64],"stored":[66],"directly":[67],"within":[68],"persistent":[70],"identifier":[71],"structure":[72],"pointing":[73],"itsself.":[77],"Such":[78],"called":[81],"PID":[82],"information":[83],"type.":[84],"correctness":[87],"of":[88,124,148,155],"entries":[91],"needs":[92],"high":[93],"accuracy,":[94],"because":[95],"all":[96],"following":[97],"relying":[100],"on":[101],"their":[102],"expressiveness.":[103],"Data":[104],"Type":[105],"Registries":[106],"emerging":[108],"describing":[110],"types,":[112],"but":[113],"currently":[114],"there":[115],"no":[117],"automated":[118],"way":[119,143],"control":[121],"content":[123],"types.":[125],"This":[126],"work":[127],"introduces":[128],"an":[129],"approach":[130],"automatically":[132],"derive":[133],"schemas":[134],"hierarchically":[136],"organized":[137],"descriptions":[139],"recursive":[142],"highlights":[145],"advantages":[147],"resulting":[150],"precision":[151],"couple":[154],"application":[156],"examples.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"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"}