{"id":"https://openalex.org/W7127194389","doi":"https://doi.org/10.1109/jcdl67857.2025.00038","title":"OntExtract: PROV-O Provenance Tracking for Document Analysis Workflows","display_name":"OntExtract: PROV-O Provenance Tracking for Document Analysis Workflows","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7127194389","doi":"https://doi.org/10.1109/jcdl67857.2025.00038"},"language":null,"primary_location":{"id":"doi:10.1109/jcdl67857.2025.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl67857.2025.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","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/A5023877206","display_name":"Christopher B. Rauch","orcid":"https://orcid.org/0000-0003-2061-3413"},"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":true,"raw_author_name":"Christopher B. Rauch","raw_affiliation_strings":["Drexel University,Philadelphia,PA,USA"],"affiliations":[{"raw_affiliation_string":"Drexel University,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124816914","display_name":"Hyung Wook Choi","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":"Hyung Wook Choi","raw_affiliation_strings":["Drexel University,Philadelphia,PA,USA"],"affiliations":[{"raw_affiliation_string":"Drexel University,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092992552","display_name":"Mat Kelly","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":"Mat Kelly","raw_affiliation_strings":["Drexel University,Philadelphia,PA,USA"],"affiliations":[{"raw_affiliation_string":"Drexel University,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023877206"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9067694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9259999990463257,"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":0.9259999990463257,"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/T11937","display_name":"Research Data Management Practices","score":0.01269999984651804,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7502999901771545},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4569999873638153},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4359000027179718},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4230000078678131},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.42149999737739563},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.37700000405311584},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.36970001459121704},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.359499990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137999773025513},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7502999901771545},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4569999873638153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.299699991941452},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl67857.2025.00038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl67857.2025.00038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2014655228","https://openalex.org/W2037248861","https://openalex.org/W2806375207","https://openalex.org/W2952276524","https://openalex.org/W2963780471","https://openalex.org/W3021480884","https://openalex.org/W3167421168","https://openalex.org/W4246334968","https://openalex.org/W4401023556"],"related_works":[],"abstract_inverted_index":{"Researchers":[0],"have":[1],"developed":[2],"sophisticated":[3],"methods":[4,10],"for":[5,48],"semantic":[6,133,139],"change":[7,140],"detection.":[8],"These":[9],"depend":[11],"on":[12,100],"foundational":[13],"document":[14,49],"processing":[15,50,68,111],"operations,":[16],"such":[17],"as":[18],"segmentation":[19],"and":[20,95,117,136],"entity":[21],"extraction,":[22],"yet":[23],"users":[24],"face":[25],"significant":[26],"obstacles":[27],"when":[28],"trying":[29],"to":[30,91,113],"combine":[31],"these":[32],"underlying":[33],"tools":[34],"into":[35],"analytical":[36,125],"workflows.":[37],"We":[38],"present":[39],"OntExtract,":[40,56],"a":[41,45,71],"system":[42,79,122],"that":[43],"provides":[44],"unified":[46],"interface":[47],"with":[51,74,130],"integrated":[52],"provenance":[53,58,76],"tracking.":[54],"In":[55],"PROV-O":[57],"concepts":[59],"are":[60],"embedded":[61],"directly":[62],"in":[63,81],"the":[64,114,121],"database":[65],"schema.":[66],"Each":[67],"operation":[69],"creates":[70],"versioned":[72],"output":[73],"corresponding":[75],"records.":[77],"The":[78,127],"operates":[80],"two":[82],"modes:":[83],"API-enhanced":[84],"mode,":[85,97],"which":[86,98],"uses":[87],"large":[88],"language":[89],"models":[90],"orchestrate":[92],"tool":[93],"selection,":[94],"standalone":[96],"relies":[99],"established":[101],"NLP":[102],"libraries":[103],"(spaCy,":[104],"NLTK,":[105],"sentence-transformers).":[106],"Users":[107],"can":[108],"apply":[109],"different":[110],"strategies":[112],"same":[115],"documents":[116],"compare":[118],"results,":[119],"while":[120],"tracks":[123],"complete":[124],"provenance.":[126],"PostgreSQL":[128],"implementation":[129],"pgvector":[131],"enables":[132],"similarity":[134],"search":[135],"supports":[137],"reproducible":[138],"analysis.":[141]},"counts_by_year":[],"updated_date":"2026-02-06T02:01:19.302388","created_date":"2026-02-03T00:00:00"}