{"id":"https://openalex.org/W1996397554","doi":"https://doi.org/10.1073/pnas.1415135111","title":"Patterns of text reuse in a scientific corpus","display_name":"Patterns of text reuse in a scientific corpus","publication_year":2014,"publication_date":"2014-12-08","ids":{"openalex":"https://openalex.org/W1996397554","doi":"https://doi.org/10.1073/pnas.1415135111","mag":"1996397554","pmid":"https://pubmed.ncbi.nlm.nih.gov/25489072"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.1415135111","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1415135111","pdf_url":"https://www.pnas.org/content/pnas/112/1/25.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.pnas.org/content/pnas/112/1/25.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085283623","display_name":"Daniel Citron","orcid":"https://orcid.org/0000-0002-1282-4176"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel T. Citron","raw_affiliation_strings":["Departments of aPhysics and"],"affiliations":[{"raw_affiliation_string":"Departments of aPhysics and","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060975667","display_name":"Paul Ginsparg","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Ginsparg","raw_affiliation_strings":["Departments of aPhysics and","Information Science, Cornell University, Ithaca, NY 14853","bInformation Science, Cornell University, Ithaca, NY 14853"],"affiliations":[{"raw_affiliation_string":"Departments of aPhysics and","institution_ids":[]},{"raw_affiliation_string":"Information Science, Cornell University, Ithaca, NY 14853","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"bInformation Science, Cornell University, Ithaca, NY 14853","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085283623"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.9757,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.98490195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"112","issue":"1","first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9570000171661377,"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/reuse","display_name":"Reuse","score":0.6953507661819458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5470609664916992},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39261722564697266},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3522137701511383},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13791722059249878},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.051287442445755005}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6953507661819458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5470609664916992},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39261722564697266},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3522137701511383},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13791722059249878},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.051287442445755005}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1073/pnas.1415135111","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1415135111","pdf_url":"https://www.pnas.org/content/pnas/112/1/25.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmid:25489072","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25489072","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":null},{"id":"pmh:oai:arXiv.org:1412.2716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1412.2716","pdf_url":"https://arxiv.org/pdf/1412.2716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"pmh:oai:europepmc.org:3456032","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4291616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1073/pnas.1415135111","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1415135111","pdf_url":"https://www.pnas.org/content/pnas/112/1/25.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G3937634086","display_name":null,"funder_award_id":"NSF grant OCI 0926550","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1996397554.pdf","grobid_xml":"https://content.openalex.org/works/W1996397554.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1544505227","https://openalex.org/W1612372972","https://openalex.org/W1760194879","https://openalex.org/W1970527458","https://openalex.org/W1973651171","https://openalex.org/W1974336599","https://openalex.org/W2031405614","https://openalex.org/W2034953475","https://openalex.org/W2040969622","https://openalex.org/W2080493973","https://openalex.org/W2088500017","https://openalex.org/W2111295912","https://openalex.org/W2128186353","https://openalex.org/W2160202225","https://openalex.org/W3101647379","https://openalex.org/W3121874977","https://openalex.org/W4242571629","https://openalex.org/W4243343826","https://openalex.org/W4256597070"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0,28,52,75],"consider":[1,99],"the":[2,15,30,50,81,100],"incidence":[3],"of":[4,14,18,33,36,72,83,102,104,106,111],"text":[5,16,37,43,85],"\"reuse\"":[6],"by":[7,94],"researchers":[8],"via":[9],"a":[10,54,68,77],"systematic":[11],"pairwise":[12],"comparison":[13],"content":[17],"all":[19],"articles":[20,107],"deposited":[21],"to":[22,26],"arXiv.org":[23],"from":[24],"1991":[25],"2012.":[27],"measure":[29,40],"global":[31],"frequencies":[32],"three":[34],"classes":[35],"reuse":[38,44],"and":[39,67,89],"how":[41],"chronic":[42],"is":[45],"distributed":[46],"among":[47],"authors":[48],"in":[49,86],"dataset.":[51],"infer":[53],"baseline":[55],"for":[56],"accepted":[57],"practice,":[58],"perhaps":[59],"surprisingly":[60],"permissive":[61],"compared":[62],"with":[63],"other":[64],"societal":[65],"contexts,":[66],"clearly":[69],"delineated":[70],"set":[71],"aberrant":[73],"authors.":[74],"find":[76],"negative":[78],"correlation":[79],"between":[80],"amount":[82],"reused":[84,112],"an":[87],"article":[88],"its":[90],"influence,":[91],"as":[92],"measured":[93],"subsequent":[95],"citations.":[96],"Finally,":[97],"we":[98],"distribution":[101],"countries":[103],"origin":[105],"containing":[108],"large":[109],"amounts":[110],"text.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
