{"id":"https://openalex.org/W2007474131","doi":"https://doi.org/10.1145/2505515.2505624","title":"Local clustering in provenance graphs","display_name":"Local clustering in provenance graphs","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2007474131","doi":"https://doi.org/10.1145/2505515.2505624","mag":"2007474131"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:33921644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069671253","display_name":"Peter Macko","orcid":"https://orcid.org/0000-0002-8320-4329"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Macko","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA","HARVARD Univ., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"HARVARD Univ., Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043465336","display_name":"Daniel Margo","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Margo","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA","HARVARD Univ., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"HARVARD Univ., Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054751297","display_name":"Margo Seltzer","orcid":"https://orcid.org/0000-0002-2165-4658"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margo Seltzer","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA","HARVARD Univ., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"HARVARD Univ., Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7494,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.71437881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"835","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9944999814033508,"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":0.763281524181366},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.7614574432373047},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7339048385620117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287905216217041},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6064531803131104},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.5161582231521606},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4979681968688965},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45280057191848755},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4453818202018738},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3549705147743225},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32872745394706726},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2408253252506256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2058190107345581},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13346442580223083},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08401024341583252}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.763281524181366},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.7614574432373047},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7339048385620117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287905216217041},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6064531803131104},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.5161582231521606},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4979681968688965},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45280057191848755},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4453818202018738},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3549705147743225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32872745394706726},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2408253252506256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2058190107345581},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13346442580223083},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08401024341583252},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2505515.2505624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:dash.harvard.edu:1/33921644","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:33921644","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.9955","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.9955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.harvard.edu/~pmacko/papers/clustering-cikm13.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:dash.harvard.edu:1/33921644","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:33921644","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7997952209","display_name":"Collaborative Research: Scalable Data Management Using Metadata and Provenance","funder_award_id":"0937914","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/F4320307904","display_name":"Oracle","ror":"https://ror.org/006c77m33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W100944330","https://openalex.org/W143174683","https://openalex.org/W1858703999","https://openalex.org/W1971744183","https://openalex.org/W1971937094","https://openalex.org/W1996790644","https://openalex.org/W2008317118","https://openalex.org/W2034331023","https://openalex.org/W2048095866","https://openalex.org/W2056944867","https://openalex.org/W2063871082","https://openalex.org/W2101096088","https://openalex.org/W2104791905","https://openalex.org/W2112615110","https://openalex.org/W2121564430","https://openalex.org/W2125806118","https://openalex.org/W2130891992","https://openalex.org/W2168270139","https://openalex.org/W2203887455","https://openalex.org/W2221158541","https://openalex.org/W2604713509","https://openalex.org/W2605173815","https://openalex.org/W4254495278","https://openalex.org/W6604134081"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Systems":[0],"that":[1],"capture":[2],"and":[3,41,86],"store":[4],"data":[5],"provenance,":[6],"the":[7],"record":[8],"of":[9,48,83],"how":[10],"an":[11,64],"object":[12],"has":[13],"arrived":[14],"at":[15,75],"its":[16],"current":[17],"state,":[18],"accumulate":[19],"historical":[20],"metadata":[21],"over":[22],"time,":[23],"forming":[24],"a":[25,38,43],"large":[26],"graph.":[27],"Local":[28],"clustering":[29,70,102],"in":[30,33,63,99],"these":[31,76],"graphs,":[32],"which":[34],"we":[35,95],"start":[36],"with":[37],"seed":[39],"vertex":[40],"grow":[42],"cluster":[44],"around":[45],"it,":[46],"is":[47],"paramount":[49],"importance":[50],"because":[51],"it":[52],"supports":[53],"critical":[54],"provenance":[55,84,104],"applications":[56],"such":[57],"as":[58],"identifying":[59],"semantically":[60],"meaningful":[61],"tasks":[62],"object's":[65],"history.":[66],"However,":[67],"generic":[68],"graph":[69],"algorithms":[71],"are":[72],"not":[73],"effective":[74],"tasks.":[77],"We":[78],"identify":[79],"three":[80],"key":[81],"properties":[82],"graphs":[85],"exploit":[87],"them":[88],"to":[89],"justify":[90],"two":[91],"new":[92],"centrality":[93],"metrics":[94],"developed":[96],"for":[97],"use":[98],"performing":[100],"local":[101],"on":[103],"graphs.":[105]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}