{"id":"https://openalex.org/W1996764654","doi":"https://doi.org/10.1145/3130348.3130362","title":"Scatter/Gather","display_name":"Scatter/Gather","publication_year":2017,"publication_date":"2017-08-02","ids":{"openalex":"https://openalex.org/W1996764654","doi":"https://doi.org/10.1145/3130348.3130362","mag":"1996764654"},"language":"en","primary_location":{"id":"doi:10.1145/3130348.3130362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130362","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-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/A5016239835","display_name":"Douglass R. Cutting","orcid":null},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Douglass R. Cutting","raw_affiliation_strings":["Xerox Palo Alto Research Center, Palo Alto, CA","XEROX Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA"],"affiliations":[{"raw_affiliation_string":"Xerox Palo Alto Research Center, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"XEROX Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028448267","display_name":"David R. Karger","orcid":"https://orcid.org/0000-0002-0024-5847"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Karger","raw_affiliation_strings":["Xerox Palo Alto Research Center, Palo Alto, CA and Stanford University","Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA and Stanford University#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Palo Alto Research Center, Palo Alto, CA and Stanford University","institution_ids":["https://openalex.org/I173498003","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA and Stanford University#TAB#","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074139750","display_name":"Jan Pedersen","orcid":"https://orcid.org/0000-0002-3099-2106"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan O. Pedersen","raw_affiliation_strings":["Xerox Palo Alto Research Center, Palo Alto, CA","XEROX Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA"],"affiliations":[{"raw_affiliation_string":"Xerox Palo Alto Research Center, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"XEROX Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023706141","display_name":"John W. Tukey","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John W. Tukey","raw_affiliation_strings":["Xerox Palo Alto Research Center, Palo Alto, CA and Princeton University","Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA and Princeton University#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Palo Alto Research Center, Palo Alto, CA and Princeton University","institution_ids":["https://openalex.org/I173498003","https://openalex.org/I20089843"]},{"raw_affiliation_string":"Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA and Princeton University#TAB#","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016239835"],"corresponding_institution_ids":["https://openalex.org/I173498003"],"apc_list":null,"apc_paid":null,"fwci":22.0344,"has_fulltext":false,"cited_by_count":1425,"citation_normalized_percentile":{"value":0.99500763,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"51","issue":"2","first_page":"148","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9959999918937683,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.9213590025901794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8884435892105103},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6208477020263672},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5461881160736084},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4892106056213379},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4599423110485077},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4496578872203827},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.42863696813583374},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4261879622936249},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3991355895996094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27224522829055786}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9213590025901794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8884435892105103},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6208477020263672},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5461881160736084},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4892106056213379},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4599423110485077},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4496578872203827},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.42863696813583374},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4261879622936249},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3991355895996094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27224522829055786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3130348.3130362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130362","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956559956","https://openalex.org/W1965080174","https://openalex.org/W1971784203","https://openalex.org/W2041565863","https://openalex.org/W2045370125","https://openalex.org/W2045584315","https://openalex.org/W2066667100","https://openalex.org/W2067761898","https://openalex.org/W2084048649","https://openalex.org/W2093377061","https://openalex.org/W2120636855","https://openalex.org/W2145036943","https://openalex.org/W4238437991"],"related_works":["https://openalex.org/W4301002638","https://openalex.org/W2163563073","https://openalex.org/W3186815950","https://openalex.org/W2371010743","https://openalex.org/W3088133960","https://openalex.org/W2606552659","https://openalex.org/W2181519036","https://openalex.org/W4253632195","https://openalex.org/W2202413591","https://openalex.org/W1987613674"],"abstract_inverted_index":{"Document":[0],"clustering":[1,23,43,57,71,100,111],"has":[2],"not":[3,45],"been":[4],"well":[5],"received":[6],"as":[7,72,101],"an":[8,61,73],"information":[9,74],"retrieval":[10],"tool.":[11],"Objections":[12],"to":[13,63],"its":[14,78,102],"use":[15],"fall":[16],"into":[17],"two":[18],"main":[19],"categories:":[20],"first,":[21],"that":[22,42,51,97],"is":[24,58],"too":[25],"slow":[26],"for":[27],"large":[28],"corpora":[29],"(with":[30],"running":[31],"time":[32],"often":[33],"quadratic":[34],"in":[35,60,77],"the":[36],"number":[37],"of":[38],"documents);":[39],"and":[40,84],"second,":[41],"does":[44],"appreciably":[46],"improve":[47,64],"retrieval.":[48],"We":[49,91,105],"argue":[50],"these":[52,82],"problems":[53],"arise":[54],"only":[55],"when":[56],"used":[59],"attempt":[62],"conventional":[65],"search":[66],"techniques.":[67],"However,":[68],"looking":[69],"at":[70],"access":[75,89],"tool":[76],"own":[79],"right":[80],"obviates":[81],"objections,":[83],"provides":[85],"a":[86,93],"powerful":[87],"new":[88],"paradigm.":[90],"present":[92,107],"document":[94],"browsing":[95],"technique":[96],"employs":[98],"docum-ent":[99],"primary":[103],"operation.":[104],"also":[106],"fast":[108],"(linear":[109],"time)":[110],"algorithm.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":45},{"year":2014,"cited_by_count":54},{"year":2013,"cited_by_count":58},{"year":2012,"cited_by_count":69}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2016-06-24T00:00:00"}