{"id":"https://openalex.org/W2109834209","doi":"https://doi.org/10.1145/1739041.1739104","title":"HARRA","display_name":"HARRA","publication_year":2010,"publication_date":"2010-03-16","ids":{"openalex":"https://openalex.org/W2109834209","doi":"https://doi.org/10.1145/1739041.1739104","mag":"2109834209"},"language":"en","primary_location":{"id":"doi:10.1145/1739041.1739104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","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/A5077735899","display_name":"Hung-Sik Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hung-sik Kim","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA","THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA","THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077735899"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":5.2393,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.95315884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9491999745368958,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9434999823570251,"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/merge","display_name":"Merge (version control)","score":0.7691640853881836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7008547782897949},{"id":"https://openalex.org/keywords/test-suite","display_name":"Test suite","score":0.6395285129547119},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5626471042633057},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5132384300231934},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.46459126472473145},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4457194209098816},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.43609052896499634},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.366796612739563},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33550816774368286},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.25297003984451294},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.21905186772346497},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17021873593330383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08962693810462952}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7691640853881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008547782897949},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.6395285129547119},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5626471042633057},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5132384300231934},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.46459126472473145},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4457194209098816},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.43609052896499634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.366796612739563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33550816774368286},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.25297003984451294},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.21905186772346497},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17021873593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08962693810462952},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"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":1,"locations":[{"id":"doi:10.1145/1739041.1739104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8729476249","display_name":null,"funder_award_id":"DUE-0817376DUE-0937891","funder_id":"https://openalex.org/F4320337408","funder_display_name":"Division of Undergraduate Education"}],"funders":[{"id":"https://openalex.org/F4320337408","display_name":"Division of Undergraduate Education","ror":"https://ror.org/02kd4km72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W130948412","https://openalex.org/W1502916507","https://openalex.org/W1540269031","https://openalex.org/W1646278814","https://openalex.org/W1742677423","https://openalex.org/W1925598861","https://openalex.org/W1967208734","https://openalex.org/W1997927541","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2048779798","https://openalex.org/W2064153048","https://openalex.org/W2067566391","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2105423800","https://openalex.org/W2111116800","https://openalex.org/W2116544254","https://openalex.org/W2116690618","https://openalex.org/W2121516976","https://openalex.org/W2123561513","https://openalex.org/W2127675794","https://openalex.org/W2129875280","https://openalex.org/W2145065594","https://openalex.org/W2148019918","https://openalex.org/W2159481891","https://openalex.org/W2165897980","https://openalex.org/W2170037597","https://openalex.org/W2295151155","https://openalex.org/W2296421186"],"related_works":["https://openalex.org/W4287326768","https://openalex.org/W2393322642","https://openalex.org/W4234886518","https://openalex.org/W3131198547","https://openalex.org/W3099654136","https://openalex.org/W2389591058","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764"],"abstract_inverted_index":{"We":[0,25],"study":[1],"the":[2,6,28,116,143],"performance":[3],"issue":[4],"of":[5,56,68,115],"\"iterative\"":[7],"record":[8],"linkage":[9],"(RL)":[10],"problem,":[11],"where":[12],"match":[13],"and":[14,41,97,103,120,123,130],"merge":[15],"operations":[16],"may":[17],"occur":[18],"together":[19],"in":[20,70,105,134],"iterations":[21],"until":[22],"convergence":[23],"emerges.":[24],"first":[26],"propose":[27],"Iterative":[29],"Locality-Sensitive":[30],"Hashing":[31],"(ILSH)":[32],"that":[33],"dynamically":[34],"merges":[35],"LSH-based":[36],"has":[37],"tables":[38],"for":[39,91],"quick":[40],"accurate":[42],"blocking.":[43],"Then,":[44],"by":[45],"exploiting":[46],"inherent":[47],"characteristics":[48],"within/across":[49],"data":[50,82],"sets,":[51],"we":[52],"develop":[53],"a":[54],"suite":[55],"I-LSH-based":[57],"RL":[58,74],"algorithms,":[59],"named":[60],"as":[61],"HARRA":[62,69,93],"(<u>HA</u>shed":[63],"<u>R</u>eco<u>R</u>d":[64],"link<u>A</u>ge).":[65],"The":[66],"superiority":[67],"speed":[71],"over":[72],"competing":[73],"solutions":[75],"is":[76],"thoroughly":[77],"validated":[78],"using":[79],"various":[80],"real":[81],"sets.":[83],"While":[84],"maintaining":[85],"equivalent":[86],"or":[87],"comparable":[88],"accuracy":[89],"levels,":[90],"instance,":[92],"runs:":[94],"(1)":[95],"4.5":[96],"10.5":[98],"times":[99,125],"faster":[100,126],"than":[101,127],"StringMap":[102],"R-Swoosh":[104],"iteratively":[106,135],"linking":[107,136],"4,000":[108,110],"x":[109,138],"short":[111],"records":[112,141],"(i.e.,":[113,142],"one":[114],"small":[117],"test":[118,145],"cases),":[119],"(2)":[121],"5.6":[122],"3.4":[124],"basic":[128],"LSH":[129,132],"Multi-Probe":[131],"algorithms":[133],"400,000":[137,139],"long":[140],"largest":[144],"case).":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2016-06-24T00:00:00"}