{"id":"https://openalex.org/W2019076926","doi":"https://doi.org/10.1145/1277741.1277832","title":"Principles of hash-based text retrieval","display_name":"Principles of hash-based text retrieval","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2019076926","doi":"https://doi.org/10.1145/1277741.1277832","mag":"2019076926"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277832","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benno Stein","raw_affiliation_strings":["Bauhaus University Weimar, Weimar, Germany","Bauhaus-University Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]},{"raw_affiliation_string":"Bauhaus-University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027915931"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":6.9043,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.97088657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"527","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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/hash-function","display_name":"Hash function","score":0.8501034379005432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134321928024292},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6490182876586914},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6042134761810303},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.5215228199958801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5141983032226562},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48178645968437195},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42142370343208313},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3806260824203491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1717827320098877}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8501034379005432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134321928024292},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6490182876586914},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6042134761810303},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.5215228199958801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5141983032226562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48178645968437195},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42142370343208313},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3806260824203491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1717827320098877},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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:10.1145/1277741.1277832","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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":29,"referenced_works":["https://openalex.org/W191422183","https://openalex.org/W1502916507","https://openalex.org/W1506254138","https://openalex.org/W1541459201","https://openalex.org/W1971238646","https://openalex.org/W2002757059","https://openalex.org/W2004026774","https://openalex.org/W2012833704","https://openalex.org/W2022286021","https://openalex.org/W2026968007","https://openalex.org/W2045533739","https://openalex.org/W2048929541","https://openalex.org/W2072863821","https://openalex.org/W2085922539","https://openalex.org/W2100495367","https://openalex.org/W2109749916","https://openalex.org/W2132988481","https://openalex.org/W2134731454","https://openalex.org/W2147152072","https://openalex.org/W2147717514","https://openalex.org/W2148694408","https://openalex.org/W2148781362","https://openalex.org/W2152565070","https://openalex.org/W2152825437","https://openalex.org/W2158018156","https://openalex.org/W2162006472","https://openalex.org/W2752885492","https://openalex.org/W3043924052","https://openalex.org/W3145128584"],"related_works":["https://openalex.org/W2069568684","https://openalex.org/W3019245231","https://openalex.org/W1984081611","https://openalex.org/W2376661060","https://openalex.org/W2119251656","https://openalex.org/W2948607823","https://openalex.org/W1554022419","https://openalex.org/W113683524","https://openalex.org/W4387251676","https://openalex.org/W4385261619"],"abstract_inverted_index":{"Hash-based":[0],"similarity":[1,6,58,130],"search":[2,59,86,109,131,147],"reduces":[3],"a":[4,69,92,141],"continuous":[5],"relation":[7],"to":[8,103],"the":[9,28,46,81,105,114],"binary":[10],"concept":[11],"\"similar":[12],"or":[13],"not":[14],"similar\":":[15],"two":[16],"feature":[17],"vectors":[18],"are":[19,25,101],"considered":[20,67],"as":[21,68],"similar":[22],"if":[23],"they":[24],"mapped":[26],"on":[27,120],"same":[29,47],"hash":[30,127],"key.":[31],"From":[32],"its":[33],"runtime":[34],"performance":[35,106],"this":[36],"principle":[37],"is":[38,51,66],"unequaled--while":[39],"being":[40],"unaffected":[41],"by":[42],"dimensionality":[43],"concerns":[44],"at":[45],"time.":[48],"Similarity":[49],"hashing":[50],"applied":[52],"with":[53],"great":[54],"success":[55],"for":[56,72,129],"near":[57],"in":[60,91],"large":[61],"document":[62],"collections,":[63],"and":[64,75,88,111],"it":[65],"key":[70],"technology":[71],"near-duplicate":[73],"detection":[74],"plagiarism":[76],"analysis.":[77],"This":[78],"papers":[79],"reveals":[80],"design":[82],"principles":[83],"behind":[84],"hash-based":[85,108,146],"methods":[87],"presents":[89],"them":[90],"unified":[93],"way.":[94],"We":[95,135],"introduce":[96],"new":[97,138],"stress":[98],"statistics":[99],"that":[100],"suited":[102],"analyze":[104],"of":[107,116,140],"methods,":[110],"we":[112,123],"explain":[113],"rationale":[115],"their":[117],"effectiveness.":[118],"Based":[119],"these":[121],"insights,":[122],"show":[124],"how":[125],"optimum":[126],"functions":[128],"can":[132],"be":[133],"derived.":[134],"also":[136],"present":[137],"results":[139],"comparative":[142],"study":[143],"between":[144],"different":[145],"methods.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}