{"id":"https://openalex.org/W2167294216","doi":"https://doi.org/10.1145/1989284.1989300","title":"Space-efficient substring occurrence estimation","display_name":"Space-efficient substring occurrence estimation","publication_year":2011,"publication_date":"2011-06-13","ids":{"openalex":"https://openalex.org/W2167294216","doi":"https://doi.org/10.1145/1989284.1989300","mag":"2167294216"},"language":"en","primary_location":{"id":"doi:10.1145/1989284.1989300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989284.1989300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirtieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","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/A5001389367","display_name":"Alessio Orlandi","orcid":"https://orcid.org/0000-0002-0676-8796"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Orlandi","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084138015","display_name":"Rossano Venturini","orcid":"https://orcid.org/0000-0002-9830-3936"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rossano Venturini","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7586,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87818955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9825999736785889,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.8415476083755493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6062325835227966},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46854934096336365},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.46019911766052246},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.13746076822280884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10204780101776123},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08954817056655884},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.054454803466796875}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8415476083755493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6062325835227966},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46854934096336365},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.46019911766052246},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.13746076822280884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10204780101776123},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08954817056655884},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.054454803466796875},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1989284.1989300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989284.1989300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirtieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/226730","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/226730","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dnet:people______::5f4522d98b8fd3c316bad8a672984f7e","is_oa":false,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::5f4522d98b8fd3c316bad8a672984f7e","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"30th symposium on Principles of Database Systems of Data, PODS 2011, pp. 95\u2013106, Athens, Greece, 12-16 June 2011","raw_type":"Conference article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1504417041","https://openalex.org/W1548702063","https://openalex.org/W1562034888","https://openalex.org/W1828691170","https://openalex.org/W1949346071","https://openalex.org/W1965853364","https://openalex.org/W1967156765","https://openalex.org/W1990061958","https://openalex.org/W2041445031","https://openalex.org/W2041851430","https://openalex.org/W2050635028","https://openalex.org/W2052196304","https://openalex.org/W2057223122","https://openalex.org/W2075833184","https://openalex.org/W2087721273","https://openalex.org/W2088386938","https://openalex.org/W2107082304","https://openalex.org/W2133137130","https://openalex.org/W2135208303","https://openalex.org/W2148659572","https://openalex.org/W2155512447","https://openalex.org/W2159647614","https://openalex.org/W2160484851","https://openalex.org/W2161488606","https://openalex.org/W2165602238","https://openalex.org/W2167439683","https://openalex.org/W2170899819","https://openalex.org/W2621280964"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1583922594","https://openalex.org/W1542422837","https://openalex.org/W1974038726","https://openalex.org/W2998448420","https://openalex.org/W1598224733","https://openalex.org/W4280502676","https://openalex.org/W2000769876","https://openalex.org/W204227468"],"abstract_inverted_index":{"We":[0,139],"study":[1],"the":[2,6,40,46,54,77,110,133,142,160,173],"problem":[3,67],"of":[4,8,10,22,39,45,53,56,64,112,144,162,176],"estimating":[5],"number":[7,52],"occurrences":[9,55],"substrings":[11],"in":[12,37,72,80,109],"textual":[13,81],"data:":[14],"A":[15],"text":[16,41],"T":[17],"on":[18,89,136],"some":[19],"alphabet":[20],"\u00a3":[21],"size":[23,157],"\u00c3":[24],"is":[25,31,35,88,132],"preprocessed":[26],"and":[27,98],"an":[28,50,57,91,120],"index":[29,34],"I":[30],"built.":[32],"The":[33,66],"used":[36],"lieu":[38],"to":[42,76],"answer":[43],"queries":[44],"form":[47],"CountH(P),":[48],"returning":[49],"approximated":[51],"arbitrary":[58],"pattern":[59],"P":[60],"as":[61],"a":[62,153],"substring":[63],"T.":[65],"has":[68],"its":[69],"main":[70],"application":[71],"selectivity":[73],"estimation":[74],"related":[75],"LIKE":[78],"predicate":[79],"databases":[82],"[15,":[83],"14,":[84],"5].":[85],"Our":[86,165],"focus":[87],"obtaining":[90],"algorithmic":[92],"solution":[93],"with":[94,159],"guaranteed":[95],"error":[96,135],"rates":[97],"small":[99],"footprint.":[100],"To":[101],"achieve":[102],"that,":[103],"we":[104],"first":[105],"enrich":[106],"previous":[107],"work":[108],"area":[111],"compressed":[113],"text-indexing":[114],"[8,":[115],"11,":[116],"6,":[117],"17]":[118],"providing":[119,152],"optimal":[121],"data":[122,154,178],"structure":[123,155],"that":[124],"requires":[125],"?(|T|log\u00c3/l)":[126],"bits":[127],"where":[128],"l":[129],"e":[130],"1":[131],"additive":[134],"any":[137],"answer.":[138],"also":[140],"approach":[141],"issue":[143],"guaranteeing":[145],"exact":[146],"answers":[147],"for":[148],"sufficiently":[149],"frequent":[150],"patterns,":[151],"whose":[156],"scales":[158],"amount":[161],"such":[163],"patterns.":[164],"theoretical":[166],"findings":[167],"are":[168],"sustained":[169],"by":[170],"experiments":[171],"showing":[172],"practical":[174],"impact":[175],"our":[177],"structures.":[179]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
