{"id":"https://openalex.org/W4388751778","doi":"https://doi.org/10.1016/j.is.2023.102316","title":"CoCo-trie: Data-aware compression and indexing of strings","display_name":"CoCo-trie: Data-aware compression and indexing of strings","publication_year":2023,"publication_date":"2023-11-17","ids":{"openalex":"https://openalex.org/W4388751778","doi":"https://doi.org/10.1016/j.is.2023.102316"},"language":"en","primary_location":{"id":"doi:10.1016/j.is.2023.102316","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2023.102316","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.is.2023.102316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044088065","display_name":"Antonio Boffa","orcid":"https://orcid.org/0000-0002-8178-135X"},"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":true,"raw_author_name":"Antonio Boffa","raw_affiliation_strings":["Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046786328","display_name":"Paolo Ferragina","orcid":"https://orcid.org/0000-0003-1353-360X"},"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":"Paolo Ferragina","raw_affiliation_strings":["Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003830291","display_name":"Francesco Tosoni","orcid":"https://orcid.org/0000-0001-8457-3866"},"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":"Francesco Tosoni","raw_affiliation_strings":["Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063461652","display_name":"Giorgio Vinciguerra","orcid":"https://orcid.org/0000-0003-0328-7791"},"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":"Giorgio Vinciguerra","raw_affiliation_strings":["Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pisa, L.go B. Pontecorvo 3, Pisa 56127, PI, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044088065"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":{"value":2970,"currency":"USD","value_usd":2970},"apc_paid":{"value":2970,"currency":"USD","value_usd":2970},"fwci":1.2075,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83689658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"120","issue":null,"first_page":"102316","last_page":"102316"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9923999905586243,"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/trie","display_name":"Trie","score":0.9494200944900513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8244768381118774},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6153109073638916},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5314273834228516},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46551087498664856},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.437975138425827},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3830181956291199},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2952418327331543},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12841477990150452}],"concepts":[{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.9494200944900513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244768381118774},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6153109073638916},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5314273834228516},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46551087498664856},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.437975138425827},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3830181956291199},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2952418327331543},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12841477990150452},{"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:10.1016/j.is.2023.102316","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2023.102316","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1212689","is_oa":true,"landing_page_url":"https://hdl.handle.net/11568/1212689","pdf_url":"https://arpi.unipi.it/bitstream/11568/1212689/2/CoCo%20trie.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.iris.sssup.it:11382/566752","is_oa":false,"landing_page_url":"https://hdl.handle.net/11382/566752","pdf_url":null,"source":{"id":"https://openalex.org/S4377196376","display_name":"CINECA IRIS Institutional Research Information System (Sant'Anna School of Advanced Studies)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162290304","host_organization_name":"Scuola Superiore Sant'Anna","host_organization_lineage":["https://openalex.org/I162290304"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.is.2023.102316","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.is.2023.102316","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2020622295","display_name":null,"funder_award_id":"Big Data","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4317964049","display_name":null,"funder_award_id":"IR0000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5538284277","display_name":null,"funder_award_id":"National Recovery","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7231943246","display_name":null,"funder_award_id":"Horizon 2020 Programme","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7926685355","display_name":null,"funder_award_id":"87104","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8274803949","display_name":null,"funder_award_id":"871042","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8826631963","display_name":null,"funder_award_id":"Horizon 2020 Program","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W564800084","https://openalex.org/W1493380042","https://openalex.org/W1514915193","https://openalex.org/W1532325895","https://openalex.org/W1569403765","https://openalex.org/W1798412263","https://openalex.org/W1969884330","https://openalex.org/W1981420413","https://openalex.org/W2000568570","https://openalex.org/W2016995838","https://openalex.org/W2018804864","https://openalex.org/W2018866650","https://openalex.org/W2050635028","https://openalex.org/W2057223122","https://openalex.org/W2065717636","https://openalex.org/W2071225564","https://openalex.org/W2075488055","https://openalex.org/W2076747312","https://openalex.org/W2077091042","https://openalex.org/W2087361130","https://openalex.org/W2087721273","https://openalex.org/W2088386938","https://openalex.org/W2098258619","https://openalex.org/W2155512447","https://openalex.org/W2161488606","https://openalex.org/W2323530184","https://openalex.org/W2406547600","https://openalex.org/W2479292667","https://openalex.org/W2517241835","https://openalex.org/W2529376784","https://openalex.org/W2738952118","https://openalex.org/W2755385361","https://openalex.org/W2805710541","https://openalex.org/W2963379900","https://openalex.org/W2963391355","https://openalex.org/W2963630872","https://openalex.org/W3089808641","https://openalex.org/W3098583838","https://openalex.org/W3197753456","https://openalex.org/W4221058058","https://openalex.org/W4225876687","https://openalex.org/W4312409437","https://openalex.org/W4312423556","https://openalex.org/W4384303994","https://openalex.org/W4386870725","https://openalex.org/W6600742786","https://openalex.org/W6619662185","https://openalex.org/W6631377939","https://openalex.org/W6637493597","https://openalex.org/W6640538453","https://openalex.org/W6641201905","https://openalex.org/W6641330010","https://openalex.org/W6642796893","https://openalex.org/W6647826766","https://openalex.org/W6650321478","https://openalex.org/W6650339521","https://openalex.org/W6650921888","https://openalex.org/W6657985338","https://openalex.org/W6669766933","https://openalex.org/W6673022145","https://openalex.org/W6682146489","https://openalex.org/W6682570212","https://openalex.org/W6684580922","https://openalex.org/W6718468305","https://openalex.org/W6733464165","https://openalex.org/W6776947008","https://openalex.org/W6782931614","https://openalex.org/W6785474229","https://openalex.org/W6787787678","https://openalex.org/W6810546822","https://openalex.org/W6823173392","https://openalex.org/W6847603521","https://openalex.org/W6894118598"],"related_works":["https://openalex.org/W2046569047","https://openalex.org/W2186419898","https://openalex.org/W2048294592","https://openalex.org/W2370961680","https://openalex.org/W2278452282","https://openalex.org/W841163430","https://openalex.org/W2156393489","https://openalex.org/W1552925710","https://openalex.org/W207628907","https://openalex.org/W2740229587"],"abstract_inverted_index":{"We":[0,58,151],"address":[1],"the":[2,48,51,56,65,98,101,107,123,129,136,141,165,192,222,228,233],"problem":[3,29,203],"of":[4,11,38,53,75,100,132,139,156,195,221],"compressing":[5],"and":[6,17,25,40,85,110,145,174,182,187,197,213,224],"indexing":[7],"a":[8,32,36,60,73,90,117,211],"sorted":[9],"dictionary":[10],"strings":[12],"to":[13,77,103,126],"support":[14],"efficient":[15,148],"lookups":[16],"more":[18],"sophisticated":[19],"operations,":[20],"such":[21],"as":[22,31],"prefix,":[23],"predecessor,":[24],"range":[26],"searches.":[27],"This":[28],"occurs":[30],"key":[33],"task":[34],"in":[35,47,55,164],"plethora":[37],"applications,":[39],"thus":[41,235],"it":[42,225],"has":[43],"been":[44],"deeply":[45],"investigated":[46],"literature":[49],"since":[50],"introduction":[52],"tries":[54],"\u201960s.":[57],"introduce":[59],"new":[61,237],"data":[62,199],"structure,":[63],"called":[64],"COmpressed":[66],"COllapsed":[67],"Trie":[68],"(CoCo-trie),":[69],"that":[70,97,121,159,191],"hinges":[71],"on":[72,106,171,227],"pool":[74,131],"techniques":[76],"compress":[78,104,127],"subtries":[79,102,125],"(of":[80],"arbitrary":[81],"depth)":[82],"into":[83],"succinctly-encoded":[84],"efficiently-searchable":[86],"trie":[87,108],"macro-nodes":[88],"with":[89,135],"possibly":[91],"large":[92,175],"fan-out.":[93],"Then,":[94],"we":[95,115],"observe":[96],"choice":[99],"depends":[105],"structure":[109],"its":[111],"edge":[112],"labels.":[113],"Hence,":[114],"develop":[116],"data-aware":[118],"optimisation":[119],"approach":[120,158],"selects":[122],"best":[124],"via":[128],"above":[130],"succinct":[133],"encodings,":[134],"overall":[137],"goal":[138],"minimising":[140],"total":[142],"space":[143],"occupancy":[144],"still":[146],"achieving":[147],"query":[149],"time.":[150],"also":[152],"investigate":[153],"some":[154],"variants":[155],"this":[157,202],"induce":[160],"interesting":[161],"space\u2013time":[162,193,230],"trade-offs":[163],"CoCo-trie":[166,209],"design.":[167],"Our":[168],"experimental":[169],"evaluation":[170],"six":[172],"diverse":[173],"datasets":[176],"(representing":[177],"URLs,":[178],"XML":[179],"data,":[180],"DNA":[181],"protein":[183],"sequences,":[184],"database":[185],"records,":[186],"search-engine":[188],"dictionaries)":[189],"shows":[190],"performance":[194],"well-established":[196],"highly-engineered":[198],"structures":[200],"solving":[201],"is":[204],"very":[205],"input-sensitive.":[206],"Conversely,":[207],"our":[208],"provides":[210],"robust":[212],"uniform":[214],"improvement":[215],"over":[216],"all":[217],"competitors":[218],"for":[219,232],"half":[220],"datasets,":[223],"results":[226],"Pareto":[229],"frontier":[231],"others,":[234],"offering":[236],"competitive":[238],"trade-offs.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}