{"id":"https://openalex.org/W2556112170","doi":"https://doi.org/10.1109/tit.2017.2730864","title":"Duplication Distance to the Root for Binary Sequences","display_name":"Duplication Distance to the Root for Binary Sequences","publication_year":2017,"publication_date":"2017-07-26","ids":{"openalex":"https://openalex.org/W2556112170","doi":"https://doi.org/10.1109/tit.2017.2730864","mag":"2556112170"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2017.2730864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2017.2730864","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://authors.library.caltech.edu/79466/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083469386","display_name":"Noga Alon","orcid":"https://orcid.org/0000-0003-1332-4883"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Noga Alon","raw_affiliation_strings":["Schools of Mathematics and Computer Science, Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Schools of Mathematics and Computer Science, Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043861677","display_name":"Jehoshua Bruck","orcid":"https://orcid.org/0000-0001-8474-0812"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jehoshua Bruck","raw_affiliation_strings":["Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011621481","display_name":"Farzad Farnoud","orcid":"https://orcid.org/0000-0002-8684-4487"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farzad Farnoud Hassanzadeh","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Department of Computer Science, University of Virginia, Charlottesville, VA, USA","Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Department of Computer Science, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612200","display_name":"Siddharth Jain","orcid":"https://orcid.org/0000-0002-9164-6119"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Jain","raw_affiliation_strings":["Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083469386"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.1701,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83360911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"63","issue":"12","first_page":"7793","last_page":"7803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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":0.9990000128746033,"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/T11567","display_name":"semigroups and automata theory","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11130","display_name":"Coding theory and cryptography","score":0.9943000078201294,"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/gene-duplication","display_name":"Gene duplication","score":0.7606179714202881},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.6884706616401672},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.675314724445343},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.644438624382019},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6335008144378662},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.6271559000015259},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6204379200935364},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5136184096336365},{"id":"https://openalex.org/keywords/tandem-exon-duplication","display_name":"Tandem exon duplication","score":0.5090107917785645},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.507056474685669},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.44439592957496643},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41841307282447815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3636934757232666},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.34084612131118774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32815825939178467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2259814441204071},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12054857611656189},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11995440721511841},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11654111742973328}],"concepts":[{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.7606179714202881},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.6884706616401672},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.675314724445343},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.644438624382019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6335008144378662},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.6271559000015259},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6204379200935364},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5136184096336365},{"id":"https://openalex.org/C156446351","wikidata":"https://www.wikidata.org/wiki/Q7682435","display_name":"Tandem exon duplication","level":4,"score":0.5090107917785645},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.507056474685669},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.44439592957496643},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41841307282447815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3636934757232666},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.34084612131118774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32815825939178467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2259814441204071},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12054857611656189},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11995440721511841},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11654111742973328},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tit.2017.2730864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2017.2730864","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:authors.library.caltech.edu:79466","is_oa":true,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20170726-162754925","pdf_url":"https://authors.library.caltech.edu/79466/","source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:authors.library.caltech.edu:79466","is_oa":true,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20170726-162754925","pdf_url":"https://authors.library.caltech.edu/79466/","source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2556112170.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1551519020","https://openalex.org/W1564690864","https://openalex.org/W1606480398","https://openalex.org/W1617423665","https://openalex.org/W1908746084","https://openalex.org/W2000690667","https://openalex.org/W2016879150","https://openalex.org/W2065247540","https://openalex.org/W2083298149","https://openalex.org/W2086397813","https://openalex.org/W2103849916","https://openalex.org/W2155603715","https://openalex.org/W2168909179","https://openalex.org/W2340242219","https://openalex.org/W2517778131","https://openalex.org/W2592570088","https://openalex.org/W2895239415","https://openalex.org/W3099104497","https://openalex.org/W3105069054","https://openalex.org/W6636629632"],"related_works":["https://openalex.org/W4377003973","https://openalex.org/W4287782403","https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W2021003109","https://openalex.org/W1998479724","https://openalex.org/W2546839375","https://openalex.org/W4386075131","https://openalex.org/W2551168410","https://openalex.org/W3082647531"],"abstract_inverted_index":{"We":[0,105,174],"study":[1,176],"the":[2,15,20,27,65,81,89,103,117,121,140,157,177,181,184,200,204,208,221],"tandem":[3,23,111,217,225],"duplication":[4,24,93,178,218,226],"distance":[5,83,119,159,179],"between":[6,84],"binary":[7,54],"sequences":[8,41,187],"and":[9,38,42,45,94,109,193,207,220],"their":[10,48],"roots.":[11],"In":[12],"other":[13],"words,":[14],"quantity":[16],"of":[17,22,26,56,79,92,123,126,142,148,186,197,224],"interest":[18],"is":[19,75,213],"number":[21,91,223],"operations":[25,96],"form":[28],"x":[29,37],"=":[30,34,137,172],"abc":[31],"\u2192":[32],"y":[33,39],"abbc,":[35],"where":[36,145],"are":[40,47],"a,":[43],"b,":[44],"c":[46],"substrings,":[49],"needed":[50],"to":[51,98,102,120,168,180,229],"generate":[52,230],"a":[53,61,76,124,146,161,190,231],"sequence":[55,63,101,125],"length":[57,127],"n":[58,128,167],"starting":[59],"from":[60,64,164,189],"square-free":[62],"set":[66,185],"{0,":[67],"1,":[68],"01,":[69],"10,":[70],"010,":[71],"101}.":[72],"This":[73],"problem":[74,212],"restricted":[77],"case":[78,141],"finding":[80],"duplication/deduplication":[82],"two":[85],"sequences,":[86,198,203],"defined":[87],"as":[88],"minimum":[90],"deduplication":[95],"required":[97,228],"transform":[99],"one":[100],"other.":[104],"consider":[106],"both":[107],"exact":[108,114],"approximate":[110,143],"duplications.":[112],"For":[113,139],"duplication,":[115,144],"denoting":[116],"maximum":[118,158],"root":[122,182,192],"by":[129,215],"f":[130,135],"(n),":[131],"we":[132,154],"prove":[133],"that":[134,156],"(n)":[136],"8(n).":[138],"\u03b2-fraction":[147],"symbols":[149],"may":[150],"be":[151],"duplicated":[152],"incorrectly,":[153],"show":[155],"has":[160],"sharp":[162],"transition":[163],"linear":[165],"in":[166],"logarithmic":[169],"at":[170],"\u03b2":[171],"1/2.":[173],"also":[175],"for":[183,194],"arising":[188],"given":[191,232],"special":[195],"classes":[196],"namely,":[199],"De":[201],"Bruijn":[202],"Thue-Morse":[205],"sequence,":[206],"Fibonacci":[209],"words.":[210],"The":[211],"motivated":[214],"genomic":[216],"mutations":[219],"smallest":[222],"events":[227],"biological":[233],"sequence.":[234]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
