{"id":"https://openalex.org/W7225588372","doi":"https://doi.org/10.5281/zenodo.24056289","title":"Greedy Byte-Pair Encoding Achieves the Tight Constant (1-e^{-2})/2 Against the Best Merge Sequence with Short Tokens","display_name":"Greedy Byte-Pair Encoding Achieves the Tight Constant (1-e^{-2})/2 Against the Best Merge Sequence with Short Tokens","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225588372","doi":"https://doi.org/10.5281/zenodo.24056289"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24056289","doi":"https://doi.org/10.5281/zenodo.24056289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24056289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24056289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119746719","display_name":"Kundan Baliga","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baliga, Kundan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160685850","display_name":"Aiden Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie, Aiden","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160585827","display_name":"Aditya Byju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byju, Aditya","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0024999999441206455,"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":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/byte-pair-encoding","display_name":"byte pair encoding","score":0.9900000095367432},{"id":"https://openalex.org/keywords/lower-bounds","display_name":"lower bounds","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4724999964237213},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44620001316070557},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.4027000069618225},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C43169469","wikidata":"https://www.wikidata.org/wiki/Q580922","display_name":"Preprint","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2779089604","wikidata":"https://www.wikidata.org/wiki/Q7169333","display_name":"Permission","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24056289","doi":"https://doi.org/10.5281/zenodo.24056289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24056289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24056290","doi":"https://doi.org/10.5281/zenodo.24056290","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24056290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24056289","doi":"https://doi.org/10.5281/zenodo.24056289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24056289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4404407951","https://openalex.org/W7225466098"],"related_works":["https://openalex.org/W7225466098","https://openalex.org/W7225296571","https://openalex.org/W4404407951","https://openalex.org/W7223760427","https://openalex.org/W4385571315","https://openalex.org/W7225400471","https://openalex.org/W7172407664","https://openalex.org/W7214733969","https://openalex.org/W7212080943","https://openalex.org/W6891899133"],"abstract_inverted_index":{"Byte-Pair":[0],"Encoding":[1],"(BPE),":[2],"widely":[3],"used":[4,226],"to":[5],"build":[6],"language-model":[7],"vocabularies,":[8],"repeatedly":[9],"merges":[10,71,73,93,144],"a":[11,49,128,242],"most":[12,80,98,179],"frequent":[13],"adjacent":[14],"pair":[15,164],"of":[16,31,62,69,78,89,156,165,167,177,197,222],"symbols.":[17],"No":[18],"constant":[19,107],"above":[20],"(1-e-2)/2":[21],"\u2248":[22],"0.432":[23],"can":[24],"bound,":[25,45],"on":[26],"every":[27],"input,":[28],"the":[29,32,40,63,86,90,105,116,157,198,212,218,223,228],"fraction":[30,88],"optimal":[33,67],"saving":[34,141],"that":[35,54],"greedy":[36,55,84],"BPE":[37],"achieves,":[38],"and":[39,145,182,187,217,220,237],"best":[41,91,109],"known":[42],"general":[43],"lower":[44],"0.391,":[46],"is":[47,108,139,173,205,239],"from":[48,127],"companion":[50],"paper.":[51],"We":[52],"prove":[53],"achieves":[56,85],"at":[57,79,97,162,178],"least":[58],"(1/2)(1-(1-2/k)k)":[59],"\u2265":[60],"(1/2)(1-e-2)":[61],"optimum":[64,104],"whenever":[65],"some":[66],"sequence":[68],"k":[70,92,135],"(partial":[72],"allowed)":[74],"builds":[75],"only":[76],"tokens":[77,95,176],"seven":[81,99,238],"letters.":[82],"Unconditionally,":[83],"same":[87],"whose":[94],"have":[96],"letters;":[100],"against":[101],"this":[102,204],"capped":[103],"limiting":[106],"possible,":[110],"by":[111,241],"Yang's":[112],"construction,":[113],"whereas":[114],"for":[115,153,175,185,233],"conditional":[117],"result":[118],"we":[119],"do":[120],"not":[121],"claim":[122],"tightness.":[123],"Both":[124],"results":[125,190],"follow":[126],"per-step":[129],"inequality,":[130],"OPT":[131],"\u2264":[132],"2Gi":[133],"+":[134],"gi+1,":[136],"where":[137],"Gi":[138],"greedy's":[140,168],"after":[142],"i":[143],"gi+1":[146],"its":[147,150,159,214],"next":[148],"saving;":[149],"proof":[151,172],"keeps,":[152],"each":[154,230],"rule":[155],"optimum,":[158],"merge":[160],"points":[161],"one":[163],"symbols":[166],"current":[169],"string.":[170],"The":[171,209],"analytic":[174],"five":[180],"letters":[181],"partly":[183],"computer-assisted":[184],"six":[186,236],"seven.":[188],"These":[189],"appeared,":[191],"with":[192],"proofs,":[193],"in":[194,227],"versions":[195],"1.0-1.2":[196],"authors'":[199],"preprint":[200],"doi:10.5281/zenodo.24023719":[201],"(now":[202],"restructured);":[203],"their":[206],"self-contained":[207],"account.":[208],"record":[210],"includes":[211],"paper,":[213],"LaTeX":[215],"source,":[216],"code":[219],"outputs":[221],"exhaustive":[224],"computations":[225],"proofs;":[229],"finite":[231],"lemma":[232],"token":[234],"lengths":[235],"repeated":[240],"second,":[243],"separately":[244],"written":[245],"program.":[246]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-09T00:00:00"}