{"id":"https://openalex.org/W7134888718","doi":"https://doi.org/10.1145/3779212.3790227","title":"Static Analysis for Efficient Streaming Tokenization","display_name":"Static Analysis for Efficient Streaming Tokenization","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134888718","doi":"https://doi.org/10.1145/3779212.3790227"},"language":null,"primary_location":{"id":"doi:10.1145/3779212.3790227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779212.3790227","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Angela W. Li","orcid":"https://orcid.org/0000-0002-4523-3401"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angela W. Li","raw_affiliation_strings":["Rice University, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0002-4523-3401","affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042033656","display_name":"Yudi Yang","orcid":"https://orcid.org/0009-0009-3156-0637"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudi Yang","raw_affiliation_strings":["Rice University, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0009-0009-3156-0637","affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052392314","display_name":"Konstantinos Mamouras","orcid":"https://orcid.org/0000-0003-1209-7738"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Mamouras","raw_affiliation_strings":["Rice University, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0003-1209-7738","affiliations":[{"raw_affiliation_string":"Rice University, Houston, Texas, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.5563,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98581892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1880","last_page":"1896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8392999768257141,"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":0.8392999768257141,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.031700000166893005,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.02539999969303608,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9154000282287598},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7002000212669373},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.5443000197410583},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4941999912261963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46320000290870667}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9154000282287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456000089645386},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7002000212669373},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C104091681","wikidata":"https://www.wikidata.org/wiki/Q837528","display_name":"Deterministic finite automaton","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779212.3790227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3779212.3790227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W148814131","https://openalex.org/W1656178763","https://openalex.org/W1982129592","https://openalex.org/W1991570511","https://openalex.org/W2007130296","https://openalex.org/W2015292449","https://openalex.org/W2033393158","https://openalex.org/W2072523621","https://openalex.org/W2132774949","https://openalex.org/W2156429182","https://openalex.org/W2179349885","https://openalex.org/W2235749104","https://openalex.org/W2249895122","https://openalex.org/W2481729626","https://openalex.org/W2572917468","https://openalex.org/W3176694602","https://openalex.org/W3182005208","https://openalex.org/W4206544982","https://openalex.org/W4213362721","https://openalex.org/W4251803872","https://openalex.org/W4281667938","https://openalex.org/W4300782170","https://openalex.org/W4317433133","https://openalex.org/W4362677176","https://openalex.org/W4388212317","https://openalex.org/W4390604686","https://openalex.org/W4390778007","https://openalex.org/W4391825533","https://openalex.org/W4394892700","https://openalex.org/W4394999076","https://openalex.org/W4399850754","https://openalex.org/W4403223278","https://openalex.org/W4406257922","https://openalex.org/W4409311790","https://openalex.org/W4411486556","https://openalex.org/W4415308628","https://openalex.org/W6966541505","https://openalex.org/W7138852503"],"related_works":[],"abstract_inverted_index":{"Tokenization,":[0],"also":[1,44,123],"referred":[2],"to":[3,101],"as":[4,54,64,125],"lexing":[5],"or":[6,50],"scanning,":[7],"is":[8,25,35,43,61,71,122],"the":[9,28,97,104,126],"computational":[10],"task":[11],"of":[12,20,27,31,67,82,94],"partitioning":[13],"an":[14],"input":[15],"text":[16,49],"into":[17],"a":[18,65,73,80,114,118],"sequence":[19],"substrings":[21],"called":[22,72],"tokens.":[23],"Tokenization":[24],"one":[26],"first":[29],"stages":[30],"program":[32],"compilation,":[33],"it":[34,42],"used":[36],"in":[37],"natural":[38],"language":[39],"processing,":[40],"and":[41,57],"useful":[45],"for":[46],"processing":[47],"unstructured":[48],"semi-structured":[51],"data":[52],"such":[53],"JSON,":[55],"CSV,":[56],"XML.":[58],"A":[59],"tokenizer":[60],"typically":[62],"specified":[63],"list":[66],"regular":[68,77],"expressions,":[69],"which":[70],"tokenization":[74,95],"grammar.":[75],"Each":[76],"expression":[78],"describes":[79],"class":[81],"tokens":[83],"(e.g.,":[84],"integer,":[85],"floating-point":[86],"number,":[87],"variable":[88],"identifier,":[89],"string":[90],"literal).":[91],"The":[92],"semantics":[93],"employs":[96],"longest":[98],"match":[99],"policy":[100,108],"disambiguate":[102],"among":[103],"possible":[105],"choices.":[106],"This":[107],"says":[109],"that":[110],"we":[111],"should":[112],"prefer":[113],"longer":[115],"token":[116],"over":[117],"shorter":[119],"one.":[120],"It":[121],"known":[124],"maximal":[127],"munch":[128],"policy.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}