{"id":"https://openalex.org/W4399850754","doi":"https://doi.org/10.1145/3656461","title":"Static Analysis for Checking the Disambiguation Robustness of Regular Expressions","display_name":"Static Analysis for Checking the Disambiguation Robustness of Regular Expressions","publication_year":2024,"publication_date":"2024-06-20","ids":{"openalex":"https://openalex.org/W4399850754","doi":"https://doi.org/10.1145/3656461"},"language":"en","primary_location":{"id":"doi:10.1145/3656461","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656461","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656461","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3656461","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Konstantinos Mamouras","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0003-1209-7738","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044196182","display_name":"Alexis Le Glaunec","orcid":"https://orcid.org/0000-0002-5444-5924"},"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":"Alexis Le Glaunec","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0002-5444-5924","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068738516","display_name":"Wu Angela 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":"Wu Angela Li","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0002-4523-3401","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050116529","display_name":"Agnishom Chattopadhyay","orcid":"https://orcid.org/0009-0007-0462-8080"},"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":"Agnishom Chattopadhyay","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0009-0007-0462-8080","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052392314"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.7285,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85639273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"PLDI","first_page":"2073","last_page":"2097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.9991000294685364,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9950000047683716,"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/T10142","display_name":"Formal Methods in Verification","score":0.9947999715805054,"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/robustness","display_name":"Robustness (evolution)","score":0.7142465114593506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605913639068604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33982163667678833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.338095486164093}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7142465114593506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605913639068604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33982163667678833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.338095486164093},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":1,"locations":[{"id":"doi:10.1145/3656461","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656461","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656461","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3656461","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656461","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656461","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4367849889","display_name":null,"funder_award_id":"2313062","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399850754.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W33792228","https://openalex.org/W35443084","https://openalex.org/W1506336181","https://openalex.org/W1574255194","https://openalex.org/W1820500785","https://openalex.org/W1982129592","https://openalex.org/W1990437388","https://openalex.org/W2013120826","https://openalex.org/W2030102079","https://openalex.org/W2031830821","https://openalex.org/W2031906380","https://openalex.org/W2058269846","https://openalex.org/W2067443406","https://openalex.org/W2071685823","https://openalex.org/W2072102045","https://openalex.org/W2101547548","https://openalex.org/W2147817491","https://openalex.org/W2167473451","https://openalex.org/W2172171378","https://openalex.org/W2293046879","https://openalex.org/W2343176345","https://openalex.org/W2523499347","https://openalex.org/W2572917468","https://openalex.org/W2618072102","https://openalex.org/W2785700716","https://openalex.org/W2899462170","https://openalex.org/W2903931520","https://openalex.org/W2922478741","https://openalex.org/W2968339949","https://openalex.org/W2999135213","https://openalex.org/W3005310062","https://openalex.org/W3048708344","https://openalex.org/W3093164660","https://openalex.org/W3118520292","https://openalex.org/W4205983429","https://openalex.org/W4249827740","https://openalex.org/W4281667938","https://openalex.org/W4362677176","https://openalex.org/W4390604686","https://openalex.org/W4394999076","https://openalex.org/W6966541505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Regular":[0],"expressions":[1,116,184,210],"are":[2,51,202],"commonly":[3],"used":[4],"for":[5,27,113,132,163,178,204],"finding":[6],"and":[7,55,79,125,185,195],"extracting":[8],"matches":[9],"from":[10,212],"sequence":[11],"data.":[12],"Due":[13],"to":[14,34,89,146,159,169],"the":[15,28,37,42,52,56,64,69,103,127,148,180,192],"inherent":[16],"ambiguity":[17],"of":[18,41,68,86,98,105,129,182,208],"regular":[19,115,133,136,164,183,209],"expressions,":[20,165],"a":[21,76,83,160,174],"disambiguation":[22,49,99,130,152],"policy":[23,54,62,74,100,153],"must":[24],"be":[25,110,170],"considered":[26],"match":[29,39,66,78,90,106],"extraction":[30,142],"problem,":[31],"in":[32],"order":[33],"uniquely":[35],"determine":[36],"desired":[38],"out":[40,67],"possibly":[43],"many":[44,92],"matches.":[45],"The":[46,60,72,96],"most":[47],"common":[48],"policies":[50],"POSIX":[53,61,149],"greedy":[57,73,84,151],"(PCRE)":[58],"policy.":[59],"chooses":[63,75],"longest":[65],"leftmost":[70,77],"ones.":[71],"further":[80],"disambiguates":[81],"using":[82],"interpretation":[85],"Kleene":[87],"iteration":[88],"as":[91,94],"times":[93],"possible.":[95],"choice":[97],"can":[101,109],"affect":[102],"output":[104],"extraction,":[107],"which":[108,166],"an":[111],"issue":[112],"reusing":[114],"across":[117],"regex":[118],"engines.":[119],"In":[120],"this":[121],"paper,":[122],"we":[123,167,196],"introduce":[124],"study":[126],"notion":[128],"robustness":[131],"expressions.":[134],"A":[135],"expression":[137],"is":[138,144,154],"robust":[139],"if":[140],"its":[141],"semantics":[143],"indifferent":[145],"whether":[147],"or":[150],"chosen.":[155],"This":[156],"gives":[157],"rise":[158],"decision":[161],"problem":[162],"prove":[168],"PSPACE-complete.":[171],"We":[172,189],"propose":[173],"static":[175],"analysis":[176],"algorithm":[177],"checking":[179],"(non-)robustness":[181],"two":[186],"performance":[187],"optimizations.":[188],"have":[190,197],"implemented":[191],"proposed":[193],"algorithms":[194],"shown":[198],"experimentally":[199],"that":[200],"they":[201],"practical":[203],"analyzing":[205],"large":[206],"datasets":[207],"derived":[211],"various":[213],"application":[214],"domains.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
