{"id":"https://openalex.org/W4311248665","doi":"https://doi.org/10.1145/3571207","title":"babble: Learning Better Abstractions with E-Graphs and Anti-unification","display_name":"babble: Learning Better Abstractions with E-Graphs and Anti-unification","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4311248665","doi":"https://doi.org/10.1145/3571207"},"language":"en","primary_location":{"id":"doi:10.1145/3571207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3571207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3571207","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3571207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103124733","display_name":"David Cao","orcid":"https://orcid.org/0000-0002-6163-1821"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Cao","raw_affiliation_strings":["University of California at San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077975106","display_name":"Rose Kunkel","orcid":"https://orcid.org/0000-0001-7432-8488"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rose Kunkel","raw_affiliation_strings":["University of California at San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066993902","display_name":"Chandrakana Nandi","orcid":"https://orcid.org/0000-0001-8633-8413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandrakana Nandi","raw_affiliation_strings":["Certora, USA"],"affiliations":[{"raw_affiliation_string":"Certora, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048760480","display_name":"Max Willsey","orcid":"https://orcid.org/0000-0001-8066-4218"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Willsey","raw_affiliation_strings":["University of Washington, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042187082","display_name":"Zachary Tatlock","orcid":"https://orcid.org/0000-0002-4731-0124"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Tatlock","raw_affiliation_strings":["University of Washington, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090671359","display_name":"Nadia Polikarpova","orcid":"https://orcid.org/0000-0001-5571-173X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nadia Polikarpova","raw_affiliation_strings":["University of California at San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103124733"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":5.7326,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96813075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"POPL","first_page":"396","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10126","display_name":"Logic, programming, and type systems","score":0.9905999898910522,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9905999898910522,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9902999997138977,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.988099992275238,"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/unification","display_name":"Unification","score":0.7552312612533569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7250458002090454},{"id":"https://openalex.org/keywords/modulo","display_name":"Modulo","score":0.6278057098388672},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46829456090927124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43508633971214294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3315544128417969},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3282496929168701},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20095565915107727},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.18291974067687988},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1573561131954193}],"concepts":[{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.7552312612533569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250458002090454},{"id":"https://openalex.org/C54732982","wikidata":"https://www.wikidata.org/wiki/Q1415345","display_name":"Modulo","level":2,"score":0.6278057098388672},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46829456090927124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43508633971214294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3315544128417969},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3282496929168701},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20095565915107727},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.18291974067687988},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1573561131954193}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3571207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3571207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3571207","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"},{"id":"pmh:oai:arXiv.org:2212.04596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04596","pdf_url":"https://arxiv.org/pdf/2212.04596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt9bj5072b","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9bj5072b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3571207","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3571207","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3571207","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":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6182133220","display_name":null,"funder_award_id":"1911149","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311248665.pdf","grobid_xml":"https://content.openalex.org/works/W4311248665.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W335088652","https://openalex.org/W2057423947","https://openalex.org/W2594908799","https://openalex.org/W2740254106","https://openalex.org/W2886686348","https://openalex.org/W2905304202","https://openalex.org/W2907839701","https://openalex.org/W2962809971","https://openalex.org/W2964341242","https://openalex.org/W2991552299","https://openalex.org/W3014415287","https://openalex.org/W3033423882","https://openalex.org/W3065734471","https://openalex.org/W3082570516","https://openalex.org/W3099525000","https://openalex.org/W3117137355","https://openalex.org/W3153044352","https://openalex.org/W3155736444","https://openalex.org/W3174357804","https://openalex.org/W3177593735","https://openalex.org/W3185574054","https://openalex.org/W3207460439","https://openalex.org/W4220706374","https://openalex.org/W4223562903","https://openalex.org/W4229487452","https://openalex.org/W4242955624","https://openalex.org/W4246264663","https://openalex.org/W4256028358","https://openalex.org/W4287116808","https://openalex.org/W4288365984","https://openalex.org/W4289129400","https://openalex.org/W4290096505","https://openalex.org/W4310557242","https://openalex.org/W6931415959"],"related_works":["https://openalex.org/W2367630557","https://openalex.org/W101666983","https://openalex.org/W2183792531","https://openalex.org/W2595286499","https://openalex.org/W2794344379","https://openalex.org/W2471908688","https://openalex.org/W1845283042","https://openalex.org/W3171337446","https://openalex.org/W2884423176","https://openalex.org/W2117548279"],"abstract_inverted_index":{"Library":[0],"learning":[1,23,66,73],"compresses":[2],"a":[3,70,84,107,127,152],"given":[4,85],"corpus":[5,14,118],"of":[6,99,140,146,165],"programs":[7,100],"by":[8],"extracting":[9],"common":[10,114],"structure":[11],"from":[12,25,31],"the":[13,61,97,103,117,144,147],"into":[15],"reusable":[16,159],"library":[17,22,44,65,72,168],"functions.":[18],"Prior":[19],"work":[20],"on":[21,161],"suffers":[24],"two":[26],"limitations":[27],"that":[28,46,75,134,156],"prevent":[29],"it":[30,39,53],"scaling":[32],"to":[33,57,94,112],"larger,":[34],"more":[35,119],"complex":[36],"inputs.":[37],"First,":[38],"explores":[40],"too":[41],"many":[42],"candidate":[43],"functions":[45,160],"are":[47],"not":[48,55],"useful":[49],"for":[50,83,167],"compression.":[51],"Second,":[52],"is":[54],"robust":[56],"syntactic":[58],"variation":[59],"in":[60,116,126],"input.":[62],"We":[63,123,149],"propose":[64],"modulo":[67,102],"theory":[68,82],"(LLMT),":[69],"new":[71],"algorithm":[74],"additionally":[76],"takes":[77],"as":[78],"input":[79],"an":[80],"equational":[81],"problem":[86],"domain.":[87],"LLMT":[88,125],"uses":[89,106],"e-graphs":[90],"and":[91,105,121],"equality":[92],"saturation":[93],"compactly":[95],"represent":[96],"space":[98],"equivalent":[101],"theory,":[104],"novel":[108],"e-graph":[109],"anti-unification":[110],"technique":[111],"find":[113],"patterns":[115],"directly":[120],"efficiently.":[122],"implemented":[124],"tool":[128],"named":[129],"babble.":[130],"Our":[131],"evaluation":[132,154],"shows":[133],"babble":[135,157],"achieves":[136],"better":[137],"compression":[138],"orders":[139],"magnitude":[141],"faster":[142],"than":[143],"state":[145],"art.":[148],"also":[150],"provide":[151],"qualitative":[153],"showing":[155],"learns":[158],"inputs":[162],"previously":[163],"out":[164],"reach":[166],"learning.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
