{"id":"https://openalex.org/W4411522841","doi":"https://doi.org/10.1145/3728969","title":"LogBase: A Large-Scale Benchmark for Semantic Log Parsing","display_name":"LogBase: A Large-Scale Benchmark for Semantic Log Parsing","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411522841","doi":"https://doi.org/10.1145/3728969"},"language":"en","primary_location":{"id":"doi:10.1145/3728969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728969","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033526358","display_name":"Chenbo Zhang","orcid":"https://orcid.org/0000-0002-6773-598X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenbo Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6773-598X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036668090","display_name":"Wenying Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenying Xu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-0688-576X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017058942","display_name":"Jinbu Liu","orcid":"https://orcid.org/0009-0003-6149-2651"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbu Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-6149-2651","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388587","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-9532-5219"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9532-5219","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081766211","display_name":"Guiyang Liu","orcid":"https://orcid.org/0009-0000-3383-9409"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyang Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3383-9409","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086316879","display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2313-7635","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631796","display_name":"Qi Zhou","orcid":"https://orcid.org/0000-0002-7759-800X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhou","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7759-800X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1949-2768","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5033526358"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":5.9677,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96239072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"2","issue":"ISSTA","first_page":"2091","last_page":"2112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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/T10260","display_name":"Software Engineering Research","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.953499972820282,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/parsing","display_name":"Parsing","score":0.8899813294410706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8655076026916504},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4931165874004364},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4810788333415985},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4665628969669342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45472943782806396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41440582275390625},{"id":"https://openalex.org/keywords/s-attributed-grammar","display_name":"S-attributed grammar","score":0.4122849702835083},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21381255984306335}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8899813294410706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655076026916504},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4931165874004364},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4810788333415985},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4665628969669342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45472943782806396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41440582275390625},{"id":"https://openalex.org/C147547768","wikidata":"https://www.wikidata.org/wiki/Q3113342","display_name":"S-attributed grammar","level":3,"score":0.4122849702835083},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21381255984306335},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728969","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1661413208","https://openalex.org/W1994625872","https://openalex.org/W2015979301","https://openalex.org/W2076809217","https://openalex.org/W2115056012","https://openalex.org/W2153470728","https://openalex.org/W2208211896","https://openalex.org/W2250539671","https://openalex.org/W2401686019","https://openalex.org/W2536393303","https://openalex.org/W2583874385","https://openalex.org/W2734941459","https://openalex.org/W2754665629","https://openalex.org/W2767094836","https://openalex.org/W2792207129","https://openalex.org/W2808242862","https://openalex.org/W2883560233","https://openalex.org/W2898944906","https://openalex.org/W2911282308","https://openalex.org/W2947815220","https://openalex.org/W2955925687","https://openalex.org/W4221079409","https://openalex.org/W4226128225","https://openalex.org/W4232648333","https://openalex.org/W4248004298","https://openalex.org/W4284692184","https://openalex.org/W4308642996","https://openalex.org/W4308643313","https://openalex.org/W4311299599","https://openalex.org/W4321504227","https://openalex.org/W4367146761","https://openalex.org/W4384158990","https://openalex.org/W4384345673","https://openalex.org/W4384345748","https://openalex.org/W4384345785","https://openalex.org/W4384347367","https://openalex.org/W4388212317","https://openalex.org/W4388483640","https://openalex.org/W4394769528","https://openalex.org/W4404783403","https://openalex.org/W4411272222","https://openalex.org/W6852168108"],"related_works":["https://openalex.org/W1975821179","https://openalex.org/W3088470625","https://openalex.org/W3035970863","https://openalex.org/W1481527871","https://openalex.org/W2034992613","https://openalex.org/W3143982968","https://openalex.org/W1623019121","https://openalex.org/W4320024782","https://openalex.org/W2389755172","https://openalex.org/W2979495269"],"abstract_inverted_index":{"Logs":[0],"generated":[1,222],"by":[2],"large-scale":[3],"software":[4],"systems":[5],"contain":[6],"a":[7,249],"huge":[8],"amount":[9],"of":[10,17,53,69,80,101,112,120,132,148,220,251,311],"useful":[11],"information.":[12],"As":[13],"the":[14,41,51,67,77,99,108,118,130,139,177,218,221,263,308],"first":[15,140],"step":[16],"automated":[18,231],"log":[19,21,28,48,61,81,86,91,96,114,122,134,142,159,166,183,188,242,259,268,280,313],"analysis,":[20],"parsing":[22,29,62,82,143,184,243],"has":[23],"been":[24],"extensively":[25,276],"studied.":[26],"General":[27],"techniques":[30,201],"focus":[31],"on":[32,195],"identifying":[33],"static":[34],"templates":[35,92],"from":[36,150,191],"raw":[37],"logs,":[38],"but":[39],"overlook":[40],"more":[42],"important":[43],"semantics":[44,94],"implied":[45],"in":[46,95,104,164,286],"dynamic":[47],"parameters.":[49,97],"With":[50,273],"popularity":[52],"Artificial":[54],"Intelligence":[55],"for":[56,180,255,266],"IT":[57],"Operations":[58],"(AIOps),":[59],"traditional":[60],"methods":[63],"no":[64],"longer":[65],"meet":[66],"requirements":[68],"various":[70],"downstream":[71],"tasks.":[72],"Researchers":[73],"are":[74],"now":[75],"exploring":[76],"next":[78],"generation":[79],"techniques,":[83],"i.e.,":[84],"semantic":[85,102,113,121,133,141,182,241,267,312],"parsing,":[87,135],"to":[88,207,216,236,304],"identify":[89],"both":[90,165],"and":[93,110,128,169,197,224,232,238,262,270,301,306],"However,":[98],"absence":[100],"annotations":[103],"existing":[105,162,279],"datasets":[106,163],"hinders":[107],"training":[109],"evaluation":[111,253],"parsers,":[115,281],"thereby":[116],"stalling":[117],"progress":[119],"parsing.":[123,314],"To":[124,172],"fill":[125],"this":[126,292],"gap":[127],"advance":[129],"field":[131],"we":[136,175,246,275],"construct":[137,240],"LogBase,":[138,256,274],"benchmark":[144],"dataset.":[145],"LogBase":[146],"consists":[147],"logs":[149],"130":[151],"popular":[152,192],"open-source":[153,193],"projects,":[154],"containing":[155],"85,300":[156],"semantically":[157],"annotated":[158],"templates,":[160],"surpassing":[161],"source":[167],"diversity":[168],"template":[170],"richness.":[171],"build":[173],"Logbase,":[174],"develop":[176],"framework":[178],"GenLog":[179,186,212,228],"constructing":[181],"datasets.":[185,244],"mines":[187],"template-parameter-context":[189],"triplets":[190],"repositories":[194],"GitHub,":[196],"uses":[198],"chain-of-thought":[199],"(CoT)":[200],"with":[202,296],"large":[203],"language":[204],"models":[205],"(LLMs)":[206],"generate":[208],"high-quality":[209],"logs.":[210],"Meanwhile,":[211],"employs":[213],"human":[214],"feedback":[215],"improve":[217],"quality":[219],"data":[223],"ensure":[225],"its":[226],"reliability.":[227],"is":[229],"highly":[230],"cost-effective,":[233],"enabling":[234],"researchers":[235,295],"easily":[237],"efficiently":[239],"Furthermore,":[245],"also":[247],"design":[248],"set":[250],"comprehensive":[252],"metrics":[254,261,264],"including":[257],"general":[258],"parser":[260],"specifically":[265],"parsers":[269],"LLM-based":[271],"parsers.":[272],"evaluate":[277],"15":[278],"revealing":[282],"their":[283],"true":[284],"performance":[285],"complex":[287],"scenarios.":[288],"We":[289],"believe":[290],"that":[291],"work":[293],"provides":[294],"valuable":[297],"data,":[298],"reliable":[299],"tools,":[300],"insightful":[302],"findings":[303],"support":[305],"guide":[307],"future":[309],"research":[310]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}