{"id":"https://openalex.org/W4403536942","doi":"https://doi.org/10.1145/3691620.3695474","title":"Unlocking the Power of Numbers: Log Compression via Numeric Token Parsing","display_name":"Unlocking the Power of Numbers: Log Compression via Numeric Token Parsing","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403536942","doi":"https://doi.org/10.1145/3691620.3695474"},"language":"en","primary_location":{"id":"doi:10.1145/3691620.3695474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691620.3695474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100714674","display_name":"Siyu Yu","orcid":"https://orcid.org/0000-0003-3793-7684"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Yu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3793-7684","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048488478","display_name":"Yifan Wu","orcid":"https://orcid.org/0000-0001-5847-3132"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5847-3132","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414277","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-6278-2357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6278-2357","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinjia He","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, Shenzhen, China","The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3377-8129","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"919","last_page":"930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9990000128746033,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9972000122070312,"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/security-token","display_name":"Security token","score":0.7579914331436157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019367814064026},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6931237578392029},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5523463487625122},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5422608852386475},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4448768198490143},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.33728092908859253},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3215944170951843},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2645329236984253},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2638740539550781},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20323210954666138},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16980209946632385}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7579914331436157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019367814064026},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6931237578392029},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5523463487625122},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5422608852386475},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4448768198490143},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.33728092908859253},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3215944170951843},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2645329236984253},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2638740539550781},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20323210954666138},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16980209946632385},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3691620.3695474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691620.3695474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1483021187","https://openalex.org/W1965853364","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2115613939","https://openalex.org/W2122962290","https://openalex.org/W2154091998","https://openalex.org/W2161628678","https://openalex.org/W2586066656","https://openalex.org/W2754665629","https://openalex.org/W2755402962","https://openalex.org/W2767094836","https://openalex.org/W2999013495","https://openalex.org/W3134064484","https://openalex.org/W3134079112","https://openalex.org/W3143573050","https://openalex.org/W4221079409","https://openalex.org/W4308642996","https://openalex.org/W4308643313","https://openalex.org/W4367146761","https://openalex.org/W4372263685","https://openalex.org/W4384345785","https://openalex.org/W4389162066","https://openalex.org/W4391558506"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Parser-based":[0],"log":[1,15,111,155,193,226,263],"compressors":[2,23,27,51,80,94,264],"have":[3,52],"been":[4,222],"widely":[5],"explored":[6],"in":[7,129,270],"recent":[8],"years":[9],"because":[10],"the":[11,18,32,36,42,56,65,76,83,127,177,191,201,216,252],"explosive":[12],"growth":[13],"of":[14,21,58,68,78,126,150,179,200],"volumes":[16],"makes":[17],"compression":[19,61,115,149,218,237,245,273,280],"performance":[20,77],"general-purpose":[22,47,211],"unsatisfactory.":[24],"These":[25],"parser-based":[26,50,79,93],"preprocess":[28],"logs":[29,33,69,85,130],"by":[30],"grouping":[31],"based":[34],"on":[35,82,224],"parsing":[37,59],"result":[38],"and":[39,60,86,117,141,144,147,170,184,213,228,239,275],"then":[40,205],"feed":[41],"preprocessed":[43],"files":[44,199],"into":[45,261],"a":[46,97,108,124,160,185,210,267],"compressor.":[48],"However,":[49],"their":[53,271],"limitations.":[54],"First,":[55],"goals":[57],"are":[62,131,204],"misaligned,":[63],"so":[64],"inherent":[66],"characteristics":[67],"were":[70],"not":[71],"fully":[72],"utilized.":[73],"In":[74],"addition,":[75],"depends":[81],"sample":[84],"thus":[87],"it":[88,214,229],"is":[89,122,152],"very":[90],"unstable.":[91],"Moreover,":[92,254],"often":[95],"incur":[96],"long":[98],"processing":[99,173],"time.":[100],"To":[101],"address":[102],"these":[103],"limitations,":[104],"we":[105],"propose":[106],"Denum,":[107],"simple,":[109],"general":[110],"compressor":[112,212],"with":[113,138],"high":[114],"ratio":[116,238,274],"speed.":[118,281],"The":[119,197],"core":[120],"insight":[121],"that":[123],"majority":[125],"tokens":[128,133,137,169],"numeric":[132,145,168],"(i.e.":[134,247],"pure":[135],"numbers,":[136],"only":[139],"numbers":[140,181],"special":[142],"characters,":[143],"variables)":[146],"effective":[148],"them":[151],"critical":[153],"for":[154],"compression.":[156],"Specifically,":[157],"Denum":[158,220],"contains":[159],"Numeric":[161,257],"Token":[162,258],"Parsing":[163,259],"module,":[164,188],"which":[165,189],"extracts":[166],"all":[167],"applies":[171],"tailored":[172],"methods":[174],"(e.g.":[175],"store":[176],"differences":[178],"incremental":[180],"like":[182],"timestamps),":[183],"String":[186],"Processing":[187],"processes":[190],"remaining":[192],"content":[194],"without":[195],"numbers.":[196],"processed":[198],"two":[202],"modules":[203],"fed":[206],"as":[207],"input":[208],"to":[209,251],"outputs":[215],"final":[217],"results.":[219],"has":[221],"evaluated":[223],"16":[225],"datasets":[227],"achieves":[230],"an":[231],"8.7%":[232],"--":[233,241],"434.7%":[234],"higher":[235],"average":[236,244,272,279],"2.6\u00d7":[240],"37.7\u00d7":[242],"faster":[243,278],"speed":[246],"26.2":[248],"MB/S)":[249],"compared":[250],"baselines.":[253],"integrating":[255],"Denum's":[256],"module":[260],"existing":[262],"can":[265],"provide":[266],"11.8%":[268],"improvement":[269],"achieve":[276],"37%":[277]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}