{"id":"https://openalex.org/W4414405078","doi":"https://doi.org/10.1109/clusterworkshops65972.2025.11164207","title":"Toward LLM-Compatible Log Representation Learning: A Hierarchical Semantic-Structural Framework for HPC Anomaly Detection","display_name":"Toward LLM-Compatible Log Representation Learning: A Hierarchical Semantic-Structural Framework for HPC Anomaly Detection","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414405078","doi":"https://doi.org/10.1109/clusterworkshops65972.2025.11164207"},"language":"en","primary_location":{"id":"doi:10.1109/clusterworkshops65972.2025.11164207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clusterworkshops65972.2025.11164207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops)","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/A5119695058","display_name":"Dumo Ngwenya","orcid":null},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dumo Ngwenya","raw_affiliation_strings":["The Open University,School of Computing & Communications,Milton Keynes,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Open University,School of Computing & Communications,Milton Keynes,UK","institution_ids":["https://openalex.org/I204136569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073705756","display_name":"Dhouha Kbaier Ben Ismail","orcid":"https://orcid.org/0000-0001-8338-6049"},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dhouha Kbaier","raw_affiliation_strings":["The Open University,School of Computing & Communications,Milton Keynes,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Open University,School of Computing & Communications,Milton Keynes,UK","institution_ids":["https://openalex.org/I204136569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028456933","display_name":"Patrick Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick Wong","raw_affiliation_strings":["The Open University,School of Computing & Communications,Milton Keynes,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Open University,School of Computing & Communications,Milton Keynes,UK","institution_ids":["https://openalex.org/I204136569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204136569"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9811000227928162,"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/T11719","display_name":"Data Quality and Management","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8719000220298767},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.729200005531311},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45660001039505005},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.3691999912261963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8719000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306999802589417},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.729200005531311},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4154999852180481},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/clusterworkshops65972.2025.11164207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clusterworkshops65972.2025.11164207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops)","raw_type":"proceedings-article"},{"id":"pmh:oai:oro.open.ac.uk:106587","is_oa":false,"landing_page_url":"https://oro.open.ac.uk/view/person/djn268.html;","pdf_url":null,"source":{"id":"https://openalex.org/S4306401187","display_name":"Open Research Online (The Open University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204136569","host_organization_name":"The Open University","host_organization_lineage":["https://openalex.org/I204136569"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1661413208","https://openalex.org/W2094924503","https://openalex.org/W2115056012","https://openalex.org/W2208211896","https://openalex.org/W2536393303","https://openalex.org/W2583874385","https://openalex.org/W2754665629","https://openalex.org/W2767094836","https://openalex.org/W2898998129","https://openalex.org/W2947815220","https://openalex.org/W2963999143","https://openalex.org/W2965838158","https://openalex.org/W3089662691","https://openalex.org/W3134079112","https://openalex.org/W3147048975","https://openalex.org/W3185341429","https://openalex.org/W3199174176","https://openalex.org/W4221079409","https://openalex.org/W4384345785","https://openalex.org/W4388129790","https://openalex.org/W4393141466","https://openalex.org/W4394745212","https://openalex.org/W4394769528","https://openalex.org/W4398239377","https://openalex.org/W4401667316"],"related_works":[],"abstract_inverted_index":{"High-Performance":[0],"Computing":[1],"(HPC)":[2],"systems":[3],"generate":[4],"massive":[5],"volumes":[6],"of":[7,30,77,90,131],"logs,":[8],"necessitating":[9],"sophisticated":[10],"parsing":[11,47,57,118],"techniques":[12],"for":[13,37,85,112,138],"anomaly":[14,39,104,142],"detection.":[15,40],"While":[16],"traditional":[17],"log":[18,46,78,139],"parsers":[19],"prioritize":[20],"syntactic":[21],"accuracy,":[22],"recent":[23],"work":[24],"underscores":[25],"semantic":[26,60,124],"distinguishability;":[27],"the":[28],"preservation":[29,125],"operational":[31,153],"meaning":[32],"in":[33,144],"templates":[34,101],"as":[35],"critical":[36],"effective":[38],"We":[41],"present":[42],"DistinctLog,":[43],"a":[44],"novel":[45],"framework":[48],"leveraging":[49,132],"lightweight":[50],"Large":[51],"Language":[52],"Model":[53],"(LLM)":[54],"embeddings":[55],"during":[56],"to":[58,69],"enhance":[59],"preservation.":[61],"DistinctLog":[62],"integrates":[63],"three":[64],"components:":[65],"(1)":[66],"template":[67],"fingerprinting":[68],"capture":[70],"structure":[71],"and":[72,80,92,141],"semantics;":[73],"(2)":[74],"hierarchical":[75],"categorisation":[76],"intent;":[79],"(3)":[81],"LLM-guided":[82],"similarity":[83],"assessment":[84],"evolving":[86],"templates.":[87],"Comprehensive":[88],"evaluation":[89],"BGL":[91],"Spirit":[93],"HPC":[94,146],"datasets":[95],"demonstrates":[96],"that":[97,123],"DistinctLog\u2019s":[98],"semantically":[99],"aware":[100],"improve":[102],"downstream":[103],"detection":[105,143],"F1":[106],"scores":[107],"on":[108],"average":[109],"by":[110,148],"4.63%":[111],"CNN-based":[113],"detectors":[114],"while":[115],"maintaining":[116],"competitive":[117],"efficiency.":[119],"Our":[120],"analysis":[121,140],"reveals":[122],"particularly":[126],"benefits":[127],"neural":[128],"architectures":[129],"capable":[130],"contextual":[133],"information,":[134],"offering":[135],"significant":[136],"implications":[137],"production":[145],"environments":[147],"balancing":[149],"computational":[150],"cost":[151],"with":[152],"insight.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}