{"id":"https://openalex.org/W4410049416","doi":"https://doi.org/10.1145/3680256.3721320","title":"FAILS: A Framework for Automated Collection and Analysis of LLM Service Incidents","display_name":"FAILS: A Framework for Automated Collection and Analysis of LLM Service Incidents","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410049416","doi":"https://doi.org/10.1145/3680256.3721320"},"language":"en","primary_location":{"id":"doi:10.1145/3680256.3721320","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680256.3721320","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3680256.3721320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117419904","display_name":"S\u00e1ndor Battaglini-Fischer","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"S\u00e1ndor Battaglini-Fischer","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0000-7285-1574","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nishanthi Srinivasan","orcid":"https://orcid.org/0009-0004-8076-5755"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nishanthi Srinivasan","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0004-8076-5755","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117419905","display_name":"B\u00e1lint L\u00e1szl\u00f3 Szarvas","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"B\u00e1lint L\u00e1szl\u00f3 Szarvas","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0009-7696-2525","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081421197","display_name":"Xiaoyu Chu","orcid":"https://orcid.org/0000-0002-0353-7968"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiaoyu Chu","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0353-7968","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986556","display_name":"Alexandru Iosup","orcid":"https://orcid.org/0000-0001-8030-9398"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexandru Iosup","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8030-9398","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I865915315"],"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":"187","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9997000098228455,"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":0.9997000098228455,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.604535698890686},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4978499412536621},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36539894342422485},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3560687303543091},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1118796169757843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.604535698890686},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4978499412536621},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36539894342422485},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3560687303543091},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1118796169757843},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3680256.3721320","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680256.3721320","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:publications/47cb36ab-0e80-4cd2-896f-4ae69de486ad","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/47cb36ab-0e80-4cd2-896f-4ae69de486ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Battaglini-Fischer, S, Srinivasan, N, Szarvas, B L, Chu, X & Iosup, A 2025, FAILS: A Framework for Automated Collection and Analysis of LLM Service Incidents. in ICPE '25 : Companion of the 16th ACM/SPEC International Conference on Performance Engineering. Association for Computing Machinery, Inc, pp. 187-194, 16th ACM/SPEC International Conference on Performance Engineering, ICPE Companion 2025, Toronto, Canada, 5/05/25. https://doi.org/10.1145/3680256.3721320","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2503.12185","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.12185","pdf_url":"https://arxiv.org/pdf/2503.12185","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:research.vu.nl:openaire_cris_publications/47cb36ab-0e80-4cd2-896f-4ae69de486ad","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/47cb36ab-0e80-4cd2-896f-4ae69de486ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Battaglini-Fischer, S, Srinivasan, N, Szarvas, B L, Chu, X & Iosup, A 2025, FAILS: A Framework for Automated Collection and Analysis of LLM Service Incidents. in ICPE '25 : Companion of the 16th ACM/SPEC International Conference on Performance Engineering. Association for Computing Machinery, Inc, pp. 187-194, 16th ACM/SPEC International Conference on Performance Engineering, ICPE Companion 2025, Toronto, Canada, 5/05/25. https://doi.org/10.1145/3680256.3721320","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3680256.3721320","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680256.3721320","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1984980195","https://openalex.org/W2017060126","https://openalex.org/W2145071552","https://openalex.org/W2767346922","https://openalex.org/W2969309550","https://openalex.org/W4205683709","https://openalex.org/W4286895919","https://openalex.org/W4362505433","https://openalex.org/W4381890996","https://openalex.org/W4387582619","https://openalex.org/W4391462666","https://openalex.org/W4395686516","https://openalex.org/W4400267110","https://openalex.org/W4401321981","https://openalex.org/W4403648037","https://openalex.org/W4403883917","https://openalex.org/W4405254491","https://openalex.org/W4406138658","https://openalex.org/W4406265565"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"services":[4,105],"such":[5,22,154],"as":[6,23,155],"ChatGPT,":[7],"DALL\u00b7E,":[8],"and":[9,18,27,40,44,64,100,106,114,124,132,161,177,184,209,216,221],"Cursor":[10],"have":[11],"quickly":[12],"become":[13],"essential":[14],"for":[15,74,96],"society,":[16],"businesses,":[17],"individuals,":[19],"empowering":[20],"applications":[21],"chatbots,":[24],"image":[25],"generation,":[26],"code":[28],"assistance.":[29],"The":[30,226],"complexity":[31],"of":[32,139,148],"LLM":[33,76,104,170,224],"systems":[34],"makes":[35],"them":[36,199],"prone":[37],"to":[38,144,158,172,181,196,212],"failures":[39,78],"affects":[41],"their":[42,47],"reliability":[43,152],"availability,":[45],"yet":[46],"failure":[48,140,214],"patterns":[49,215],"are":[50,61,189],"not":[51],"fully":[52],"understood,":[53],"making":[54],"it":[55],"an":[56,71],"emerging":[57],"problem.":[58],"However,":[59],"there":[60],"limited":[62],"datasets":[63],"studies":[65],"in":[66,86,174,191,223],"this":[67,87],"area,":[68],"particularly":[69],"lacking":[70],"open-access":[72],"tool":[73],"analyzing":[75],"service":[77,151],"based":[79],"on":[80,102,231],"incident":[81,97,126],"reports.":[82],"Addressing":[83],"these":[84],"problems,":[85],"work":[88],"we":[89],"propose":[90],"FAILS,":[91],"the":[92,192],"first":[93],"open-sourced":[94],"framework":[95,227],"reports":[98],"collection":[99],"analysis":[101,176],"different":[103],"providers.":[107],"FAILS":[108,205],"provides":[109,136],"comprehensive":[110],"data":[111,127,130,175],"collection,":[112],"analysis,":[113,141],"visualization":[115],"capabilities,":[116],"including:":[117],"(1)":[118],"It":[119,135,167],"can":[120],"automatically":[121],"collect,":[122],"clean,":[123],"update":[125],"through":[128,200],"its":[129],"scraper":[131],"processing":[133],"components;(2)":[134],"17":[137],"types":[138],"allowing":[142,194],"users":[143,180,195,211],"explore":[145],"temporal":[146],"trends":[147],"incidents,":[149],"analyze":[150],"metrics,":[153],"Mean":[156,162],"Time":[157,163],"Recovery":[159],"(MTTR)":[160],"Between":[164],"Failures":[165],"(MTBF);(3)":[166],"leverages":[168],"advanced":[169],"tools":[171],"assist":[173],"interpretation,":[178],"enabling":[179],"gain":[182],"observations":[183],"insights":[185],"efficiently.":[186],"All":[187],"functions":[188],"integrated":[190],"backend,":[193],"easily":[197],"access":[198],"a":[201],"web-based":[202],"frontend":[203],"interface.":[204],"supports":[206],"researchers,":[207],"engineers,":[208],"general":[210],"understand":[213],"further":[217],"mitigate":[218],"operational":[219],"incidents":[220],"outages":[222],"services.":[225],"is":[228],"publicly":[229],"available":[230],"https://github.com/atlarge-research/FAILS.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
