{"id":"https://openalex.org/W4413267905","doi":"https://doi.org/10.1145/3696630.3728531","title":"L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis","display_name":"L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4413267905","doi":"https://doi.org/10.1145/3696630.3728531"},"language":null,"primary_location":{"id":"doi:10.1145/3696630.3728531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696630.3728531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-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/A5068670072","display_name":"Zhihan Jiang","orcid":"https://orcid.org/0009-0003-1988-6219"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhihan Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040653412","display_name":"Junjie Huang","orcid":"https://orcid.org/0009-0004-6962-5292"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075077822","display_name":"Guangba Yu","orcid":"https://orcid.org/0000-0001-6195-9088"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guangba Yu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048929944","display_name":"Zhuangbin Chen","orcid":"https://orcid.org/0000-0001-5158-6716"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuangbin Chen","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426730","display_name":"Yichen Li","orcid":"https://orcid.org/0009-0009-8370-644X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yichen Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098969559","display_name":"Renyi Zhong","orcid":"https://orcid.org/0000-0001-6626-4437"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renyi Zhong","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035644557","display_name":"C. Q. Feng","orcid":"https://orcid.org/0009-0000-5556-4004"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Feng","raw_affiliation_strings":["Computing and Networking Innovation Lab,Huawei Cloud Computing Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computing and Networking Innovation Lab,Huawei Cloud Computing Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049498035","display_name":"Yongqiang Yang","orcid":"https://orcid.org/0000-0001-9733-4346"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Yang","raw_affiliation_strings":["Huawei Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071672297","display_name":"Zengyin Yang","orcid":"https://orcid.org/0000-0001-6307-7310"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengyin Yang","raw_affiliation_strings":["Huawei Cloud Computing Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069596903","display_name":"Michael R. Lyu","orcid":"https://orcid.org/0000-0002-3666-5798"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Michael Lyu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5068670072"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":8.9326,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9772395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9610000252723694,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9573000073432922,"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/computer-science","display_name":"Computer science","score":0.7073162794113159},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5776340365409851},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4960575997829437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3909373879432678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3458738923072815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073162794113159},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5776340365409851},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4960575997829437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3909373879432678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3458738923072815},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696630.3728531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696630.3728531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of 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/W95608104","https://openalex.org/W170732776","https://openalex.org/W1482147200","https://openalex.org/W2079054072","https://openalex.org/W2734941459","https://openalex.org/W2911282308","https://openalex.org/W2912378279","https://openalex.org/W2914874661","https://openalex.org/W2965838158","https://openalex.org/W2991130147","https://openalex.org/W3035438476","https://openalex.org/W3109716606","https://openalex.org/W4233869839","https://openalex.org/W4238124605","https://openalex.org/W4248799824","https://openalex.org/W4253439680","https://openalex.org/W4253752119","https://openalex.org/W4387302738","https://openalex.org/W4387841511","https://openalex.org/W4389162688","https://openalex.org/W4391983842","https://openalex.org/W4394907705","https://openalex.org/W4399213764","https://openalex.org/W4402443087"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-08-18T00:00:00"}
