{"id":"https://openalex.org/W4414736132","doi":"https://doi.org/10.1145/3731569.3764848","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","display_name":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414736132","doi":"https://doi.org/10.1145/3731569.3764848"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731569.3764848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","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/A5003662255","display_name":"Yangtao Deng","orcid":"https://orcid.org/0000-0003-4072-7696"},"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":"Yangtao Deng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4072-7696","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746462","display_name":"Lei Zhang","orcid":"https://orcid.org/0009-0002-5132-4251"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["ByteDance, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0002-5132-4251","affiliations":[{"raw_affiliation_string":"ByteDance, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068611075","display_name":"Qinlong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinlong Wang","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5406-6354","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyun Zhi","orcid":"https://orcid.org/0009-0002-5403-9720"},"institutions":[{"id":"https://openalex.org/I3130757197","display_name":"Distance State University","ror":"https://ror.org/0529rbt18","country_code":"CR","type":"education","lineage":["https://openalex.org/I3130757197"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Xiaoyun Zhi","raw_affiliation_strings":["ByteDance Seed, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0002-5403-9720","affiliations":[{"raw_affiliation_string":"ByteDance Seed, San Jose, USA","institution_ids":["https://openalex.org/I3130757197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031506917","display_name":"Xinlei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinlei Zhang","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2279-4258","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101871699","display_name":"Zhuo Jiang","orcid":"https://orcid.org/0000-0002-6144-7899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Jiang","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6144-7899","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101277211","display_name":"Haohan Xu","orcid":"https://orcid.org/0000-0002-9813-4570"},"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":"Haohan Xu","raw_affiliation_strings":["ByteDance, Beijing, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9813-4570","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134511265","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0002-3809-1879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3809-1879","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zuquan Song","orcid":"https://orcid.org/0009-0008-7576-6162"},"institutions":[{"id":"https://openalex.org/I1316868585","display_name":"Fidal","ror":"https://ror.org/04nwdyy60","country_code":"FR","type":"other","lineage":["https://openalex.org/I1316868585"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zuquan Song","raw_affiliation_strings":["ByteDance Seed, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0008-7576-6162","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Seattle, USA","institution_ids":["https://openalex.org/I1316868585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111269350","display_name":"G L Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaohong Liu","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-2551-7879","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101098174","display_name":"Yang Bai","orcid":"https://orcid.org/0009-0009-6416-0074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Bai","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6416-0074","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034563547","display_name":"Shuguang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuguang Wang","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4249-4092","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086945155","display_name":"Wencong Xiao","orcid":"https://orcid.org/0000-0002-3043-522X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wencong Xiao","raw_affiliation_strings":["ByteDance Seed, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3043-522X","affiliations":[{"raw_affiliation_string":"ByteDance Seed, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049104908","display_name":"Jianxi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianxi Ye","raw_affiliation_strings":["ByteDance, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0007-3395-3624","affiliations":[{"raw_affiliation_string":"ByteDance, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035157838","display_name":"Minlan Yu","orcid":"https://orcid.org/0000-0002-2381-0212"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minlan Yu","raw_affiliation_strings":["Harvard University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-2381-0212","affiliations":[{"raw_affiliation_string":"Harvard University, Boston, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022420830","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0002-9359-9571"},"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":"Hong Xu","raw_affiliation_strings":["ByteDance, Beijing, China","The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9359-9571","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5003662255"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30249372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"254","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9961000084877014,"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":0.9961000084877014,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9886000156402588,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9790999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6894000172615051},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.5724999904632568},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.49799999594688416},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.39750000834465027},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.3698999881744385},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3449000120162964}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6894000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294999718666077},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C67363961","wikidata":"https://www.wikidata.org/wiki/Q5268834","display_name":"Information and Communications Technology","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27639999985694885},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C89057211","wikidata":"https://www.wikidata.org/wiki/Q432197","display_name":"Collective intelligence","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731569.3764848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731569.3764848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles","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":16,"referenced_works":["https://openalex.org/W2734941459","https://openalex.org/W2895690683","https://openalex.org/W2902547091","https://openalex.org/W2913613239","https://openalex.org/W2914997739","https://openalex.org/W4205983429","https://openalex.org/W4226064176","https://openalex.org/W4234493895","https://openalex.org/W4254620533","https://openalex.org/W4301647871","https://openalex.org/W4386768656","https://openalex.org/W4387302738","https://openalex.org/W4400484607","https://openalex.org/W4404400739","https://openalex.org/W4409248182","https://openalex.org/W4413757026"],"related_works":[],"abstract_inverted_index":{"Reliability":[0],"is":[1],"essential":[2],"for":[3,39],"ensuring":[4],"efficiency":[5],"in":[6,19],"LLM":[7],"training.":[8],"However,":[9],"many":[10],"real-world":[11],"reliability":[12],"issues":[13],"remain":[14],"difficult":[15],"to":[16],"resolve,":[17],"resulting":[18],"wasted":[20],"resources":[21],"and":[22],"degraded":[23],"model":[24],"performance.":[25],"Unfortunately,":[26],"today's":[27],"collective":[28],"communication":[29],"libraries":[30],"operate":[31],"as":[32],"black":[33],"boxes,":[34],"hiding":[35],"critical":[36],"information":[37],"needed":[38],"effective":[40],"root":[41],"cause":[42],"analysis.":[43]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
