{"id":"https://openalex.org/W4414735796","doi":"https://doi.org/10.1145/3731569.3764850","title":"TrainVerify: Equivalence-Based Verification for Distributed LLM Training","display_name":"TrainVerify: Equivalence-Based Verification for Distributed LLM Training","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414735796","doi":"https://doi.org/10.1145/3731569.3764850"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764850","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731569.3764850","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yunchi Lu","orcid":"https://orcid.org/0009-0004-6360-7392"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunchi Lu","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"raw_orcid":"https://orcid.org/0009-0004-6360-7392","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075076538","display_name":"Youshan Miao","orcid":"https://orcid.org/0000-0002-2395-9965"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youshan Miao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2395-9965","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759092","display_name":"Cheng Tan","orcid":"https://orcid.org/0000-0002-1420-5125"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Tan","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-1420-5125","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778324","display_name":"Peng Huang","orcid":"https://orcid.org/0000-0001-6315-0848"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"raw_orcid":"https://orcid.org/0000-0001-6315-0848","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Zhu","orcid":"https://orcid.org/0009-0002-7755-6624"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7755-6624","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079184162","display_name":"Xian Zhang","orcid":"https://orcid.org/0000-0003-4875-2132"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4875-2132","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346602","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-0378-060X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0378-060X","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.9940999746322632,"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/T10028","display_name":"Topic Modeling","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6945000290870667},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5077999830245972},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/expose","display_name":"EXPOSE","score":0.3303000032901764},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.32359999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6945000290870667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C2779137570","wikidata":"https://www.wikidata.org/wiki/Q16243196","display_name":"EXPOSE","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662999927997589}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731569.3764850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764850","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":{"id":"doi:10.1145/3731569.3764850","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764850","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W109452506","https://openalex.org/W2140609507","https://openalex.org/W2417863416","https://openalex.org/W2735532640","https://openalex.org/W2899771611","https://openalex.org/W2990138404","https://openalex.org/W3177828909","https://openalex.org/W4213153339","https://openalex.org/W4221157022","https://openalex.org/W4237661429","https://openalex.org/W4242726609","https://openalex.org/W4376272906","https://openalex.org/W4405903187"],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"at":[5],"scale":[6],"requires":[7],"parallel":[8],"execution":[9],"across":[10],"thousands":[11],"of":[12,35],"devices,":[13],"incurring":[14],"enormous":[15],"computational":[16],"costs.":[17],"Yet,":[18],"these":[19],"costly":[20],"distributed":[21],"trainings":[22],"are":[23,40],"prone":[24],"to":[25,42],"correctness":[26],"bugs,":[27],"causing":[28],"silent":[29],"errors":[30],"and":[31],"potentially":[32],"wasting":[33],"millions":[34],"GPU":[36],"hours.":[37],"These":[38],"bugs":[39],"challenging":[41],"expose":[43],"through":[44],"testing.":[45]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}