{"id":"https://openalex.org/W4416943839","doi":"https://doi.org/10.1145/3786181.3788729","title":"Statistical Independence Aware Caching for LLM Workflows","display_name":"Statistical Independence Aware Caching for LLM Workflows","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4416943839","doi":"https://doi.org/10.1145/3786181.3788729"},"language":null,"primary_location":{"id":"doi:10.1145/3786181.3788729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788729","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786181.3788729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016228290","display_name":"Y. Sophia Dai","orcid":"https://orcid.org/0000-0002-7928-416X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Dai","raw_affiliation_strings":["Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0259-6174","affiliations":[{"raw_affiliation_string":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120538976","display_name":"Dimitrios Stamatios Bouras","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dimitrios Stamatios Bouras","raw_affiliation_strings":["Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3171-5194","affiliations":[{"raw_affiliation_string":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoxiang Jia","orcid":"https://orcid.org/0009-0005-6027-231X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxiang Jia","raw_affiliation_strings":["Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-6027-231X","affiliations":[{"raw_affiliation_string":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011184280","display_name":"Sergey Mechtaev","orcid":"https://orcid.org/0000-0001-6088-4993"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sergey Mechatev","raw_affiliation_strings":["Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6088-4993","affiliations":[{"raw_affiliation_string":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00397808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.15150000154972076,"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":0.15150000154972076,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.14630000293254852,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0681999996304512,"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/modular-design","display_name":"Modular design","score":0.5365999937057495},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.5152000188827515},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.48080000281333923},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4564000070095062},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4275999963283539},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4196999967098236},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815500020980835},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42640000581741333},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2563000023365021}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3786181.3788729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788729","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.22118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22118","pdf_url":"https://arxiv.org/pdf/2511.22118","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":"doi:10.48550/arxiv.2511.22118","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22118","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3786181.3788729","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788729","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"inference":[4],"is":[5],"both":[6],"expensive":[7],"and":[8,22,34,67,78,132,140,157,183],"slow.":[9],"Local":[10],"caching":[11,30,82],"of":[12,24,42,56,125,142,155,180],"responses":[13,44],"offers":[14],"a":[15,48,97,153,167],"practical":[16],"solution":[17],"to":[18,86,130,137],"reduce":[19],"the":[20,111,123,138],"cost":[21,184],"latency":[23],"LLM":[25,57,81,104,126],"queries.":[26],"In":[27,54],"research":[28],"contexts,":[29],"also":[31],"enhances":[32],"reproducibility":[33],"provides":[35],"flexibility":[36],"for":[37,51,58],"experimentation.":[38],"However,":[39],"naive":[40],"reuse":[41],"cached":[43],"compromises":[45],"statistical":[46,88,108,120,188],"independence,":[47],"critical":[49],"property":[50],"probabilistic":[52],"workflows.":[53],"applications":[55],"code,":[59],"it":[60],"underpins":[61],"performance":[62],"metrics":[63],"such":[64],"as":[65,70,72],"Pass@k":[66],"uncertainty":[68],"estimation,":[69],"well":[71],"algorithms":[73],"like":[74],"program":[75,170],"repair":[76,172],"loops":[77],"retries.":[79],"Existing":[80],"systems":[83],"lack":[84],"ways":[85],"enforce":[87],"independence":[89],"constraints.":[90],"To":[91],"address":[92],"this,":[93],"we":[94],"introduce":[95],"Mnimi,":[96],"cache":[98],"design":[99,148],"pattern":[100,149],"that":[101],"supports":[102],"modular":[103],"workflows":[105],"while":[106,186],"ensuring":[107],"integrity":[109],"at":[110],"component":[112],"level.":[113],"Its":[114],"core":[115],"innovation":[116],"lies":[117],"in":[118,150],"encapsulating":[119],"constraints":[121],"within":[122],"type":[124],"references,":[127],"allowing":[128],"users":[129],"manage":[131],"transform":[133],"these":[134],"types":[135],"according":[136],"scope":[139],"requirements":[141],"their":[143],"algorithm.":[144],"We":[145],"implemented":[146],"this":[147],"Python":[151],"using":[152],"combination":[154],"decorators":[156],"iterators":[158],"over":[159],"infinite":[160],"sequences.":[161],"A":[162],"case":[163],"study":[164],"on":[165],"SpecFix,":[166],"recent":[168],"automated":[169],"specification":[171],"system,":[173],"highlights":[174],"how":[175],"Mnimi":[176],"improves":[177],"reproducibility,":[178],"ease":[179],"debugging,":[181],"time":[182],"efficiency":[185],"preserving":[187],"correctness.":[189]},"counts_by_year":[],"updated_date":"2026-07-09T05:49:46.723101","created_date":"2025-12-03T00:00:00"}
