{"id":"https://openalex.org/W7215129010","doi":"https://doi.org/10.48550/arxiv.2609.39067","title":"Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple Checkpointing","display_name":"Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple Checkpointing","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215129010","doi":"https://doi.org/10.48550/arxiv.2609.39067"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.39067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.39067","pdf_url":"https://arxiv.org/pdf/2609.39067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.39067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138138219","display_name":"Angshuman Chakravertty","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakravertty, Angshuman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153738541","display_name":"MD Rayyan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rayyan, MD","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.0027000000700354576,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/checkpointing","display_name":"checkpointing","score":0.8880000114440918},{"id":"https://openalex.org/keywords/kubernetes-operator","display_name":"Kubernetes operator","score":0.8370000123977661},{"id":"https://openalex.org/keywords/argus","display_name":"Argus","score":0.5870000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.5855000019073486},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2780317896","wikidata":"https://www.wikidata.org/wiki/Q2703","display_name":"Epoch (astronomy)","level":3,"score":0.4300999939441681},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C164624739","wikidata":"https://www.wikidata.org/wiki/Q754331","display_name":"Activity-based costing","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2776760603","wikidata":"https://www.wikidata.org/wiki/Q3622471","display_name":"Argus","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C70452415","wikidata":"https://www.wikidata.org/wiki/Q3182448","display_name":"Predictive maintenance","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.39067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.39067","pdf_url":"https://arxiv.org/pdf/2609.39067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2609.39067","doi":"https://doi.org/10.48550/arxiv.2609.39067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.39067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.39067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.39067","pdf_url":"https://arxiv.org/pdf/2609.39067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215129010.pdf","grobid_xml":"https://content.openalex.org/works/W7215129010.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2973727699"],"related_works":["https://openalex.org/W4384666648","https://openalex.org/W2113139643","https://openalex.org/W7096051475","https://openalex.org/W2008793665","https://openalex.org/W2160016350","https://openalex.org/W4396758652","https://openalex.org/W7158267722","https://openalex.org/W1978647546","https://openalex.org/W3011362884","https://openalex.org/W6892919419"],"abstract_inverted_index":{"Elastic":[0],"Compute":[1],"Cloud":[2],"(EC2)":[3],"Spot":[4,64],"is":[5,107,134,160,165],"60%":[6],"to":[7,109],"90%":[8],"cheaper":[9],"than":[10],"On-Demand":[11],"but":[12,111,157],"can":[13,27],"be":[14,28],"reclaimed":[15],"on":[16,47,58],"just":[17],"a":[18,41,48,62,67,135,147,150],"2-minute":[19,101],"notice;":[20],"for":[21,154],"expensive":[22],"multi-node":[23],"training":[24],"this":[25],"loss":[26],"severe,":[29],"with":[30,66,112],"one":[31,127],"reclaim":[32],"costing":[33],"hours":[34],"of":[35,128],"synchronous":[36],"progress.":[37],"We":[38],"build":[39],"Argus,":[40],"Kubernetes":[42],"operator,":[43],"and":[44,75,103,173],"ask":[45],"empirically,":[46],"CIFAR-10":[49],"testbed,":[50],"when":[51],"predicting":[52],"interruptions":[53],"beats":[54],"simple":[55],"checkpointing.":[56],"Argus":[57],"real":[59,63,170],"EKS":[60],"survives":[61],"drain":[65],"graceful":[68],"SIGTERM":[69],"checkpoint,":[70],"resuming":[71],"from":[72],"epoch":[73],"8":[74],"losing":[76],"only":[77,126],"the":[78,90,99,123,143],"in-progress":[79],"epoch.":[80],"Alongside,":[81],"we":[82],"further":[83],"find":[84],"that":[85,121],"in":[86],"an":[87,113],"80-trial":[88],"benchmark,":[89],"reactive-on-notice":[91],"degrades":[92],"toward":[93],"no":[94],"protection":[95],"once":[96],"interruption":[97,171],"outpaces":[98],"fixed":[100,115],"notice,":[102],"predictive":[104],"wasted":[105],"compute":[106],"driven":[108],"zero,":[110],"oversized":[114],"lead":[116,144,152,159],"it":[117],"over-migrates":[118],"so":[119],"severely":[120],"at":[122],"fastest":[124],"rate":[125],"five":[129],"runs":[130],"completes,":[131],"while":[132],"periodic":[133],"strong":[136],"ML-free":[137],"baseline.":[138],"A":[139],"lead-time":[140],"sweep":[141],"turns":[142],"prediction":[145],"into":[146],"guideline":[148],"where":[149],"small":[151],"suffices":[153],"zero":[155],"waste,":[156],"excess":[158],"wasteful.":[161],"The":[162],"predictor":[163],"built":[164],"advisory":[166],"(a":[167],"proxy":[168],"label);":[169],"labels":[172],"large-model-scale":[174],"validation":[175],"are":[176],"future":[177],"work.":[178]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-02T00:00:00"}