{"id":"https://openalex.org/W7225406400","doi":"https://doi.org/10.5281/zenodo.24021816","title":"Memory Grows. Context Does Not Have To. (ExergyNet: Persistent Machine Infrastructure for the 100M-Token Horizon)","display_name":"Memory Grows. Context Does Not Have To. (ExergyNet: Persistent Machine Infrastructure for the 100M-Token Horizon)","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225406400","doi":"https://doi.org/10.5281/zenodo.24021816"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24021816","doi":"https://doi.org/10.5281/zenodo.24021816","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24021816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24021816","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161069787","display_name":"Seven Ezumba","orcid":"https://orcid.org/0009-0008-4212-1739","observed_orcids":["https://orcid.org/0009-0008-4212-1739"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ezumba, Seven","raw_affiliation_strings":["EXERGYNET"],"raw_orcid":"https://orcid.org/0009-0008-4212-1739","affiliations":[{"raw_affiliation_string":"EXERGYNET","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161051688","display_name":"VEENA BONTU","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"BONTU, VEENA","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":false,"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/T10028","display_name":"Topic Modeling","score":0.36010000109672546,"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/T10028","display_name":"Topic Modeling","score":0.36010000109672546,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16920000314712524,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09269999712705612,"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/large-language-models","display_name":"large language models","score":0.5180000066757202},{"id":"https://openalex.org/keywords/retrieval-latency","display_name":"retrieval latency","score":0.3889999985694885},{"id":"https://openalex.org/keywords/semantic-routing","display_name":"semantic routing","score":0.5870000123977661},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383999824523926},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5625},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4869999885559082},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24021816","doi":"https://doi.org/10.5281/zenodo.24021816","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24021816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24021817","doi":"https://doi.org/10.5281/zenodo.24021817","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24021817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.24021816","doi":"https://doi.org/10.5281/zenodo.24021816","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24021816","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214910163","https://openalex.org/W7114774851","https://openalex.org/W7130826843","https://openalex.org/W7162522705","https://openalex.org/W7223684159","https://openalex.org/W7149901884","https://openalex.org/W7213301781","https://openalex.org/W7225416879","https://openalex.org/W7203528792","https://openalex.org/W7222049030"],"abstract_inverted_index":{"The":[0,87],"practical":[1],"challenge":[2],"in":[3],"scaling":[4,53],"autonomous":[5,207],"machine":[6],"intelligence":[7,189],"is":[8,12],"not":[9],"model":[10],"capability\u2014it":[11],"infrastructure.":[13],"As":[14],"agents":[15],"accumulate":[16],"persistent":[17,62,213],"histories,":[18],"prior":[19],"approaches":[20],"have":[21],"treated":[22],"the":[23,29,37,46,79,91,112,148,163,227],"growth":[24,30,107,110],"of":[25,31,75,226],"stored":[26],"context":[27,35,69,109],"and":[28,108,156,217],"active":[32,67],"model-facing":[33,68],"inference":[34],"as":[36,223],"same":[38],"problem.":[39],"They":[40],"are":[41],"not.":[42],"This":[43,194],"paper":[44],"measures":[45],"distinction.":[47],"Across":[48],"a":[49,73,124,153,187,205],"sealed":[50],"development":[51],"campaign":[52],"from":[54,190],"32,000":[55],"to":[56],"101,152,694":[57],"estimated":[58],"tokens,":[59,77],"ExergyNet\u2019s":[60],"externalized":[61],"evidence":[63],"architecture":[64,195],"(xLMP)":[65],"held":[66],"(K)":[70],"bounded":[71],"at":[72,90,128,147],"median":[74,155],"800":[76],"while":[78],"underlying":[80],"corpus":[81,106],"grew":[82],"by":[83],"more":[84],"than":[85],"3,100x.":[86],"state-to-active-context":[88],"ratio":[89],"100M-token":[92,149],"operating":[93],"point":[94],"was":[95,99,196],"approximately":[96],"125,000:1.":[97],"There":[98],"no":[100],"statistically":[101],"significant":[102],"positive":[103],"trend":[104],"between":[105],"within":[111],"tested":[113],"envelope.":[114],"Furthermore,":[115],"we":[116,175],"demonstrate":[117],"that":[118,184,212],"legacy":[119],"full-corpus":[120],"retrieval":[121,145,160],"scanning":[122],"presents":[123],"severe":[125],"computational":[126],"bottleneck":[127],"scale,":[129],"masking":[130],"GPU":[131],"efficiency":[132],"behind":[133],"CPU":[134],"idle":[135],"time.":[136],"By":[137],"implementing":[138],"an":[139,178],"O(vocab)":[140],"morphological":[141],"prefix-expansion":[142],"index":[143],"(LNES-84),":[144],"latency":[146],"scale":[150],"collapsed,":[151],"yielding":[152],"220.5x":[154],"415.9x":[157],"P95":[158],"paired":[159],"speedup":[161],"over":[162],"baseline,":[164],"with":[165],"zero":[166],"right-to-wrong":[167],"answer":[168],"regressions":[169],"across":[170],"190":[171],"matched":[172],"queries.":[173],"Finally,":[174],"formalize":[176],"LNES-22,":[177],"out-of-band":[179],"cryptographic":[180],"authority":[181,219],"control":[182],"plane":[183],"mathematically":[185],"decouples":[186],"model's":[188],"its":[191],"execution":[192,218],"authority.":[193],"physically":[197],"validated":[198],"via":[199],"FAA":[200],"Exemption":[201],"No.":[202],"26214":[203],"for":[204],"275-lb":[206],"heavy-lift":[208],"aircraft.":[209],"We":[210],"conclude":[211],"state,":[214],"semantic":[215],"routing,":[216],"must":[220],"be":[221],"established":[222],"infrastructure":[224],"independent":[225],"reasoning":[228],"model.":[229]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}