{"id":"https://openalex.org/W7225409594","doi":"https://doi.org/10.5281/zenodo.24002243","title":"Accuracy- and Utility-Driven Adaptive Predictive Computing for Generative AI: Automatically Optimizing Computational Strategies Through Prediction Performance and Realized Operational Benefits","display_name":"Accuracy- and Utility-Driven Adaptive Predictive Computing for Generative AI: Automatically Optimizing Computational Strategies Through Prediction Performance and Realized Operational Benefits","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225409594","doi":"https://doi.org/10.5281/zenodo.24002243"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24002243","doi":"https://doi.org/10.5281/zenodo.24002243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002243","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.24002243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9657999873161316,"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":0.9657999873161316,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.017400000244379044,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.008700000122189522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptive-strategy-selection","display_name":"adaptive strategy selection","score":0.7670000195503235},{"id":"https://openalex.org/keywords/prediction-accuracy","display_name":"prediction accuracy","score":0.7480000257492065},{"id":"https://openalex.org/keywords/precomputation","display_name":"precomputation","score":0.7319999933242798},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.6700000166893005},{"id":"https://openalex.org/keywords/workload-prediction","display_name":"workload prediction","score":0.5230000019073486},{"id":"https://openalex.org/keywords/electricity-price-variation","display_name":"electricity price variation","score":0.6309999823570251},{"id":"https://openalex.org/keywords/prediction-threshold","display_name":"prediction threshold","score":0.48100000619888306},{"id":"https://openalex.org/keywords/task-prioritization","display_name":"task prioritization","score":0.7170000076293945},{"id":"https://openalex.org/keywords/execution-timing","display_name":"execution timing","score":0.5709999799728394},{"id":"https://openalex.org/keywords/operational-stability","display_name":"operational stability","score":0.6729999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889999747276306},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.5960999727249146},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24002243","doi":"https://doi.org/10.5281/zenodo.24002243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002243","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24002244","doi":"https://doi.org/10.5281/zenodo.24002244","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002244","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24002243","doi":"https://doi.org/10.5281/zenodo.24002243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002243","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5378999710083008,"id":"https://metadata.un.org/sdg/9"}],"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/W7225376051","https://openalex.org/W7225405760","https://openalex.org/W7225425116","https://openalex.org/W7225390624","https://openalex.org/W7225389561","https://openalex.org/W7225400146","https://openalex.org/W7225433507","https://openalex.org/W7225397254","https://openalex.org/W7225411818","https://openalex.org/W7225423500"],"abstract_inverted_index":{"The":[0,201,266,314],"increasing":[1],"deployment":[2],"of":[3,56,66,346],"generative":[4,129],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8,271],"has":[9],"created":[10],"computational":[11,42,47,108,137,172,186,208,220,257,363],"environments":[12],"characterized":[13],"by":[14],"fluctuating":[15],"inference":[16],"demand,":[17],"heterogeneous":[18],"GPU":[19],"availability,":[20,107],"changing":[21,312],"electricity":[22],"prices,":[23],"variable":[24],"cloud":[25],"resource":[26,70,106,259,281],"costs,":[27,109],"and":[28,44,81,118,144,177,197,207,238,263,285,307,332,374],"uncertain":[29],"future":[30,41,362],"information":[31,111],"requirements.":[32],"Predictive":[33,121],"computing":[34,151,359],"provides":[35,242],"a":[36,124,165],"potential":[37],"mechanism":[38,168],"for":[39,335],"anticipating":[40,361],"workloads":[43,157],"preparing":[45],"reusable":[46],"resources":[48],"before":[49],"corresponding":[50],"requests":[51],"arrive.":[52],"However,":[53],"the":[54,63,75,330,343],"effectiveness":[55,345],"predictive":[57,91,136,150,301,347,358],"computation":[58],"depends":[59],"not":[60,215,318],"only":[61],"on":[62,74,289],"initial":[64],"quality":[65],"demand":[67,104,364,370],"forecasting":[68],"or":[69,110,219],"allocation,":[71,282],"but":[72],"also":[73],"system's":[76],"ability":[77],"to":[78,87,132,140,251,298],"continuously":[79,366],"evaluate":[80],"improve":[82,342],"its":[83],"operational":[84,146,198,291],"strategies":[85,138],"according":[86,139],"actual":[88],"outcomes.":[89],"A":[90,245],"strategy":[92,175,190,286],"that":[93,127,153,211,320,369],"performs":[94],"effectively":[95],"under":[96,311],"one":[97],"workload":[98],"distribution":[99],"may":[100,226],"become":[101],"inefficient":[102],"when":[103,230,337],"patterns,":[105],"characteristics":[112],"change.":[113],"This":[114],"paper":[115],"introduces":[116,164],"Accuracy-":[117],"Utility-Driven":[119],"Adaptive":[120],"Computing":[122],"(AUAPC-GAI),":[123],"conceptual":[125],"framework":[126,202,267],"enables":[128],"AI":[130],"infrastructures":[131],"automatically":[133,273],"adjust":[134,274],"their":[135,231,239],"observed":[141],"prediction":[142,170,205,254,277],"accuracy":[143,206],"realized":[145,185],"benefits.":[147],"Unlike":[148],"conventional":[149],"approaches":[152],"primarily":[154],"determine":[155],"which":[156],"should":[158],"be":[159,228],"prepared":[160],"in":[161],"advance,":[162],"AUAPC-GAI":[163],"continuous":[166,321],"feedback":[167],"connecting":[169],"evaluation,":[171],"outcome":[173],"measurement,":[174],"adjustment,":[176,193],"subsequent":[178],"execution.":[179],"Its":[180],"architecture":[181],"integrates":[182],"prediction-performance":[183],"assessment,":[184],"benefit":[187],"estimation,":[188],"adaptive":[189],"selection,":[191],"resource-allocation":[192],"feedback-driven":[194,338],"policy":[195],"optimization,":[196],"stability":[199],"control.":[200],"distinguishes":[203],"between":[204],"utility,":[209],"recognizing":[210],"accurate":[212,224],"predictions":[213,225],"do":[214],"necessarily":[216,323],"generate":[217],"economic":[218],"benefits,":[221,258],"while":[222],"moderately":[223],"still":[227],"valuable":[229],"associated":[232],"preparation":[233],"costs":[234],"are":[235],"sufficiently":[236],"low":[237],"successful":[240],"reuse":[241],"substantial":[243],"savings.":[244],"unified":[246],"optimization":[247],"formulation":[248],"is":[249,296,371],"developed":[250],"jointly":[252],"characterize":[253],"quality,":[255],"net":[256],"constraints,":[260],"service-level":[261],"requirements,":[262],"adaptation":[264,310,322,353],"costs.":[265],"further":[268],"investigates":[269],"how":[270,368],"can":[272,341],"precomputation":[275],"intensity,":[276],"thresholds,":[278],"task":[279],"priorities,":[280],"execution":[283],"timing,":[284],"selection":[287],"based":[288],"accumulated":[290],"evidence.":[292],"An":[293],"experimental":[294,333],"methodology":[295],"proposed":[297,315],"compare":[299],"static":[300],"strategies,":[302],"accuracy-only":[303],"adaptation,":[304,306],"utility-only":[305],"integrated":[308],"accuracy-and-utility-driven":[309],"workloads.":[313],"research":[316,356],"does":[317],"assume":[319],"improves":[324],"system":[325],"performance;":[326],"rather,":[327],"it":[328],"establishes":[329],"theoretical":[331],"foundations":[334],"determining":[336],"strategic":[339],"adjustment":[340],"long-term":[344],"computation.":[348],"By":[349],"introducing":[350],"an":[351],"outcome-driven":[352],"mechanism,":[354],"this":[355],"extends":[357],"from":[360],"toward":[365],"improving":[367],"anticipated,":[372],"prepared,":[373],"managed.":[375]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}