{"id":"https://openalex.org/W7225397254","doi":"https://doi.org/10.5281/zenodo.24002039","title":"Confidence-Aware Predictive Computing for Generative AI: Estimating Prediction Reliability for Uncertainty-Aware Computational Preparation","display_name":"Confidence-Aware Predictive Computing for Generative AI: Estimating Prediction Reliability for Uncertainty-Aware Computational Preparation","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225397254","doi":"https://doi.org/10.5281/zenodo.24002039"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24002039","doi":"https://doi.org/10.5281/zenodo.24002039","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002039","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.24002039","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":0.8246999979019165,"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":0.8246999979019165,"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":0.04699999839067459,"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":0.03790000081062317,"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/generative-ai","display_name":"generative AI","score":0.8640000224113464},{"id":"https://openalex.org/keywords/prediction-confidence","display_name":"prediction confidence","score":0.8510000109672546},{"id":"https://openalex.org/keywords/prediction-reliability","display_name":"forecast reliability","score":0.699999988079071},{"id":"https://openalex.org/keywords/uncertainty-decomposition","display_name":"uncertainty decomposition","score":0.593999981880188},{"id":"https://openalex.org/keywords/epistemic-uncertainty","display_name":"epistemic uncertainty","score":0.9509999752044678},{"id":"https://openalex.org/keywords/aleatoric-uncertainty","display_name":"aleatoric uncertainty","score":1.0},{"id":"https://openalex.org/keywords/forecast-calibration","display_name":"forecast calibration","score":0.6589999794960022},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.6639999747276306},{"id":"https://openalex.org/keywords/gpu-scheduling","display_name":"GPU scheduling","score":0.8569999933242798},{"id":"https://openalex.org/keywords/resource-reuse","display_name":"resource reuse","score":0.5789999961853027},{"id":"https://openalex.org/keywords/confidence-threshold","display_name":"confidence threshold","score":0.8029999732971191},{"id":"https://openalex.org/keywords/workload-prediction","display_name":"workload prediction","score":0.5789999961853027},{"id":"https://openalex.org/keywords/risk-sensitive-decision-making","display_name":"risk-sensitive decision making","score":0.5789999961853027},{"id":"https://openalex.org/keywords/computational-cost-optimization","display_name":"computational cost optimization","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473999857902527},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6384000182151794},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.5942000150680542},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5716999769210815},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47699999809265137},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.3529999852180481},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C70452415","wikidata":"https://www.wikidata.org/wiki/Q3182448","display_name":"Predictive maintenance","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C103402496","wikidata":"https://www.wikidata.org/wiki/Q1106171","display_name":"Prediction interval","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24002039","doi":"https://doi.org/10.5281/zenodo.24002039","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002039","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.24002040","doi":"https://doi.org/10.5281/zenodo.24002040","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002040","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.24002039","doi":"https://doi.org/10.5281/zenodo.24002039","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002039","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":[],"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/W7225425116","https://openalex.org/W7225389561","https://openalex.org/W7225423500","https://openalex.org/W7225414723","https://openalex.org/W7225376051","https://openalex.org/W7225409594","https://openalex.org/W7225390624","https://openalex.org/W7225227005","https://openalex.org/W7225378232","https://openalex.org/W7225383195"],"abstract_inverted_index":{"The":[0,206,248,319,399],"increasing":[1],"deployment":[2],"of":[3,42,161,254,357,395,411],"generative":[4],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8],"has":[9],"created":[10],"new":[11],"opportunities":[12,138],"for":[13,150,157,413],"predictive":[14,36,76,171,176,213,255,306,365],"computational":[15,26,44,84,110,163,172,187,204,237,275,317,351,397],"preparation,":[16,238,368],"in":[17,127],"which":[18],"future":[19,43,65,162,295],"inference":[20],"requirements":[21],"are":[22,28,372],"anticipated":[23],"and":[24,53,106,136,166,201,225,232,239,274,315,330,353,369,386,420,424],"selected":[25],"resources":[27],"prepared":[29,109],"before":[30],"corresponding":[31],"user":[32],"requests":[33],"materialize.":[34],"Existing":[35],"computing":[37,177],"approaches":[38,178],"investigate":[39],"the":[40,86,101,108,159,354,409],"forecasting":[41],"demand,":[45],"proactive":[46],"response":[47,422],"generation,":[48],"resource":[49,111,311,326],"allocation,":[50,132,327],"GPU":[51,131],"scheduling,":[52],"economic":[54,355],"optimization.":[55],"However,":[56],"a":[57,63,70,75,79,154,193],"fundamental":[58],"challenge":[59],"remains":[60,430],"insufficiently":[61],"addressed:":[62],"predicted":[64,182],"workload":[66,103,268,336],"is":[67,301,341,378,389],"not":[68,379,390],"necessarily":[69],"reliable":[71,123,404],"prediction.":[72],"Even":[73],"when":[74,115],"model":[77,286],"identifies":[78],"potentially":[80],"recurring":[81],"question":[82],"or":[83,185],"requirement,":[85],"system":[87],"may":[88],"have":[89],"limited":[90,285],"knowledge":[91,287],"about":[92],"whether":[93,107,403],"that":[94,179],"prediction":[95,168,230,246,264,328,347,376,384],"will":[96,104,112],"actually":[97],"materialize,":[98],"how":[99],"frequently":[100],"associated":[102,291],"occur,":[105],"be":[113],"reusable":[114],"demand":[116,164,183,219,258],"arrives.":[117],"Treating":[118],"all":[119],"predictions":[120,165],"as":[121,392],"equally":[122],"can":[124,407],"consequently":[125],"result":[126],"unnecessary":[128,418],"precomputation,":[129,324],"inefficient":[130],"excessive":[133],"storage":[134],"consumption,":[135],"missed":[137],"to":[139,303,343,381,432],"prepare":[140],"genuinely":[141],"valuable":[142],"workloads.":[143],"This":[144],"paper":[145],"introduces":[146],"Confidence-Aware":[147],"Predictive":[148],"Computing":[149],"Generative":[151],"AI":[152],"(CAPC-GAI),":[153],"conceptual":[155],"framework":[156,207,320,400],"estimating":[158],"reliability":[160,215,233],"incorporating":[167],"confidence":[169,220,227,242,332,377,405],"into":[170],"preparation.":[173,359],"Unlike":[174],"conventional":[175,364],"primarily":[180],"emphasize":[181],"magnitude":[184],"expected":[186,261,310],"benefit,":[188],"CAPC-GAI":[189],"explicitly":[190],"distinguishes":[191,251,280],"between":[192],"prediction,":[194],"its":[195,198,202],"estimated":[196],"confidence,":[197,260,263,270,273],"eventual":[199],"realization,":[200],"practical":[203,396,428],"value.":[205],"integrates":[208],"six":[209],"interconnected":[210],"functions:":[211],"(1)":[212],"signal":[214],"assessment,":[216],"(2)":[217],"probabilistic":[218,345],"estimation,":[221,350],"(3)":[222],"uncertainty":[223,282,290,308,349],"decomposition":[224],"temporal":[226,271],"modeling,":[228],"(4)":[229],"calibration":[231,387],"validation,":[234],"(5)":[235],"confidence-aware":[236,358],"(6)":[240],"continuous":[241],"adaptation":[243],"through":[244],"observed":[245],"outcomes.":[247],"proposed":[249],"architecture":[250],"several":[252],"dimensions":[253],"reliability,":[256,266],"including":[257],"occurrence":[259],"request-volume":[262],"interval":[265],"semantic":[267],"compatibility":[269],"validity":[272],"benefit":[276],"confidence.":[277],"It":[278],"further":[279],"epistemic":[281],"arising":[283],"from":[284,288],"aleatoric":[289],"with":[292,361],"inherently":[293],"variable":[294],"demand.":[296],"A":[297],"unified":[298],"mathematical":[299],"formulation":[300],"developed":[302],"incorporate":[304],"calibrated":[305],"probabilities,":[307],"estimates,":[309],"reuse,":[312],"preparation":[313,415],"costs,":[314],"risk-sensitive":[316],"decisions.":[318],"also":[321],"investigates":[322,402],"selective":[323],"confidence-dependent":[325],"abstention,":[329],"adaptive":[331],"thresholds":[333],"under":[334],"changing":[335],"distributions.":[337],"An":[338],"experimental":[339],"methodology":[340],"established":[342],"evaluate":[344],"calibration,":[346],"discrimination,":[348],"efficiency,":[352],"consequences":[356],"Comparisons":[360],"uncalibrated":[362],"forecasting,":[363],"computing,":[366],"confidence-independent":[367],"uncertainty-aware":[370],"scheduling":[371],"proposed.":[373],"Importantly,":[374],"high":[375,383],"assumed":[380],"imply":[382],"accuracy,":[385],"alone":[388],"treated":[391],"sufficient":[393],"evidence":[394],"benefit.":[398],"instead":[401],"estimates":[406],"improve":[408],"selection":[410],"workloads":[412],"advance":[414],"while":[416],"reducing":[417],"computation":[419],"maintaining":[421],"quality":[423],"service-level":[425],"requirements.":[426],"Its":[427],"effectiveness":[429],"subject":[431],"empirical":[433],"validation.":[434]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}