{"id":"https://openalex.org/W7225340348","doi":"https://doi.org/10.3390/computers15110807","title":"Budget-Aware Adaptive Test-Time Compute with Hierarchical Self-Verification for Semantic ID Generative Recommendation","display_name":"Budget-Aware Adaptive Test-Time Compute with Hierarchical Self-Verification for Semantic ID Generative Recommendation","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225340348","doi":"https://doi.org/10.3390/computers15110807"},"language":"en","primary_location":{"id":"doi:10.3390/computers15110807","doi":"https://doi.org/10.3390/computers15110807","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15110807","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computers15110807","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140004806","display_name":"Aowei Shen","orcid":"https://orcid.org/0009-0001-6925-1129","observed_orcids":["https://orcid.org/0009-0001-6925-1129","https://orcid.org/0009-0003-0233-2316"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aowei Shen","raw_affiliation_strings":["Department of Statistics, University of Washington, Seattle, WA 98195, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Washington, Seattle, WA 98195, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045007670","display_name":"Wenhe Liu","orcid":"https://orcid.org/0000-0003-4679-2958","observed_orcids":["https://orcid.org/0000-0003-4679-2958"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhe Liu","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5140004806"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"11","first_page":"807","last_page":"807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","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/T10203","display_name":"Recommender Systems and Techniques","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.002300000051036477,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-recommendation","display_name":"generative recommendation","score":0.7490000128746033},{"id":"https://openalex.org/keywords/residual-quantization","display_name":"residual quantization","score":0.6859999895095825},{"id":"https://openalex.org/keywords/cold-start","display_name":"cold start","score":0.5339999794960022},{"id":"https://openalex.org/keywords/accuracy-latency-trade-off","display_name":"accuracy-latency trade-off","score":0.6909999847412109},{"id":"https://openalex.org/keywords/lagrangian-optimization","display_name":"Lagrangian optimization","score":0.6850000023841858},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.699999988079071},{"id":"https://openalex.org/keywords/bastions","display_name":"bastions","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746999979019165},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/computers15110807","doi":"https://doi.org/10.3390/computers15110807","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15110807","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/computers15110807","doi":"https://doi.org/10.3390/computers15110807","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15110807","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"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/W7223660444","https://openalex.org/W7214391951","https://openalex.org/W7202170560","https://openalex.org/W7171681072","https://openalex.org/W7168406928","https://openalex.org/W7214313132","https://openalex.org/W7160561802","https://openalex.org/W7223096887","https://openalex.org/W7214383090","https://openalex.org/W7168339908"],"abstract_inverted_index":{"Semantic":[0],"identifier":[1],"(SID)":[2],"generative":[3],"recommenders":[4,19],"cast":[5],"retrieval":[6],"as":[7,125,140],"autoregressive":[8],"decoding":[9,79,95,146],"over":[10,97,167,202],"short":[11],"sequences":[12],"of":[13,36,72,78,89,110,136,148,244],"residual-quantized":[14],"codewords.":[15],"Most":[16],"published":[17],"SID":[18,145],"decode":[20],"all":[21,245],"requests":[22],"with":[23,54,105,162],"one":[24],"fixed":[25],"beam":[26],"width,":[27],"which":[28,82,122,252],"is":[29,38,46,75,128,133,211],"optimal":[30],"only":[31],"if":[32],"the":[33,86,98,103,106,134,141,160,168,203,248],"marginal":[34],"utility":[35],"compute":[37],"constant":[39],"across":[40],"requests.":[41],"We":[42],"find":[43],"that":[44,243],"it":[45],"not;":[47],"additional":[48],"search":[49],"changes":[50],"little":[51],"for":[52,61,144,217,251],"users":[53],"consistent":[55],"histories,":[56],"but":[57],"improves":[58,196],"accuracy":[59,87,241,253],"substantially":[60],"cold":[62],"start,":[63],"interest-drifting,":[64],"and":[65,101,178,193,225,233],"long-tail":[66],"users.":[67],"The":[68,114,154],"main":[69],"methodological":[70],"contribution":[71],"this":[73,131,137],"paper":[74],"request-level":[76],"allocation":[77],"compute,":[80],"in":[81,92],"a":[83,93,111,149,163,171,218],"router":[84,161],"predicts":[85],"gain":[88,108,139],"each":[90],"configuration":[91,100,104],"finite":[94],"menu":[96],"cheapest":[99],"selects":[102],"largest":[107],"net":[109],"priced":[112],"cost.":[113],"selection":[115],"rule":[116],"follows":[117],"from":[118,188],"standard":[119],"Lagrangian":[120],"arguments,":[121],"we":[123],"use":[124,135],"tools;":[126],"what":[127],"specific":[129],"to":[130,200],"work":[132],"per-configuration":[138],"routing":[142],"target":[143],"instead":[147],"difficulty":[150],"or":[151],"uncertainty":[152],"score.":[153],"resulting":[155],"framework,":[156],"called":[157],"Bastion,":[158],"combines":[159],"hierarchical":[164],"process":[165],"verifier":[166],"quantization":[169],"levels,":[170],"listwise":[172],"terminal":[173],"verifier,":[174],"codeword":[175],"consistency":[176],"voting,":[177],"budget-constrained":[179],"group":[180],"relative":[181],"policy":[182],"optimization.":[183],"On":[184],"five":[185],"benchmarks":[186],"built":[187],"Amazon":[189],"Reviews":[190],"2023,":[191],"MovieLens,":[192],"MicroLens,":[194],"Bastion":[195],"NDCG@10":[197],"by":[198,230],"5.7%":[199],"8.7%":[201],"strongest":[204],"baseline.":[205],"Its":[206],"mean":[207],"latency":[208,255],"on":[209,247],"Amazon-Beauty":[210],"14.5":[212],"ms,":[213],"against":[214],"14.6":[215],"ms":[216,232],"beam-20":[219],"TIGER":[220],"decoder,":[221],"while":[222],"its":[223,240],"median":[224],"99th-percentile":[226],"latencies":[227],"are":[228],"higher":[229],"0.9":[231],"7.0":[234],"ms.":[235],"At":[236],"every":[237],"evaluated":[238],"budget,":[239],"exceeds":[242],"baselines":[246],"three":[249],"datasets":[250],"versus":[254],"frontiers":[256],"was":[257],"measured.":[258]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}