{"id":"https://openalex.org/W7162454978","doi":"https://doi.org/10.48550/arxiv.2605.24989","title":"Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration","display_name":"Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162454978","doi":"https://doi.org/10.48550/arxiv.2605.24989"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24989","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.24989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137074493","display_name":"Moyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Moyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137068699","display_name":"Yun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137054712","display_name":"Yujun Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137006243","display_name":"Jinxin Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jinxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137015624","display_name":"Yu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137019514","display_name":"Xiaoyi Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xiaoyi","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/T10036","display_name":"Advanced Neural Network Applications","score":0.18889999389648438,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.18889999389648438,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09780000150203705,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06700000166893005,"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/estimator","display_name":"Estimator","score":0.5385000109672546},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5314000248908997},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.517799973487854},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5175999999046326},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5108000040054321},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.504800021648407},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44670000672340393},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6753000020980835},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5108000040054321},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4880000054836273},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24989","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.24989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24989","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"test-time":[1,178],"compute":[2,179],"has":[3],"proven":[4],"highly":[5],"effective":[6],"for":[7,16,188],"language":[8],"models,":[9],"yet":[10],"this":[11],"opportunity":[12],"remains":[13],"largely":[14],"unexplored":[15],"industrial":[17],"Click-Through":[18],"Rate":[19],"(CTR)":[20],"prediction.":[21,190],"CTR":[22,171,189],"models":[23],"suffer":[24],"from":[25,100],"a":[26,52,73,93,168,182],"fundamental":[27],"asymmetry:":[28],"feature":[29,107],"combinations":[30],"well-represented":[31],"in":[32],"training":[33],"yield":[34],"confident":[35],"predictions,":[36],"while":[37],"sparsely":[38],"observed":[39],"ones":[40],"produce":[41],"unreliable":[42,111],"outputs.":[43],"Existing":[44],"training-phase":[45,159,186],"solutions":[46],"such":[47],"as":[48,181],"adaptive":[49,106],"gating":[50],"learn":[51],"fixed":[53],"selection":[54],"function":[55],"subject":[56],"to":[57,82,109,185],"the":[58],"same":[59],"sparsity,":[60],"offering":[61],"no":[62],"per-instance":[63,83],"recourse":[64],"at":[65,135],"deployment.We":[66],"propose":[67],"UTTSI":[68],"(Uncertainty-Triggered":[69],"Test-Time":[70],"Selective":[71],"Inference),":[72],"training-free":[74],"model-agnostic":[75],"framework":[76],"that":[77],"scales":[78],"inference":[79],"depth":[80],"proportionally":[81],"uncertainty.":[84],"A":[85,161],"dual-signal":[86],"estimator":[87],"combining":[88],"model":[89,139],"logit":[90],"confidence":[91],"with":[92,141,148],"data-level":[94],"frequency":[95],"prior":[96],"distinguishes":[97],"epistemic":[98],"uncertainty":[99],"aleatoric":[101],"ambiguity.":[102],"Every":[103],"instance":[104],"undergoes":[105],"filtering":[108],"remove":[110],"embeddings;":[112],"uncertain":[113],"instances":[114,128],"additionally":[115],"receive":[116],"stochastic":[117],"feature-path":[118],"explorations":[119],"whose":[120],"predictions":[121],"are":[122],"aggregated":[123],"via":[124],"consistency-weighted":[125],"ensembling.":[126],"Confident":[127],"bypass":[129],"exploration":[130],"entirely,":[131],"keeping":[132],"average":[133],"overhead":[134],"approximately":[136],"$2.8\\times$":[137],"base":[138],"cost":[140],"worst-case":[142],"latency":[143],"unchanged.Experiments":[144],"on":[145],"four":[146],"datasets":[147],"three":[149],"backbone":[150],"architectures":[151],"demonstrate":[152],"consistent,":[153],"statistically":[154],"significant":[155],"gains":[156],"over":[157],"all":[158],"baselines.":[160],"seven-day":[162],"online":[163],"A/B":[164],"test":[165],"further":[166],"confirms":[167],"5.3%":[169],"relative":[170],"gain":[172],"($p":[173],"<":[174],"0.01$),":[175],"establishing":[176],"selective":[177],"allocation":[180],"practical":[183],"complement":[184],"advances":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}