{"id":"https://openalex.org/W7161727352","doi":"https://doi.org/10.48550/arxiv.2605.17591","title":"Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception","display_name":"Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161727352","doi":"https://doi.org/10.48550/arxiv.2605.17591"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17591","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136482240","display_name":"Guowei Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Guowei","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136478269","display_name":"Ziqi Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I3129496460","display_name":"Lishui University","ror":"https://ror.org/0418kp584","country_code":"CN","type":"education","lineage":["https://openalex.org/I3129496460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi, Ziqi","raw_affiliation_strings":["Lishui University, Lishui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lishui University, Lishui, China","institution_ids":["https://openalex.org/I3129496460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100457290","display_name":"Zhao Xie","orcid":"https://orcid.org/0000-0001-9834-4730"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Zhao","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.45559999346733093,"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":0.45559999346733093,"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":0.40939998626708984,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.019899999722838402,"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/reliability","display_name":"Reliability (semiconductor)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5339999794960022},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.499099999666214},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4832000136375427},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4700999855995178},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4675000011920929},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.4124999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083999872207642},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5716000199317932},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17591","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17591","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17591","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Aggregate":[0],"object":[1],"detection":[2],"metrics":[3],"inherently":[4],"mask":[5],"catastrophic":[6],"and":[7,153],"repeatable":[8],"failures":[9],"in":[10],"operationally":[11],"critical,":[12],"long-tail":[13],"minority":[14],"classes.":[15],"This":[16],"paper":[17],"formally":[18],"defines":[19],"this":[20,52,159],"pervasive":[21],"vulnerability":[22,100],"as":[23,97,165],"the":[24,29,40,98,125],"Hard-Category":[25],"Reliability":[26],"Problem":[27],"(HCRP):":[28],"fundamental":[30],"architectural":[31],"challenge":[32],"of":[33,43,128],"strictly":[34],"rectifying":[35],"vulnerable":[36],"categories":[37],"without":[38],"compromising":[39],"performance":[41],"boundaries":[42],"stable":[44],"classes":[45],"under":[46],"stringent":[47],"protocols.":[48],"To":[49],"systematically":[50],"dismantle":[51],"limitation,":[53],"we":[54],"propose":[55],"Error-Decomposed":[56],"Class-Conditional":[57],"Fusion":[58],"(ED-CCF),":[59],"an":[60,148,166],"elegant":[61],"decision-layer":[62],"inference":[63],"framework.":[64],"Diverging":[65],"from":[66,113,134],"heuristic":[67],"global":[68,129],"post-processing,":[69],"ED-CCF":[70],"projects":[71],"predictions":[72],"into":[73],"a":[74,89,106],"sophisticated":[75],"quad-state":[76],"error":[77],"taxonomy,":[78],"dynamically":[79],"activating":[80],"calibration":[81],"pathways":[82],"exclusively":[83],"upon":[84],"rigorous":[85],"empirical":[86],"justification.":[87],"On":[88],"highly":[90],"constrained":[91],"600-image":[92],"validation":[93,141],"benchmark,":[94],"isolating":[95],"cz":[96,111],"critical":[99],"(HCEC=0.86,":[101],"BSR=0.14),":[102],"our":[103],"framework":[104],"achieves":[105],"targeted":[107],"breakthrough:":[108],"it":[109],"elevates":[110],"mAP50":[112,133],"0.089343":[114],"to":[115,136],"0.109353":[116],"(a":[117],"massive":[118],"+22.4%":[119],"relative":[120],"surge)":[121],"while":[122],"flawlessly":[123],"preserving":[124],"Pareto":[126],"optimality":[127],"stability":[130],"(raising":[131],"all":[132],"0.581925":[135],"0.584864).":[137],"Backed":[138],"by":[139],"exhaustive":[140],"across":[142],"50":[143],"paired":[144],"subset":[145],"trials":[146],"demonstrating":[147],"overwhelming":[149],"96%":[150],"win":[151],"rate":[152],"strict":[154],"Bonferroni-corrected":[155],"Wilcoxon":[156],"significance":[157],"(p<0.05),":[158],"work":[160],"fundamentally":[161],"redefines":[162],"output-level":[163],"fusion":[164],"auditable,":[167],"statistically":[168],"guaranteed":[169],"paradigm":[170],"for":[171],"safety-critical":[172],"visual":[173],"perception.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}