{"id":"https://openalex.org/W7139929422","doi":"https://doi.org/10.48550/arxiv.2603.18290","title":"CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring","display_name":"CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7139929422","doi":"https://doi.org/10.48550/arxiv.2603.18290"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129679710","display_name":"Jin Mo Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jin Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051791136","display_name":"Hee-Gab Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hyung-Sin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130233913","display_name":"Saewoong Bahk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bahk, Saewoong","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6270999908447266,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6270999908447266,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11349999904632568,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.06809999793767929,"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/residual","display_name":"Residual","score":0.7297999858856201},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6186000108718872},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5785999894142151},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5773000121116638},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6292999982833862},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032000184059143},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3684000074863434},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32499998807907104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Out-of-distribution":[0],"(OOD)":[1],"detection":[2,167],"is":[3,172],"essential":[4],"for":[5,111],"deploying":[6],"deep":[7],"learning":[8],"models":[9],"reliably,":[10],"yet":[11],"no":[12],"single":[13],"method":[14],"performs":[15],"consistently":[16],"across":[17,180],"architectures":[18,182],"and":[19,71,95,122,145,183,194],"datasets":[20],"--":[21,114],"a":[22,38,90,96,107,115],"scorer":[23],"that":[24,81,103],"leads":[25],"on":[26,31],"one":[27],"benchmark":[28,185],"often":[29],"falters":[30],"another.":[32],"We":[33,79,101,129],"attribute":[34],"this":[35,104],"inconsistency":[36],"to":[37,54,119],"shared":[39],"structural":[40],"limitation:":[41],"logit-based":[42,120],"methods":[43,52,121],"see":[44],"only":[45],"the":[46,58,65,98,137,152,196],"classifier's":[47],"confidence":[48,70],"signal,":[49],"while":[50],"feature-based":[51,127],"attempt":[53],"measure":[55],"membership":[56,72,116],"in":[57,64,126,189],"training":[59],"distribution":[60],"but":[61],"do":[62],"so":[63],"full":[66],"feature":[67],"space":[68],"where":[69,168],"are":[73,155,162],"entangled,":[74],"inheriting":[75],"architecture-sensitive":[76],"failure":[77,160],"modes.":[78],"observe":[80],"penultimate":[82],"features":[83],"naturally":[84],"decompose":[85],"into":[86],"two":[87,138,153],"orthogonal":[88,156],"subspaces:":[89],"classifier-aligned":[91],"component":[92],"encoding":[93],"confidence,":[94],"residual":[97,105],"classifier":[99],"discards.":[100],"discover":[102],"carries":[106],"class-specific":[108],"directional":[109],"signature":[110],"in-distribution":[112],"data":[113],"signal":[117],"invisible":[118],"entangled":[123],"with":[124,201],"noise":[125],"methods.":[128],"propose":[130],"CORE":[131,174],"(COnfidence":[132],"+":[133],"REsidual),":[134],"which":[135],"disentangles":[136],"signals":[139,154],"by":[140,157],"scoring":[141],"each":[142],"subspace":[143],"independently":[144],"combines":[146],"them":[147],"via":[148],"normalized":[149],"summation.":[150],"Because":[151],"construction,":[158],"their":[159],"modes":[161],"approximately":[163],"independent,":[164],"producing":[165],"robust":[166],"either":[169],"view":[170],"alone":[171],"unreliable.":[173],"achieves":[175],"competitive":[176],"or":[177],"state-of-the-art":[178],"performance":[179],"five":[181,184,192],"configurations,":[186],"ranking":[187],"first":[188],"three":[190],"of":[191],"settings":[193],"achieving":[195],"highest":[197],"grand":[198],"average":[199],"AUROC":[200],"negligible":[202],"computational":[203],"overhead.":[204]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-21T00:00:00"}