{"id":"https://openalex.org/W7161128971","doi":"https://doi.org/10.48550/arxiv.2605.13340","title":"Shortcut Mitigation via Spurious-Positive Samples","display_name":"Shortcut Mitigation via Spurious-Positive Samples","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161128971","doi":"https://doi.org/10.48550/arxiv.2605.13340"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13340","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.13340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045692299","display_name":"Phuong Le","orcid":"https://orcid.org/0000-0003-4724-7118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Phuong Quynh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029341868","display_name":"J\u00f6rg Schl\u00f6tterer","orcid":"https://orcid.org/0000-0002-3678-0390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schl\u00f6tterer, J\u00f6rg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133777712","display_name":"sari sadiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sadiya, Sari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136131246","display_name":"Gemma Roig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roig, Gemma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054484216","display_name":"Christin Seifert","orcid":"https://orcid.org/0000-0002-6776-3868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seifert, Christin","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":0.4032000005245209,"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":0.4032000005245209,"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":0.37689998745918274,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03280000016093254,"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/spurious-relationship","display_name":"Spurious relationship","score":0.7922999858856201},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6437000036239624},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5842000246047974},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5300999879837036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.3865000009536743}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7922999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621999740600586},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6437000036239624},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13340","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.13340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13340","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":"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":{"Shortcut":[0],"mitigation":[1],"strategies":[2],"commonly":[3],"rely":[4],"on":[5,59,96],"training":[6,28],"data":[7,11,115],"annotations,":[8],"group-balanced":[9],"held-out":[10,114],"or":[12,116],"the":[13,27,56,104],"presence":[14],"of":[15,21,52],"all":[16,19],"groups,":[17],"i.e.,":[18],"combinations":[20],"(spurious)":[22],"attributes":[23],"and":[24,65,85],"classes,":[25],"in":[26,36,54,81],"data.":[29],"However,":[30],"these":[31],"requirements":[32],"are":[33],"rarely":[34],"met":[35],"practice.":[37],"We":[38],"instead":[39],"propose":[40],"a":[41,49],"method":[42],"for":[43,73,103],"targeted":[44],"model":[45,57],"analysis":[46],"to":[47,94],"identify":[48,77],"small":[50],"set":[51,64],"instances":[53],"which":[55],"relies":[58],"spurious":[60],"attributes.":[61],"Using":[62],"that":[63,91],"following":[66],"``this":[67],"feature":[68],"should":[69],"not":[70],"be":[71],"used":[72],"prediction''":[74],"reasoning,":[75],"we":[76],"highly":[78],"relevant":[79],"neurons":[80],"an":[82],"intermediate":[83],"layer":[84],"regularize":[86],"their":[87],"impact.":[88],"This":[89],"ensures":[90],"models":[92],"learn":[93],"depend":[95],"informative":[97],"features":[98],"rather":[99],"than":[100],"being":[101],"right":[102],"wrong":[105],"reasons,":[106],"thereby":[107],"improving":[108],"robustness":[109],"without":[110],"requiring":[111],"additional":[112],"balanced":[113],"annotations.":[117]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2026-05-15T00:00:00"}