{"id":"https://openalex.org/W7166740925","doi":"https://doi.org/10.48550/arxiv.2606.30201","title":"SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation","display_name":"SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166740925","doi":"https://doi.org/10.48550/arxiv.2606.30201"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.30201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30201","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.2606.30201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098821281","display_name":"Filippo Ruffini","orcid":"https://orcid.org/0009-0003-9759-5492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruffini, Filippo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116839622","display_name":"Marco Salm\u00e8","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salm\u00e9, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023365911","display_name":"Rosa Sicilia","orcid":"https://orcid.org/0000-0002-2513-0827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sicilia, Rosa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139701157","display_name":"Valerio Guarrasi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guarrasi, Valerio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139637367","display_name":"Paolo Soda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soda, Paolo","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5042999982833862,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5042999982833862,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.1761000007390976,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.08100000023841858,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7735999822616577},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7013999819755554},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6251000165939331},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5541999936103821},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/rework","display_name":"Rework","score":0.5055000185966492},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42010000348091125}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7735999822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337999939918518},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7013999819755554},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6251000165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5666999816894531},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418999791145325},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C2776543023","wikidata":"https://www.wikidata.org/wiki/Q2147046","display_name":"Rework","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.30201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30201","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.2606.30201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30201","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":[{"score":0.6848812103271484,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"evaluation":[1,206],"protocols":[2],"for":[3,72],"Vision-Language":[4],"Models":[5,169],"(VLMs)":[6],"in":[7,41,77,181,203],"Radiology":[8],"Report":[9],"Generation":[10],"(RRG)":[11],"rely":[12],"on":[13,105,194],"report-level":[14],"metrics":[15,26],"that":[16,101,160,185],"measure":[17],"lexical":[18],"overlap":[19],"or":[20,55],"aggregate":[21],"clinical":[22],"correctness.":[23],"However,":[24],"such":[25],"do":[27,176],"not":[28,177],"test":[29],"whether":[30],"individual":[31],"diagnostic":[32],"statements":[33],"stem":[34],"from":[35],"the":[36,42,122,149,171],"actual":[37],"pathological":[38],"evidence":[39,134],"visible":[40],"image.":[43],"This":[44],"allows":[45],"models":[46],"to":[47,63],"achieve":[48],"competitive":[49],"scores":[50],"by":[51],"exploiting":[52],"learned":[53],"priors":[54],"spurious":[56],"correlations,":[57],"a":[58,70,128,200],"failure":[59,119],"mode":[60],"we":[61,158],"refer":[62],"as":[64],"vision":[65,74],"shortcut.":[66],"We":[67],"introduce":[68],"SHOVIR,":[69],"benchmark":[71],"evaluating":[73],"shortcut":[75,161],"behavior":[76,162],"RRG.":[78],"SHOVIR":[79],"extends":[80],"two":[81,118],"spatially":[82],"annotated":[83],"chest":[84],"X-ray":[85],"datasets,":[86],"MIMIC-CXR":[87],"and":[88,94,97,137,167,207],"PadChest-GR,":[89],"with":[90,191],"per-box":[91],"CheXpert":[92],"labels,":[93],"defines":[95],"image-level":[96],"disease-level":[98],"occlusion":[99],"experiments":[100],"contrast":[102],"baseline":[103,173],"performance":[104],"clean":[106],"images":[107],"against":[108],"localized,":[109],"region-specific":[110],"perturbations.":[111],"Comparing":[112],"predictions":[113],"across":[114,165],"these":[115],"conditions":[116],"isolates":[117],"modes":[120],"at":[121],"disease-class":[123],"level:":[124],"direct":[125],"shortcuts,":[126,139],"where":[127,140],"finding":[129],"persists":[130],"after":[131],"its":[132],"visual":[133,195],"is":[135],"removed,":[136],"contextual":[138],"detection":[141],"degrades":[142],"once":[143],"co-occurring":[144],"pathologies":[145],"are":[146],"occluded":[147],"despite":[148],"target":[150],"region":[151],"remaining":[152],"intact.":[153],"Benchmarking":[154],"eight":[155],"state-of-the-art":[156],"VLMs,":[157],"find":[159],"varies":[163],"substantially":[164],"architectures":[166],"datasets.":[168],"achieving":[170],"highest":[172,180],"report":[174],"quality":[175],"necessarily":[178],"rank":[179],"spatial":[182],"grounding,":[183],"revealing":[184],"clinically":[186],"fluent":[187],"generation":[188],"can":[189],"coexist":[190],"shallow":[192],"reliance":[193],"evidence.":[196],"These":[197],"findings":[198],"expose":[199],"blind":[201],"spot":[202],"current":[204],"RRG":[205],"motivate":[208],"region-aware":[209],"assessment":[210],"protocols.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}