{"id":"https://openalex.org/W7161937702","doi":"https://doi.org/10.48550/arxiv.2605.21109","title":"Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction","display_name":"Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161937702","doi":"https://doi.org/10.48550/arxiv.2605.21109"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21109","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":"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.2605.21109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136708943","display_name":"Zhenjiang Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Zhenjiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136642680","display_name":"Jiawen Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiawen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136676354","display_name":"Gabriel Wagner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wagner, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056139780","display_name":"Zhongzheng Zhang","orcid":"https://orcid.org/0009-0002-8297-1793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhongzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021509994","display_name":"Ivan Ruchkin","orcid":"https://orcid.org/0000-0003-3546-414X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruchkin, Ivan","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":0.4081000089645386,"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":0.4081000089645386,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.31859999895095825,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.1046999990940094,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.8490999937057495},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7486000061035156},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.7329000234603882},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5807999968528748},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5539000034332275},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4803999960422516},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/measurement-uncertainty","display_name":"Measurement uncertainty","score":0.3982999920845032}],"concepts":[{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.8490999937057495},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7486000061035156},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.7329000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327000260353088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6078000068664551},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5807999968528748},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5539000034332275},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4059999883174896},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21109","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":"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.2605.21109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21109","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":"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":[{"score":0.8201110363006592,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reliable":[0],"confidence":[1],"estimates":[2],"are":[3],"important":[4],"for":[5],"safely":[6],"deploying":[7],"vision-based":[8],"controllers":[9],"in":[10,38],"autonomous":[11],"racing,":[12],"where":[13,61],"safety":[14,172],"predictions":[15],"must":[16],"be":[17],"derived":[18],"from":[19,91,98,105,157],"camera":[20],"images,":[21],"yet":[22],"modern":[23],"predictors":[24],"become":[25],"dangerously":[26],"overconfident":[27],"under":[28,127,138],"test-time":[29,121],"distribution":[30],"shifts.":[31],"We":[32],"identify":[33],"a":[34,92,95,102,116,135,161],"critical":[35],"perception-dynamics":[36],"gap":[37],"existing":[39],"anomaly":[40,88,141],"signals:":[41],"widely":[42],"used":[43],"scores,":[44,115],"such":[45],"as":[46],"autoencoder":[47],"reconstruction":[48,99],"error,":[49],"capture":[50],"visual":[51],"corruptions":[52],"but":[53],"miss":[54],"dynamics":[55,103],"anomalies":[56],"(e.g.,":[57],"actuation":[58,148],"bias,":[59,149],"latency),":[60],"images":[62],"remain":[63],"plausible":[64],"while":[65,129],"the":[66,165,170],"trajectory":[67],"degrades.":[68],"To":[69],"address":[70],"this,":[71],"we":[72],"propose":[73],"an":[74],"Anomaly-Informed":[75],"Online":[76],"Calibration":[77],"approach":[78],"that,":[79],"without":[80,168],"retraining":[81],"any":[82],"model":[83],"component,":[84],"fuses":[85],"two":[86],"complementary":[87],"scores":[89],"extracted":[90],"world":[93],"model:":[94],"perceptual":[96],"score":[97,104],"error":[100,156],"and":[101,108],"epistemic":[106],"uncertainty":[107],"control-stream":[109],"statistics.":[110],"Based":[111],"on":[112,134],"these":[113],"fused":[114],"lightweight":[117],"temperature-scaling":[118],"calibrator":[119],"leverages":[120],"augmentation":[122],"to":[123,159],"selectively":[124],"reduce":[125,152],"overconfidence":[126],"shift":[128],"preserving":[130],"nominal-condition":[131],"performance.":[132],"Experiments":[133],"physical":[136],"DonkeyCar":[137],"four":[139],"real-world":[140],"protocols":[142],"unseen":[143],"during":[144],"training":[145],"(darkness,":[146],"blur,":[147],"processing":[150],"latency)":[151],"average":[153],"expected":[154],"calibration":[155],"0.184":[158],"0.116,":[160],"37%":[162],"improvement":[163],"over":[164],"best":[166],"baseline,":[167],"modifying":[169],"base":[171],"predictor.":[173]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}