{"id":"https://openalex.org/W7160289157","doi":"https://doi.org/10.48550/arxiv.2605.01502","title":"RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty","display_name":"RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7160289157","doi":"https://doi.org/10.48550/arxiv.2605.01502"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01502","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.01502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135314143","display_name":"William Stevens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stevens, William","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010958338","display_name":"Mohit Prabhushankar","orcid":"https://orcid.org/0000-0002-8743-7058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prabhushankar, Mohit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135358495","display_name":"Ghassan AlRegib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AlRegib, Ghassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.22439999878406525,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.22439999878406525,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.17739999294281006,"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":0.061799999326467514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6761000156402588},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.598800003528595},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4948999881744385},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.47519999742507935},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.435699999332428},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.41760000586509705},{"id":"https://openalex.org/keywords/spatial-correlation","display_name":"Spatial correlation","score":0.38909998536109924},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3878999948501587},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6761000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247000098228455},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.510699987411499},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C150060386","wikidata":"https://www.wikidata.org/wiki/Q7574054","display_name":"Spatial correlation","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C109510780","wikidata":"https://www.wikidata.org/wiki/Q17149502","display_name":"Total correlation","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01502","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01502","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"Epistemic":[0],"uncertainty":[1,51,104,140,163],"estimation":[2],"is":[3],"essential":[4],"for":[5,161],"identifying":[6],"regions":[7,84],"where":[8],"deep":[9,102],"learning":[10],"system":[11],"outputs":[12],"may":[13],"be":[14],"unreliable.":[15],"However,":[16],"existing":[17],"approaches":[18],"require":[19],"computationally":[20],"expensive":[21],"ensemble":[22,103],"methods":[23],"or":[24,131],"multiple":[25],"stochastic":[26],"forward":[27],"passes,":[28],"limiting":[29],"their":[30],"scalability":[31],"to":[32,124],"dense":[33],"prediction":[34,50,72,162],"tasks":[35],"like":[36],"segmentation.":[37],"We":[38,64],"propose":[39],"Resolution-Aggregated":[40],"Decoder":[41],"Mutual":[42],"Information":[43],"(RADMI),":[44],"a":[45,91,156],"single-pass":[46,107],"method":[47],"that":[48,66,126,148],"estimates":[49],"by":[52,113],"measuring":[53],"mutual":[54],"information":[55,81,153],"(MI)":[56],"between":[57],"consecutive":[58],"decoder":[59],"layers":[60],"in":[61,115,119,164],"segmentation":[62,94],"networks.":[63],"observe":[65],"elevated":[67],"inter-layer":[68],"MI":[69],"correlates":[70],"with":[71,101],"uncertainty,":[73],"as":[74,86],"the":[75,98,110],"network":[76],"must":[77],"integrate":[78],"conflicting":[79],"contextual":[80],"at":[82],"ambiguous":[83],"such":[85],"class":[87],"boundaries.":[88],"Evaluating":[89],"on":[90],"seismic":[92],"facies":[93],"benchmark,":[95],"RADMI":[96,136],"achieves":[97],"highest":[99],"correlation":[100,121],"among":[105],"all":[106],"methods,":[108],"outperforming":[109],"next-best":[111],"baselines":[112,125],"5.5%":[114],"Pearson":[116],"and":[117,158],"10.7%":[118],"Spearman":[120],"coefficients.":[122],"Compared":[123],"either":[127],"lack":[128],"spatial":[129],"precision":[130],"demand":[132],"significant":[133],"computational":[134],"overhead,":[135],"yields":[137],"sharp,":[138],"boundary-localized":[139],"maps":[141],"without":[142],"architectural":[143],"modifications.":[144],"Our":[145],"results":[146],"suggest":[147],"linear":[149],"aggregation":[150],"of":[151],"normalized":[152],"flow":[154],"provides":[155],"principled":[157],"efficient":[159],"proxy":[160],"encoder-decoder":[165],"architectures.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}