{"id":"https://openalex.org/W7225324869","doi":"https://doi.org/10.1038/s41598-026-74619-9","title":"A hybrid uncertainty-aware deep learning framework for reliable Malayalam fake news detection","display_name":"A hybrid uncertainty-aware deep learning framework for reliable Malayalam fake news detection","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225324869","doi":"https://doi.org/10.1038/s41598-026-74619-9"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-74619-9","doi":"https://doi.org/10.1038/s41598-026-74619-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74619-9","pdf_url":"https://www.nature.com/articles/s41598-026-74619-9.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-74619-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120072710","display_name":"O. V. Likha","orcid":"https://orcid.org/0009-0003-0091-4339","observed_orcids":["https://orcid.org/0009-0003-0091-4339"]},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"O. V. Likha","raw_affiliation_strings":["Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160803721","display_name":"S. Sachin Kumar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S. Sachin Kumar","raw_affiliation_strings":["Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080015706","display_name":"Neethu Mohan","orcid":"https://orcid.org/0000-0003-4853-8670","observed_orcids":["https://orcid.org/0000-0003-4853-8670"]},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neethu Mohan","raw_affiliation_strings":["Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amrita School of Artificial Intelligence, Coimbatore Amrita Vishwa Vidyapeetham, Coimbatore, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010817006","display_name":"O. K. Sikha","orcid":"https://orcid.org/0000-0002-3499-8062","observed_orcids":["https://orcid.org/0000-0002-3499-8062"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"O. K. Sikha","raw_affiliation_strings":["Department of Engineering, BCN MedTech, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, BCN MedTech, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5160803721"],"corresponding_institution_ids":["https://openalex.org/I81556334"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.00039999998989515007,"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/fake-news-detection","display_name":"fake news detection","score":0.9900000095367432},{"id":"https://openalex.org/keywords/malayalam-language","display_name":"Malayalam language","score":0.9319999814033508},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.953000009059906},{"id":"https://openalex.org/keywords/aleatoric-and-epistemic-uncertainty","display_name":"aleatory and epistemic uncertainty","score":0.8569999933242798},{"id":"https://openalex.org/keywords/evidential-deep-learning","display_name":"evidential deep learning","score":0.9279999732971191},{"id":"https://openalex.org/keywords/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.8870000243186951},{"id":"https://openalex.org/keywords/ensemble-deep-learning","display_name":"ensemble deep learning","score":0.8500000238418579},{"id":"https://openalex.org/keywords/test-time-augmentation","display_name":"test-time augmentation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.6060000061988831},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.7590000033378601},{"id":"https://openalex.org/keywords/prediction-reliability","display_name":"forecast reliability","score":0.6150000095367432},{"id":"https://openalex.org/keywords/calibration-analysis","display_name":"calibration analysis","score":0.699999988079071},{"id":"https://openalex.org/keywords/cnn-bilstm","display_name":"CNN-BiLSTM","score":0.6660000085830688},{"id":"https://openalex.org/keywords/cnn-gru","display_name":"CNN-GRU","score":0.8149999976158142},{"id":"https://openalex.org/keywords/cnn-lstm","display_name":"CNN-LSTM","score":0.8209999799728394},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.8068000078201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7728000283241272},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7692999839782715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5799000263214111},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5698999762535095},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4478999972343445},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.4253000020980835},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2779662586","wikidata":"https://www.wikidata.org/wiki/Q36236","display_name":"Malayalam","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1038/s41598-026-74619-9","doi":"https://doi.org/10.1038/s41598-026-74619-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74619-9","pdf_url":"https://www.nature.com/articles/s41598-026-74619-9.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:28de1d4097584c50944409dd32eba0dc","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/28de1d4097584c50944409dd32eba0dc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Reports, Vol 16, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-74619-9","doi":"https://doi.org/10.1038/s41598-026-74619-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-74619-9","pdf_url":"https://www.nature.com/articles/s41598-026-74619-9.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225324869.pdf","grobid_xml":"https://content.openalex.org/works/W7225324869.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1965555277","https://openalex.org/W2064675550","https://openalex.org/W2493916176","https://openalex.org/W2742330194","https://openalex.org/W2887976372","https://openalex.org/W2900246445","https://openalex.org/W2912082611","https://openalex.org/W2964317943","https://openalex.org/W3001895040","https://openalex.org/W3007083472","https://openalex.org/W3014339631","https://openalex.org/W3014596384","https://openalex.org/W3042569426","https://openalex.org/W3119962516","https://openalex.org/W3139850432","https://openalex.org/W3183048323","https://openalex.org/W3210027319","https://openalex.org/W4285816679","https://openalex.org/W4379958381","https://openalex.org/W4385573323","https://openalex.org/W4385692515","https://openalex.org/W4388099454","https://openalex.org/W4388623142","https://openalex.org/W4392096499","https://openalex.org/W4394787157","https://openalex.org/W4401541180","https://openalex.org/W4403507364","https://openalex.org/W4404088575","https://openalex.org/W4404609187","https://openalex.org/W4404784419","https://openalex.org/W4406213428","https://openalex.org/W4411121371","https://openalex.org/W4412875472","https://openalex.org/W4415368537","https://openalex.org/W4415721211","https://openalex.org/W7116694432","https://openalex.org/W7126435167","https://openalex.org/W7126457253"],"related_works":["https://openalex.org/W4415721211","https://openalex.org/W7161823182","https://openalex.org/W4285816679","https://openalex.org/W4400910830","https://openalex.org/W4388032074","https://openalex.org/W4411113337","https://openalex.org/W4411113379","https://openalex.org/W4411113205","https://openalex.org/W4394597511","https://openalex.org/W4415763952"],"abstract_inverted_index":{"Fake":[0],"news":[1,88,136,479],"detection":[2,89],"in":[3,33,271,414,474],"low":[4,475],"resource":[5,476],"languages":[6],"like":[7],"Malayalam":[8,86],"is":[9,174,336],"a":[10,185],"challenging":[11],"task":[12],"due":[13,222],"to":[14,61,176,223,438],"linguistic":[15,18],"complexity,":[16],"limited":[17],"resources":[19],"and":[20,41,104,121,128,152,171,180,206,219,252,288,322,346,368,378,402,434,457,464],"lack":[21,39],"of":[22,68,158,198,201,204,208,214,238,243,248,254,281,286,291,304,410,471],"annotated":[23],"datasets.":[24],"The":[25,191,232,297,423,446],"deep":[26,92],"learning":[27,93],"models":[28,351,430],"has":[29,74],"proven":[30],"good":[31],"impact":[32],"text":[34],"classification":[35,356,421,444],"tasks,":[36],"but":[37,65],"they":[38],"reliability":[40,67,436],"interpretability":[42],"that":[43,55,427,449,467],"are":[44,51,126],"critical":[45],"for":[46,85,330],"real":[47],"world":[48],"deployment.":[49],"There":[50],"some":[52],"recent":[53],"studies":[54],"focus":[56],"on":[57],"explainable":[58],"artificial":[59],"intelligence":[60],"interpret":[62],"model":[63,217,234],"predictions":[64,73,417],"the":[66,138,156,212,265,275,331,343,358,363,372,408,411,450,469],"these":[69],"explanations":[70],"under":[71],"uncertain":[72,416,465],"not":[75],"been":[76],"addressed.":[77],"This":[78],"paper":[79],"proposes":[80],"an":[81,196,226,236,302],"uncertainty":[82,107,143,163,182,189,385,428,452,472],"aware":[83,429],"framework":[84,140,164,194,413],"fake":[87,135,478],"using":[90,384],"different":[91],"architectures,":[94],"including":[95],"Bidirectional":[96,100],"LSTM":[97],"(BiLSTM),":[98],"CNN-LSTM,":[99],"GRU":[101],"(BiGRU),":[102],"CNN-GRU,":[103],"CNN-BiLSTM.":[105],"Four":[106],"estimation":[108],"techniques":[109],"Monte":[110],"Carlo":[111],"(MC)":[112],"Dropout,":[113,167],"Deep":[114,123,168,344],"Ensemble":[115,169,345,350],"Learning,":[116],"Test":[117],"Time":[118],"Augmentation":[119],"(TTA)":[120],"Evidential":[122,172],"Learning":[124,170,173],"(EDL)":[125],"used":[127],"compared":[129,437],"with":[130,134],"baseline":[131,439],"models.":[132,296,341],"Along":[133],"classification,":[137],"proposed":[139,175,192,215,332,359,412],"quantifies":[141],"predictive":[142],"through":[144],"entropy,":[145],"Kullback-Leibler":[146],"(KL)":[147],"divergence,":[148],"mutual":[149],"information,":[150],"variance,":[151],"vacuity":[153],"measures,":[154],"enabling":[155],"identification":[157],"unreliable":[159],"predictions.":[160],"A":[161],"hybrid":[162,193,216,333,451],"combining":[165],"MC":[166,347],"jointly":[177],"capture":[178],"epistemic":[179],"aleatoric":[181],"while":[183,418,441],"providing":[184],"complementary":[186],"evidence":[187],"based":[188],"estimates.":[190],"achieves":[195,362],"accuracy":[197,237],"96.51%,":[199,205],"precision":[200,242],"96.52%,":[202],"recall":[203,247],"F1-score":[207,253],"96.51%.":[209],"To":[210],"assess":[211],"robustness":[213],"result":[218],"address":[220],"variability":[221],"random":[224],"initialization,":[225],"additional":[227],"five-seed":[228,373],"experiment":[229,300],"was":[230],"conducted.":[231],"Hybrid":[233,360],"achieved":[235,301],"95.85":[239,244,249,255],"\u00b1":[240,245,250,256],"0.18,":[241],"0.18%,":[246,251,257],"indicating":[258,375],"stable":[259],"performance":[260],"across":[261,371],"multiple":[262],"runs.":[263],"Furthermore,":[264],"calibration":[266,377,433],"analysis":[267],"demonstrates":[268,426],"substantial":[269],"improvements":[270],"prediction":[272,380],"reliability,":[273],"achieving":[274],"lowest":[276,364],"Expected":[277],"Calibration":[278],"Error":[279],"(ECE)":[280],"0.0066,":[282],"Negative":[283],"Log-Likelihood":[284],"(NLL)":[285],"0.1014,":[287],"Brier":[289,323,369],"Score":[290],"0.0546":[292],"among":[293],"all":[294,339],"evaluated":[295],"five":[298],"seed":[299],"ECE":[303],"(":[305,311,317,325],"$$0.0067":[306],"\\pm":[307,313,319,327],"0.0023$$":[308],"),":[309,315,321],"MCE":[310],"$$0.0955":[312],"0.0494$$":[314],"NLL":[316],"$$0.1229":[318],"0.0027$$":[320],"score":[324,370],"$$0.0659":[326],"0.0007$$":[328],")":[329],"model,":[334],"which":[335],"lower":[337],"than":[338],"other":[340],"Although":[342],"Dropout":[348],"+":[349],"achieve":[352],"slightly":[353],"higher":[354],"mean":[355],"accuracy,":[357],"Model":[361],"ECE,":[365],"MCE,":[366],"NLL,":[367],"experiments,":[374],"improved":[376,435],"probabilistic":[379],"quality.":[381],"Additional":[382],"evaluation":[383],"specific":[386],"metrics":[387],"such":[388],"as":[389],"Uncertainty":[390,394,398,403],"Accuracy":[391],"Coefficient":[392],"(UAC),":[393],"Precision":[395],"Ratio":[396],"(UPR),":[397],"Sensitivity":[399],"Estimate":[400],"(USE),":[401],"Specificity":[404],"Percentage":[405],"(USP)":[406],"confirms":[407],"effectiveness":[409],"identifying":[415],"maintaining":[419,442],"high":[420],"performance.":[422,445],"experimental":[424],"evaluations":[425],"provide":[431],"better":[432],"architectures":[440],"competitive":[443],"results":[447],"shows":[448],"modeling":[453],"effectively":[454],"reduces":[455],"overconfidence":[456],"enhances":[458],"trustworthiness":[459],"by":[460],"distinguishing":[461],"between":[462],"confident":[463],"samples,":[466],"highlights":[468],"importance":[470],"quantification":[473],"language":[477],"detection.":[480]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-06T00:00:00"}