{"id":"https://openalex.org/W7222995148","doi":"https://doi.org/10.48550/arxiv.2610.26730","title":"EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition","display_name":"EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition","publication_year":2026,"publication_date":"2026-10-19","ids":{"openalex":"https://openalex.org/W7222995148","doi":"https://doi.org/10.48550/arxiv.2610.26730"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.26730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.26730","pdf_url":"https://arxiv.org/pdf/2610.26730","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.26730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102975886","display_name":"Vincenzo Perri","orcid":"https://orcid.org/0000-0002-4203-1177","observed_orcids":["https://orcid.org/0000-0002-4203-1177"]},"institutions":[{"id":"https://openalex.org/I134940468","display_name":"Institute for Scientific Interchange","ror":"https://ror.org/00te2x188","country_code":"IT","type":"facility","lineage":["https://openalex.org/I134940468"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Perri, Vincenzo","raw_affiliation_strings":["ISI Foundation , Turin , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISI Foundation , Turin , Italy","institution_ids":["https://openalex.org/I134940468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069885186","display_name":"Ciro Cattuto","orcid":"https://orcid.org/0000-0001-9526-4364","observed_orcids":["https://orcid.org/0000-0001-9526-4364"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cattuto, Ciro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020744129","display_name":"Daniela Paolotti","orcid":"https://orcid.org/0000-0003-1356-3470","observed_orcids":["https://orcid.org/0000-0003-1356-3470"]},"institutions":[{"id":"https://openalex.org/I134940468","display_name":"Institute for Scientific Interchange","ror":"https://ror.org/00te2x188","country_code":"IT","type":"facility","lineage":["https://openalex.org/I134940468"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolotti, Daniela","raw_affiliation_strings":["ISI Foundation , Turin , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISI Foundation , Turin , Italy","institution_ids":["https://openalex.org/I134940468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10028","display_name":"Topic Modeling","score":0.6840999722480774,"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/T10028","display_name":"Topic Modeling","score":0.6840999722480774,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07639999687671661,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.03449999913573265,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/literature-mapping","display_name":"literature mapping","score":0.4749999940395355},{"id":"https://openalex.org/keywords/paper-classification","display_name":"paper classification","score":0.8659999966621399},{"id":"https://openalex.org/keywords/open-weight-models","display_name":"open-weight models","score":0.5130000114440918},{"id":"https://openalex.org/keywords/reproduction-number","display_name":"reproduction number","score":0.7409999966621399},{"id":"https://openalex.org/keywords/transmission-model","display_name":"transmission model","score":0.8299999833106995},{"id":"https://openalex.org/keywords/epidemic-preparedness","display_name":"epidemic preparedness","score":0.8029999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908000111579895},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684000015258789},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.26730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.26730","pdf_url":"https://arxiv.org/pdf/2610.26730","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.26730","doi":"https://doi.org/10.48550/arxiv.2610.26730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.26730","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.26730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.26730","pdf_url":"https://arxiv.org/pdf/2610.26730","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,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1481412291","display_name":null,"funder_award_id":"101095619","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G1876066754","display_name":"Efficient and rapidly SCAlable EU-wide evidence-driven Pandemic response plans through dynamic Epidemic data assimilation","funder_award_id":"101095619","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222995148.pdf","grobid_xml":"https://content.openalex.org/works/W7222995148.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2120146852","https://openalex.org/W2121044470","https://openalex.org/W2126728600","https://openalex.org/W2765453497","https://openalex.org/W4221142221","https://openalex.org/W4296959557","https://openalex.org/W4362515116","https://openalex.org/W4402385990","https://openalex.org/W4403795293","https://openalex.org/W4406311019","https://openalex.org/W4417183323","https://openalex.org/W4417290549","https://openalex.org/W7125770334","https://openalex.org/W7127589252","https://openalex.org/W7196924653","https://openalex.org/W7213325359","https://openalex.org/W7214915851"],"related_works":["https://openalex.org/W7212074826","https://openalex.org/W7163748899","https://openalex.org/W7119513889","https://openalex.org/W7221508192","https://openalex.org/W4221112447","https://openalex.org/W3158236767","https://openalex.org/W7170135834","https://openalex.org/W3144007026","https://openalex.org/W7064363752","https://openalex.org/W4408928827"],"abstract_inverted_index":{"To":[0],"prepare":[1],"for":[2,140],"future":[3],"outbreaks,":[4],"researchers":[5],"need":[6],"to":[7,55,64,111,147,152,165,180,211],"know":[8],"what":[9,15],"studies":[10,154],"have":[11],"been":[12],"done":[13],"and":[14,52,61,82,119,173,215],"data":[16],"they":[17],"use.":[18],"Mapping":[19],"a":[20,40,48,59,69,78,148,157],"large":[21,28],"literature":[22],"by":[23,156],"hand":[24],"is":[25,109,202],"slow,":[26],"while":[27],"language":[29],"models":[30,210],"alone":[31],"can":[32],"misstate":[33],"or":[34,151],"conflate":[35],"sources.":[36],"We":[37,67,143],"present":[38],"EpiLens,":[39],"lightweight,":[41],"open-source":[42],"retrieval-augmented":[43],"generation":[44],"package":[45],"that":[46,99],"applies":[47],"fixed":[49],"retrieval":[50],"template":[51],"output":[53],"schema":[54],"every":[56],"paper":[57],"in":[58,196],"corpus":[60,70,153],"links":[62],"outputs":[63],"source":[65],"passages.":[66],"build":[68],"of":[71,77,121,128,208],"2,297":[72],"papers":[73,168,178],"from":[74],"the":[75,107,116,126,162,167,197,205],"sources":[76,139],"multi-pathogen":[79],"parameter":[80],"study":[81],"evaluate":[83],"EpiLens's":[84],"paper-classification":[85],"workflow":[86],"against":[87],"214":[88],"manually":[89],"labelled":[90],"papers.":[91],"Run":[92],"locally":[93],"with":[94,170,192,204],"an":[95],"open-weight":[96],"model,":[97],"so":[98],"licensed":[100],"full":[101],"texts":[102],"never":[103],"leave":[104],"our":[105],"hardware,":[106],"classifier":[108],"comparable":[110],"supervised":[112],"baselines":[113],"trained":[114],"on":[115,123],"manual":[117,198],"labels,":[118],"ahead":[120],"them":[122],"geography,":[124],"despite":[125],"lack":[127],"task-specific":[129],"training":[130],"data.":[131],"The":[132,200],"study's":[133],"early":[134],"extraction":[135],"sheets":[136],"cite":[137],"published":[138],"327":[141],"estimates.":[142],"link":[144],"each":[145],"estimate":[146,212],"cited":[149],"document":[150],"included":[155],"review.":[158],"Then,":[159],"we":[160],"use":[161,207],"classifier's":[163],"labels":[164,176],"compare":[166],"associated":[169],"different":[171],"parameters":[172],"pathogens.":[174,219],"EpiLens":[175],"more":[177],"linked":[179],"reproduction":[181,213],"numbers":[182,214],"than":[183],"fatality":[184],"risks":[185],"as":[186],"model-based":[187],"(53%":[188],"versus":[189,194],"15%,":[190],"compared":[191],"62%":[193],"24%":[195],"labels).":[199],"gap":[201],"consistent":[203],"frequent":[206],"transmission":[209],"largely":[216],"persists":[217],"within":[218]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-21T00:00:00"}