{"id":"https://openalex.org/W7225418723","doi":"https://doi.org/10.32942/x2c11r","title":"BioCosmos: computer vision and large language models for large-scale image-based biodiversity data and trait exploration","display_name":"BioCosmos: computer vision and large language models for large-scale image-based biodiversity data and trait exploration","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225418723","doi":"https://doi.org/10.32942/x2c11r"},"language":"en","primary_location":{"id":"doi:10.32942/x2c11r","doi":"https://doi.org/10.32942/x2c11r","is_oa":true,"landing_page_url":"https://doi.org/10.32942/x2c11r","pdf_url":"https://ecoevorxiv.org/repository/object/15964/download/27618/","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ecoevorxiv.org/repository/object/15964/download/27618/","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040224738","display_name":"Heru Handika","orcid":"https://orcid.org/0000-0002-2834-7175","observed_orcids":["https://orcid.org/0000-0002-2834-7175"]},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heru Handika","raw_affiliation_strings":["Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA"],"raw_orcid":"https://orcid.org/0000-0002-2834-7175","affiliations":[{"raw_affiliation_string":"Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040717971","display_name":"Moritz L\u00fcrig","orcid":"https://orcid.org/0000-0002-8175-6234","observed_orcids":["https://orcid.org/0000-0002-8175-6234"]},"institutions":[{"id":"https://openalex.org/I4387155279","display_name":"Leibniz Institute for the Analysis of Biodiversity Change","ror":"https://ror.org/03k5bhd83","country_code":"DE","type":"education","lineage":["https://openalex.org/I315704651","https://openalex.org/I4387155279"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz L\u00fcrig","raw_affiliation_strings":["Leibniz Institute for the Analysis of Biodiversity Change , Center for Taxonomy & Morphology , Bonn , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute for the Analysis of Biodiversity Change , Center for Taxonomy & Morphology , Bonn , Germany","institution_ids":["https://openalex.org/I4387155279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160376076","display_name":"Kira Nichtawitz","orcid":"https://orcid.org/0009-0003-5379-094X","observed_orcids":["https://orcid.org/0009-0003-5379-094X"]},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kira Nichtawitz","raw_affiliation_strings":["Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018466694","display_name":"Oliver Dobon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Dobon","raw_affiliation_strings":["College of Computing , Georgia Institute of Technology , Atlanta , Georgia , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing , Georgia Institute of Technology , Atlanta , Georgia , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160355994","display_name":"Venkata Yarava","orcid":"https://orcid.org/0009-0009-3025-4478","observed_orcids":["https://orcid.org/0009-0009-3025-4478"]},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata Yarava","raw_affiliation_strings":["Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160356106","display_name":"Justin Sobayo","orcid":"https://orcid.org/0009-0002-5620-8348","observed_orcids":["https://orcid.org/0009-0002-5620-8348"]},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Sobayo","raw_affiliation_strings":["Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158363552","display_name":"Breanna Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Breanna Shi","raw_affiliation_strings":["College of Computing , Georgia Institute of Technology , Atlanta , Georgia , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing , Georgia Institute of Technology , Atlanta , Georgia , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081674008","display_name":"Michael J. Elliott","orcid":"https://orcid.org/0000-0001-9243-3978","observed_orcids":["https://orcid.org/0000-0001-9243-3978"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Elliott","raw_affiliation_strings":["Advanced Computing and Information Systems Laboratory , Department of Electrical and Computer Engineering , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems Laboratory , Department of Electrical and Computer Engineering , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003181544","display_name":"J.A.B. Fortes","orcid":"https://orcid.org/0000-0001-8870-5205","observed_orcids":["https://orcid.org/0000-0001-8870-5205"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose Fortes","raw_affiliation_strings":["Advanced Computing and Information Systems Laboratory , Department of Electrical and Computer Engineering , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing and Information Systems Laboratory , Department of Electrical and Computer Engineering , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052849461","display_name":"Arthur Porto","orcid":"https://orcid.org/0000-0002-9210-8750","observed_orcids":["https://orcid.org/0000-0002-9210-8750"]},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arthur Porto","raw_affiliation_strings":["Department of Biology , University of Florida , Gainesville , Florida , USA","Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Florida Museum of Natural History , University of Florida , Gainesville , Florida , USA","institution_ids":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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/T11937","display_name":"Research Data Management Practices","score":0.5166000127792358,"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"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.5166000127792358,"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/T11974","display_name":"Lepidoptera: Biology and Taxonomy","score":0.2897999882698059,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.05090000107884407,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/butterfly-specimens","display_name":"butterfly specimens","score":0.652999997138977},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"image retrieval","score":0.8330000042915344},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/computer-vision","display_name":"computer vision","score":0.9480000138282776},{"id":"https://openalex.org/keywords/phenotypic-traits","display_name":"phenotypic traits","score":0.7009999752044678},{"id":"https://openalex.org/keywords/morphospace","display_name":"morphospace","score":0.6769999861717224},{"id":"https://openalex.org/keywords/taxonomic-harmonization","display_name":"taxonomic harmonization","score":0.8650000095367432},{"id":"https://openalex.org/keywords/georeferencing","display_name":"georeferencing","score":0.8169999718666077},{"id":"https://openalex.org/keywords/lepidoptera","display_name":"Lepidoptera","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C2778531742","wikidata":"https://www.wikidata.org/wiki/Q17009281","display_name":"Discoverability","level":2,"score":0.7894999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C98108635","wikidata":"https://www.wikidata.org/wiki/Q6497275","display_name":"Phenomics","level":5,"score":0.3253999948501587},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C163276114","wikidata":"https://www.wikidata.org/wiki/Q484591","display_name":"Natural history","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2702000141143799},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C53605480","wikidata":"https://www.wikidata.org/wiki/Q852595","display_name":"Geotagging","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32942/x2c11r","doi":"https://doi.org/10.32942/x2c11r","is_oa":true,"landing_page_url":"https://doi.org/10.32942/x2c11r","pdf_url":"https://ecoevorxiv.org/repository/object/15964/download/27618/","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.32942/x2c11r","doi":"https://doi.org/10.32942/x2c11r","is_oa":true,"landing_page_url":"https://doi.org/10.32942/x2c11r","pdf_url":"https://ecoevorxiv.org/repository/object/15964/download/27618/","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313425","display_name":"Florida Museum of Natural History","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225418723.pdf","grobid_xml":"https://content.openalex.org/works/W7225418723.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204083022","https://openalex.org/W7116989400","https://openalex.org/W6901960247","https://openalex.org/W6964961619","https://openalex.org/W7099036499","https://openalex.org/W3113961666","https://openalex.org/W4404726321","https://openalex.org/W2410598288","https://openalex.org/W4389194212","https://openalex.org/W4225409719"],"abstract_inverted_index":{"Millions":[0],"of":[1,20],"natural":[2,51,72],"history":[3,73],"specimen":[4,68],"images":[5,69],"are":[6],"now":[7],"online,":[8],"but":[9],"poor":[10],"discoverability":[11],"keeps":[12],"their":[13],"rich":[14],"phenotypic":[15],"and":[16,40,50,79,81,86,97,99,112,142],"evolutionary":[17],"data":[18,107],"out":[19],"reach":[21],"for":[22,44],"most":[23],"users.":[24],"We":[25],"developed":[26],"BioCosmos,":[27],"a":[28,60,130],"web":[29,62],"platform":[30,115],"that":[31],"combines":[32],"conventional":[33],"biodiversity":[34],"databases":[35],"with":[36,64,106],"emerging":[37,121],"computer":[38],"vision":[39],"large":[41],"language":[42,52],"models":[43],"image":[45,126],"retrieval,":[46],"visual":[47,92],"feature":[48],"recognition,":[49],"queries.":[53],"Its":[54],"first":[55],"implementation,":[56],"LepiVerse":[57],"(https://lepiverse.com),":[58],"is":[59],"butterfly":[61],"portal":[63],"more":[65],"than":[66],"600,000":[67],"aggregated":[70],"from":[71,108],"museums":[74],"worldwide":[75],"via":[76],"GBIF,":[77],"SCAN,":[78],"Ecdysis,":[80],"curated":[82],"through":[83],"taxonomic":[84],"harmonization":[85],"georeference":[87],"validation":[88],"pipelines.":[89],"BioCosmos":[90],"features":[91],"similarity,":[93],"interactive":[94],"morphospace":[95],"plots,":[96],"text-":[98],"image-based":[100],"searches,":[101],"alongside":[102],"species":[103],"pages":[104],"enriched":[105],"GenBank,":[109],"LepTraits,":[110],"Wikipedia,":[111],"Crossref.":[113],"The":[114],"demonstrates":[116],"how":[117],"an":[118],"open-source,":[119],"low-cost":[120],"AI":[122],"can":[123],"make":[124],"vast":[125],"collections":[127],"accessible":[128],"to":[129],"broad":[131],"audience,":[132],"while":[133],"highlighting":[134],"the":[135,139],"digitization":[136],"gap":[137],"between":[138],"Global":[140],"North":[141],"South.":[143]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}
