{"id":"https://openalex.org/W7167621077","doi":"https://doi.org/10.48550/arxiv.2607.04688","title":"URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment","display_name":"URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7167621077","doi":"https://doi.org/10.48550/arxiv.2607.04688"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.04688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.04688","pdf_url":"https://arxiv.org/pdf/2607.04688","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2607.04688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160215502","display_name":"Bogdan Zagribelnyy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zagribelnyy, Bogdan","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153504318","display_name":"Ivan Ilin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilin, Ivan","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160151807","display_name":"Nikita Bondarev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bondarev, Nikita","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075906555","display_name":"Anton Morgunov","orcid":"https://orcid.org/0009-0004-6245-0354","observed_orcids":["https://orcid.org/0009-0004-6245-0354"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morgunov, Anton","raw_affiliation_strings":["Independent researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160168277","display_name":"Arkadii Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Arkadii","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128186584","display_name":"Maksim Kuznetsov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuznetsov, Maksim","raw_affiliation_strings":["Insilico Medicine Canada Inc. , Montreal , Quebec , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine Canada Inc. , Montreal , Quebec , Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160208897","display_name":"Rim Shayakhmetov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shayakhmetov, Rim","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150714615","display_name":"Vladimir Aladinskiy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aladinskiy, Vladimir","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113161674","display_name":"Alex Aliper","orcid":"https://orcid.org/0000-0002-4363-0710","observed_orcids":["https://orcid.org/0000-0002-4363-0710"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aliper, Alex","raw_affiliation_strings":["Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insilico Medicine AI Limited , Masdar City , Abu Dhabi , UAE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160230568","display_name":"Alex Zhavoronkov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhavoronkov, Alex","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":true,"cited_by_count":5,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.004399999976158142,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthesis","display_name":"retrosynthesis","score":0.9520000219345093},{"id":"https://openalex.org/keywords/synthesis-planning","display_name":"synthesis planning","score":0.828000009059906},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5809999704360962},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8569999933242798},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8845999836921692},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.72079998254776},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.4162999987602234},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.41269999742507935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2596000134944916}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2607.04688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.04688","pdf_url":"https://arxiv.org/pdf/2607.04688","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.04688","doi":"https://doi.org/10.48550/arxiv.2607.04688","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.04688","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.20810715","doi":"https://doi.org/10.5281/zenodo.20810715","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20810715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},{"id":"doi:10.5281/zenodo.20810716","doi":"https://doi.org/10.5281/zenodo.20810716","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20810716","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.04688","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.04688","pdf_url":"https://arxiv.org/pdf/2607.04688","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167621077.pdf","grobid_xml":"https://content.openalex.org/works/W7167621077.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1997974358","https://openalex.org/W2909063104","https://openalex.org/W3035505522","https://openalex.org/W3101155908","https://openalex.org/W3101755431","https://openalex.org/W3167144918","https://openalex.org/W3189262114","https://openalex.org/W4283449818","https://openalex.org/W4285193863","https://openalex.org/W4386385748","https://openalex.org/W4391826941","https://openalex.org/W4398255643","https://openalex.org/W4401335328","https://openalex.org/W4405963578","https://openalex.org/W4406001199","https://openalex.org/W4409246334","https://openalex.org/W4410552772","https://openalex.org/W4415202617","https://openalex.org/W4416965058","https://openalex.org/W4417006854","https://openalex.org/W4417530433","https://openalex.org/W7111150328","https://openalex.org/W7127611024","https://openalex.org/W7133635491","https://openalex.org/W7140573957","https://openalex.org/W7213877507"],"related_works":["https://openalex.org/W4391474865","https://openalex.org/W7221765839","https://openalex.org/W7090721549","https://openalex.org/W7111150328","https://openalex.org/W7221797331","https://openalex.org/W4398255643","https://openalex.org/W7203864446","https://openalex.org/W4401335328","https://openalex.org/W4285193863","https://openalex.org/W7208240372"],"abstract_inverted_index":{"Synthesis":[0],"planning":[1,124,168],"aiming":[2],"to":[3,44,71,85],"find":[4,149],"pathways":[5],"of":[6,14,47,113,129],"reactions":[7,104],"for":[8,121],"a":[9,79,93,110,127],"target":[10,132],"molecule":[11],"is":[12],"one":[13],"the":[15,45,54,60,69,73,98,103,122,143],"most":[16],"important":[17],"and":[18,33,105,119],"challenging":[19],"tasks":[20,141],"in":[21,142,164],"drug":[22,145],"discovery.":[23],"Recent":[24],"progress":[25],"has":[26],"produced":[27],"both":[28,114],"specialized":[29,161],"deep-learning":[30],"retrosynthesis":[31,117,162],"systems":[32],"general-purpose":[34],"large":[35],"language":[36],"models,":[37],"but":[38,90],"objective":[39],"comparison":[40],"remains":[41],"difficult":[42],"due":[43],"lack":[46],"flexible,":[48],"chemically":[49],"interpretable":[50],"benchmarking":[51],"protocols.":[52],"In":[53],"current":[55],"study,":[56],"we":[57],"are":[58],"introducing":[59],"URSA":[61],"(Utilitarian":[62],"RetroSynthesis":[63],"Assessment)":[64],"evaluation":[65,112],"framework":[66],"that":[67,150],"provides":[68],"opportunity":[70],"benchmark":[72],"synthetic":[74,136],"routes":[75],"not":[76],"only":[77],"from":[78,92],"formal":[80],"perspective,":[81,96],"such":[82],"as":[83],"convergence":[84],"commercially":[86],"available":[87],"starting":[88],"materials,":[89],"also":[91],"chemical":[94],"plausibility":[95],"mimicking":[97],"way":[99],"expert":[100],"chemists":[101],"evaluate":[102],"routes.":[106],"The":[107],"study":[108],"covers":[109],"comprehensive":[111],"conventional":[115],"end-to-end":[116],"solutions":[118],"LLMs":[120,152],"synthesis":[123,167],"task":[125],"on":[126],"set":[128],"novel,":[130],"diverse":[131],"molecules":[133],"with":[134],"undisclosed":[135],"routes,":[137],"which":[138],"represent":[139],"realistic":[140],"daily":[144],"design":[146],"routine.":[147],"We":[148],"while":[151],"can":[153],"support":[154],"high-level":[155],"strategic":[156],"planning,":[157],"they":[158],"currently":[159],"underperform":[160],"models":[163],"reliably":[165],"solving":[166],"tasks.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-07-08T00:00:00"}