{"id":"https://openalex.org/W4410636956","doi":"https://doi.org/10.1145/3701716.3715295","title":"USPTO-LLM: A Large Language Model-Assisted Information-enriched Chemical Reaction Dataset","display_name":"USPTO-LLM: A Large Language Model-Assisted Information-enriched Chemical Reaction Dataset","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636956","doi":"https://doi.org/10.1145/3701716.3715295"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715295","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100521735","display_name":"Shen Yuan","orcid":"https://orcid.org/0009-0008-4238-0538"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shen Yuan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4238-0538","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117649524","display_name":"Shukai Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shukai Gong","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3322-7830","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"https://orcid.org/0000-0003-4192-5360"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongteng Xu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4192-5360","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100521735"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.459,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58861823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"817","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.9366999864578247,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6419825553894043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36511483788490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419825553894043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36511483788490295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715295","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715295","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636956.pdf","grobid_xml":"https://content.openalex.org/works/W4410636956.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1988500898","https://openalex.org/W2325811289","https://openalex.org/W2551217916","https://openalex.org/W2913954081","https://openalex.org/W3181403764","https://openalex.org/W4283715583","https://openalex.org/W4378783602","https://openalex.org/W4385571445","https://openalex.org/W4404982891"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Over":[0],"the":[1,5,22,31,37,43,50,53,69,85,109,126,131,135,139,149],"past":[2],"few":[3],"years,":[4],"machine":[6],"learning":[7],"community":[8],"has":[9],"given":[10],"increasing":[11],"attention":[12],"to":[13,107],"chemical":[14,63,81],"reaction":[15,46,64,100],"prediction":[16],"and":[17,42,93,130,148],"retrosynthesis.":[18],"Despite":[19],"impressive":[20],"achievements,":[21],"existing":[23,127],"datasets":[24],"in":[25,134],"this":[26,57],"field":[27],"have":[28],"gradually":[29],"become":[30],"bottleneck":[32],"of":[33,39,45,52,71,88],"current":[34,54],"research":[35],"---":[36],"limitation":[38],"dataset":[40,65,77,136,143],"size":[41],"lack":[44],"condition":[47,132],"information":[48,98,133],"hinder":[49],"practicability":[51],"methods.":[55],"In":[56],"study,":[58],"we":[59],"construct":[60],"an":[61],"information-enriched":[62],"called":[66],"USPTO-LLM,":[67],"with":[68,114],"help":[70],"large":[72,104],"language":[73,105],"models":[74,106],"(LLMs).":[75],"This":[76],"comprises":[78],"over":[79],"247K":[80],"reactions":[82],"extracted":[83],"from":[84],"patent":[86],"documents":[87],"USPTO":[89],"(United":[90],"States":[91],"Patent":[92],"Trademark":[94],"Office),":[95],"encompassing":[96],"abundant":[97],"on":[99],"conditions.":[101],"We":[102],"employ":[103],"expedite":[108],"data":[110],"collection":[111],"procedures":[112],"automatically":[113],"a":[115],"reliable":[116],"quality":[117],"control":[118],"process.":[119],"Experiments":[120],"show":[121],"that":[122],"USPTO-LLM":[123],"helps":[124,137],"pre-train":[125],"retrosynthesis":[128],"methods":[129],"improve":[138],"model":[140],"performance.":[141],"The":[142],"is":[144,152],"open-sourced":[145,153],"at":[146,154],"https://zenodo.org/records/14396156":[147],"annotation":[150],"code":[151],"https://github.com/GONGSHUKAI/USPTO_LLM.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}