{"id":"https://openalex.org/W7166849583","doi":"https://doi.org/10.18653/v1/2026.acl-long.1566","title":"MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding","display_name":"MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166849583","doi":"https://doi.org/10.18653/v1/2026.acl-long.1566"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1566","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1566","pdf_url":"https://aclanthology.org/2026.acl-long.1566.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1566.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139834176","display_name":"Xue Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139747227","display_name":"Zheyuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139769256","display_name":"Arman Cohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arman Cohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139773668","display_name":"Yilun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilun Zhao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90451036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33981","last_page":"33999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.14300000667572021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.14300000667572021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.09529999643564224,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.06549999862909317,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.3061000108718872},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.25690001249313354},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2484000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434000134468079},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2484000027179718},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24770000576972961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1566","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1566","pdf_url":"https://aclanthology.org/2026.acl-long.1566.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1566","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1566","pdf_url":"https://aclanthology.org/2026.acl-long.1566.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5225014090538025,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166849583.pdf","grobid_xml":"https://content.openalex.org/works/W7166849583.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"MMSciCode,":[2],"a":[3,62],"comprehensive":[4,82],"expert-level,":[5],"multilingual":[6],"multi-discipline":[7],"benchmark":[8],"for":[9,128],"evaluating":[10],"foundation":[11,108],"models":[12,38,109,121],"in":[13],"scientific":[14,26,131],"code":[15,132],"generation.It":[16],"includes":[17],"624":[18],"expert-annotated":[19],"research":[20,51],"coding":[21,112],"problems":[22],"spanning":[23],"six":[24],"core":[25,48],"disciplines.Compared":[27],"to":[28,39,46,71],"prior":[29],"benchmarks,":[30],"MMSciCode":[31],"features":[32],"three":[33],"key":[34],"advancements.First,":[35],"it":[36],"challenges":[37],"integrate":[40],"domain-specific":[41],"knowledge":[42],"with":[43,66,81],"algorithmic":[44],"reasoning":[45],"implement":[47],"functions":[49],"from":[50],"papers.Second,":[52],"each":[53,77],"problem":[54,78],"is":[55,79],"meticulously":[56],"annotated":[57],"by":[58],"domain":[59,99],"experts":[60],"through":[61],"rigorous":[63],"papergrounded":[64],"process,":[65],"strict":[67],"quality":[68],"controls":[69],"implemented":[70],"ensure":[72],"dataset":[73],"integrity":[74],"and":[75,86,91,98,110,122],"authenticity.Finally,":[76],"equipped":[80],"unit":[83],"test":[84],"suites":[85],"containerized":[87],"environments,":[88],"enabling":[89],"reproducible":[90],"diagnostic":[92],"evaluation":[93,104],"of":[94,105],"both":[95],"functional":[96],"correctness":[97],"validity.We":[100],"conduct":[101],"an":[102],"extensive":[103],"23":[106],"state-of-the-art":[107],"2":[111],"agents":[113],"on":[114],"MMSciCode.We":[115],"identify":[116],"substantial":[117],"performance":[118],"gaps":[119],"between":[120],"human":[123],"experts,":[124],"providing":[125],"actionable":[126],"insights":[127],"advancing":[129],"expert-level":[130],"generation.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}