{"id":"https://openalex.org/W4404781986","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","title":"A Semantic Search Engine for Mathlib4","display_name":"A Semantic Search Engine for Mathlib4","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404781986","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.470"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.470","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","pdf_url":"https://aclanthology.org/2024.findings-emnlp.470.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-emnlp.470.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104262609","display_name":"Guoxiong Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxiong Gao","raw_affiliation_strings":["School of Mathematical Sciences , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113149225","display_name":"Haocheng Ju","orcid":"https://orcid.org/0009-0005-0429-4805","observed_orcids":["https://orcid.org/0009-0005-0429-4805"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haocheng Ju","raw_affiliation_strings":["Beijing International Center for Mathematical Research , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing International Center for Mathematical Research , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109694215","display_name":"Jiedong Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiedong Jiang","raw_affiliation_strings":["Beijing International Center for Mathematical Research , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing International Center for Mathematical Research , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113231943","display_name":"Zihan Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Qin","raw_affiliation_strings":["School of Mathematical Sciences , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Beijing International Center for Mathematical Research , Peking University ,","Center for Machine Learning Research , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing International Center for Mathematical Research , Peking University ,","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Machine Learning Research , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.9499,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86502494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8001","last_page":"8013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9643999934196472,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9643999934196472,"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/T10126","display_name":"Logic, programming, and type systems","score":0.02239999920129776,"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":0.006300000008195639,"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/semantic-search","display_name":"semantic search","score":0.8309999704360962},{"id":"https://openalex.org/keywords/mathlib4","display_name":"Mathlib4","score":0.8180000185966492},{"id":"https://openalex.org/keywords/lean-theorem-prover","display_name":"Lean theorem prover","score":0.9409999847412109},{"id":"https://openalex.org/keywords/formal-verification","display_name":"formal verification","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127081155776978},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.565614640712738},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.5307854413986206},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.42775455117225647},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35063308477401733}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.470","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","pdf_url":"https://aclanthology.org/2024.findings-emnlp.470.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.13310","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13310","pdf_url":"https://arxiv.org/pdf/2403.13310","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.13310","doi":"https://doi.org/10.48550/arxiv.2403.13310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.13310","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"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.470","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.470","pdf_url":"https://aclanthology.org/2024.findings-emnlp.470.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404781986.pdf","grobid_xml":"https://content.openalex.org/works/W4404781986.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415947887","https://openalex.org/W7223326373","https://openalex.org/W7161168200","https://openalex.org/W7222406367","https://openalex.org/W7128079605","https://openalex.org/W7165882237","https://openalex.org/W7127563226","https://openalex.org/W1596352562","https://openalex.org/W7218976966","https://openalex.org/W2893457448"],"abstract_inverted_index":{"The":[0],"interactive":[1],"theorem":[2],"prover":[3],"Lean":[4],"enables":[5],"the":[6,29,32,103,112],"verification":[7],"of":[8,34,38,114],"formal":[9],"mathematical":[10,24,39],"proofs":[11],"and":[12,101],"is":[13,22,83],"backed":[14],"by":[15,76],"an":[16,35],"expanding":[17,36],"community.Central":[18],"to":[19,56],"this":[20,86],"ecosystem":[21],"its":[23,60],"library,":[25],"mathlib4,":[26,52],"which":[27],"lays":[28],"groundwork":[30],"for":[31,42,95,110,118],"formalization":[33],"range":[37],"theories.However,":[40],"searching":[41],"theorems":[43],"in":[44,51],"mathlib4":[45,82,96],"can":[46,72],"be":[47,57,73],"challenging.To":[48],"successfully":[49],"search":[50,69,92,116],"users":[53],"often":[54],"need":[55],"familiar":[58],"with":[59,78,81],"naming":[61],"conventions":[62],"or":[63],"documentation":[64],"strings.Therefore,":[65],"creating":[66],"a":[67,90,108],"semantic":[68,91],"engine":[70,93],"that":[71,97],"used":[74],"easily":[75],"individuals":[77],"varying":[79],"familiarity":[80],"very":[84],"important.In":[85],"paper,":[87],"we":[88],"present":[89],"1":[94],"accepts":[98],"informal":[99],"queries":[100],"finds":[102],"relevant":[104],"theorems.We":[105],"also":[106],"establish":[107],"benchmark":[109],"assessing":[111],"performance":[113],"various":[115],"engines":[117],"mathlib4.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-11-28T00:00:00"}