{"id":"https://openalex.org/W4402457354","doi":"https://doi.org/10.1145/3650212.3652145","title":"CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision","display_name":"CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402457354","doi":"https://doi.org/10.1145/3650212.3652145"},"language":"en","primary_location":{"id":"doi:10.1145/3650212.3652145","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650212.3652145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100743772","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-0536-5039"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101050114","display_name":"Zeyu Gao","orcid":"https://orcid.org/0009-0003-2318-9061"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Gao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460096","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-7894-8828"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011640001","display_name":"Zihan Sha","orcid":"https://orcid.org/0000-0002-1020-9006"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Sha","raw_affiliation_strings":["Information Engineering University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000712575","display_name":"Mingyang Sun","orcid":"https://orcid.org/0009-0004-7858-9246"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022291585","display_name":"Yuchen Zhou","orcid":"https://orcid.org/0000-0002-7021-1183"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Zhou","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052765512","display_name":"Wenyu Zhu","orcid":"https://orcid.org/0009-0005-0559-8915"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102202526","display_name":"Wenju Sun","orcid":"https://orcid.org/0009-0003-1923-1749"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Sun","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019692903","display_name":"Han Qiu","orcid":"https://orcid.org/0000-0003-2678-8070"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Qiu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Xiao","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100743772"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":11.3529,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.98764121,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512468099594116},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6266869902610779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5638991594314575},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5501750111579895},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5244826674461365},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4785114526748657},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47800174355506897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4711379408836365},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.113080233335495},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09279438853263855},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05001822113990784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512468099594116},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6266869902610779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5638991594314575},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5501750111579895},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5244826674461365},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4785114526748657},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47800174355506897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4711379408836365},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.113080233335495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09279438853263855},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05001822113990784},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650212.3652145","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3650212.3652145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2074466695","https://openalex.org/W2112796928","https://openalex.org/W2187089797","https://openalex.org/W2350778671","https://openalex.org/W2749008552","https://openalex.org/W2888320512","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W2963979492","https://openalex.org/W2965373594","https://openalex.org/W2997915791","https://openalex.org/W3001279689","https://openalex.org/W3008088841","https://openalex.org/W3098380913","https://openalex.org/W3105926539","https://openalex.org/W3127424491","https://openalex.org/W3133719257","https://openalex.org/W3192256856","https://openalex.org/W4225323055","https://openalex.org/W4253813365","https://openalex.org/W4283378019","https://openalex.org/W4285586654","https://openalex.org/W4311166089","https://openalex.org/W4377297670","https://openalex.org/W4385681674","https://openalex.org/W4394745954","https://openalex.org/W4402443222","https://openalex.org/W4402665833"],"related_works":["https://openalex.org/W4283262748","https://openalex.org/W2502773048","https://openalex.org/W4252362398","https://openalex.org/W48866389","https://openalex.org/W2117651364","https://openalex.org/W3112533414","https://openalex.org/W2490481324","https://openalex.org/W1993278628","https://openalex.org/W1979668694","https://openalex.org/W4312662746"],"abstract_inverted_index":{"Binary":[0],"code":[1,57,79,122,136],"representation":[2],"learning":[3,73],"has":[4],"shown":[5],"significant":[6],"performance":[7],"in":[8,20,153],"binary":[9,56,78,96,121,135,154],"analysis":[10,155],"tasks.":[11,35],"But":[12],"existing":[13],"solutions":[14],"often":[15,167],"have":[16,129],"poor":[17],"transferability,":[18],"particularly":[19],"few-shot":[21],"and":[22,61,116,123,137,139],"zero-shot":[23],"scenarios":[24],"where":[25],"few":[26],"or":[27],"no":[28],"training":[29],"samples":[30],"are":[31],"available":[32],"for":[33,95],"the":[34,66],"To":[36,98],"address":[37],"this":[38,100],"problem,":[39],"we":[40,103],"present":[41],"CLAP":[42,148,165],"(Contrastive":[43],"Language-Assembly":[44],"Pre-training),":[45],"which":[46],"employs":[47],"natural":[48,85,125],"language":[49,126],"supervision":[50],"to":[51,91],"learn":[52],"better":[53,63,93],"representations":[54],"of":[55,120,134,143,147],"(i.e.,":[58],"assembly":[59],"code)":[60],"get":[62],"transferability.":[64,176],"At":[65],"core,":[67],"our":[68],"approach":[69],"boosts":[70],"superior":[71],"transfer":[72],"capabilities":[74],"by":[75],"effectively":[76],"aligning":[77],"with":[80,169],"their":[81],"semantics":[82],"explanations":[83,138],"(in":[84],"language),":[86],"resulting":[87],"a":[88,114,141,170],"model":[89],"able":[90],"generate":[92,113],"embeddings":[94],"code.":[97],"enable":[99],"alignment":[101],"training,":[102,164],"then":[104],"propose":[105],"an":[106],"efficient":[107],"dataset":[108,118],"engine":[109],"that":[110],"could":[111],"automatically":[112],"large":[115],"diverse":[117],"comprising":[119],"corresponding":[124],"explanations.":[127],"We":[128],"generated":[130],"195":[131],"million":[132],"pairs":[133],"trained":[140],"prototype":[142],"CLAP.":[144],"The":[145],"evaluations":[146],"across":[149],"various":[150],"downstream":[151],"tasks":[152],"all":[156],"demonstrate":[157],"exceptional":[158],"performance.":[159],"Notably,":[160],"without":[161],"any":[162],"task-specific":[163],"is":[166],"competitive":[168],"fully":[171],"supervised":[172],"baseline,":[173],"showing":[174],"excellent":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}