{"id":"https://openalex.org/W4400582776","doi":"https://doi.org/10.1145/3643752","title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","display_name":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582776","doi":"https://doi.org/10.1145/3643752"},"language":"en","primary_location":{"id":"doi:10.1145/3643752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643752","source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3643752","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092103115","display_name":"Zian Su","orcid":"https://orcid.org/0009-0001-8283-2825"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zian Su","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0009-0001-8283-2825","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036121611","display_name":"Xiangzhe Xu","orcid":"https://orcid.org/0000-0001-6619-781X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangzhe Xu","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0001-6619-781X","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyang Huang","orcid":"https://orcid.org/0009-0009-2764-6091"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyang Huang","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0009-0009-2764-6091","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429710","display_name":"Zhuo Zhang","orcid":"https://orcid.org/0000-0002-6515-0021"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Zhang","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-6515-0021","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055043003","display_name":"Yapeng Ye","orcid":"https://orcid.org/0000-0001-7232-0650"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yapeng Ye","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0001-7232-0650","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037117080","display_name":"Jianjun Huang","orcid":"https://orcid.org/0000-0003-4403-0060"},"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":"Jianjun Huang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4403-0060","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107249133","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0002-9544-2500"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-9544-2500","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5092103115"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76158578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"1","issue":"FSE","first_page":"562","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8261362314224243},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6167888641357422},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.502061128616333},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4975641071796417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4935828447341919},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.44422829151153564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42724549770355225},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37927332520484924},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3668364882469177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261362314224243},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6167888641357422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.502061128616333},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4975641071796417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4935828447341919},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.44422829151153564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42724549770355225},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37927332520484924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3668364882469177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3643752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643752","source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3643752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643752","source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G175455262","display_name":null,"funder_award_id":"W911NF-19-S-0012","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G3657828537","display_name":null,"funder_award_id":"1901242 and 1910300","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8595151890","display_name":null,"funder_award_id":"HR001120S0058","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400582776.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W1557561422","https://openalex.org/W1902237438","https://openalex.org/W2010065958","https://openalex.org/W2144344516","https://openalex.org/W2162436812","https://openalex.org/W2579698096","https://openalex.org/W2979393298","https://openalex.org/W2997847174","https://openalex.org/W3093497259","https://openalex.org/W3098605233","https://openalex.org/W3116924855","https://openalex.org/W3162962341","https://openalex.org/W3170092793","https://openalex.org/W3177441850","https://openalex.org/W3194586437","https://openalex.org/W3194813479","https://openalex.org/W3208494144","https://openalex.org/W3208507830","https://openalex.org/W4200186003","https://openalex.org/W4200633062","https://openalex.org/W4221061332","https://openalex.org/W4221166942","https://openalex.org/W4226208698","https://openalex.org/W4246219036","https://openalex.org/W4281753584","https://openalex.org/W4281763794","https://openalex.org/W4282033849","https://openalex.org/W4284708426","https://openalex.org/W4285490409","https://openalex.org/W4285586654","https://openalex.org/W4297795493","https://openalex.org/W4308643024","https://openalex.org/W4308731473","https://openalex.org/W4312282218","https://openalex.org/W4312727366","https://openalex.org/W4319083508","https://openalex.org/W4384009682","https://openalex.org/W4384154511","https://openalex.org/W4384155611","https://openalex.org/W4384345745","https://openalex.org/W4384347367","https://openalex.org/W4389162095","https://openalex.org/W4391558545","https://openalex.org/W6948955743"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4389520445","https://openalex.org/W4387800341","https://openalex.org/W4388347706"],"abstract_inverted_index":{"Transformer":[0],"based":[1],"code":[2,52,285],"models":[3,53],"have":[4],"impressive":[5],"performance":[6],"in":[7,61,69,96,203,222],"many":[8],"software":[9],"engineering":[10],"tasks.":[11],"However,":[12],"their":[13],"effectiveness":[14],"degrades":[15],"when":[16,54],"symbols":[17,55,90],"are":[18,56,141],"missing":[19],"or":[20],"not":[21,30],"informative.":[22],"The":[23],"reason":[24],"is":[25,132],"that":[26,60],"the":[27,36,40,110,126,128,138,149,153,201,220],"model":[28,111,157,178,202,217],"may":[29],"learn":[31,135],"to":[32,35,49,66,77,81,107,113,134,145,234,246,265],"pay":[33],"attention":[34,104,166],"right":[37],"correlations/contexts":[38],"without":[39],"help":[41],"of":[42,87,137,159,184,284],"symbols.":[43],"We":[44,58,74,99,174,199],"propose":[45,76],"a":[46,70,84,102,160,170,182],"new":[47,171],"method":[48,106],"pre-train":[50,175],"general":[51,281],"lacking.":[57],"observe":[59],"such":[62],"cases,":[63],"programs":[64],"degenerate":[65],"something":[67],"written":[68],"very":[71],"primitive":[72],"language.":[73],"hence":[75],"use":[78],"program":[79,118,192],"analysis":[80],"extract":[82],"contexts":[83],"priori":[85],"(instead":[86],"relying":[88],"on":[89],"and":[91,122,156,164,168,211,256],"masked":[92],"language":[93],"modeling":[94],"as":[95],"vanilla":[97,154],"models).":[98],"then":[100],"leverage":[101],"novel":[103],"masking":[105],"only":[108],"allow":[109],"attending":[112],"these":[114,223],"contexts,":[115],"e.g.,":[116],"bi-directional":[117],"dependence":[119,193],"transitive":[120],"closures":[121],"token":[123],"co-occurrences.":[124],"In":[125],"meantime,":[127],"inherent":[129],"self-attention":[130],"mechanism":[131],"utilized":[133],"which":[136],"allowed":[139],"attentions":[140],"more":[142],"important":[143],"compared":[144],"others.":[146],"To":[147],"realize":[148],"idea,":[150],"we":[151],"enhance":[152],"tokenization":[155],"architecture":[158],"BERT":[161],"model,":[162],"construct":[163],"utilize":[165],"masks,":[167],"introduce":[169],"pre-training":[172,282],"algorithm.":[173],"this":[176],"BERT-like":[177],"from":[179,225],"scratch,":[180],"using":[181],"dataset":[183],"26":[185],"million":[186],"stripped":[187],"binary":[188,207],"functions":[189],"with":[190],"explicit":[191],"information":[194],"extracted":[195],"by":[196],"our":[197],"tool.":[198],"apply":[200],"three":[204],"downstream":[205],"tasks:":[206],"similarity,":[208],"type":[209],"inference,":[210],"malware":[212],"family":[213],"classification.":[214],"Our":[215],"pre-trained":[216],"can":[218],"improve":[219],"SOTAs":[221],"tasks":[224],"<mml:math":[226,235,247,257,266],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[227,236,248,258,267],"display=\"inline\">":[228,237,249,259,268],"<mml:mrow>":[229,238,250,260,269],"<mml:mn>53</mml:mn>":[230],"<mml:mtext>%</mml:mtext>":[231,240,243,252,262,271],"</mml:mrow>":[232,244,253,263,272],"</mml:math>":[233,245,254,264,273],"<mml:mn>64</mml:mn>":[239],"<mml:mo>,</mml:mo>":[241],"<mml:mn>49</mml:mn>":[242],"<mml:mn>60</mml:mn>":[251],",":[255,274],"<mml:mn>74</mml:mn>":[261],"<mml:mn>94</mml:mn>":[270],"respectively.":[275],"It":[276],"also":[277],"substantially":[278],"outperforms":[279],"other":[280],"techniques":[283],"understanding":[286],"models.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}