{"id":"https://openalex.org/W4386590753","doi":"https://doi.org/10.1109/tnnls.2023.3308595","title":"Comparing the Pretrained Models of Source Code by Re-pretraining Under a Unified Setup","display_name":"Comparing the Pretrained Models of Source Code by Re-pretraining Under a Unified Setup","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590753","doi":"https://doi.org/10.1109/tnnls.2023.3308595","pmid":"https://pubmed.ncbi.nlm.nih.gov/37695950"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3308595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3308595","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5061689324","display_name":"Changan Niu","orcid":"https://orcid.org/0000-0003-4358-5451"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changan Niu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053034433","display_name":"Chuanyi Li","orcid":"https://orcid.org/0000-0003-4956-8142"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyi Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4956-8142","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732054","display_name":"Vincent Ng","orcid":"https://orcid.org/0000-0001-8237-429X"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Ng","raw_affiliation_strings":["Human Language Technology Research Institute, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8237-429X","affiliations":[{"raw_affiliation_string":"Human Language Technology Research Institute, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Luo","orcid":"https://orcid.org/0009-0001-1102-9584"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Luo","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-1102-9584","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]},{"raw_affiliation_string":"Software Institute, State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1568,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90112514,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"12","first_page":"17768","last_page":"17778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.98580002784729,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9470999836921692,"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":0.8099377751350403},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7502747774124146},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6843445301055908},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6273139715194702},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5535680055618286},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5359789729118347},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5259109735488892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220665335655212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4863934814929962},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4194122552871704},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3607771098613739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3437789976596832},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1216057538986206},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07179847359657288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099377751350403},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7502747774124146},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6843445301055908},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6273139715194702},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5535680055618286},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5359789729118347},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5259109735488892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220665335655212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4863934814929962},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4194122552871704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3607771098613739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3437789976596832},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1216057538986206},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07179847359657288},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3308595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3308595","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37695950","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37695950","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4931251985","display_name":null,"funder_award_id":"2034508","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6607556526","display_name":null,"funder_award_id":"61802167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2065053490","https://openalex.org/W2160204597","https://openalex.org/W2282866165","https://openalex.org/W2533695286","https://openalex.org/W2896457183","https://openalex.org/W2962936887","https://openalex.org/W2972082064","https://openalex.org/W3093464584","https://openalex.org/W3098605233","https://openalex.org/W3161997752","https://openalex.org/W3170092793","https://openalex.org/W3170962973","https://openalex.org/W3173450168","https://openalex.org/W3176015924","https://openalex.org/W3176724752","https://openalex.org/W3183962691","https://openalex.org/W3198685994","https://openalex.org/W4225407062","https://openalex.org/W4253028564","https://openalex.org/W4284697810","https://openalex.org/W4385245566","https://openalex.org/W4385573867","https://openalex.org/W6757817989","https://openalex.org/W6767260250","https://openalex.org/W6768003788","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6772110955","https://openalex.org/W6778883912","https://openalex.org/W6779580516","https://openalex.org/W6779877867","https://openalex.org/W6783227185","https://openalex.org/W6783958930","https://openalex.org/W6784593087","https://openalex.org/W6787895855","https://openalex.org/W6790588633","https://openalex.org/W6790913202","https://openalex.org/W6795460807","https://openalex.org/W6796120359","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4386977688","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,20,56],"seen":[3,41],"the":[4,22,36,87,107,115,122,148,157,180],"successful":[5],"application":[6],"of":[7,11,24,54,109,162,183],"large":[8],"pretrained":[9],"models":[10],"source":[12],"code":[13,16],"(CodePTMs)":[14],"to":[15,31,99,105,168],"representation":[17],"learning,":[18],"which":[19],"taken":[21],"field":[23],"software":[25],"engineering":[26],"(SE)":[27],"from":[28],"task-specific":[29],"solutions":[30],"task-agnostic":[32],"generic":[33],"models.":[34],"By":[35],"remarkable":[37],"results,":[38],"CodePTMs":[39,55,104,120],"are":[40,60],"as":[42,72,131],"a":[43,52,96,153],"promising":[44],"direction":[45],"in":[46,68,91],"both":[47],"academia":[48],"and":[49,79,94,128,134,151,160,178],"industry.":[50],"While":[51],"number":[53],"been":[57],"proposed,":[58],"they":[59,66,132],"often":[61],"not":[62],"directly":[63],"comparable":[64],"because":[65],"differ":[67],"experimental":[69,88,149],"setups":[70],"such":[71],"pretraining":[73,111,129,164],"dataset,":[74],"model":[75,124,137],"size,":[76],"evaluation":[77,140],"tasks,":[78,130],"datasets.":[80],"In":[81],"this":[82],"article,":[83],"we":[84,118,146],"first":[85],"review":[86],"setup":[89,98],"used":[90],"previous":[92],"work":[93],"propose":[95],"standardized":[97,116],"facilitate":[100],"fair":[101],"comparisons":[102],"among":[103],"explore":[106],"impacts":[108],"their":[110],"tasks.":[112],"Then,":[113],"under":[114],"setup,":[117],"re-pretrain":[119],"using":[121],"same":[123],"architecture,":[125],"input":[126],"modalities,":[127],"declared":[133],"fine-tune":[135],"each":[136,139,169],"on":[138,156],"SE":[141,170],"task":[142],"for":[143],"evaluating.":[144],"Finally,":[145],"present":[147],"results":[150],"make":[152],"comprehensive":[154],"discussion":[155],"relative":[158],"strength":[159],"weakness":[161],"different":[163],"tasks":[165],"with":[166],"respect":[167],"task.":[171],"We":[172],"hope":[173],"our":[174],"view":[175],"can":[176],"inspire":[177],"advance":[179],"future":[181],"study":[182],"more":[184],"powerful":[185],"CodePTMs.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}