{"id":"https://openalex.org/W4308641647","doi":"https://doi.org/10.1145/3540250.3549145","title":"Are we building on the rock? on the importance of data preprocessing for code summarization","display_name":"Are we building on the rock? on the importance of data preprocessing for code summarization","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308641647","doi":"https://doi.org/10.1145/3540250.3549145"},"language":"en","primary_location":{"id":"doi:10.1145/3540250.3549145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549145","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549145","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549145","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014381743","display_name":"Lin Shi","orcid":"https://orcid.org/0000-0003-1476-7213"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Shi","raw_affiliation_strings":["Institute of Software at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028315053","display_name":"Fangwen Mu","orcid":"https://orcid.org/0000-0001-8577-7932"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangwen Mu","raw_affiliation_strings":["Institute of Software at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373745","display_name":"Xiaohong Chen","orcid":"https://orcid.org/0000-0002-9797-8384"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Institute of Software at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326210","display_name":"Song Wang","orcid":"https://orcid.org/0000-0002-8224-0424"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Song Wang","raw_affiliation_strings":["York University, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108814327","display_name":"Junjie Wang","orcid":"https://orcid.org/0000-0002-9941-6713"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["Institute of Software at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925551","display_name":"Ye Yang","orcid":"https://orcid.org/0000-0002-5571-9747"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Yang","raw_affiliation_strings":["Stevens Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447691","display_name":"Ge Li","orcid":"https://orcid.org/0000-0003-0140-0949"},"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":"Ge Li","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["Huawei, China"],"affiliations":[{"raw_affiliation_string":"Huawei, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103567145","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0004-8834-957X"},"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Institute of Software at Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software at Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5014381743"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":5.3219,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96709062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10260","display_name":"Software Engineering Research","score":0.9970999956130981,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9602741599082947},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8918141722679138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8660067319869995},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7857900857925415},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6943453550338745},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6500382423400879},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5932981967926025},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5364388227462769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42560920119285583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4201776087284088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013410806655884},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06282681226730347}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9602741599082947},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8918141722679138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660067319869995},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7857900857925415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6943453550338745},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6500382423400879},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5932981967926025},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5364388227462769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42560920119285583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4201776087284088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013410806655884},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06282681226730347},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3540250.3549145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549145","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549145","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3540250.3549145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3540250.3549145","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3540250.3549145","source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1292274175","display_name":null,"funder_award_id":"B14034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1303213773","display_name":null,"funder_award_id":"2018YFB1403400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1581568102","display_name":null,"funder_award_id":"62072442","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1599553943","display_name":null,"funder_award_id":"B14034","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1866959750","display_name":null,"funder_award_id":"614220920020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G204947145","display_name":"CRII: CHS: Collaboratively Perceiving, Comprehending, and Projecting into the Future: Supporting Team Situational Awareness with Adaptive Collaborative Tactons","funder_award_id":"2002348","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3194369973","display_name":null,"funder_award_id":"62002348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5515744711","display_name":"IAA for special issuance passports.","funder_award_id":"1802374","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5848258319","display_name":null,"funder_award_id":"0 and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6258415954","display_name":null,"funder_award_id":"Chinese","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6688104968","display_name":null,"funder_award_id":"620023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7761914512","display_name":null,"funder_award_id":"61802374","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308641647.pdf","grobid_xml":"https://content.openalex.org/works/W4308641647.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1956340063","https://openalex.org/W2018844270","https://openalex.org/W2034209539","https://openalex.org/W2036740395","https://openalex.org/W2070111972","https://openalex.org/W2081749632","https://openalex.org/W2082160726","https://openalex.org/W2395955025","https://openalex.org/W2402619042","https://openalex.org/W2516621648","https://openalex.org/W2547106995","https://openalex.org/W2747329762","https://openalex.org/W2884276923","https://openalex.org/W2888312537","https://openalex.org/W2888557792","https://openalex.org/W2888651608","https://openalex.org/W2930957955","https://openalex.org/W2949297108","https://openalex.org/W2964322208","https://openalex.org/W2979792666","https://openalex.org/W2990259449","https://openalex.org/W3008733198","https://openalex.org/W3011632945","https://openalex.org/W3016234956","https://openalex.org/W3086449553","https://openalex.org/W3086831424","https://openalex.org/W3091730360","https://openalex.org/W3099636232","https://openalex.org/W3103748122","https://openalex.org/W3131328028","https://openalex.org/W3159559013","https://openalex.org/W3161997752","https://openalex.org/W3167948855","https://openalex.org/W3173493489","https://openalex.org/W3176248591","https://openalex.org/W3177492177","https://openalex.org/W3184008713","https://openalex.org/W3186816466","https://openalex.org/W3195727321","https://openalex.org/W3214739505","https://openalex.org/W4205596491","https://openalex.org/W4206070857","https://openalex.org/W4237993802","https://openalex.org/W4246945666","https://openalex.org/W4249122235","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W4399363378","https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021"],"abstract_inverted_index":{"Code":[0],"summarization,":[1],"the":[2,9,18,38,41,49,58,69,108,113,117,123,133,139,171,179,197],"task":[3],"of":[4,14,17,40,71,116,135,141,173,188],"generating":[5],"useful":[6],"comments":[7],"given":[8],"code,":[10],"has":[11],"long":[12],"been":[13],"interest.":[15],"Most":[16],"existing":[19,102],"code":[20,29,78,142,174,192],"summarization":[21,79,143,193],"models":[22],"are":[23],"trained":[24],"and":[25,67,160,181,195,202],"validated":[26],"on":[27,122,138,170],"widely-used":[28],"comment":[30],"benchmark":[31,42,50,73,103,119,158],"datasets.":[32,104],"However,":[33],"little":[34],"is":[35],"known":[36],"about":[37],"quality":[39,70,115,190],"datasets":[43,51,74],"built":[44],"from":[45,101],"real-world":[46],"projects.":[47],"Are":[48],"as":[52,54],"good":[53],"expected?":[55],"To":[56],"bridge":[57],"gap,":[59],"we":[60,82,106,127],"conduct":[61,128],"a":[62,167,185],"systematic":[63],"research":[64,201],"to":[65,110,131,166],"assess":[66,112],"improve":[68],"four":[72,118,157],"widely":[75,153],"used":[76],"for":[77,199],"tasks.":[80],"First,":[81],"propose":[83],"an":[84],"automated":[85],"code-comment":[86],"cleaning":[87],"tool":[88,109],"that":[89,148,178],"can":[90],"accurately":[91],"detect":[92],"noisy":[93,136,163],"data":[94,98,114,137,150,164,189],"caused":[95],"by":[96],"inappropriate":[97],"preprocessing":[99,151],"operations":[100],"Then,":[105],"apply":[107],"further":[111],"datasets,":[120,159],"based":[121],"detected":[124],"noises.":[125],"Finally,":[126],"comparative":[129],"experiments":[130],"investigate":[132],"impact":[134],"performance":[140,172],"models.":[144],"The":[145],"results":[146],"show":[147],"these":[149,162],"noises":[152],"exist":[154],"in":[155,191],"all":[156],"removing":[161],"leads":[165],"significant":[168],"improvement":[169],"summarization.":[175],"We":[176],"believe":[177],"findings":[180],"insights":[182],"will":[183],"enable":[184],"better":[186],"understanding":[187],"tasks,":[194],"pave":[196],"way":[198],"relevant":[200],"practice.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
