{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:54:53Z","timestamp":1773708893471,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CCF-Huawei Populus Grove Fund"},{"name":"Huawei-NJU Creative Laboratory for the Next Programming"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,24]]},"DOI":"10.1145\/3671016.3672580","type":"proceedings-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T20:19:32Z","timestamp":1721247572000},"page":"41-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An Empirical Study on Code Search Pre-trained Models: Academic Progresses vs. Industry Requirements"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6639-4128","authenticated-orcid":false,"given":"Kuo","family":"Chi","sequence":"first","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9270-5072","authenticated-orcid":false,"given":"Chuanyi","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-0942","authenticated-orcid":false,"given":"Jidong","family":"Ge","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1102-9584","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510049"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3340458"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527917"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450127"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xuanang Chen Jian Luo Ben He Le\u00a0Sun 0001 and Yingfei Sun. 2022. Towards Robust Dense Retrieval via Local Ranking Alignment.. In IJCAI. 1980\u20131986.","DOI":"10.24963\/ijcai.2022\/275"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3565971"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616356"},{"key":"e_1_3_2_1_9_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Fatos T\u00a0Yarman Vural, and Kyunghyun Cho","author":"Firat Orhan","year":"2016","unstructured":"Orhan Firat, Baskaran Sankaran, Yaser Al-Onaizan, Fatos T\u00a0Yarman Vural, and Kyunghyun Cho. 2016. Zero-resource translation with multi-lingual neural machine translation. arXiv preprint arXiv:1606.04164 (2016)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180167"},{"key":"e_1_3_2_1_12_1","volume-title":"Unixcoder: Unified cross-modal pre-training for code representation. arXiv preprint arXiv:2203.03850","author":"Guo Daya","year":"2022","unstructured":"Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, and Jian Yin. 2022. Unixcoder: Unified cross-modal pre-training for code representation. arXiv preprint arXiv:2203.03850 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)."},{"key":"e_1_3_2_1_14_1","volume-title":"On the effectiveness of adapter-based tuning for pretrained language model adaptation. arXiv preprint arXiv:2106.03164","author":"He Ruidan","year":"2021","unstructured":"Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jia-Wei Low, Lidong Bing, and Luo Si. 2021. On the effectiveness of adapter-based tuning for pretrained language model adaptation. arXiv preprint arXiv:2106.03164 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2011.6100115"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 2790\u20132799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De\u00a0Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678927"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of NAACL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604905"},{"key":"e_1_3_2_1_20_1","volume-title":"Exploring representation-level augmentation for code search. arXiv preprint arXiv:2210.12285","author":"Li Haochen","year":"2022","unstructured":"Haochen Li, Chunyan Miao, Cyril Leung, Yanxian Huang, Yuan Huang, Hongyu Zhang, and Yanlin Wang. 2022. Exploring representation-level augmentation for code search. arXiv preprint arXiv:2210.12285 (2022)."},{"key":"e_1_3_2_1_21_1","volume-title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search. arXiv preprint arXiv:2401.04514","author":"Li Haochen","year":"2024","unstructured":"Haochen Li, Xin Zhou, and Zhiqi Shen. 2024. Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search. arXiv preprint arXiv:2401.04514 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Rethinking negative pairs in code search. arXiv preprint arXiv:2310.08069","author":"Li Haochen","year":"2023","unstructured":"Haochen Li, Xin Zhou, Luu\u00a0Anh Tuan, and Chunyan Miao. 2023. Rethinking negative pairs in code search. arXiv preprint arXiv:2310.08069 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389278"},{"key":"e_1_3_2_1_24_1","first-page":"1","article-title":"Opportunities and challenges in code search tools","volume":"54","author":"Liu Chao","year":"2021","unstructured":"Chao Liu, Xin Xia, David Lo, Cuiyun Gao, Xiaohu Yang, and John Grundy. 2021. Opportunities and challenges in code search tools. ACM Computing Surveys (CSUR) 54, 9 (2021), 1\u201340.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00181"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep learning meets software engineering: A survey on pre-trained models of source code. arXiv preprint arXiv:2205.11739","author":"Niu Changan","year":"2022","unstructured":"Changan Niu, Chuanyi Li, Bin Luo, and Vincent Ng. 2022. Deep learning meets software engineering: A survey on pre-trained models of source code. arXiv preprint arXiv:2205.11739 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00180"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510096"},{"key":"e_1_3_2_1_29_1","volume-title":"Comparing the Pretrained Models of Source Code by Re-pretraining Under a Unified Setup","author":"Niu Changan","year":"2023","unstructured":"Changan Niu, Chuanyi Li, Vincent Ng, and Bin Luo. 2023. Comparing the Pretrained Models of Source Code by Re-pretraining Under a Unified Setup. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00055"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196425"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786855"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCITECHN.2016.7860264"},{"key":"e_1_3_2_1_34_1","volume-title":"CoCoSoDa: Effective Contrastive Learning for Code Search. arXiv preprint arXiv:2204.03293","author":"Shi Ensheng","year":"2022","unstructured":"Ensheng Shi, Yanlin Wang, Wenchao Gu, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, and Hongbin Sun. 2022. CoCoSoDa: Effective Contrastive Learning for Code Search. arXiv preprint arXiv:2204.03293 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598036"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389269"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3561165"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-C.2017.90"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00012"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510050"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00013"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510062"},{"key":"e_1_3_2_1_43_1","volume-title":"Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query expansion with large language models. arXiv preprint arXiv:2303.07678 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859","author":"Wang Yue","year":"2021","unstructured":"Yue Wang, Weishi Wang, Shafiq Joty, and Steven\u00a0CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510146"},{"key":"e_1_3_2_1_46_1","volume-title":"security, privacy, explainability, efficiency, and usability of large language models for code. arXiv preprint arXiv:2403.07506","author":"Yang Zhou","year":"2024","unstructured":"Zhou Yang, Zhensu Sun, Terry\u00a0Zhuo Yue, Premkumar Devanbu, and David Lo. 2024. Robustness, security, privacy, explainability, efficiency, and usability of large language models for code. arXiv preprint arXiv:2403.07506 (2024)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3546066"},{"key":"e_1_3_2_1_48_1","volume-title":"Code Search Debiasing: Improve Search Results beyond Overall Ranking Performance. arXiv preprint arXiv:2311.14901","author":"Zhang Sheng","year":"2023","unstructured":"Sheng Zhang, Hui Li, Yanlin Wang, Zhao Wei, Yong Xiu, Juhong Wang, and Rongong Ji. 2023. Code Search Debiasing: Improve Search Results beyond Overall Ranking Performance. arXiv preprint arXiv:2311.14901 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00044"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531951"},{"key":"e_1_3_2_1_51_1","volume-title":"Data augmentation approaches for source code models: A survey. arXiv preprint arXiv:2305.19915","author":"Zhuo Terry\u00a0Yue","year":"2023","unstructured":"Terry\u00a0Yue Zhuo, Zhou Yang, Zhensu Sun, Yufei Wang, Li Li, Xiaoning Du, Zhenchang Xing, and David Lo. 2023. Data augmentation approaches for source code models: A survey. arXiv preprint arXiv:2305.19915 (2023)."}],"event":{"name":"Internetware 2024: 15th Asia-Pacific Symposium on Internetware","location":"Macau China","acronym":"Internetware 2024","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 15th Asia-Pacific Symposium on Internetware"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671016.3672580","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3671016.3672580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:36:17Z","timestamp":1755909377000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3671016.3672580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,24]]},"references-count":51,"alternative-id":["10.1145\/3671016.3672580","10.1145\/3671016"],"URL":"https:\/\/doi.org\/10.1145\/3671016.3672580","relation":{},"subject":[],"published":{"date-parts":[[2024,7,24]]},"assertion":[{"value":"2024-07-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}