{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T14:48:44Z","timestamp":1778770124391,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"European Union’s Horizon Research and Innovation Programme"},{"name":"Project LAZARUS","award":["101070303"],"award-info":[{"award-number":["101070303"]}]},{"DOI":"10.13039\/501100001866","name":"Luxembourg National Research Funds","doi-asserted-by":"publisher","award":["C18\/IS\/12669767\/STELLAR\/LeTraon"],"award-info":[{"award-number":["C18\/IS\/12669767\/STELLAR\/LeTraon"]}],"id":[{"id":"10.13039\/501100001866","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tse.2024.3376964","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:11:04Z","timestamp":1710357064000},"page":"1080-1095","source":"Crossref","is-referenced-by-count":9,"title":["Active Code Learning: Benchmarking Sample-Efficient Training of Code Models"],"prefix":"10.1109","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8251-1669","authenticated-orcid":false,"given":"Qiang","family":"Hu","sequence":"first","affiliation":[{"name":"University of Luxembourg, Belval, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-2420","authenticated-orcid":false,"given":"Yuejun","family":"Guo","sequence":"additional","affiliation":[{"name":"Luxembourg Institute of Science and Technology, Belval, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-6502","authenticated-orcid":false,"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8312-1358","authenticated-orcid":false,"given":"Maxime","family":"Cordy","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Belval, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8621-2420","authenticated-orcid":false,"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1852-2547","authenticated-orcid":false,"given":"Mike","family":"Papadakis","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Belval, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1045-4861","authenticated-orcid":false,"given":"Yves Le","family":"Traon","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Belval, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2017.46"},{"key":"ref4","article-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhou","year":"2019"},{"key":"ref5","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Syst. Demonstrations","author":"Wolf","year":"2020"},{"key":"ref6","article-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref7","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sener","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613855"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678672"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.66"},{"key":"ref12","article-title":"Active code learning","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889457"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397357"},{"key":"ref15","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal","year":"2017"},{"key":"ref16","first-page":"650","article-title":"Active learning by acquiring contrastive examples","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Margatina","year":"2021"},{"key":"ref17","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ash","year":"2020"},{"key":"ref18","first-page":"1536","article-title":"CodeBERT: A pre-trained model for programming and natural languages","volume-title":"Proc. Findings Assoc. Comput. Linguistics (EMNLP)","author":"Feng","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref20","article-title":"GraphCodeBERT: Pre-training code representations with data flow","author":"Guo","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ase56229.2023.00149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510146"},{"key":"ref23","first-page":"8696","article-title":"CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wang","year":"2021"},{"key":"ref24","article-title":"CodeNet: A large-scale AI for code dataset for learning a diversity of coding tasks","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS) Track Datasets Benchmarks","author":"Puri","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"ref26","article-title":"Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhou","year":"2019"},{"key":"ref27","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021"},{"key":"ref28","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"issue":"1","key":"ref29","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238206"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2307\/2283156"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3511598"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556903"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.859"},{"key":"ref35","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref36","article-title":"An empirical study on the efficacy of deep active learning for image classification","author":"Li","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07812-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.105"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9587-0"},{"key":"ref40","first-page":"2904","article-title":"Deep Bayesian active learning for natural language processing: Results of a large-scale empirical study","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Siddhant","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0469-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468611"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00180"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00188"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00206"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00181"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-NIER58687.2023.00007"},{"key":"ref49","first-page":"4936","article-title":"Impact of evaluation methodologies on code summarization","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","volume":"1","author":"Nie","year":"2022"},{"key":"ref50","article-title":"Is ChatGPT the ultimate programming assistant\u2014How far is it?","author":"Tian","year":"2023"},{"key":"ref51","article-title":"Automatic code summarization via ChatGPT: How far are we?","author":"Sun","year":"2023"},{"key":"ref52","article-title":"A new era in software security: Towards self-healing software via large language models and formal verification","author":"Charalambous","year":"2023"},{"key":"ref53","article-title":"Keep the conversation going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","author":"Xia","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598067"},{"key":"ref55","article-title":"The scope of ChatGPT in software engineering: A thorough investigation","author":"Ma","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01718-6_6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-016-0918-z"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.02.053"},{"key":"ref59","article-title":"A unified active learning framework for annotating graph data with application to software source code performance prediction","author":"Samoaa","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.060"},{"key":"ref61","first-page":"3:1","article-title":"COLA-Gen: Active learning techniques for automatic code generation of benchmarks","volume-title":"Proc. 13th Workshop Parallel Program. Run-Time Manage. Techn. Many-Core Archit.\/11th Workshop Des. Tools Archit. Multicore Embedded Comput. Platforms (PARMA-DITAM)","author":"Berezov","year":"2022"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/32\/10531114\/10471610.pdf?arnumber=10471610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T04:54:11Z","timestamp":1715835251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10471610\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":61,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tse.2024.3376964","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}