{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T10:44:38Z","timestamp":1773917078026,"version":"3.50.1"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["H53D23003520006"],"award-info":[{"award-number":["H53D23003520006"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["PE00000014"],"award-info":[{"award-number":["PE00000014"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["H73C22000890001"],"award-info":[{"award-number":["H73C22000890001"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["B43C22000750006"],"award-info":[{"award-number":["B43C22000750006"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems and Software"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jss.2025.112729","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T16:11:58Z","timestamp":1765296718000},"page":"112729","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Peeking inside the black box: Training data exposure in code language models"],"prefix":"10.1016","volume":"234","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6904-6184","authenticated-orcid":false,"given":"Angelica","family":"Spina","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8860-1739","authenticated-orcid":false,"given":"Marco","family":"Russodivito","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1764-9685","authenticated-orcid":false,"given":"Simone","family":"Scalabrino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7995-8582","authenticated-orcid":false,"given":"Rocco","family":"Oliveto","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jss.2025.112729_bib0001","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi","year":"2016"},{"key":"10.1016\/j.jss.2025.112729_bib0002","series-title":"Proceedings of the IEEE\/ACM 46Th International Conference on Software Engineering","first-page":"1","article-title":"Automatic semantic augmentation of language model prompts (for code summarization)","author":"Ahmed","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0003","series-title":"IEEE\/ACM International Conference on Software Engineering (ICSE)","first-page":"1","article-title":"Traces of memorisation in large language models for code","author":"Al-Kaswan","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0004","series-title":"Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization","first-page":"65","article-title":"Meteor: an automatic metric for mt evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.jss.2025.112729_bib0005","unstructured":"Bouzenia, I., Devanbu, P., Pradel, M., 2024. Repairagent: An autonomous, llm-based agent for program repair. arXiv preprint arXiv: 2403.17134."},{"key":"10.1016\/j.jss.2025.112729_bib0006","unstructured":"Bucher, M. J. J., Martini, M., 2024. Fine-tuned\u2019small\u2019LLMs (still) significantly outperform zero-shot generative AI models in text classification. arXiv preprint arXiv: 2406.08660."},{"key":"10.1016\/j.jss.2025.112729_bib0007","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"16178","article-title":"Knowledge-enriched distributional model inversion attacks","author":"Chen","year":"2021"},{"key":"10.1016\/j.jss.2025.112729_bib0008","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"23669","article-title":"Security attacks on LLM-based code completion tools","volume":"Vol. 39","author":"Cheng","year":"2025"},{"key":"10.1016\/j.jss.2025.112729_bib0009","series-title":"International Colloquium on Automata, Languages, and Programming","first-page":"1","article-title":"Differential privacy","author":"Dwork","year":"2006"},{"key":"10.1016\/j.jss.2025.112729_bib0010","series-title":"International Conference on Theory and Applications of Models of Computation","first-page":"1","article-title":"Differential privacy: a survey of results","author":"Dwork","year":"2008"},{"key":"10.1016\/j.jss.2025.112729_bib0011","unstructured":"Fang, H., Qiu, Y., Yu, H., Yu, W., Kong, J., Chong, B., Chen, B., Wang, X., Xia, S.-T., Xu, K., 2024. Privacy leakage on dnns: A survey of model inversion attacks and defenses. arXiv preprint arXiv: 2402.04013."},{"key":"10.1016\/j.jss.2025.112729_bib0012","series-title":"ACM SIGSAC Conference on Computer and Communications Security (CCS)","first-page":"1322","article-title":"Model inversion attacks that exploit confidence information and basic countermeasures","author":"Fredrikson","year":"2015"},{"key":"10.1016\/j.jss.2025.112729_bib0013","series-title":"USENIX Security Symposium","first-page":"17","article-title":"Privacy in pharmacogenetics: an {End-to-End} case study of personalized warfarin dosing","author":"Fredrikson","year":"2014"},{"key":"10.1016\/j.jss.2025.112729_bib0014","series-title":"2018 IEEE Conference on Decision and Control (CDC)","first-page":"184","article-title":"Privacy-preserving distributed learning via obfuscated stochastic gradients","author":"Gade","year":"2018"},{"issue":"6","key":"10.1016\/j.jss.2025.112729_bib0015","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TBDATA.2023.3239116","article-title":"Improved gradient inversion attacks and defenses in federated learning","volume":"10","author":"Geng","year":"2023","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.jss.2025.112729_bib0016","series-title":"International Conference on Machine Learning","first-page":"201","article-title":"Cryptonets: applying neural networks to encrypted data with high throughput and accuracy","author":"Gilad-Bachrach","year":"2016"},{"key":"10.1016\/j.jss.2025.112729_bib0017","doi-asserted-by":"crossref","first-page":"4475","DOI":"10.1109\/TIFS.2023.3295944","article-title":"A gan-based defense framework against model inversion attacks","volume":"18","author":"Gong","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.jss.2025.112729_bib0018","unstructured":"Guo, D., Zhu, Q., Yang, D., Xie, Z., Dong, K., Zhang, W., Chen, G., Bi, X., Wu, Y., Li, Y. K., et al., 2024. Deepseek-coder: When the large language model meets programming\u2013the rise of code intelligence. arXiv preprint arXiv: 2401.14196."},{"key":"10.1016\/j.jss.2025.112729_bib0019","series-title":"2019 International Conference on Advanced Computing and Applications (ACOMP)","first-page":"97","article-title":"Differential privacy in deep learning: an overview","author":"Ha","year":"2019"},{"key":"10.1016\/j.jss.2025.112729_bib0020","unstructured":"Haldar, R., Hockenmaier, J., 2024. Analyzing the performance of large language models on code summarization. arXiv preprint arXiv: 2404.08018."},{"key":"10.1016\/j.jss.2025.112729_bib0021","unstructured":"Hassid, M., Remez, T., Gehring, J., Schwartz, R., Adi, Y., 2024. The larger the better? improved llm code-generation via budget reallocation. arXiv preprint arXiv: 2404.00725."},{"issue":"4","key":"10.1016\/j.jss.2025.112729_bib0022","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1111\/ijsa.12479","article-title":"The performance of large language models on quantitative and verbal ability tests: initial evidence and implications for unproctored high-stakes testing","volume":"32","author":"Hickman","year":"2024","journal-title":"Int. J. Select. Assess."},{"key":"10.1016\/j.jss.2025.112729_bib0023","series-title":"ACM SIGSAC Conference on Computer and Communications Security (CCS)","first-page":"603","article-title":"Deep models under the GAN: information leakage from collaborative deep learning","author":"Hitaj","year":"2017"},{"issue":"8","key":"10.1016\/j.jss.2025.112729_bib0024","doi-asserted-by":"crossref","DOI":"10.1002\/advs.202412279","article-title":"Comparing large language models and human programmers for generating programming code","volume":"12","author":"Hou","year":"2025","journal-title":"Adv. Sci."},{"key":"10.1016\/j.jss.2025.112729_bib0025","series-title":"IEEE\/ACM International Conference on Program Comprehension (ICPC)","first-page":"200","article-title":"Deep code comment generation","author":"Hu","year":"2018"},{"key":"10.1016\/j.jss.2025.112729_bib0026","series-title":"International Joint Conference on Artificial Intelligence (IJCAI)","first-page":"2269-2275","article-title":"Summarizing source code with transferred api knowledge","author":"Hu","year":"2018"},{"key":"10.1016\/j.jss.2025.112729_bib0027","unstructured":"Husain, H., Wu, H.-H., Gazit, T., Allamanis, M., Brockschmidt, M., 2019. Codesearchnet challenge: evaluating the state of semantic code search. preprint (arXiv: 1909.09436)."},{"key":"10.1016\/j.jss.2025.112729_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15045","article-title":"Label-only model inversion attacks via boundary repulsion","author":"Kahla","year":"2022"},{"key":"10.1016\/j.jss.2025.112729_bib0029","first-page":"27469","article-title":"Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense","volume":"36","author":"Krishna","year":"2023","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.jss.2025.112729_bib0030","series-title":"2019 IEEE\/ACM 41St International Conference on Software Engineering (ICSE)","first-page":"795","article-title":"A neural model for generating natural language summaries of program subroutines","author":"LeClair","year":"2019"},{"key":"10.1016\/j.jss.2025.112729_bib0031","doi-asserted-by":"crossref","unstructured":"Lepagnol, P., Gerald, T., Ghannay, S., Servan, C., Rosset, S., 2024. Small language models are good too: an empirical study of zero-shot classification. arXiv preprint arXiv: 2404.11122.","DOI":"10.63317\/2ez6qsknsvwe"},{"key":"10.1016\/j.jss.2025.112729_bib0032","doi-asserted-by":"crossref","unstructured":"Li, H., Xu, M., Song, Y., 2023. Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence. arXiv preprint arXiv: 2305.03010.","DOI":"10.18653\/v1\/2023.findings-acl.881"},{"key":"10.1016\/j.jss.2025.112729_bib0033","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.jss.2025.112729_bib0034","unstructured":"Liu, F., Liu, Y., Shi, L., Huang, H., Wang, R., Yang, Z., Zhang, L., Li, Z., Ma, Y., 2024. Exploring and evaluating hallucinations in llm-powered code generation. arXiv preprint arXiv: 2404.00971."},{"key":"10.1016\/j.jss.2025.112729_bib0035","unstructured":"Liu, Y., Deng, G., Li, Y., Wang, K., Wang, Z., Wang, X., Zhang, T., Liu, Y., Wang, H., Zheng, Y., et al., 2023. Prompt injection attack against LLM-integrated applications. arXiv preprint arXiv: 2306.05499."},{"key":"10.1016\/j.jss.2025.112729_bib0036","first-page":"124069","article-title":"Llm dataset inference: did you train on my dataset?","volume":"37","author":"Maini","year":"2024","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.jss.2025.112729_bib0037","series-title":"2021 IEEE\/ACM 43Rd International Conference on Software Engineering (ICSE)","first-page":"336","article-title":"Studying the usage of text-to-text transfer transformer to support code-related tasks","author":"Mastropaolo","year":"2021"},{"key":"10.1016\/j.jss.2025.112729_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16384","article-title":"Re-thinking model inversion attacks against deep neural networks","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.jss.2025.112729_bib0039","series-title":"2021 36Th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","first-page":"253","article-title":"Adversarial attacks to api recommender systems: time to wake up and smell the coffee?","author":"Nguyen","year":"2021"},{"key":"10.1016\/j.jss.2025.112729_bib0040","series-title":"Annual Meeting of the Association for Computational Linguistics (ACL)","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.jss.2025.112729_bib0041","series-title":"Proceedings of the 28Th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1358","article-title":"Bilateral dependency optimization: defending against model-inversion attacks","author":"Peng","year":"2022"},{"key":"10.1016\/j.jss.2025.112729_bib0042","series-title":"GLOBECOM 2020-2020 IEEE Global Communications Conference","first-page":"1","article-title":"Privacy preserving facial recognition against model inversion attacks","author":"Prakash","year":"2020"},{"issue":"1","key":"10.1016\/j.jss.2025.112729_bib0043","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. (JMLR)"},{"key":"10.1016\/j.jss.2025.112729_bib0044","unstructured":"Ren, S., Guo, D., Lu, S., Zhou, L., Liu, S., Tang, D., Sundaresan, N., Zhou, M., Blanco, A., Ma, S., 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv: 2009.10297."},{"issue":"4","key":"10.1016\/j.jss.2025.112729_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3624010","article-title":"A survey of privacy attacks in machine learning","volume":"56","author":"Rigaki","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.jss.2025.112729_bib0046","series-title":"International Conference on the Quality of Information and Communications Technology","first-page":"391","article-title":"Black-box reconstruction attacks on LLMs: a preliminary study in code summarization","author":"Russodivito","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0047","doi-asserted-by":"crossref","unstructured":"Salerno, F., Al-Kaswan, A., Izadi, M., 2025. How much do code language models remember? an investigation on data extraction attacks before and after fine-tuning. arXiv preprint arXiv: 2501.17501.","DOI":"10.1109\/MSR66628.2025.00080"},{"key":"10.1016\/j.jss.2025.112729_bib0048","series-title":"Proceedings of the 30Th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"107","article-title":"Are we building on the rock? on the importance of data preprocessing for code summarization","author":"Shi","year":"2022"},{"key":"10.1016\/j.jss.2025.112729_bib0049","series-title":"Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security","first-page":"377","article-title":"Information leakage in embedding models","author":"Song","year":"2020"},{"key":"10.1016\/j.jss.2025.112729_bib0050","unstructured":"Spina, A., Russodivito, M., Scalabrino, S., Oliveto, R., 2025. Replication package of \u201dPeeking inside the black box: training data exposure in code language models\u201d. https:\/\/figshare.com\/s\/cde6e04ec67f24fc3ee5."},{"key":"10.1016\/j.jss.2025.112729_bib0051","unstructured":"Struppek, L., Hintersdorf, D., Kersting, K., 2023. Be careful what you smooth for: Label smoothing can be a privacy shield but also a catalyst for model inversion attacks. arXiv preprint arXiv: 2310.06549."},{"key":"10.1016\/j.jss.2025.112729_bib0052","series-title":"2025 IEEE\/ACM 47Th International Conference on Software Engineering (ICSE)","first-page":"419","article-title":"Source code summarization in the era of large language models","author":"Sun","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0053","article-title":"How to use cyber kill chain model to build cybersecurity?","author":"Tarnowski","year":"2017","journal-title":"Eur. J. High. Edu. IT"},{"key":"10.1016\/j.jss.2025.112729_bib0054","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.jss.2025.112729_bib0055","first-page":"9706","article-title":"Variational model inversion attacks","volume":"34","author":"Wang","year":"2021","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.jss.2025.112729_bib0056","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11666","article-title":"Improving robustness to model inversion attacks via mutual information regularization","volume":"Vol. 35","author":"Wang","year":"2021"},{"key":"10.1016\/j.jss.2025.112729_bib0057","doi-asserted-by":"crossref","unstructured":"Wang, Y., Le, H., Gotmare, A. D., Bui, N. D. Q., Li, J., Hoi, S. C. H., 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv: 2305.07922.","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"10.1016\/j.jss.2025.112729_bib0058","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, W., Joty, S., Hoi, S. C. H., 2021c. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv: 2109.00859.","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"10.1016\/j.jss.2025.112729_bib0059","series-title":"2016 IEEE 29Th Computer Security Foundations Symposium (CSF)","first-page":"355","article-title":"A methodology for formalizing model-inversion attacks","author":"Wu","year":"2016"},{"key":"10.1016\/j.jss.2025.112729_bib0060","series-title":"Proceedings of the 6Th ACM SIGPLAN International Symposium on Machine Programming","first-page":"1","article-title":"A systematic evaluation of large language models of code","author":"Xu","year":"2022"},{"issue":"8","key":"10.1016\/j.jss.2025.112729_bib0061","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1007\/s10462-025-11248-0","article-title":"Deep learning model inversion attacks and defenses: a comprehensive survey","volume":"58","author":"Yang","year":"2025","journal-title":"Artif. Intell Rev."},{"key":"10.1016\/j.jss.2025.112729_bib0062","series-title":"ACM SIGSAC Conference on Computer and Communications Security (CCS)","first-page":"225","article-title":"Neural network inversion in adversarial setting via background knowledge alignment","author":"Yang","year":"2019"},{"key":"10.1016\/j.jss.2025.112729_bib0063","series-title":"IEEE\/ACM International Conference on Software Engineering (ICSE)","article-title":"Unveiling memorization in code models","author":"Yang","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0064","series-title":"Proceedings of the 33Rd ACM SIGSOFT International Symposium on Software Testing and Analysis","first-page":"1274","article-title":"Thinkrepair: self-directed automated program repair","author":"Yin","year":"2024"},{"key":"10.1016\/j.jss.2025.112729_bib0065","unstructured":"Yu, D., Naik, S., Backurs, A., Gopi, S., Inan, H. A., Kamath, G., Kulkarni, J., Lee, Y. T., Manoel, A., Wutschitz, L., et al., 2021. Differentially private fine-tuning of language models. arXiv preprint arXiv: 2110.06500."},{"key":"10.1016\/j.jss.2025.112729_bib0066","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3349","article-title":"Pseudo label-guided model inversion attack via conditional generative adversarial network","volume":"Vol. 37","author":"Yuan","year":"2023"},{"key":"10.1016\/j.jss.2025.112729_bib0067","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"682","article-title":"Exploiting explanations for model inversion attacks","author":"Zhao","year":"2021"},{"issue":"3","key":"10.1016\/j.jss.2025.112729_bib0068","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3633453","article-title":"Measuring github copilot\u2019s impact on productivity","volume":"67","author":"Ziegler","year":"2024","journal-title":"Commun. ACM"}],"container-title":["Journal of Systems and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016412122500398X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016412122500398X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:31:34Z","timestamp":1773898294000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016412122500398X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":68,"alternative-id":["S016412122500398X"],"URL":"https:\/\/doi.org\/10.1016\/j.jss.2025.112729","relation":{},"ISSN":["0164-1212"],"issn-type":[{"value":"0164-1212","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Peeking inside the black box: Training data exposure in code language models","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems and Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jss.2025.112729","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112729"}}