{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T20:48:35Z","timestamp":1791492515054,"version":"4.3.4"},"reference-count":99,"publisher":"Association for Computing Machinery (ACM)","issue":"5","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    We introduce\n                    <jats:sc>Modelizer<\/jats:sc>\n                    \u2014a novel framework that, given a black-box program, learns a\n                    <jats:italic toggle=\"yes\">model from its input\/output behavior<\/jats:italic>\n                    using\n                    <jats:italic toggle=\"yes\">neural machine translation<\/jats:italic>\n                    algorithms. The resulting model\n                    <jats:italic toggle=\"yes\">mocks<\/jats:italic>\n                    the original program: Given an input, the model predicts the output that would have been produced by the program. However, the model is also\n                    <jats:italic toggle=\"yes\">reversible<\/jats:italic>\n                    \u2014that is, the model can predict the input that would have produced a given output. Finally, the model is\n                    <jats:italic toggle=\"yes\">differentiable<\/jats:italic>\n                    and can be efficiently restricted to predict only a certain aspect of the program behavior.\n                    <jats:sc>Modelizer<\/jats:sc>\n                    uses\n                    <jats:italic toggle=\"yes\">grammars<\/jats:italic>\n                    to synthesize and inputs and unsupervised tokenizers to decompose the resulting outputs, allowing it to learn sequence-to-sequence associations between token streams. Other than input grammars,\n                    <jats:sc>Modelizer<\/jats:sc>\n                    only requires the ability to execute the program. The resulting models are\n                    <jats:italic toggle=\"yes\">small,<\/jats:italic>\n                    requiring fewer than 6.3 million parameters for languages such as Markdown or HTML; and they are\n                    <jats:italic toggle=\"yes\">accurate,<\/jats:italic>\n                    achieving up to 95.4% accuracy and a BLEU score of 0.98 with standard error of 0.04 in mocking real-world applications. As it learns from and predicts\n                    <jats:italic toggle=\"yes\">executions<\/jats:italic>\n                    rather than code,\n                    <jats:sc>Modelizer<\/jats:sc>\n                    departs from the LLM-centric research trend, opening new opportunities for\n                    <jats:italic toggle=\"yes\">program-specific models<\/jats:italic>\n                    that are fully tuned toward individual programs. Indeed, we foresee several\n                    <jats:italic toggle=\"yes\">applications<\/jats:italic>\n                    of these models, especially as the output of the program can be any aspect of program behavior. Beyond mocking and predicting program behavior, the models can also synthesize inputs that are likely to produce a particular behavior, such as failures or coverage, thus assisting in program understanding and maintenance.\n                  <\/jats:p>","DOI":"10.1145\/3748720","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T14:22:23Z","timestamp":1752675743000},"page":"1-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Learning Program Behavioral Models from Synthesized Input\u2013Output Pairs"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8466-3694","authenticated-orcid":false,"given":"Tural","family":"Mammadov","sequence":"first","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbrucken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4147-9690","authenticated-orcid":false,"given":"Dietrich","family":"Klakow","sequence":"additional","affiliation":[{"name":"Saarland University, Saarbrucken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5317-6689","authenticated-orcid":false,"given":"Alexander","family":"Koller","sequence":"additional","affiliation":[{"name":"Saarland University, Saarbrucken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4719-8803","authenticated-orcid":false,"given":"Andreas","family":"Zeller","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbrucken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"Bo Adler Niket Agarwal Ashwath Aithal Dong H. Anh Pallab Bhattacharya Annika Brundyn Jared Casper Bryan Catanzaro Sharon Clay Jonathan Cohen et al. 2024. Nemotron-4 340B technical report. arXiv:2406.11704. Retrieved from https:\/\/arxiv.org\/abs\/2406.11704"},{"key":"e_1_3_3_3_2","unstructured":"AI@Meta. 2024. Llama 3 Model Card. Retrieved from https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_3_5_2","unstructured":"Jordi Armengol-Estap\u00e9 and Michael F. P. O\u2019Boyle. 2022. Learning C to x86 translation: An experiment in neural compilation. arXiv:2108.07639. Retrieved from https:\/\/arxiv.org\/abs\/2108.07639"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23412"},{"key":"e_1_3_3_7_2","unstructured":"Ron Ausbrooks Stephen Buswell David Carlisle St\u00e9phane Dalmas Stan Devitt Angel Diaz Max Froumentin Roger Hunter Patrick Ion Michael Kohlhase et al. 2003. Mathematical Markup Language (MathML) Version 2.0. Specification. World Wide Web Consortium (W3C). Retrieved from https:\/\/www.w3.org\/TR\/MathML2\/"},{"key":"e_1_3_3_8_2","unstructured":"b mc2. 2023. sql-create-context dataset. Retrieved January 10 2024 from https:\/\/huggingface.co\/datasets\/b-mc2\/sql-create-context\/blob\/main\/sql_create_context_v4.json"},{"key":"e_1_3_3_9_2","first-page":"7950","volume-title":"Post training 4-bit quantization of convolutional networks for rapid-deploymentProceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Banner Ron","year":"2019","unstructured":"Ron Banner, Yury Nahshan, and Daniel Soudry. 2019. Post training 4-bit quantization of convolutional networks for rapid-deployment. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 714, 7950\u20137958."},{"key":"e_1_3_3_10_2","unstructured":"Federico Belotti. 2020. py_asciimath. Retrieved February 29 2024 from https:\/\/github.com\/belerico\/py_asciimath"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663790"},{"key":"e_1_3_3_12_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems. H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877\u20131901. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564625.3567998"},{"key":"e_1_3_3_14_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1956.1056813"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294969"},{"key":"e_1_3_3_17_2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In North American Chapter of the Association for Computational Linguistics. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:52967399","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"e_1_3_3_18_2","first-page":"990","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML \u201917)","author":"Devlin Jacob","year":"2017","unstructured":"Jacob Devlin, Jonathan Uesato, Surya Bhupatiraju, Rishabh Singh, Abdel Rahman Mohamed, and Pushmeet Kohli. 2017. RobustFill: Neural program learning under noisy I\/O. In Proceedings of the 34th International Conference on Machine Learning (ICML \u201917). JMLR.org, 990\u2013998."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510141"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.5555\/1289189.1289273"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/362007.362035"},{"key":"e_1_3_3_22_2","first-page":"1","article-title":"GDBMiner: Mining precise input grammars on (almost) any system","author":"Eisele Max","year":"2025","unstructured":"Max Eisele, Johannes H\u00e4gele, Christopher Huth, and Andreas Zeller. 2025. GDBMiner: Mining precise input grammars on (almost) any system. Leibniz Transactions on Embedded Systems 10 (2025), 1\u201326.","journal-title":"Leibniz Transactions on Embedded Systems"},{"key":"e_1_3_3_23_2","unstructured":"Hugging Face. 2024. Hugging Face Hub. Retrieved January 10 2024 from https:\/\/huggingface.co\/datasets"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_25_2","first-page":"1","volume-title":"Proceedings of the 14th USENIX Conference on Offensive Technologies (WOOT \u201920)","volume":"10","author":"Fioraldi Andrea","year":"2020","unstructured":"Andrea Fioraldi, Dominik Maier, Heiko Ei\u00dffeldt, and Marc Heuse. 2020. AFL++: Combining incremental steps of fuzzing research. In Proceedings of the 14th USENIX Conference on Offensive Technologies (WOOT \u201920). USENIX Association, Article 10, 1."},{"key":"e_1_3_3_26_2","unstructured":"Michel Fortin. 2003. Markdown Extra Language Specification. Specification. Michel Fortin. Retrieved from https:\/\/michelf.ca\/projects\/php-markdown\/extra\/"},{"key":"e_1_3_3_27_2","unstructured":"Python Software Foundation. 2021. Python Numeric and Mathematical Modules\u2014Mathematical functions\u2014Math. Retrieved March 1 2024 from https:\/\/docs.python.org\/3.10\/library\/math.html"},{"key":"e_1_3_3_28_2","volume-title":"Advances in Neural Information Processing Systems","author":"Fu Cheng","year":"2019","unstructured":"Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong, Farinaz Koushanfar, and Jishen Zhao. 2019. Coda: An end-to-end neural program decompiler. In Advances in Neural Information Processing Systems. H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/093b60fd0557804c8ba0cbf1453da22f-Paper.pdf"},{"key":"e_1_3_3_29_2","unstructured":"Cheng Fu Kunlin Yang Xinyun Chen Yuandong Tian and Jishen Zhao. 2021. N-Bref : A High-Fidelity Decompiler Exploiting Programming Structures. Retrieved from https:\/\/openreview.net\/forum?id=6GkL6qM3LV"},{"key":"e_1_3_3_30_2","unstructured":"GitHub Flavored Markdown Specification. 2019. GitHub Flavored Markdown Spec 0.29. Specification. GitHub. Retrieved from https:\/\/github.github.com\/gfm\/"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115618"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397349"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409679"},{"key":"e_1_3_3_34_2","unstructured":"Alex Graves Greg Wayne and Ivo Danihelka. 2014. Neural turing machines. arXiv:1410.5401. Retrieved from https:\/\/arxiv.org\/abs\/1410.5401"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10742"},{"key":"e_1_3_3_36_2","unstructured":"Patrick Haluptzok Matthew Bowers and Adam Tauman Kalai. 2023. Language models can teach themselves to program better. arXiv:2207.14502. Retrieved from https:\/\/arxiv.org\/abs\/2207.14502"},{"key":"e_1_3_3_37_2","unstructured":"Daniel Han Michael Han and Unsloth team. 2023. Unsloth. Retrieved from http:\/\/github.com\/unslothai\/unsloth"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.17487\/RFC6234"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00027"},{"key":"e_1_3_3_40_2","unstructured":"Jingxuan He and Martin T. Vechev. 2023. Controlling large language models to generate secure and vulnerable code. arXiv:2302.05319. Retrieved from https:\/\/arxiv.org\/abs\/2302.05319"},{"key":"e_1_3_3_41_2","unstructured":"Ian Hellen. 2019. MSTIC Jupyter and Python Security Tools. Retrieved January 22 2024 from https:\/\/github.com\/microsoft\/msticpy"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Matthew Honnibal Ines Montani Sofie Van Landeghem and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. DOI: 10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"e_1_3_3_44_2","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-rank adaptation of large language models. arXiv:2106.09685. Retrieved from https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_45_2","volume-title":"Information Technology\u2014Database Languages\u2014SQL","author":"ISO\/IEC 9075:1992 1992","unstructured":"ISO\/IEC 9075:1992 1992. Information Technology\u2014Database Languages\u2014SQL. Standard. International Organization for Standardization, Geneva, CH."},{"key":"e_1_3_3_46_2","first-page":"190","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS \u201915)","author":"Joulin Armand","year":"2015","unstructured":"Armand Joulin and Tomas Mikolov. 2015. Inferring algorithmic patterns with stack-augmented recurrent nets. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS \u201915). MIT Press, Cambridge, MA, 190\u2013198."},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00194"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2018.8330222"},{"key":"e_1_3_3_49_2","unstructured":"Omer Katz Yuval Olshaker Yoav Goldberg and Eran Yahav. 2019. Towards neural decompilation. arXiv:1905.08325. Retrieved from https:\/\/arxiv.org\/abs\/1905.08325"},{"key":"e_1_3_3_50_2","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A paper. arXiv:1806.08342. Retrieved from https:\/\/arxiv.org\/abs\/1806.08342"},{"key":"e_1_3_3_51_2","first-page":"37","volume-title":"Proceedings of the 4th Workshop on Threat, Aggression and Cyberbullying at LREC-COLING-2024","author":"Kruschwitz Udo","year":"2024","unstructured":"Udo Kruschwitz and Maximilian Schmidhuber. 2024. LLM-based synthetic datasets: Applications and limitations in toxicity detection. In Proceedings of the 4th Workshop on Threat, Aggression and Cyberbullying at LREC-COLING-2024. ELRA and ICCL, Torino, Italia, 37\u201351. Retrieved from https:\/\/aclanthology.org\/2024.trac-1.6"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678879"},{"key":"e_1_3_3_54_2","volume-title":"Conference Track Proceedings of the 4th International Conference on Learning Representations (ICLR \u201916)","author":"Kurach Karol","year":"2016","unstructured":"Karol Kurach, Marcin Andrychowicz, and Ilya Sutskever. 2016. Neural random-access machines. In Conference Track Proceedings of the 4th International Conference on Learning Representations (ICLR \u201916). Retrieved from http:\/\/arxiv.org\/abs\/1511.06392"},{"key":"e_1_3_3_55_2","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"Levenshtein Vladimir I.","year":"1965","unstructured":"Vladimir I. Levenshtein. 1965. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics. Doklady 10 (1965), 707\u2013710. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:60827152","journal-title":"Soviet physics"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-021-00070-0"},{"key":"e_1_3_3_58_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. arXiv:1711.05101. Retrieved from https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_3_59_2","unstructured":"John MacFarlane. 2006. Pandoc a universal document converter. Retrieved January 26 2024 from https:\/\/github.com\/jgm\/pandoc"},{"key":"e_1_3_3_60_2","unstructured":"John MacFarlane. 2014. CommonMark Spec Version 0.29. Specification. John MacFarlane. Retrieved from https:\/\/spec.commonmark.org\/0.29\/"},{"key":"e_1_3_3_61_2","unstructured":"Christopher D. Manning Prabhakar Raghavan and Hinrich Sch\u00fctze. 2008. Introduction to Information Retrieval. Cambridge University Press. Retrieved from https:\/\/books.google.de\/books?id=t1PoSh4uwVcC"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/96267.96279"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-668"},{"key":"e_1_3_3_64_2","volume-title":"Conference Track Proceedings of the 4th International Conference on Learning Representations (ICLR \u201916)","author":"Neelakantan Arvind","year":"2016","unstructured":"Arvind Neelakantan, Quoc V. Le, and Ilya Sutskever. 2016. Neural programmer: Inducing latent programs with gradient descent. In Conference Track Proceedings of the 4th International Conference on Learning Representations (ICLR \u201916). Retrieved from http:\/\/arxiv.org\/abs\/1511.04834"},{"key":"e_1_3_3_65_2","unstructured":"Yusuke Oda. 2020. latexify. Retrieved February 29 2024 from https:\/\/github.com\/google\/latexify_py"},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_3_67_2","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","unstructured":"Hammond Pearce Baleegh Ahmad Benjamin Tan Brendan Dolan-Gavitt and Ramesh Karri. 2022. Asleep at the Keyboard? Assessing the Security of GitHub Copilot\u2019s Code Contributions. 754\u2013768. DOI: 10.1109\/SP46214.2022.9833571","DOI":"10.1109\/SP46214.2022.9833571"},{"issue":"9","key":"e_1_3_3_69_2","first-page":"1980","volume":"47","author":"Pham Van-Thuan","year":"2019","unstructured":"Van-Thuan Pham, Marcel B\u00f6hme, Andrew E. Santosa, Alexandru R\u0103zvan C\u0103ciulescu, and Abhik Roychoudhury. 2019. Smart greybox fuzzing. IEEE Transactions on Software Engineering 47, 9 (2019), 1980\u20131997.","journal-title":"IEEE Transactions on Software Engineering"},{"issue":"140","key":"e_1_3_3_70_2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research 21, 140 (2020), 1\u201367. Retrieved from http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_71_2","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez et al. 2024. Code Llama: Open foundation models for code. arXiv:2308.12950. Retrieved from https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"e_1_3_3_72_2","first-page":"11","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS \u201920)","volume":"1730","author":"Rozi\u00e8re Baptiste","year":"2020","unstructured":"Baptiste Rozi\u00e8re, Marie-Anne Lachaux, Lowik, and Chanussot, Guillaume. 2020. Unsupervised translation of programming languages. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS \u201920). Curran Associates Inc., Red Hook, NY, Article 1730, 11."},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"e_1_3_3_74_2","unstructured":"Philipp Schmid. 2023. markdown-documentation-transformers dataset. Retrieved January 10 2024 from https:\/\/huggingface.co\/datasets\/philschmid\/markdown-documentation-transformers\/blob\/main\/transformers-4-34-0.jsonl"},{"key":"e_1_3_3_75_2","first-page":"1559","volume-title":"30th USENIX Security Symposium (USENIX Security \u201921)","author":"Schuster Roei","year":"2021","unstructured":"Roei Schuster, Congzheng Song, Eran Tromer, and Vitaly Shmatikov. 2021. You autocomplete me: Poisoning vulnerabilities in neural code completion. In 30th USENIX Security Symposium (USENIX Security \u201921). USENIX Association, 1559\u20131575. Retrieved from https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/schuster"},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3430952"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3512759"},{"key":"e_1_3_3_79_2","unstructured":"Richard Shin Neel Kant Kavi Gupta Christopher Bender Brandon Trabucco Rishabh Singh and Dawn Song. 2019. Synthetic datasets for neural program synthesis. arXiv:1912.12345. Retrieved from https:\/\/arxiv.org\/abs\/1912.12345"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3013716"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549139"},{"key":"e_1_3_3_82_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. MIT Press."},{"key":"e_1_3_3_83_2","unstructured":"CodeGemma Team Heri Zhao Jeffrey Hui Joshua Howland Nam Nguyen Siqi Zuo Andrea Hu Christopher A. Choquette-Choo Jingyue Shen Joe Kelley et al. CodeGemma: Open code models based on gemma. arXiv:2406.11409. Retrieved from https:\/\/arxiv.org\/abs\/2406.11409"},{"key":"e_1_3_3_84_2","unstructured":"NLTK Team. 2007. Natural Language Toolkit\u2014A Python Package for Natural Language Processing. Retrieved February 22 2024 from https:\/\/pypi.org\/project\/nltk\/"},{"key":"e_1_3_3_85_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00021"},{"key":"e_1_3_3_87_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Nikki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_88_2","unstructured":"Ashwin J. Vijayakumar Abhishek Mohta Oleksandr Polozov Dhruv Batra Prateek Jain and Sumit Gulwani. 2018. Neural-guided deductive search for real-time program synthesis from examples. arXiv:1804.01186. Retrieved from https:\/\/arxiv.org\/abs\/1804.01186"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549153"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_92_2","first-page":"11941","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139)","author":"Yasunaga Michihiro","year":"2021","unstructured":"Michihiro Yasunaga and Percy Liang. 2021. Break-it-fix-it: Unsupervised learning for program repair. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139). PMLR, 11941\u201311952. Retrieved from https:\/\/proceedings.mlr.press\/v139\/yasunaga21a.html"},{"key":"e_1_3_3_93_2","unstructured":"Richard Zanibbi. 2016. NTCIR-12 Dataset. Retrieved January 10 2024 from https:\/\/www.cs.rit.edu\/\u223crlaz\/Wiki\\_formulas\\_v0.1.tar.bz2"},{"key":"e_1_3_3_94_2","first-page":"421","volume-title":"Proceedings of the 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 48)","author":"Zaremba Wojciech","year":"2016","unstructured":"Wojciech Zaremba, Tomas Mikolov, Armand Joulin, and Rob Fergus. 2016. Learning simple algorithms from examples. In Proceedings of the 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 48). PMLR, New York, 421\u2013429. Retrieved from https:\/\/proceedings.mlr.press\/v48\/zaremba16.html"},{"key":"e_1_3_3_95_2","unstructured":"Wojciech Zaremba and Ilya Sutskever. 2015. Learning to execute. arXiv:1410.4615. Retrieved from https:\/\/arxiv.org\/abs\/1410.4615"},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2014.07.010"},{"key":"e_1_3_3_97_2","volume-title":"The Fuzzing Book","author":"Zeller Andreas","year":"2023","unstructured":"Andreas Zeller, Rahul Gopinath, Marcel B\u00f6hme, Gordon Fraser, and Christian Holler. 2023. Guide for authors. In The Fuzzing Book. CISPA Helmholtz Center for Information Security. Retrieved November 11, 2023 from https:\/\/www.fuzzingbook.org\/html\/Guide\\_for\\_Authors.html"},{"key":"e_1_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534864"},{"key":"e_1_3_3_99_2","first-page":"652","volume-title":"IET Conference Proceedings","author":"Ayg\u00fcn \u0130rfan","year":"2023","unstructured":"\u0130rfan Ayg\u00fcn and Mehmet Kaya. 2023. Use of large language models for medical synthetic data generation in mental illness. In IET Conference Proceedings, 652\u2013656. Retrieved from https:\/\/digital-library.theiet.org\/content\/conferences\/10.1049\/icp.2024.1033"},{"key":"e_1_3_3_100_2","first-page":"400","article-title":"LlamaFactory: Unified efficient fine-tuning of 100 language models","author":"Yaowei Zheng","unstructured":"Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, and Zheyan Luo. LlamaFactory: Unified efficient fine-tuning of 100 language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, 400\u2013410.","journal-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T06:33:28Z","timestamp":1777098808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":99,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3748720"],"URL":"https:\/\/doi.org\/10.1145\/3748720","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2024-07-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}