{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T18:17:18Z","timestamp":1783534638328,"version":"3.55.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3587104","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T13:39:17Z","timestamp":1751981957000},"page":"142990-142997","source":"Crossref","is-referenced-by-count":1,"title":["On the Effectiveness of Automatic Code Generation for Synthetic Dataset Creation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1397-0771","authenticated-orcid":false,"given":"Josh","family":"Mitchell","sequence":"first","affiliation":[{"name":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9737-242X","authenticated-orcid":false,"given":"Varghese","family":"Mathew Vaidyan","sequence":"additional","affiliation":[{"name":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-4847","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"ref2","article-title":"Neural code comprehension: A learnable representation of code semantics","author":"Ben-Nun","year":"2018","journal-title":"arXiv:1806.07336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1993316.1993532"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11219-013-9207-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3058671"},{"key":"ref7","article-title":"CodeNet: A large-scale AI for code dataset for learning a diversity of coding tasks","author":"Puri","year":"2021","journal-title":"arXiv:2105.12655"},{"key":"ref8","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021","journal-title":"arXiv:2102.04664"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3418463","article-title":"IR2VEC LLVM IR based scalable program embeddings","volume":"17","author":"VenkataKeerthy","year":"2020","journal-title":"ACM Trans. Archit. Code Optim. (TACO)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510217"},{"key":"ref11","article-title":"Program representations for predictive compilation: State of affairs in the early 20\u2019s","volume":"73","author":"da Silva","year":"2022","journal-title":"J. Comput. Lang."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-021-00070-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397370"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2012.6227142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3664597"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534867"},{"key":"ref17","article-title":"An empirical study on divergence of differently-sourced LLVM IRs","volume":"81","author":"Tian","year":"2024","journal-title":"J. Comput. Lang."},{"key":"ref18","article-title":"ProGraML: Graph-based deep learning for program optimization and analysis","author":"Cummins","year":"2020","journal-title":"arXiv:2003.10536"},{"key":"ref19","article-title":"Deep data flow analysis","author":"Cummins","year":"2021","journal-title":"arXiv:2012.01470"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/NNICE61279.2024.10499062"},{"key":"ref21","article-title":"Code translation with compiler representations","author":"Szafraniec","year":"2022","journal-title":"arXiv:2207.03578"},{"key":"ref22","article-title":"Learning c to x86 translation: An experiment in neural compilation","author":"Armengol-Estap\u00e8","year":"2021","journal-title":"arXiv:2108.07639"},{"key":"ref23","article-title":"Large language models for compiler optimization","author":"Cummins","year":"2023","journal-title":"arXiv:2309.07062"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676895"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11072675.pdf?arnumber=11072675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:02:40Z","timestamp":1755910960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3587104","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}