{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:27:39Z","timestamp":1786508859106,"version":"build-2736575974"},"reference-count":31,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T00:00:00Z","timestamp":1778976000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572363"],"award-info":[{"award-number":["62572363"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502352"],"award-info":[{"award-number":["62502352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["SoftwareX"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.softx.2026.102735","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T08:55:18Z","timestamp":1779699318000},"page":"102735","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CRec: A tool for recovering the compilability of OCRed code"],"prefix":"10.1016","volume":"34","author":[{"given":"Zhengjie","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2968-3496","authenticated-orcid":false,"given":"Jifeng","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.softx.2026.102735_bib0005","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1016\/j.patcog.2012.10.002","article-title":"Unsupervised profiling of ocred historical documents","volume":"46","author":"Reffle","year":"2013","journal-title":"Pattern Recognit"},{"issue":"5","key":"10.1016\/j.softx.2026.102735_bib0010","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1016\/j.ipm.2016.03.006","article-title":"Improving information retrieval performance on ocred text in the absence of clean text ground truth","volume":"52","author":"Ghosh","year":"2016","journal-title":"Inf Process Manag"},{"key":"10.1016\/j.softx.2026.102735_bib0015","series-title":"Proceedings of the 18th joint conference on digital libraries, JCDL \u201919","first-page":"333","article-title":"An analysis of the performance of named entity recognition over ocred documents","author":"Hamdi","year":"2020"},{"key":"10.1016\/j.softx.2026.102735_bib0020","series-title":"2018 IEEE 25th international conference on software analysis, evolution and reengineering (SANER)","first-page":"311","article-title":"Syntax and sensibility: using language models to detect and correct syntax errors","author":"Santos","year":"2018"},{"issue":"2","key":"10.1016\/j.softx.2026.102735_bib0025","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s10664-021-09942-y","article-title":"Learning lenient parsing & typing via indirect supervision","volume":"26","author":"Ahmed","year":"2021","journal-title":"Empir Softw Eng"},{"issue":"4","key":"10.1016\/j.softx.2026.102735_bib0030","doi-asserted-by":"crossref","first-page":"2169","DOI":"10.1109\/TSE.2022.3212635","article-title":"Synshine: improved fixing of syntax errors","volume":"49","author":"Ahmed","year":"2023","journal-title":"IEEE Trans. Software Eng."},{"key":"10.1016\/j.softx.2026.102735_bib0035","series-title":"Proceedings of the 38th IEEE\/ACM international conference on automated software engineering, ASE \u201923","first-page":"1492","article-title":"Improving code extraction from coding screencasts using a code-aware encoder-decoder model","author":"Malkadi","year":"2024"},{"key":"10.1016\/j.softx.2026.102735_bib0040","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"8696","article-title":"CodeT5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation","author":"Wang","year":"2021"},{"key":"10.1016\/j.softx.2026.102735_bib0045","series-title":"ClangFormat. Version 14.0.0 [software]","year":"2022"},{"key":"10.1016\/j.softx.2026.102735_bib0055","author":"Parr"},{"key":"10.1016\/j.softx.2026.102735_bib0060","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"7212","article-title":"UniXcoder: unified cross-modal pre-training for code representation","author":"Guo","year":"2022"},{"key":"10.1016\/j.softx.2026.102735_bib0065","series-title":"Proceedings of the 30th ACM joint European software engineering conference and symposium on the foundations of software engineering, ESEC\/FSE 2022, Association for Computing Machinery","first-page":"959","article-title":"Less training, more repairing please: revisiting automated program repair via zero-shot learning","author":"Xia","year":"2022"},{"key":"10.1016\/j.softx.2026.102735_bib0070","series-title":"Proceedings of the 38th IEEE\/ACM international conference on automated software engineering, ASE \u201923","first-page":"535","article-title":"Gamma: revisiting template-based automated program repair via mask prediction","author":"Zhang","year":"2024"},{"key":"10.1016\/j.softx.2026.102735_bib0075","series-title":"Proceedings of the 33rd ACM SIGSOFT international symposium on software testing and analysis, ISSTA 2024","first-page":"1554","article-title":"One size does not fit all: multi-granularity patch generation for better automated program repair","author":"Lin","year":"2024"},{"key":"10.1016\/j.softx.2026.102735_bib0080","series-title":"Proceedings of 44th IEEE\/ACM international conference on software engineering, ICSE \u201922","first-page":"200","article-title":"Automated patching for unreproducible builds","author":"Ren","year":"2022"},{"key":"10.1016\/j.softx.2026.102735_bib0085","author":"Xuan"},{"issue":"8","key":"10.1016\/j.softx.2026.102735_bib0090","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Sov. Phys. Dokl."},{"issue":"7","key":"10.1016\/j.softx.2026.102735_bib0095","doi-asserted-by":"crossref","first-page":"3112","DOI":"10.3390\/app16073112","article-title":"Testing explainability of chain of thought for large language models","volume":"6","author":"Chen","year":"2026","journal-title":"Appl Sci"},{"key":"10.1016\/j.softx.2026.102735_bib0100","series-title":"Core Java, volume I: fundamentals","author":"Horstmann","year":"2021"},{"key":"10.1016\/j.softx.2026.102735_bib0105","series-title":"Core Java, volume II: advanced features","author":"Horstmann","year":"2022"},{"key":"10.1016\/j.softx.2026.102735_bib0110","series-title":"Effective Java","author":"Bloch","year":"2018"},{"key":"10.1016\/j.softx.2026.102735_bib0115","series-title":"Head first Java","author":"Sierra","year":"2005"},{"key":"10.1016\/j.softx.2026.102735_bib0120","series-title":"Thinking in Java","author":"Eckel","year":"2006"},{"key":"10.1016\/j.softx.2026.102735_bib0125","series-title":"Proceedings of the 17th international conference on mining software repositories, MSR \u201920, Association for Computing Machinery","first-page":"65","article-title":"A study on the accuracy of OCR engines for source code transcription from programming screencasts","author":"Malkadi","year":"2020"},{"key":"10.1016\/j.softx.2026.102735_bib0130","unstructured":"ABBYY (n.d.), ABBYY FineReader Engine [software]. ABBYY. https:\/\/www.abbyy.com\/ocr-sdk\/"},{"key":"10.1016\/j.softx.2026.102735_bib0140","author":"Terdalkar"},{"key":"10.1016\/j.softx.2026.102735_bib0145","author":"Smith"},{"key":"10.1016\/j.softx.2026.102735_bib0150","series-title":"Proceedings of the fifth annual ACM conference on learning at scale, L@S \u201918, Association for Computing Machinery","first-page":"1","article-title":"Codemotion: expanding the design space of learner interactions with computer programming tutorial videos","volume":"vol. 57","author":"Khandwala","year":"2018"},{"issue":"3","key":"10.1016\/j.softx.2026.102735_bib0155","doi-asserted-by":"crossref","DOI":"10.1145\/3392093","article-title":"PSC2code: denoising code extraction from programming screencasts","volume":"29","author":"Bao","year":"2020","journal-title":"ACM Trans Softw Eng Methodol"},{"issue":"2","key":"10.1016\/j.softx.2026.102735_bib0165","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1007\/s10664-019-09759-w","article-title":"Code localization in programming screencasts","volume":"25","author":"Alahmadi","year":"2020","journal-title":"Empir Softw Eng"},{"key":"10.1016\/j.softx.2026.102735_bib0170","series-title":"Exceptions can be nested: an exploratory study on nested exceptions in Java crashes","author":"Liu","year":"2026"}],"container-title":["SoftwareX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S235271102600227X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S235271102600227X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T03:37:16Z","timestamp":1786505836000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S235271102600227X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":31,"alternative-id":["S235271102600227X"],"URL":"https:\/\/doi.org\/10.1016\/j.softx.2026.102735","relation":{},"ISSN":["2352-7110"],"issn-type":[{"value":"2352-7110","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CRec: A tool for recovering the compilability of OCRed code","name":"articletitle","label":"Article Title"},{"value":"SoftwareX","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.softx.2026.102735","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102735"}}