{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T08:37:58Z","timestamp":1771576678872,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T00:00:00Z","timestamp":1647475200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T00:00:00Z","timestamp":1647475200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"crossref","award":["P2-0057"],"award-info":[{"award-number":["P2-0057"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s10664-022-10122-9","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T14:06:53Z","timestamp":1647526013000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Software system comparison with semantic source code embeddings"],"prefix":"10.1007","volume":"27","author":[{"given":"Sa\u0161o","family":"Karakati\u010d","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksej","family":"Milo\u0161evi\u010d","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0410-7724","authenticated-orcid":false,"given":"Tja\u0161a","family":"Heri\u010dko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,17]]},"reference":[{"key":"10122_CR1","doi-asserted-by":"publisher","first-page":"86121","DOI":"10.1109\/ACCESS.2019.2918202","volume":"7","author":"QU Ain","year":"2019","unstructured":"Ain QU, Butt WH, Anwar MW, Azam F, Maqbool B (2019) A systematic review on code clone detection. IEEE Access 7:86121\u201386144. https:\/\/doi.org\/10.1109\/ACCESS.2019.2918202","journal-title":"IEEE Access"},{"issue":"1","key":"10122_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.12694\/scpe.v22i1.1836","volume":"22","author":"O Al-Debagy","year":"2021","unstructured":"Al-Debagy O, Martinek P (2021) A microservice decomposition method through using distributed representation of source code. Scalable Comput Pract Experience 22(1):39\u201352. https:\/\/doi.org\/10.12694\/scpe.v22i1.1836","journal-title":"Scalable Comput Pract Experience"},{"key":"10122_CR3","unstructured":"Alon U, Brody S, Levy O, Yahav E (2019) code2seq: Generating sequences from structured representations of code. In: International conference on learning representations"},{"key":"10122_CR4","doi-asserted-by":"crossref","unstructured":"Alon U, Zilberstein M, Levy O, Yahav E (2018) A general path-based representation for predicting program properties. In: Proceedings of the 39th ACM SIGPLAN conference on programming language design and implementation. Association for Computing Machinery, New York, pp 404\u2013419","DOI":"10.1145\/3192366.3192412"},{"issue":"POPL","key":"10122_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3290353","volume":"3","author":"U Alon","year":"2019","unstructured":"Alon U, Zilberstein M, Levy O, Yahav E (2019) code2vec: Learning distributed representations of code. Proc ACM Program Lang 3 (POPL):1\u201329. https:\/\/doi.org\/10.1145\/3290353","journal-title":"Proc ACM Program Lang"},{"key":"10122_CR6","doi-asserted-by":"crossref","unstructured":"Barr JR, Shaw P, Abu-Khzam FN, Yu S, Yin H, Thatcher T (2020) Combinatorial code classification vulnerability rating. In: 2020 second international conference on transdisciplinary AI (TransAI), pp 80\u201383","DOI":"10.1109\/TransAI49837.2020.00017"},{"key":"10122_CR7","doi-asserted-by":"crossref","unstructured":"Baxter ID, Yahin A, Moura L, Sant\u2019Anna M, Bier L (1998) Clone detection using abstract syntax trees. In: Proceedings of international conference on software maintenance, pp 368\u2013377","DOI":"10.1109\/ICSM.1998.738528"},{"issue":"1","key":"10122_CR8","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/nbt.4314","volume":"37","author":"E Becht","year":"2019","unstructured":"Becht E, McInnes L, Healy J, Dutertre C-A, Kwok Immanuel WH, Ng LG, Ginhoux F, Newell EW (2019) Dimensionality reduction for visualizing single-cell data using umap. Nat Biotechnol 37(1):38\u201344. https:\/\/doi.org\/10.1038\/nbt.4314","journal-title":"Nat Biotechnol"},{"issue":"9","key":"10122_CR9","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TSE.2007.70725","volume":"33","author":"S Bellon","year":"2007","unstructured":"Bellon S, Koschke R, Antoniol G, Krinke J, Merlo E (2007) Comparison and evaluation of clone detection tools. IEEE Trans Softw Eng 33(9):577\u2013591. https:\/\/doi.org\/10.1109\/TSE.2007.70725","journal-title":"IEEE Trans Softw Eng"},{"key":"10122_CR10","unstructured":"Ben-Nun T, Jakobovits AS, Hoefler T (2018) Neural code comprehension: A learnable representation of code semantics. In: Proceedings of the 32nd international conference on neural information processing systems. Curran Associates Inc., Red Hook, pp 3589\u20133601"},{"key":"10122_CR11","doi-asserted-by":"publisher","first-page":"106279","DOI":"10.1016\/j.infsof.2020.106279","volume":"122","author":"A Capiluppi","year":"2020","unstructured":"Capiluppi A, Di Ruscio D, Di Rocco J, Nguyen PT, Ajienka N (2020) Detecting java software similarities by using different clustering techniques. Inf Softw Technol 122:106279. https:\/\/doi.org\/10.1016\/j.infsof.2020.106279","journal-title":"Inf Softw Technol"},{"key":"10122_CR12","doi-asserted-by":"crossref","unstructured":"Chae D-K, Ha J, Kim S-W, Kang B, Im EG (2013) Software plagiarism detection: A graph-based approach. In: Proceedings of the 22nd ACM international conference on information & knowledge management. Association for Computing Machinery, New York, pp 1577\u20131580","DOI":"10.1145\/2505515.2507848"},{"key":"10122_CR13","doi-asserted-by":"crossref","unstructured":"Cheers H, Lin Y, Smith SP (2019) A novel approach for detecting logic similarity in plagiarised source code. In: 2019 IEEE 10th international conference on software engineering and service science (ICSESS). IEEE, pp 1\u20136","DOI":"10.1109\/ICSESS47205.2019.9040752"},{"key":"10122_CR14","doi-asserted-by":"crossref","unstructured":"Chen K, Liu P, Zhang Y (2014) Achieving accuracy and scalability simultaneously in detecting application clones on android markets. In: Proceedings of the 36th international conference on software engineering. Association for Computing Machinery, New York, pp 175\u2013186","DOI":"10.1145\/2568225.2568286"},{"key":"10122_CR15","doi-asserted-by":"crossref","unstructured":"Compton R, Frank E, Patros P, Koay A (2020) Embedding java classes with code2vec: Improvements from variable obfuscation. In: Proceedings of the 17th international conference on mining software repositories. MSR \u201920. Association for Computing Machinery, New York, pp 243\u2013253","DOI":"10.1145\/3379597.3387445"},{"key":"10122_CR16","doi-asserted-by":"crossref","unstructured":"Csuvik V, Kicsi A, Vid\u00e1cs L (2019) Evaluation of textual similarity techniques in code level traceability. In: Computational science and its applications. Springer, pp 529\u2013543","DOI":"10.1007\/978-3-030-24305-0_40"},{"key":"10122_CR17","doi-asserted-by":"crossref","unstructured":"Dann A, Hermann B, Bodden E (2019) Sootdiff: Bytecode comparison across different java compilers. In: Proceedings of the 8th ACM SIGPLAN international workshop on state of the art in program analysis. Association for Computing Machinery, New York, pp 14\u201319","DOI":"10.1145\/3315568.3329966"},{"key":"10122_CR18","doi-asserted-by":"publisher","unstructured":"Decker MJ, Collard ML, Volkert LG, Maletic JI (2020) srcdiff: A syntactic differencing approach to improve the understandability of deltas. J Softw Evol Process 32(4). https:\/\/doi.org\/10.1002\/smr.2226","DOI":"10.1002\/smr.2226"},{"key":"10122_CR19","doi-asserted-by":"crossref","unstructured":"DeFreez D, Thakur AV, Rubio-Gonz\u00e1lez C (2018) Path-based function embedding and its application to error-handling specification mining. In: Proceedings of the 2018 26th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering. Association for Computing Machinery, New York, pp 423\u2013433","DOI":"10.1145\/3236024.3236059"},{"key":"10122_CR20","doi-asserted-by":"crossref","unstructured":"Deza MM, Deza E (2009) Encyclopedia of distances. In: Encyclopedia of distances. Springer, pp 1\u2013583","DOI":"10.1007\/978-3-642-00234-2_1"},{"key":"10122_CR21","unstructured":"Dubuisson M-P, Jain AK (1994) A modified hausdorff distance for object matching. In: Proceedings of 12th international conference on pattern recognition, vol 1. IEEE, pp 566\u2013568"},{"issue":"1","key":"10122_CR22","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1093\/comjnl\/bxs018","volume":"56","author":"Z Duri\u0107","year":"2012","unstructured":"Duri\u0107 Z, Ga\u0161vi\u0107 D (2012) A source code similarity system for plagiarism detection. Comput J 56(1):70\u201386. https:\/\/doi.org\/10.1093\/comjnl\/bxs018","journal-title":"Comput J"},{"issue":"1","key":"10122_CR23","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/0360-1315(87)90042-X","volume":"11","author":"JAW Faidhi","year":"1987","unstructured":"Faidhi JAW, Robinson SK (1987) An empirical approach for detecting program similarity and plagiarism within a university programming environment. Comput Educ 11(1):11\u201319. https:\/\/doi.org\/10.1016\/0360-1315(87)90042-X","journal-title":"Comput Educ"},{"key":"10122_CR24","doi-asserted-by":"crossref","unstructured":"Falleri J-R, Morandat F, Blanc X, Martinez M, Monperrus M (2014) Fine-grained and accurate source code differencing. In: Proceedings of the 29th ACM\/IEEE international conference on automated software engineering, ASE \u201914. Association for Computing Machinery, New York, pp 313\u2013324","DOI":"10.1145\/2642937.2642982"},{"issue":"2","key":"10122_CR25","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.matpur.2009.11.005","volume":"94","author":"A Figalli","year":"2010","unstructured":"Figalli A, Gigli N (2010) A new transportation distance between non-negative measures, with applications to gradients flows with dirichlet boundary conditions. J Math Appl 94(2):107\u2013130. https:\/\/doi.org\/10.1016\/j.matpur.2009.11.005","journal-title":"J Math Appl"},{"key":"10122_CR26","doi-asserted-by":"crossref","unstructured":"Gardner A, Kanno J, Duncan CA, Selmic R (2014) Measuring distance between unordered sets of different sizes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 137\u2013143","DOI":"10.1109\/CVPR.2014.25"},{"key":"10122_CR27","volume-title":"Elements of software science (operating and programming systems series)","author":"MH Halstead","year":"1977","unstructured":"Halstead MH (1977) Elements of software science (operating and programming systems series). Elsevier Science Inc., USA"},{"key":"10122_CR28","doi-asserted-by":"crossref","unstructured":"Hemel A, Kalleberg KT, Vermaas R, Dolstra E (2011) Finding software license violations through binary code clone detection. In: Proceedings of the 8th working conference on mining software repositories. Association for Computing Machinery, New York, pp 63\u201372","DOI":"10.1145\/1985441.1985453"},{"key":"10122_CR29","doi-asserted-by":"crossref","unstructured":"Henkel J, Lahiri SK, Liblit B, Reps T (2018) Code vectors: Understanding programs through embedded abstracted symbolic traces. In: Proceedings of the 2018 26th ACM joint meeting on european software engineering conference and symposium on the foundations of software engineering. Association for Computing Machinery, New York, pp 163\u2013174","DOI":"10.1145\/3236024.3236085"},{"issue":"9","key":"10122_CR30","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/34.232073","volume":"15","author":"DP Huttenlocher","year":"1993","unstructured":"Huttenlocher DP, Klanderman GA, Rucklidge WJ (1993) Comparing images using the hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15 (9):850\u2013863. https:\/\/doi.org\/10.1109\/34.232073","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10122_CR31","doi-asserted-by":"crossref","unstructured":"Jhi Y-C, Wang X, Jia X, Zhu S, Liu P, Wu D (2011) Value-based program characterization and its application to software plagiarism detection. In: Proceedings of the 33rd international conference on software engineering, pp 756\u2013765","DOI":"10.1145\/1985793.1985899"},{"issue":"7","key":"10122_CR32","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1109\/TSE.2002.1019480","volume":"28","author":"T Kamiya","year":"2002","unstructured":"Kamiya T, Kusumoto S, Inoue K (2002) Ccfinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans Softw Eng 28(7):654\u2013670. https:\/\/doi.org\/10.1109\/TSE.2002.1019480","journal-title":"IEEE Trans Softw Eng"},{"key":"10122_CR33","doi-asserted-by":"crossref","unstructured":"Kang HJ, Bissyand\u00e9 TF, Lo D (2019) Assessing the generalizability of code2vec token embeddings. In: 2019 34th IEEE\/ACM international conference on automated software engineering (ASE), pp 1\u201312","DOI":"10.1109\/ASE.2019.00011"},{"key":"10122_CR34","first-page":"107","volume":"16","author":"C Kapser","year":"2003","unstructured":"Kapser C, Godfrey MW (2003) Toward a taxonomy of clones in source code: A case study. Evol Large Scale Ind Softw Architectures 16:107\u2013113","journal-title":"Evol Large Scale Ind Softw Architectures"},{"issue":"2","key":"10122_CR35","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41587-020-00809-z","volume":"39","author":"D Kobak","year":"2021","unstructured":"Kobak D, Linderman GC (2021) Initialization is critical for preserving global data structure in both t-sne and umap. Nat Biotechnol 39(2):156\u2013157. https:\/\/doi.org\/10.1038\/s41587-020-00809-z","journal-title":"Nat Biotechnol"},{"key":"10122_CR36","doi-asserted-by":"crossref","unstructured":"Kovalenko V, Bogomolov E, Bryksin T, Bacchelli A (2019) Pathminer: A library for mining of path-based representations of code. In: Proceedings of the 16th international conference on mining software repositories, pp 13\u201317","DOI":"10.1109\/MSR.2019.00013"},{"key":"10122_CR37","doi-asserted-by":"crossref","unstructured":"Krinke J (2001) Identifying similar code with program dependence graphs. In: Proceedings eighth working conference on reverse engineering, pp 301\u2013309","DOI":"10.1109\/WCRE.2001.957835"},{"key":"10122_CR38","doi-asserted-by":"crossref","unstructured":"Levina E, Bickel P (2001) The earth mover\u2019s distance is the mallows distance: Some insights from statistics. In: Proceedings Eighth IEEE international conference on computer vision. ICCV 2001, vol 2. IEEE, pp 251\u2013256","DOI":"10.1109\/ICCV.2001.937632"},{"key":"10122_CR39","doi-asserted-by":"crossref","unstructured":"Li L, Feng H, Zhuang W, Meng N, Ryder B (2017) Cclearner: A deep learning-based clone detection approach. In: 2017 IEEE international conference on software maintenance and evolution (ICSME), pp 249\u2013260","DOI":"10.1109\/ICSME.2017.46"},{"key":"10122_CR40","doi-asserted-by":"crossref","unstructured":"Li X, Zhong XJ (2010) The source code plagiarism detection using ast. In: 2010 international symposium on intelligence information processing and trusted computing, pp 406\u2013408","DOI":"10.1109\/IPTC.2010.90"},{"issue":"OOPSLA","key":"10122_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3360578","volume":"3","author":"S Luan","year":"2019","unstructured":"Luan S, Yang D, Barnaby C, Sen K, Chandra S (2019) Aroma: Code recommendation via structural code search. Proc ACM on Program Lang 3(OOPSLA):1\u201328. https:\/\/doi.org\/10.1145\/3360578","journal-title":"Proc ACM on Program Lang"},{"issue":"12","key":"10122_CR42","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1109\/TSE.2017.2655046","volume":"43","author":"L Luo","year":"2017","unstructured":"Luo L, Ming J, Wu D, Liu P, Zhu S (2017) Semantics-based obfuscation-resilient binary code similarity comparison with applications to software plagiarism detection. IEEE Trans Softw Eng 43(12):1157\u20131177","journal-title":"IEEE Trans Softw Eng"},{"key":"10122_CR43","doi-asserted-by":"crossref","unstructured":"Mathur A, Choudhary H, Vashist P, Thies W, Thilagam S (2012) An empirical study of license violations in open source projects. In: Proceedings of the 2012 35th annual IEEE software engineering workshop. IEEE Computer Society, pp 168\u2013176","DOI":"10.1109\/SEW.2012.24"},{"key":"10122_CR44","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J (2018) UMAP: uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426","DOI":"10.21105\/joss.00861"},{"issue":"29","key":"10122_CR45","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","volume":"3","author":"L McInnes","year":"2018","unstructured":"McInnes L, Healy J, Saul N, Grossberger L (2018) Umap: Uniform manifold approximation and projection. J Open Source Softw 3(29):861. https:\/\/doi.org\/10.21105\/joss.00861","journal-title":"J Open Source Softw"},{"key":"10122_CR46","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:1301.3781"},{"key":"10122_CR47","doi-asserted-by":"crossref","unstructured":"Nafi KW, Kar TS, Roy B, Roy CK, Schneider KA (2019) Clcdsa: Cross language code clone detection using syntactical features and api documentation. In: 2019 34th IEEE\/ACM international conference on automated software engineering (ASE). IEEE, pp 1026\u20131037","DOI":"10.1109\/ASE.2019.00099"},{"key":"10122_CR48","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s11219-019-09483-0","volume":"28","author":"PT Nguyen","year":"2020","unstructured":"Nguyen PT, Di Rocco J, Rubei R, Di Ruscio D (2020) An automated approach to assess the similarity of github repositories. Softw Qual J 28:595\u2013631. https:\/\/doi.org\/10.1007\/s11219-019-09483-0","journal-title":"Softw Qual J"},{"issue":"4","key":"10122_CR49","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/382222.382462","volume":"8","author":"KJ Ottenstein","year":"1976","unstructured":"Ottenstein KJ (1976) An algorithmic approach to the detection and prevention of plagiarism. SIGCSE Bull 8(4):30\u201341. https:\/\/doi.org\/10.1145\/382222.382462","journal-title":"SIGCSE Bull"},{"key":"10122_CR50","doi-asserted-by":"crossref","unstructured":"Palo HK, Sahoo S, Subudhi AK (2021) Dimensionality reduction techniques: Principles, benefits, and limitations. Wiley, chap 4, pp 77\u2013107","DOI":"10.1002\/9781119785620.ch4"},{"key":"10122_CR51","doi-asserted-by":"crossref","unstructured":"Pauzi Z, Capiluppi A (2020) Text similarity between concepts extracted from source code and documentation. In: International conference on intelligent data engineering and automated learning. Springer, pp 124\u2013135","DOI":"10.1007\/978-3-030-62362-3_12"},{"key":"10122_CR52","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), vol 14. Association for Computational Linguistics, Doha, Qatar, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"10122_CR53","doi-asserted-by":"crossref","unstructured":"Pigazzini I (2019) Automatic detection of architectural bad smells through semantic representation of code. In: Proceedings of the 13th european conference on software architecture, vol 2. Association for Computing Machinery, New York, pp 59\u201362","DOI":"10.1145\/3344948.3344951"},{"key":"10122_CR54","unstructured":"Prechelt L, Malpohl G, Philippsen M (2002) Finding plagiarisms among a set of programs with jplag. J Univers Comput Sci 8(11)"},{"key":"10122_CR55","doi-asserted-by":"crossref","unstructured":"Rabin MRI, Mukherjee A, Gnawali O, Alipour MA (2020) Towards demystifying dimensions of source code embeddings. In: Proceedings of the 1st ACM SIGSOFT international workshop on representation learning for software engineering and program languages. Association for Computing Machinery, New York, pp 29\u201338","DOI":"10.1145\/3416506.3423580"},{"issue":"4","key":"10122_CR56","doi-asserted-by":"publisher","first-page":"2464","DOI":"10.1007\/s10664-017-9564-7","volume":"23","author":"C Ragkhitwetsagul","year":"2018","unstructured":"Ragkhitwetsagul C, Krinke J, Clark D (2018) A comparison of code similarity analysers. Empir Softw Eng 23(4):2464\u20132519. https:\/\/doi.org\/10.1007\/s10664-017-9564-7","journal-title":"Empir Softw Eng"},{"key":"10122_CR57","doi-asserted-by":"crossref","unstructured":"Roy CK, Cordy JR (2008) Nicad: Accurate detection of near-miss intentional clones using flexible pretty-printing and code normalization. In: 2008 16th IEEE international conference on program comprehension, pp 172\u2013181","DOI":"10.1109\/ICPC.2008.41"},{"key":"10122_CR58","doi-asserted-by":"crossref","unstructured":"Sajnani H, Saini V, Svajlenko J, Roy CK, Lopes CV (2016) Sourcerercc: Scaling code clone detection to big-code. In: Proceedings of the 38th International Conference on Software Engineering. Association for Computing Machinery, New York, pp 1157\u20131168","DOI":"10.1145\/2884781.2884877"},{"key":"10122_CR59","doi-asserted-by":"crossref","unstructured":"Schleimer S, Wilkerson D S, Aiken A (2003) Winnowing: Local algorithms for document fingerprinting. In: Proceedings of the 2003 ACM SIGMOD international conference on management of data. Association for Computing Machinery, New York, pp 76\u201385","DOI":"10.1145\/872757.872770"},{"key":"10122_CR60","doi-asserted-by":"crossref","unstructured":"Shan SQ, Tian ZG, Guo FJ, Ren JX (2014) Similarity detection\u2019s application using chi-square test in the property of counting method. In: Advances in computers, electronics and mechatronics, Trans Tech Publications Ltd, Applied Mechanics and Materials, vol 667, pp 32\u201335","DOI":"10.4028\/www.scientific.net\/AMM.667.32"},{"key":"10122_CR61","doi-asserted-by":"crossref","unstructured":"Sheneamer A, Kalita J (2016) Semantic clone detection using machine learning. In: 2016 15th IEEE international conference on machine learning and applications (ICMLA), pp 1024\u20131028","DOI":"10.1109\/ICMLA.2016.0185"},{"key":"10122_CR62","doi-asserted-by":"publisher","unstructured":"Shi K, Lu Y, Chang J, Wei Z (2020) Pathpair2vec: An ast path pair-based code representation method for defect prediction. J Comput Lang 59. https:\/\/doi.org\/10.1016\/j.cola.2020.100979","DOI":"10.1016\/j.cola.2020.100979"},{"key":"10122_CR63","doi-asserted-by":"crossref","unstructured":"Tufano M, Watson C, Bavota G, Di Penta M, White M, Poshyvanyk D (2018) Deep learning similarities from different representations of source code. In: 2018 IEEE\/ACM 15th international conference on mining software repositories (MSR), pp 542\u2013553","DOI":"10.1145\/3196398.3196431"},{"key":"10122_CR64","unstructured":"Turian J, Ratinov L-A, Bengio Y (2010) Word representations: A simple and general method for semi-supervised learning. In: Proceedings of the 48th annual meeting of the association for computational linguistics, vol 2010. Association for Computational Linguistics, Uppsala, Sweden, pp 384\u2013394"},{"key":"10122_CR65","doi-asserted-by":"crossref","unstructured":"White M, Tufano M, Vendome C, Poshyvanyk D (2016) Deep learning code fragments for code clone detection. In: Proceedings of the 31st IEEE\/ACM international conference on automated software engineering. Association for Computing Machinery, New York, pp 87\u201398","DOI":"10.1145\/2970276.2970326"},{"key":"10122_CR66","unstructured":"Ye F, Zhou S, Venkat A, Marucs R, Tatbul N, Tithi JJ, Petersen P, Mattson T, Kraska T, Dubey P et al (2021) Misim: A novel code similarity system"},{"key":"10122_CR67","doi-asserted-by":"crossref","unstructured":"Yuan Y, Guo Y (2012) Boreas: an accurate and scalable token-based approach to code clone detection. In: Proceedings of the 27th IEEE\/ACM international conference on automated software engineering, pp 286\u2013289","DOI":"10.1145\/2351676.2351725"},{"key":"10122_CR68","doi-asserted-by":"crossref","unstructured":"Zhang J, Wang X, Zhang H, Sun H, Wang K, Liu X (2019) A novel neural source code representation based on abstract syntax tree. In: Proceedings of the 41st international conference on software engineering. IEEE Press, pp 783\u2013794","DOI":"10.1109\/ICSE.2019.00086"},{"key":"10122_CR69","doi-asserted-by":"crossref","unstructured":"Zhao J, Xia K, Fu Y, Cui B (2015) An ast-based code plagiarism detection algorithm. In: 2015 10th international conference on broadband and wireless computing, communication and applications (BWCCA), pp 178\u2013182","DOI":"10.1109\/BWCCA.2015.52"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10122-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-022-10122-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10122-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,23]],"date-time":"2022-04-23T10:17:00Z","timestamp":1650709020000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-022-10122-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,17]]},"references-count":69,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10122"],"URL":"https:\/\/doi.org\/10.1007\/s10664-022-10122-9","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,17]]},"assertion":[{"value":"13 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}],"article-number":"70"}}