{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:30:24Z","timestamp":1761895824334},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,3,22]],"date-time":"2014-03-22T00:00:00Z","timestamp":1395446400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1007\/s10115-014-0742-2","type":"journal-article","created":{"date-parts":[[2014,3,21]],"date-time":"2014-03-21T14:46:35Z","timestamp":1395413195000},"page":"445-472","source":"Crossref","is-referenced-by-count":22,"title":["Efficient clustering-based source code plagiarism detection using PIY"],"prefix":"10.1007","volume":"43","author":[{"given":"Tony","family":"Ohmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imad","family":"Rahal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,3,22]]},"reference":[{"key":"742_CR1","doi-asserted-by":"crossref","unstructured":"Bhattacharjee A, Jamil HM (2013) CodeBlast: a two-stage algorithm for improved program similarity matching in large software repositories. In: Proceedings of the 28th annual ACM symposium on applied computing. ACM, Coimbra, pp 846\u2013852","DOI":"10.1145\/2480362.2480525"},{"issue":"7","key":"742_CR2","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1109\/TIT.2004.830793","volume":"50","author":"X Chen","year":"2004","unstructured":"Chen X, Francia B, Li M et al (2004) Shared information and program plagiarism detection. IEEE Trans Inf Theory 50(7):1545\u20131551","journal-title":"IEEE Trans Inf Theory"},{"key":"742_CR3","doi-asserted-by":"crossref","unstructured":"Choi Y, Park Y, Choi J et al (2013) RAMC: runtime abstract memory context based plagiarism detection in binary code. In: Proceedings of the 7th international conference on ubiquitous information management and communication. Kota Kinabalu, Malaysia, pp 67\u201373","DOI":"10.1145\/2448556.2448623"},{"issue":"1","key":"742_CR4","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/TE.2011.2112768","volume":"55","author":"D Chuda","year":"2012","unstructured":"Chuda D, Navrat P, Kovacova B et al (2012) The issue of (software) plagiarism: a student view. IEEE Trans Educ 55(1):22\u201328","journal-title":"IEEE Trans Educ"},{"issue":"2","key":"742_CR5","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/TE.2007.906776","volume":"51","author":"G Cosma","year":"2008","unstructured":"Cosma G, Joy M (2008) Towards a definition of source-code plagiarism. IEEE Trans Educ 51(2):195\u2013200","journal-title":"IEEE Trans Educ"},{"key":"742_CR6","doi-asserted-by":"crossref","unstructured":"El Bachir Menai M, Al-Hassoun NS (2010) Similarity detection in Java programming assignments. In: Proceedings of the 5th international conference on computer science and education (ICCSE). IEEE, Hefei, pp 356\u2013361","DOI":"10.1109\/ICCSE.2010.5593613"},{"key":"742_CR7","unstructured":"Ester M, Kriegel HP, Sander J et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd international conference on knowledge discovery and data mining. AAAI Press, Portland, pp 226\u2013231"},{"issue":"1","key":"742_CR8","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/0360-1315(87)90042-X","volume":"11","author":"JA Faidhi","year":"1987","unstructured":"Faidhi JA, Robinson S (1987) An empirical approach for detecting program similarity within a university programming environment. Comput Educ 11(1):11\u201319","journal-title":"Comput Educ"},{"key":"742_CR9","doi-asserted-by":"crossref","unstructured":"Flores E, Barr\u00f3n-Cede\u00f1o A, Rosso P et al (2011) Towards the detection of cross-language source code reuse. In: Proceedings of the 16th international conference on applications of natural language to information systems. Springer, Salford, pp 250\u2013253","DOI":"10.1007\/978-3-642-22327-3_31"},{"issue":"2","key":"742_CR10","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1147\/rd.312.0249","volume":"31","author":"RM Karp","year":"1987","unstructured":"Karp RM, Rabin MO (1987) Efficient randomized pattern-matching algorithms. IBM J Res Dev 31(2):249\u2013260","journal-title":"IBM J Res Dev"},{"key":"742_CR11","unstructured":"Klieman AB, Kowaltowski T (2009) Qualitative analysis and comparison of plagiarism-detection systems in student programs. Instituto de Computacao Universidade Estadual de Campinas (UNICAMP): Sao Poalo, Brazil"},{"key":"742_CR12","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"L Kaufman","year":"1990","unstructured":"Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley, New York"},{"key":"742_CR13","doi-asserted-by":"crossref","unstructured":"Kuo JY, Huang FC, Hung C, et al (2012) The study of plagiarism detection for object-oriented programming. In: Proceedings of the 6th international conference on genetic and evolutionary computing (ICGEC). IEEE, Kitakyushu, pp 188\u2013191","DOI":"10.1109\/ICGEC.2012.145"},{"key":"742_CR14","doi-asserted-by":"crossref","unstructured":"Lea D (2000) A Java fork\/join framework. In: Proceedings of the ACM 2000 conference on Java Grande. ACM, San Francisco, pp 36\u201343","DOI":"10.1145\/337449.337465"},{"key":"742_CR15","volume-title":"Principles of parallel programming","author":"C Lin","year":"2008","unstructured":"Lin C, Snyder L (2008) Principles of parallel programming. Addison-Wesley, Boston"},{"key":"742_CR16","doi-asserted-by":"crossref","unstructured":"Liu C, Chen C, Han J, et al (2006) GPLAG: detection of software plagiarism by program dependence graph analysis. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining. ACM, Philadelphia, pp 872\u2013881","DOI":"10.1145\/1150402.1150522"},{"issue":"1","key":"742_CR17","first-page":"22","volume":"3","author":"D Marinescu","year":"2013","unstructured":"Marinescu D, Baicoianu A, Dimitriu S (2013) A plagiarism detection system in computer source code. Int J Comput Sci Res Appl 3(1):22\u201330","journal-title":"Int J Comput Sci Res Appl"},{"key":"742_CR18","unstructured":"Ng RT, Han J (1994) Efficient and effective clustering methods for spatial data mining. In: Proceedings of the 20th international conference on very large data bases. Morgan Kaufmann Publishers, San Francisco, pp 144\u2013155"},{"key":"742_CR19","volume-title":"Introduction to data mining","author":"T Pang-Ning","year":"2006","unstructured":"Pang-Ning T, Steinbach M, Kumar V (2006) Introduction to data mining. Addison-Wesley, Boston"},{"key":"742_CR20","first-page":"1016","volume":"8","author":"L Prechelt","year":"2002","unstructured":"Prechelt L, Malpohl G, Philippsen M (2002) Finding plagiarisms among a set of programs with JPLAG. J Univers Comput Sci 8:1016\u20131038","journal-title":"J Univers Comput Sci"},{"key":"742_CR21","doi-asserted-by":"crossref","unstructured":"Rahal I, Wang B, Schnepf J (2009) A primer on text-data analysis. In: (2nd ed) Encyclopedia of information science and technology. IGI Publishing, Hershey, pp 3111\u20133118","DOI":"10.4018\/978-1-60566-026-4.ch496"},{"issue":"2","key":"742_CR22","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TE.2007.906778","volume":"51","author":"F Rosales","year":"2008","unstructured":"Rosales F, Garc\u00eda A, Rodr\u00edguez S et al (2008) Detection of plagiarism in programming assignments. IEEE Trans Educ 51(2):174\u2013183","journal-title":"IEEE Trans Educ"},{"key":"742_CR23","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365","journal-title":"J Comput Appl Math"},{"key":"742_CR24","doi-asserted-by":"crossref","unstructured":"Schleimer S, Wilkerson DS, Aiken A (2003) Winnowing: local algorithms for document fingerprinting. In: Proceedings of the 2003 ACM SIGMOD international conference on management of data. ACM, San Diego, pp 76\u201385","DOI":"10.1145\/872757.872770"},{"issue":"2","key":"742_CR25","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1108\/eb026637","volume":"33","author":"CJ Rijsbergen Van","year":"1977","unstructured":"Van Rijsbergen CJ (1977) A theoretical basis for the use of co-occurrence data in information retrieval. J Doc 33(2):106\u2013119","journal-title":"J Doc"},{"issue":"2","key":"742_CR26","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1093\/comjnl\/33.2.140","volume":"33","author":"G Whale","year":"1990","unstructured":"Whale G (1990) Identification of program similarity in large populations. Comput J 33(2):140\u2013146","journal-title":"Comput J"},{"key":"742_CR27","unstructured":"Wise MJ (1995) A system for comparing biological sequences using the running Karp-Rabin Greedy String-Tiling algorithm. In: Proceedings of the third international conference on intelligent systems for molecular biology. AAAI Press, Cambridge, pp 393\u2013401"},{"key":"742_CR28","doi-asserted-by":"crossref","unstructured":"Wise MJ (1996) YAP3: improved detection of similarities in computer program and other texts. In: Proceedings of the ACM SIGCSE technical symposium on computer science education. ACM, Philadelphia, pp 130\u2013134","DOI":"10.1145\/236452.236525"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-014-0742-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-014-0742-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-014-0742-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T06:11:15Z","timestamp":1559110275000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-014-0742-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3,22]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,5]]}},"alternative-id":["742"],"URL":"https:\/\/doi.org\/10.1007\/s10115-014-0742-2","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3,22]]}}}