{"id":"https://openalex.org/W2162624122","doi":"https://doi.org/10.1145/1774088.1774101","title":"A novel framework to detect source code plagiarism","display_name":"A novel framework to detect source code plagiarism","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W2162624122","doi":"https://doi.org/10.1145/1774088.1774101","mag":"2162624122"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01067161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088549422","display_name":"Boris Lesner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Boris Lesner","raw_affiliation_strings":["GREYC, Caen Cedex - France","Equipe Hultech - Laboratoire GREYC - UMR6072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GREYC, Caen Cedex - France","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Equipe Hultech - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022820267","display_name":"Romain Brixtel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Brixtel","raw_affiliation_strings":["GREYC, Caen Cedex - France","Equipe Hultech - Laboratoire GREYC - UMR6072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GREYC, Caen Cedex - France","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Equipe Hultech - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024898630","display_name":"Cyril Bazin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cyril Bazin","raw_affiliation_strings":["GREYC, Caen Cedex - France","Equipe Hultech - Laboratoire GREYC - UMR6072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GREYC, Caen Cedex - France","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Equipe Hultech - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078697158","display_name":"Guillaume Bagan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Bagan","raw_affiliation_strings":["GREYC, Caen Cedex - France","Equipe AMACC - Laboratoire GREYC - UMR6072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GREYC, Caen Cedex - France","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Equipe AMACC - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210139483"],"apc_list":null,"apc_paid":null,"fwci":4.4143,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94813614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8765273094177246},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.7492556571960449},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7010325193405151},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6868575811386108},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5832830667495728},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5651187300682068},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5577201247215271},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5378401279449463},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5252484679222107},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5155977606773376},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43650686740875244},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38220810890197754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37466514110565186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3401648998260498},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16969633102416992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765273094177246},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.7492556571960449},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7010325193405151},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6868575811386108},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5832830667495728},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5651187300682068},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5577201247215271},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5378401279449463},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5252484679222107},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5155977606773376},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43650686740875244},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38220810890197754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37466514110565186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3401648998260498},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16969633102416992},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1774088.1774101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01067161v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01067161","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAC '10 Proceedings of the 2010 ACM Symposium on Applied Computing, Mar 2010, Sierre, Switzerland. pp.57-58, &#x27E8;10.1145/1774088.1774101&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01067161v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01067161","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAC '10 Proceedings of the 2010 ACM Symposium on Applied Computing, Mar 2010, Sierre, Switzerland. pp.57-58, &#x27E8;10.1145/1774088.1774101&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2128859735","https://openalex.org/W2222512263"],"related_works":["https://openalex.org/W3127553152","https://openalex.org/W3002459461","https://openalex.org/W3173165160","https://openalex.org/W3127649977","https://openalex.org/W4287331153","https://openalex.org/W2155491649","https://openalex.org/W4224015079","https://openalex.org/W2100097978","https://openalex.org/W3091649732","https://openalex.org/W1985086575"],"abstract_inverted_index":{"Our":[0,73],"work":[1,45],"focuses":[2],"on":[3,61,133,144],"detecting":[4],"plagiarism":[5,23,137],"within":[6,24],"a":[7,17,57,79,90,110,127],"source":[8,25,148],"code":[9,26],"corpus.":[10],"The":[11,96],"case":[12],"study":[13],"is":[14,75,136],"to":[15,20,49,67,71,87,116,156],"help":[16],"human":[18,128],"corrector":[19],"find":[21],"out":[22,77],"written":[27],"by":[28],"Computer":[29],"Science":[30],"students.":[31],"Like":[32],"other":[33],"approaches,":[34],"we":[35,46,123],"use":[36],"the":[37,62,102,114,118],"notion":[38],"of":[39,64,113,146],"similarity":[40],"distance.":[41],"However,":[42],"in":[43],"this":[44],"introduce":[47],"segmentation":[48],"split":[50],"documents":[51],"into":[52],"smaller":[53],"parts":[54],"and":[55],"propose":[56],"document-wise":[58],"distance":[59],"based":[60],"cost":[63],"permuting":[65],"segments":[66],"transform":[68],"one":[69],"document":[70],"another.":[72],"framework":[74,143],"laid":[76],"as":[78,122],"pipeline,":[80],"where":[81],"each":[82],"stage":[83],"can":[84],"be":[85],"parameterized":[86],"build":[88],"up":[89],"plagirism":[91],"detector":[92],"fitting":[93],"user":[94,129],"needs.":[95],"approach":[97],"makes":[98],"no":[99],"assumption":[100],"about":[101],"programming":[103,152],"language":[104],"being":[105],"analyzed.":[106],"Furthermore,":[107],"it":[108,135],"provides":[109],"synthetical":[111],"report":[112],"results":[115],"ease":[117],"decision":[119],"making":[120],"process,":[121],"consider":[124],"that":[125],"only":[126],"has":[130],"final":[131],"word":[132],"wether":[134],"or":[138],"not.":[139],"We":[140],"tested":[141],"our":[142],"hundreds":[145],"real":[147],"files,":[149],"involving":[150],"many":[151],"languages,":[153],"allowing":[154],"us":[155],"discover":[157],"previously":[158],"undetected":[159],"frauds.":[160]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}
