{"id":"https://openalex.org/W7097106959","doi":null,"title":"Efficient and Effective Plagiarism Detection for Large Code Repositories","display_name":"Efficient and Effective Plagiarism Detection for Large Code Repositories","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7097106959"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.4500","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.4500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://goanna.cs.rmit.edu.au/~sdb/publications/burrows-hons04.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7097106959"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Justin Zobel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Steven Burrows","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Burrows","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Steven Burrows","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Burrows","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7782999873161316,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7782999873161316,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11492","display_name":"Academic integrity and plagiarism","score":0.21889999508857727,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/source-code-plagiarism-detection","display_name":"code plagiarism detection","score":0.9629999995231628},{"id":"https://openalex.org/keywords/academic-dishonesty","display_name":"academic dishonesty","score":0.45399999618530273},{"id":"https://openalex.org/keywords/programming-exercises","display_name":"programming exercises","score":0.7450000047683716},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.9229999780654907},{"id":"https://openalex.org/keywords/jplag","display_name":"JPlag","score":0.7459999918937683},{"id":"https://openalex.org/keywords/code-similarity","display_name":"code similarity","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.9196000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.7407000064849854},{"id":"https://openalex.org/C2777880217","wikidata":"https://www.wikidata.org/wiki/Q4674282","display_name":"Acknowledgement","level":2,"score":0.6345999836921692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5590000152587891},{"id":"https://openalex.org/C138147947","wikidata":"https://www.wikidata.org/wiki/Q1183659","display_name":"Declaration","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2694999873638153}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.4500","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.4500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://goanna.cs.rmit.edu.au/~sdb/publications/burrows-hons04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7098474846","https://openalex.org/W4236036072","https://openalex.org/W2155491649","https://openalex.org/W7150205320","https://openalex.org/W1979637212","https://openalex.org/W7101045566","https://openalex.org/W7061910782","https://openalex.org/W7024787372","https://openalex.org/W2921168655"],"abstract_inverted_index":{"The":[0],"copying":[1],"of":[2,38,41,72,86,90],"programming":[3],"assignments":[4],"is":[5,15,79,99],"a":[6],"widespread":[7],"problem":[8],"in":[9,51],"academic":[10],"institutions.":[11],"Manual":[12],"plagiarism":[13,20,34,48,65],"detection":[14,21,35,49],"time-consuming,":[16],"and":[17,59,69,110],"current":[18],"popular":[19],"systems":[22,36,45],"are":[23,32,50],"not":[24],"scalable":[25,81],"to":[26,88],"large":[27,70],"code":[28,64],"repositories.":[29],"While":[30],"there":[31],"text-based":[33],"capable":[37],"handling":[39],"millions":[40],"student":[42],"papers,":[43],"comparable":[44],"for":[46,63],"code-based":[47],"their":[52],"infancy.":[53],"In":[54],"this":[55,97],"thesis,":[56],"we":[57,74],"propose":[58],"evaluate":[60],"new":[61],"techniques":[62],"detection.":[66],"Using":[67],"small":[68],"collections":[71],"programs,":[73],"show":[75],"that":[76,89,96],"our":[77],"approach":[78],"highly":[80],"while":[82],"maintaining":[83],"similar":[84],"levels":[85],"effectiveness":[87],"JPlag.":[91],"1":[92],"Declaration":[93],"I":[94],"declare":[95],"work":[98],"entirely":[100],"my":[101],"own":[102],"except":[103],"where":[104],"due":[105],"acknowledgement":[106],"has":[107],"been":[108],"made":[109]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2025-10-27T00:00:00"}