{"id":"https://openalex.org/W2963625196","doi":"https://doi.org/10.1145/3304221.3319789","title":"Syntax-based Improvements to Plagiarism Detectors and their Evaluations","display_name":"Syntax-based Improvements to Plagiarism Detectors and their Evaluations","publication_year":2019,"publication_date":"2019-07-02","ids":{"openalex":"https://openalex.org/W2963625196","doi":"https://doi.org/10.1145/3304221.3319789","mag":"2963625196"},"language":"en","primary_location":{"id":"doi:10.1145/3304221.3319789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3304221.3319789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3304221.3319789","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM Conference on Innovation and Technology in Computer Science Education","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3304221.3319789","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060968441","display_name":"Lawton Nichols","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lawton Nichols","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059923669","display_name":"Kyle Dewey","orcid":"https://orcid.org/0000-0002-7998-3104"},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Dewey","raw_affiliation_strings":["California State University Northridge, Northridge, CA, USA"],"affiliations":[{"raw_affiliation_string":"California State University Northridge, Northridge, CA, USA","institution_ids":["https://openalex.org/I157638225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068320315","display_name":"Mehmet Emre","orcid":"https://orcid.org/0000-0001-8744-6459"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Emre","raw_affiliation_strings":["University of California,Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California,Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027847451","display_name":"Sitao Chen","orcid":"https://orcid.org/0009-0000-8913-6059"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sitao Chen","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074393511","display_name":"Ben Hardekopf","orcid":"https://orcid.org/0009-0008-1199-6129"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Hardekopf","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060968441"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":3.0806,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92084682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.998199999332428,"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":0.998199999332428,"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/T10260","display_name":"Software Engineering Research","score":0.9944999814033508,"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/T10028","display_name":"Topic Modeling","score":0.9771999716758728,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/plagiarism-detection","display_name":"Plagiarism detection","score":0.8882499933242798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8545310497283936},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5659794211387634},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.5419467687606812},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5402870178222656},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5138916969299316},{"id":"https://openalex.org/keywords/syntax-error","display_name":"Syntax error","score":0.49689486622810364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4738866686820984},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47216862440109253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4557892084121704},{"id":"https://openalex.org/keywords/metaprogramming","display_name":"Metaprogramming","score":0.44760674238204956},{"id":"https://openalex.org/keywords/grammar-induction","display_name":"Grammar induction","score":0.4378727972507477},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.4361550509929657},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40329280495643616},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3554595708847046},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.3066679835319519},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.14566779136657715}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.8882499933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545310497283936},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5659794211387634},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.5419467687606812},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5402870178222656},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5138916969299316},{"id":"https://openalex.org/C11742125","wikidata":"https://www.wikidata.org/wiki/Q1195374","display_name":"Syntax error","level":4,"score":0.49689486622810364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4738866686820984},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47216862440109253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4557892084121704},{"id":"https://openalex.org/C35390924","wikidata":"https://www.wikidata.org/wiki/Q661075","display_name":"Metaprogramming","level":2,"score":0.44760674238204956},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.4378727972507477},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.4361550509929657},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40329280495643616},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3554595708847046},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.3066679835319519},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.14566779136657715},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3304221.3319789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3304221.3319789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3304221.3319789","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM Conference on Innovation and Technology in Computer Science Education","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3304221.3319789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3304221.3319789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3304221.3319789","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM Conference on Innovation and Technology in Computer Science Education","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1575194763","display_name":"SHF: Small: Static Analysis for Safe Browser Addons","funder_award_id":"1319060","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G794432730","display_name":null,"funder_award_id":"CCF-1319060","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963625196.pdf","grobid_xml":"https://content.openalex.org/works/W2963625196.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W584037522","https://openalex.org/W1583371541","https://openalex.org/W2018951244","https://openalex.org/W2044348688","https://openalex.org/W2074805222","https://openalex.org/W2085698608","https://openalex.org/W2087064593","https://openalex.org/W2096498787","https://openalex.org/W2111295912","https://openalex.org/W2122992911","https://openalex.org/W2141128179","https://openalex.org/W2163840964","https://openalex.org/W2588341850","https://openalex.org/W2794792966","https://openalex.org/W2886751322","https://openalex.org/W2890485822","https://openalex.org/W4252211664"],"related_works":["https://openalex.org/W2613250302","https://openalex.org/W1988370859","https://openalex.org/W2005927140","https://openalex.org/W2965097461","https://openalex.org/W4288358733","https://openalex.org/W2910182226","https://openalex.org/W2944379287","https://openalex.org/W4288639287","https://openalex.org/W2804930929","https://openalex.org/W2963625196"],"abstract_inverted_index":{"Software":[0],"plagiarism":[1,16,24],"cheats":[2],"students":[3],"out":[4],"of":[5,94],"their":[6,34],"own":[7],"education":[8],"and":[9,101,113],"leads":[10],"to":[11,41,57,69,75],"unfair":[12],"grading,":[13],"making":[14],"software":[15],"detection":[17,25,66,117],"an":[18,80],"important":[19],"problem.":[20],"However,":[21],"many":[22],"popular":[23],"tools":[26],"are":[27],"inaccurate,":[28],"language-specific,":[29],"or":[30],"closed":[31],"source,":[32],"limiting":[33],"applicability.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,104],"seek":[40],"address":[42],"these":[43],"problems":[44],"via":[45],"a":[46,91],"novel":[47],"approach.":[48],"We":[49,88],"adapt":[50],"the":[51,60],"optimal":[52],"Smith-Waterman":[53],"sequence":[54],"alignment":[55],"algorithm":[56],"precisely":[58],"measure":[59],"similarity":[61],"between":[62],"programs,":[63],"greatly":[64],"improving":[65],"accuracy":[67],"relative":[68],"competitors.":[70],"Our":[71],"approach":[72,107],"is":[73],"applicable":[74],"any":[76],"language":[77],"describable":[78],"by":[79],"ANTLR":[81],"grammar,":[82],"which":[83],"includes":[84],"most":[85],"programming":[86],"languages.":[87],"also":[89],"provide":[90],"new":[92],"type":[93],"evaluation":[95],"based":[96],"on":[97],"random":[98],"program":[99],"generation":[100],"obfuscation.":[102],"Finally,":[103],"make":[105],"our":[106],"freely":[108],"available,":[109],"allowing":[110],"for":[111],"customizations":[112],"transparent":[114],"reasoning":[115],"about":[116],"behavior.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
