{"id":"https://openalex.org/W2122992911","doi":"https://doi.org/10.1109/icpc.2009.5090050","title":"Syntax tree fingerprinting for source code similarity detection","display_name":"Syntax tree fingerprinting for source code similarity detection","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2122992911","doi":"https://doi.org/10.1109/icpc.2009.5090050","mag":"2122992911"},"language":"en","primary_location":{"id":"doi:10.1109/icpc.2009.5090050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpc.2009.5090050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 17th International Conference on Program Comprehension","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042865519","display_name":"Michel Chilowicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Michel Chilowicz","raw_affiliation_strings":["Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071886522","display_name":"\u00c9tienne Duris","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Etienne Duris","raw_affiliation_strings":["Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037869012","display_name":"Gilles Roussel","orcid":"https://orcid.org/0000-0002-8531-1566"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gilles Roussel","raw_affiliation_strings":["Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, Universit\u00e9 Paris-Est, Marne-la-Vallee, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'Informatique de l'Institut Gaspard-Monge, UMR CNRS 8049, 5 Bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042865519"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210152518"],"apc_list":null,"apc_paid":null,"fwci":10.8463,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98138065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9997000098228455,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8507364392280579},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.7928591966629028},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6747769117355347},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.5962246656417847},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.5159326195716858},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5064667463302612},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5049274563789368},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4966629147529602},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4886065125465393},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.487263560295105},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.47721797227859497},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4478437304496765},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4209938049316406},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4186646342277527},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.33908581733703613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2627963721752167},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12390902638435364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507364392280579},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.7928591966629028},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6747769117355347},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5962246656417847},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.5159326195716858},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5064667463302612},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5049274563789368},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4966629147529602},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4886065125465393},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.487263560295105},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.47721797227859497},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4478437304496765},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4209938049316406},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4186646342277527},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.33908581733703613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2627963721752167},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12390902638435364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpc.2009.5090050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpc.2009.5090050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 17th International Conference on Program Comprehension","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00620320v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00620320","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th IEEE International Conference on Program Comprehension (ICPC'09), May 2009, Vancouver, BC, Canada, Canada. pp.243-247","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1489909987","https://openalex.org/W1539221976","https://openalex.org/W1872325575","https://openalex.org/W1989130222","https://openalex.org/W2073265902","https://openalex.org/W2097631008","https://openalex.org/W2101222922","https://openalex.org/W2107697055","https://openalex.org/W2109943392","https://openalex.org/W2111295912","https://openalex.org/W2114790775","https://openalex.org/W2120319185","https://openalex.org/W2120836115","https://openalex.org/W2122992911","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2130564474","https://openalex.org/W2145009222","https://openalex.org/W2157532207","https://openalex.org/W2165739648","https://openalex.org/W2166278331","https://openalex.org/W2166901988","https://openalex.org/W2730427097","https://openalex.org/W2901608006","https://openalex.org/W6675500526"],"related_works":["https://openalex.org/W4389751695","https://openalex.org/W2077104824","https://openalex.org/W3176913510","https://openalex.org/W3138016835","https://openalex.org/W2536864162","https://openalex.org/W3197333277","https://openalex.org/W1625533892","https://openalex.org/W3149405943","https://openalex.org/W1599055565","https://openalex.org/W2342230821"],"abstract_inverted_index":{"Numerous":[0],"approaches":[1],"based":[2,38],"on":[3,39],"metrics,":[4],"token":[5],"sequence":[6],"pattern-matching,":[7],"abstract":[8],"syntax":[9],"tree":[10],"(AST)":[11],"or":[12],"program":[13],"dependency":[14],"graph":[15],"(PDG)":[16],"analysis":[17],"have":[18],"already":[19],"been":[20],"proposed":[21],"to":[22,43,85,95],"highlight":[23],"similarities":[24],"in":[25,28,62,93,108,113],"source":[26,70],"code:":[27],"this":[29],"paper":[30],"we":[31,53],"present":[32],"a":[33,44,55,63],"simple":[34],"and":[35,75,112],"scalable":[36],"architecture":[37],"AST":[40,60],"fingerprinting.":[41],"Thanks":[42],"study":[45],"of":[46,89],"several":[47],"hashing":[48],"strategies":[49],"reducing":[50],"false-positive":[51],"collisions,":[52],"propose":[54],"framework":[56],"that":[57,65,76],"efficiently":[58],"indexes":[59],"representations":[61],"database,":[64],"quickly":[66],"detects":[67],"exact":[68,91],"(w.r.t":[69],"code":[71],"abstraction)":[72],"clone":[73],"clusters":[74],"easily":[77],"retrieves":[78],"their":[79],"corresponding":[80],"ASTs.":[81],"Our":[82],"aim":[83],"is":[84],"allow":[86],"further":[87],"processing":[88],"neighboring":[90],"matches":[92],"order":[94],"identify":[96],"the":[97,103,109,114],"larger":[98],"approximate":[99],"matches,":[100],"dealing":[101],"with":[102],"common":[104],"modification":[105],"patterns":[106],"seen":[107],"intra-project":[110],"copy-pastes":[111],"plagiarism":[115],"cases.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
