{"id":"https://openalex.org/W2095291909","doi":"https://doi.org/10.1145/1651309.1651312","title":"Tree-pattern-based duplicate code detection","display_name":"Tree-pattern-based duplicate code detection","publication_year":2009,"publication_date":"2009-11-06","ids":{"openalex":"https://openalex.org/W2095291909","doi":"https://doi.org/10.1145/1651309.1651312","mag":"2095291909"},"language":"en","primary_location":{"id":"doi:10.1145/1651309.1651312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651309.1651312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM first international workshop on Data-intensive software management and mining","raw_type":"proceedings-article"},"type":"article","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/A5077229529","display_name":"Hyo-Sub Lee","orcid":"https://orcid.org/0000-0002-7021-2514"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyo-Sub Lee","raw_affiliation_strings":["Hanyang University, Ansan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University, Ansan, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109880753","display_name":"Kyung-Goo Doh","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyung-Goo Doh","raw_affiliation_strings":["Hanyang University, Ansan, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University, Ansan, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.14936139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615812420845032},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6095550060272217},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.5431126952171326},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5338059067726135},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.46047157049179077},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4518331289291382},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.447626531124115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3308103680610657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26512426137924194},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.26231855154037476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2065856158733368},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17445901036262512},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1641623079776764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615812420845032},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6095550060272217},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.5431126952171326},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5338059067726135},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.46047157049179077},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4518331289291382},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.447626531124115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3308103680610657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26512426137924194},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.26231855154037476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2065856158733368},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17445901036262512},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1641623079776764},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1145/1651309.1651312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651309.1651312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM first international workshop on Data-intensive software management and mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hanyang.ac.kr:20.500.11754/82199","is_oa":false,"landing_page_url":"http://repository.hanyang.ac.kr/handle/20.500.11754/82199","pdf_url":null,"source":{"id":"https://openalex.org/S4306401328","display_name":"The Royal Society of Chemistry\u2019s Journals, Books and Databases (The Royal Society of Chemistry)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2751430930","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/I2751430930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1569963244","https://openalex.org/W1587010832","https://openalex.org/W1989130222","https://openalex.org/W2048382152","https://openalex.org/W2049461910","https://openalex.org/W2104301886","https://openalex.org/W2109943392","https://openalex.org/W2120836115","https://openalex.org/W2128782367","https://openalex.org/W2138756793","https://openalex.org/W2153029781","https://openalex.org/W2157532207","https://openalex.org/W2166278331","https://openalex.org/W2298313545","https://openalex.org/W4285719527","https://openalex.org/W6634246166"],"related_works":["https://openalex.org/W170547082","https://openalex.org/W2136735429","https://openalex.org/W4229950834","https://openalex.org/W3107197685","https://openalex.org/W2908418870","https://openalex.org/W48124421","https://openalex.org/W272774291","https://openalex.org/W2604902477","https://openalex.org/W3202117991","https://openalex.org/W1972574144"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,38],"tree-pattern-based":[4],"method":[5,61],"of":[6,55,66,75,79],"automatically":[7],"and":[8,24,28],"accurately":[9],"finding":[10,76],"code":[11,67],"clones":[12,80],"in":[13,36,68],"program":[14],"files.":[15],"Duplicate":[16],"tree-patterns":[17],"are":[18],"first":[19],"collected":[20],"by":[21],"anti-unification":[22],"algorithm":[23,33],"redundancy-free":[25],"exhaustive":[26],"comparisons,":[27],"then":[29],"finally":[30],"clustered.":[31],"The":[32],"is":[34,44],"designed":[35],"such":[37],"way":[39],"that":[40],"the":[41,63,73,83],"same":[42],"comparison":[43],"not":[45],"repeated":[46],"for":[47,58],"speed,":[48],"while":[49,81],"thoroughly":[50],"examining":[51],"every":[52],"possible":[53],"pairs":[54],"tree":[56],"patterns":[57],"accuracy.":[59],"Our":[60],"maintains":[62],"syntax":[64],"structure":[65],"tree-pattern":[69],"clusters,":[70],"which":[71],"gives":[72],"flexibility":[74],"different":[77],"types":[78],"keeping":[82],"precision.":[84]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}