{"id":"https://openalex.org/W7166344709","doi":"https://doi.org/10.5281/zenodo.20980134","title":"Token-Based Clone Detection for PHP: An Empirical Evaluation of Methods and a Labelled Benchmark","display_name":"Token-Based Clone Detection for PHP: An Empirical Evaluation of Methods and a Labelled Benchmark","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166344709","doi":"https://doi.org/10.5281/zenodo.20980134"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.20980134","doi":"https://doi.org/10.5281/zenodo.20980134","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20980134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.20980134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125894854","display_name":"Luciano Federico Pereira","orcid":"https://orcid.org/0009-0002-4591-6568","observed_orcids":["https://orcid.org/0009-0002-4591-6568"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pereira, Luciano Federico","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-4591-6568","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5125894854"],"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":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/T11492","display_name":"Academic integrity and plagiarism","score":0.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"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/code-duplication","display_name":"code duplication","score":0.421999990940094},{"id":"https://openalex.org/keywords/mutation-testing","display_name":"mutation testing","score":0.6510000228881836},{"id":"https://openalex.org/keywords/edit-distance","display_name":"edit distance","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7785999774932861},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692000031471252},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5787000060081482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5550000071525574},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.20980134","doi":"https://doi.org/10.5281/zenodo.20980134","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20980134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.20980135","doi":"https://doi.org/10.5281/zenodo.20980135","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20980135","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.20980134","doi":"https://doi.org/10.5281/zenodo.20980134","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20980134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"phpcpd":[0],"is":[1,224,247,253],"a":[2,30,144,148,162,169,180,184,195,201,217],"widely":[3],"used":[4],"PHP":[5,93,118,171],"copy/paste":[6],"(clone)":[7],"detector":[8],"whose":[9],"last":[10],"released":[11,49,248,254],"version":[12],"(6.0.3,":[13],"2020)":[14],"performs":[15],"Rabin\u2013Karp":[16],"exact":[17],"matching":[18,72,238],"of":[19,102,204],"Type-1":[20],"and":[21,50,73,120,122,155,165,200,251],"Type-2":[22],"clones.":[23],"An":[24],"unreleased":[25,126],"7.0.0":[26,46],"development":[27],"line":[28],"added":[29],"ConQAT-style":[31],"approximate":[32],"suffix-tree":[33,127,237],"algorithm":[34],"for":[35,255],"Type-3":[36],"(near-miss)":[37],"detection":[38],"(contributed":[39],"upstream":[40],"as":[41,134],"pull":[42],"request":[43],"#199),":[44],"but":[45],"was":[47,53],"never":[48,60],"the":[51,111,177],"project":[52],"archived":[54,112],"in":[55],"2023,":[56],"so":[57],"this":[58],"capability":[59],"reached":[61],"users.":[62],"The":[63,245],"clone-detection":[64],"literature":[65],"offers":[66],"further":[67,235],"methods":[68,133],"\u2014":[69,76],"order-invariant":[70],"token-bag":[71,139],"type-aware":[74,141],"normalization":[75,211],"that":[77,159],"had":[78],"not":[79],"been":[80],"applied":[81],"to":[82,99,117,206,226],"PHP,":[83],"and,":[84],"unlike":[85],"Java":[86],"(BigCloneBench)":[87],"or":[88],"C":[89],"(POJ-104),":[90],"no":[91,213],"labelled":[92,170],"clone":[94,172],"benchmark":[95,173],"existed":[96],"on":[97,110,192],"which":[98],"evaluate":[100,123],"any":[101],"them.":[103],"This":[104],"work":[105],"addresses":[106],"both":[107],"gaps.":[108],"Building":[109],"codebase,":[113],"we":[114,129,166],"modernize":[115],"it":[116],"8.5,":[119],"complete":[121],"its":[124],"previously":[125],"engine;":[128],"implement":[130],"additional":[131],"literature-grounded":[132],"selectable":[135],"engines":[136],"(a":[137],"SourcererCC":[138],"matcher,":[140],"edit":[142],"weights,":[143],"token-type":[145],"abstraction":[146],"with":[147,242],"type-anchored":[149,210],"variant,":[150],"an":[151,156],"IDF":[152],"stopword":[153],"filter,":[154],"incremental":[157],"index":[158],"provably":[160],"reproduces":[161],"full":[163],"pass);":[164],"construct":[167],"BCB-PHP,":[168],"(to":[174],"our":[175],"knowledge":[176],"first),":[178],"comprising":[179],"mutation-injection":[181],"harness":[182],"over":[183],"pinned,":[185],"six-corpus":[186],"type-density":[187,196],"gradient.":[188],"Evaluating":[189],"each":[190],"method":[191],"BCB-PHP":[193,252],"yields":[194],"\u00d7":[197],"clone-density":[198],"map":[199],"specificity":[202],"increase":[203],"+10.9":[205],"+45.3":[207],"points":[208],"from":[209],"at":[212],"recall":[214],"cost,":[215],"motivating":[216],"combined":[218],"exact-and-reorder-tolerant":[219],"default":[220],"configuration;":[221],"identifier":[222],"fuzzing":[223],"shown":[225],"reduce":[227],"precision":[228],"substantially.":[229],"A":[230],"profiler-guided":[231],"banded":[232],"edit-distance":[233],"optimization":[234],"cuts":[236],"cost":[239],"by":[240],"~3.5\u00d7":[241],"byte-identical":[243],"output.":[244],"tool":[246],"under":[249],"BSD-3-Clause,":[250],"reuse.":[256]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-06-28T00:00:00"}