{"id":"https://openalex.org/W4402673861","doi":"https://doi.org/10.1109/e-science62913.2024.10678701","title":"Multi-Level AI-Driven Analysis of Software Repository Similarities","display_name":"Multi-Level AI-Driven Analysis of Software Repository Similarities","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402673861","doi":"https://doi.org/10.1109/e-science62913.2024.10678701"},"language":"en","primary_location":{"id":"doi:10.1109/e-science62913.2024.10678701","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/e-science62913.2024.10678701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","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/A5100634084","display_name":"Honglin Zhang","orcid":"https://orcid.org/0000-0003-1727-975X"},"institutions":[{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Honglin Zhang","raw_affiliation_strings":["University of St. Andrews,School of Computer Science,St Andrews,UK"],"affiliations":[{"raw_affiliation_string":"University of St. Andrews,School of Computer Science,St Andrews,UK","institution_ids":["https://openalex.org/I16835326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392433","display_name":"Leyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leyu Zhang","raw_affiliation_strings":["University of St. Andrews,School of Computer Science,St Andrews,UK"],"affiliations":[{"raw_affiliation_string":"University of St. Andrews,School of Computer Science,St Andrews,UK","institution_ids":["https://openalex.org/I16835326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053363846","display_name":"Lei Fang","orcid":"https://orcid.org/0000-0002-1546-7645"},"institutions":[{"id":"https://openalex.org/I16835326","display_name":"University of St Andrews","ror":"https://ror.org/02wn5qz54","country_code":"GB","type":"education","lineage":["https://openalex.org/I16835326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":["University of St. Andrews,School of Computer Science,St Andrews,UK"],"affiliations":[{"raw_affiliation_string":"University of St. Andrews,School of Computer Science,St Andrews,UK","institution_ids":["https://openalex.org/I16835326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003692107","display_name":"Rosa Filgueira","orcid":"https://orcid.org/0000-0002-5715-3046"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rosa Filgueira","raw_affiliation_strings":["University of Edinburgh,EPCC,Edinburgh,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,EPCC,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100634084"],"corresponding_institution_ids":["https://openalex.org/I16835326"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24966229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2102.04664","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.978600025177002,"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":0.978600025177002,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9052000045776367,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9046000242233276,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7392235398292542},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47230982780456543},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.42703500390052795},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3077705502510071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392235398292542},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47230982780456543},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42703500390052795},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3077705502510071}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science62913.2024.10678701","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/e-science62913.2024.10678701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"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/W2041004593","https://openalex.org/W2301906523","https://openalex.org/W2302501749","https://openalex.org/W2596043126","https://openalex.org/W2794601162","https://openalex.org/W2943971163","https://openalex.org/W3081886688","https://openalex.org/W3098605233","https://openalex.org/W3136398522","https://openalex.org/W3140103367","https://openalex.org/W3199034492","https://openalex.org/W3215622429","https://openalex.org/W4221166942","https://openalex.org/W4295991108","https://openalex.org/W4301168982","https://openalex.org/W4306173528","https://openalex.org/W4312613141","https://openalex.org/W4322007924","https://openalex.org/W4385687379","https://openalex.org/W4385821148","https://openalex.org/W4385977054","https://openalex.org/W4387005714","https://openalex.org/W4387006420","https://openalex.org/W6682124274","https://openalex.org/W6790588633"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2,52],"significant":[3],"enhancements":[4],"to":[5,77,95],"RepoSim4Py":[6,18],"and":[7,30,51,60,79,90,108],"RepoSnipy,":[8],"advanced":[9],"semantic":[10],"tools":[11,94],"for":[12],"deep":[13],"analysis":[14],"of":[15,38,100,114],"software":[16,101,106],"repositories.":[17],"commandline":[19],"toolbox":[20],"now":[21],"supports":[22],"multi-level":[23],"embedding,":[24],"encompassing":[25],"code,":[26],"documentation,":[27],"requirements,":[28],"README,":[29],"comprehensive":[31],"repository":[32,39,48,57,81],"analysis,":[33],"which":[34],"enable":[35],"the":[36,97],"understanding":[37],"dynamics.":[40],"Concurrently,":[41],"RepoSnipy":[42],"webbased":[43],"search":[44],"engine":[45],"facilitates":[46],"sophisticated":[47],"similarity":[49],"searches":[50],"clustering":[53],"based":[54],"on":[55,74],"both":[56],"tags":[58],"(topic_cluster)":[59],"code":[61],"embeddings":[62],"(code_cluster).":[63],"We":[64],"also":[65],"introduce":[66],"SimilarityCal,":[67],"a":[68],"novel":[69],"binary":[70],"classification":[71],"model":[72],"trained":[73],"these":[75],"clusters,":[76],"predict":[78],"quantify":[80],"similarities":[82],"with":[83,92],"high":[84],"accuracy.":[85],"These":[86],"developments":[87],"provide":[88],"researchers":[89],"developers":[91],"powerful":[93],"navigate":[96],"complex":[98],"landscape":[99],"repositories,":[102],"improving":[103],"efficiency":[104],"in":[105],"development":[107],"fostering":[109],"innovation":[110],"through":[111],"better":[112],"reuse":[113],"existing":[115],"resources.":[116]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}