{"id":"https://openalex.org/W3126053546","doi":"https://doi.org/10.1145/3324884.3415291","title":"Sosed","display_name":"Sosed","publication_year":2020,"publication_date":"2020-12-21","ids":{"openalex":"https://openalex.org/W3126053546","doi":"https://doi.org/10.1145/3324884.3415291","mag":"3126053546"},"language":"en","primary_location":{"id":"doi:10.1145/3324884.3415291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3324884.3415291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering","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/A5088461870","display_name":"Egor Bogomolov","orcid":"https://orcid.org/0000-0002-3499-2402"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Egor Bogomolov","raw_affiliation_strings":["JetBrains Research, Saint Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, Saint Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013316832","display_name":"Yaroslav Golubev","orcid":"https://orcid.org/0000-0001-7009-635X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaroslav Golubev","raw_affiliation_strings":["JetBrains Research, Saint Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, Saint Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002763663","display_name":"Artyom Lobanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artyom Lobanov","raw_affiliation_strings":["JetBrains Research, Saint Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, Saint Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005183323","display_name":"Vladimir Kovalenko","orcid":"https://orcid.org/0000-0001-5880-7323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Kovalenko","raw_affiliation_strings":["JetBrains Research, JetBrains N.V., Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"JetBrains Research, JetBrains N.V., Amsterdam, The Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065316896","display_name":"Timofey Bryksin","orcid":"https://orcid.org/0000-0001-9022-3563"},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Timofey Bryksin","raw_affiliation_strings":["Saint Petersburg State University, Saint Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"Saint Petersburg State University, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I172901346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088461870"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5338,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77221373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1316","last_page":"1320"},"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/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9886999726295471,"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":0.7589578628540039},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.6282410621643066},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.578295111656189},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5666235089302063},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5109209418296814},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4992096424102783},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48753997683525085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4342527687549591},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4217313528060913},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3254881203174591},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3138556182384491},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11080870032310486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10657456517219543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589578628540039},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.6282410621643066},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.578295111656189},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5666235089302063},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5109209418296814},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4992096424102783},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48753997683525085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4342527687549591},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4217313528060913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3254881203174591},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3138556182384491},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11080870032310486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10657456517219543},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3324884.3415291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3324884.3415291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W572111793","https://openalex.org/W1673310716","https://openalex.org/W1880262756","https://openalex.org/W1965555277","https://openalex.org/W1969157788","https://openalex.org/W1986535241","https://openalex.org/W2071949631","https://openalex.org/W2112546494","https://openalex.org/W2125980283","https://openalex.org/W2147152072","https://openalex.org/W2150376021","https://openalex.org/W2150593711","https://openalex.org/W2252211741","https://openalex.org/W2401896535","https://openalex.org/W2470924201","https://openalex.org/W2475828198","https://openalex.org/W2493916176","https://openalex.org/W2593864460","https://openalex.org/W2597820098","https://openalex.org/W2604710676","https://openalex.org/W2733829216","https://openalex.org/W2996086147","https://openalex.org/W4231134532","https://openalex.org/W4252347043"],"related_works":["https://openalex.org/W2107962325","https://openalex.org/W2248928492","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W4292559016","https://openalex.org/W4231937131","https://openalex.org/W1589342014","https://openalex.org/W598950423","https://openalex.org/W2008053682","https://openalex.org/W3081644756"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,34,68],"present":[4],"Sosed,":[5],"a":[6,23,52,60],"tool":[7,78],"for":[8,26],"discovering":[9],"similar":[10,42,66],"software":[11],"projects.":[12],"We":[13,50,107],"use":[14,51],"fastText":[15],"to":[16,37,114,117],"compute":[17],"the":[18,70,100,104],"embeddings":[19,36],"of":[20,40,54,72],"subtokens":[21,43,86],"into":[22],"dense":[24],"space":[25],"120,000":[27],"GitHub":[28,57],"projects":[29,58,98],"in":[30,47,87,103],"200":[31],"languages.":[32],"Then,":[33],"cluster":[35,94],"identify":[38,65],"groups":[39],"semantically":[41],"that":[44],"reflect":[45],"topics":[46],"source":[48],"code.":[49],"dataset":[53],"9":[55],"million":[56],"as":[59,83],"reference":[61],"search":[62,105],"base.":[63,106],"To":[64],"projects,":[67],"compare":[69],"distributions":[71],"clusters":[73,110],"among":[74],"their":[75],"subtokens.":[76],"The":[77],"receives":[79],"an":[80],"arbitrary":[81],"project":[82],"input,":[84],"extracts":[85],"16":[88],"most":[89],"popular":[90],"programming":[91],"languages,":[92],"computes":[93],"distribution,":[95],"and":[96],"finds":[97],"with":[99,111],"closest":[101],"distribution":[102],"labeled":[108],"subtoken":[109],"short":[112],"descriptions":[113],"enable":[115],"Sosed":[116],"produce":[118],"interpretable":[119],"output.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-02-01T00:00:00"}
