{"id":"https://openalex.org/W3203324567","doi":"https://doi.org/10.1145/3460210.3493578","title":"A Toolkit for Generating Code Knowledge Graphs","display_name":"A Toolkit for Generating Code Knowledge Graphs","publication_year":2021,"publication_date":"2021-11-24","ids":{"openalex":"https://openalex.org/W3203324567","doi":"https://doi.org/10.1145/3460210.3493578","mag":"3203324567"},"language":"en","primary_location":{"id":"doi:10.1145/3460210.3493578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460210.3493578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Knowledge Capture Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.09440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031546123","display_name":"Ibrahim Abdelaziz","orcid":"https://orcid.org/0000-0003-1449-5115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Abdelaziz","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA","IBM/TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]},{"raw_affiliation_string":"IBM/TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012855077","display_name":"Julian Dolby","orcid":"https://orcid.org/0000-0002-6658-2678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Dolby","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA","IBM/TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]},{"raw_affiliation_string":"IBM/TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030875887","display_name":"Jamie P. McCusker","orcid":"https://orcid.org/0000-0003-1085-6059"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie McCusker","raw_affiliation_strings":["Rensselaer Polytechnic Institute (RPI), Troy, NY, USA","Rensselaer Polytechnic Institute(RPI), Troy, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute (RPI), Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute(RPI), Troy, NY, USA#TAB#","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kavitha Srinivas","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA","IBM/TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]},{"raw_affiliation_string":"IBM/TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.977400004863739,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9613000154495239,"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":0.8278016448020935},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7929306030273438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6256322264671326},{"id":"https://openalex.org/keywords/call-graph","display_name":"Call graph","score":0.614937424659729},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5792663097381592},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5164563655853271},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.4923797845840454},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.49193906784057617},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45386362075805664},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3916317820549011},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33981412649154663},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2628536820411682},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2597522735595703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278016448020935},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7929306030273438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6256322264671326},{"id":"https://openalex.org/C102379954","wikidata":"https://www.wikidata.org/wiki/Q2589940","display_name":"Call graph","level":2,"score":0.614937424659729},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5792663097381592},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5164563655853271},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.4923797845840454},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.49193906784057617},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45386362075805664},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3916317820549011},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33981412649154663},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2628536820411682},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2597522735595703}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3460210.3493578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460210.3493578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Knowledge Capture Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.09440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09440","pdf_url":"https://arxiv.org/pdf/2002.09440","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3203324567","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.09440.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.09440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.09440","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.57702/nzehbfdc","is_oa":true,"landing_page_url":"https://doi.org/10.57702/nzehbfdc","pdf_url":null,"source":{"id":"https://openalex.org/S7407053387","display_name":"TIB Data Manager","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.09440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09440","pdf_url":"https://arxiv.org/pdf/2002.09440","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3203324567.pdf","grobid_xml":"https://content.openalex.org/works/W3203324567.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W148369031","https://openalex.org/W1512387364","https://openalex.org/W1552847225","https://openalex.org/W1970607969","https://openalex.org/W1980075035","https://openalex.org/W1983167413","https://openalex.org/W2022166150","https://openalex.org/W2035484480","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2098936704","https://openalex.org/W2140021378","https://openalex.org/W2144427809","https://openalex.org/W2159750251","https://openalex.org/W2189149111","https://openalex.org/W2266912522","https://openalex.org/W2510906045","https://openalex.org/W2514626402","https://openalex.org/W2516621648","https://openalex.org/W2764017292","https://openalex.org/W2799423598","https://openalex.org/W2810583043","https://openalex.org/W2887364112","https://openalex.org/W2890961898","https://openalex.org/W2963015915","https://openalex.org/W2963499994","https://openalex.org/W2963895422","https://openalex.org/W2963935794","https://openalex.org/W2964150020","https://openalex.org/W2968527697","https://openalex.org/W2969603092","https://openalex.org/W2973529529","https://openalex.org/W2980941512","https://openalex.org/W3008088841","https://openalex.org/W3022580834","https://openalex.org/W3099972168","https://openalex.org/W3108726049","https://openalex.org/W3176061953"],"related_works":["https://openalex.org/W3087951766","https://openalex.org/W2275719818","https://openalex.org/W3131055623","https://openalex.org/W2956062508","https://openalex.org/W3034976548","https://openalex.org/W2395168724","https://openalex.org/W2482382985","https://openalex.org/W2728773317","https://openalex.org/W2042559624","https://openalex.org/W2034209539","https://openalex.org/W2117642462","https://openalex.org/W2100447922","https://openalex.org/W2126859103","https://openalex.org/W3203756598","https://openalex.org/W2398283722","https://openalex.org/W3164350412","https://openalex.org/W2970004377","https://openalex.org/W1974020522","https://openalex.org/W3133121539","https://openalex.org/W2145021485"],"abstract_inverted_index":{"Knowledge":[0],"graphs":[1,30,106,111,117,165],"have":[2],"been":[3],"proven":[4],"extremely":[5],"useful":[6],"in":[7,11,60,107,148],"powering":[8],"diverse":[9],"applications":[10,36],"semantic":[12],"search":[13],"and":[14,45,66,87,141],"natural":[15],"language":[16],"understanding.":[17],"In":[18],"this":[19],"work,":[20],"we":[21],"present":[22],"GraphGen4Code,":[23],"a":[24],"toolkit":[25,103,126,161],"to":[26,52,109,130,162,180],"build":[27,163],"code":[28,41,46,54,92,151],"knowledge":[29],"that":[31],"can":[32,115],"similarly":[33],"power":[34],"various":[35],"such":[37,99,164],"as":[38,79,100,118,166,168],"program":[39,82],"search,":[40],"understanding,":[42],"bug":[43],"detection,":[44],"automation.":[47],"GraphGen4Code":[48],"uses":[49,104],"generic":[50],"techniques":[51],"capture":[53],"semantics":[55],"with":[56,153],"the":[57,61,122,125,160,169,173,181],"key":[58],"nodes":[59],"graph":[62,152,177],"representing":[63],"classes,":[64],"functions":[65,90],"methods.":[67],"Edges":[68],"indicate":[69],"function":[70,77],"usage":[71,94],"(e.g.,":[72,91],"how":[73],"data":[74],"flows":[75],"through":[76],"calls,":[78],"derived":[80],"from":[81,136],"analysis":[83],"of":[84,124,172],"real":[85],"code),":[86],"documentation":[88],"about":[89],"documentation,":[93,95],"or":[96,114],"forum":[97,144],"discussions":[98],"StackOverflow).":[101],"Our":[102],"named":[105],"RDF":[108],"model":[110],"per":[112],"program,":[113],"output":[116],"JSON.":[119],"We":[120,158],"show":[121],"scalability":[123],"by":[127],"applying":[128],"it":[129],"1.3":[131],"million":[132,143],"Python":[133,139],"files":[134],"drawn":[135],"GitHub,":[137],"2,300":[138],"modules,":[140],"47":[142],"posts.":[145],"This":[146],"results":[147],"an":[149],"integrated":[150],"over":[154],"2":[155,174],"billion":[156,175],"triples.":[157],"make":[159],"well":[167],"sample":[170],"extraction":[171],"triples":[176],"publicly":[178],"available":[179],"community":[182],"for":[183],"use.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}