{"id":"https://openalex.org/W3000141146","doi":"https://doi.org/10.14778/3401960.3401972","title":"Searching a database of source codes using contextualized code search","display_name":"Searching a database of source codes using contextualized code search","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3000141146","doi":"https://doi.org/10.14778/3401960.3401972","mag":"3000141146"},"language":"en","primary_location":{"id":"doi:10.14778/3401960.3401972","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3401960.3401972","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.03277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rohan Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohan Mukherjee","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Swarat Chaudhuri","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swarat Chaudhuri","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chris Jermaine","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Jermaine","raw_affiliation_strings":["Rice University"],"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":1.1126,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83424809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"13","issue":"10","first_page":"1765","last_page":"1778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9606000185012817,"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":0.9606000185012817,"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":0.00930000003427267,"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":0.0032999999821186066,"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/code","display_name":"Code (set theory)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.45399999618530273},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.40450000762939453},{"id":"https://openalex.org/keywords/database-model","display_name":"Database model","score":0.34200000762939453},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3357999920845032},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.3319999873638153},{"id":"https://openalex.org/keywords/redundant-code","display_name":"Redundant code","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198000192642212},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5239999890327454},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.3296000063419342},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.32350000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C47434764","wikidata":"https://www.wikidata.org/wiki/Q1770035","display_name":"Dead code","level":5,"score":0.2761000096797943},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.2687999904155731},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.2646999955177307},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3401960.3401972","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3401960.3401972","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2001.03277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03277","pdf_url":"https://arxiv.org/pdf/2001.03277","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.03277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03277","pdf_url":"https://arxiv.org/pdf/2001.03277","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1986541713","https://openalex.org/W2002219703","https://openalex.org/W2037237472","https://openalex.org/W2101414596","https://openalex.org/W2106259924","https://openalex.org/W2106999256","https://openalex.org/W2115317346","https://openalex.org/W2123570619","https://openalex.org/W2131774270","https://openalex.org/W2134092629","https://openalex.org/W2135194391","https://openalex.org/W2247374552","https://openalex.org/W2387719207","https://openalex.org/W2467604901","https://openalex.org/W2794601162","https://openalex.org/W2795013376","https://openalex.org/W2805788202","https://openalex.org/W2888651608","https://openalex.org/W2913932916","https://openalex.org/W2950368691","https://openalex.org/W2954552517","https://openalex.org/W2954823997","https://openalex.org/W2963355447","https://openalex.org/W2968179027","https://openalex.org/W2999343753","https://openalex.org/W3106889297","https://openalex.org/W4229675450","https://openalex.org/W4230667638","https://openalex.org/W4232188856","https://openalex.org/W4249157519"],"related_works":[],"abstract_inverted_index":{"Consider":[0],"the":[1,18,34,37,46,49,55,62,70,73,80,113,122,129,198],"case":[2],"where":[3,112],"a":[4,11,22,25,109,118,133,155,162,181,189,207],"programmer":[5,56],"has":[6,14],"written":[7],"some":[8],"part":[9,16],"of":[10,17,45,164,168,174,200,209],"program,":[12,130],"but":[13],"left":[15],"program":[19],"(such":[20],"as":[21,108],"method":[23],"or":[24,166],"function":[26,120],"body)":[27],"incomplete.":[28],"The":[29,65,92],"goal":[30,114],"is":[31,67,89,115,141,179],"to":[32,40,54,59,83,98,116,143,153,158,196,205],"use":[33,77],"context":[35],"surrounding":[36],"missing":[38,63],"code":[39,82,88,106,127,140,160,204],"automatically":[41],"\"figure":[42],"out\"":[43],"which":[44,86,138],"codes":[47,169],"in":[48,57,69,79,161],"database":[50,87,126,139,163,203],"would":[51],"be":[52,96,144,150,194],"useful":[53],"order":[58],"help":[60],"complete":[61],"code.":[64],"search":[66,74,107,171],"\"contextualized\"":[68],"sense":[71],"that":[72,124,192],"engine":[75],"should":[76,94],"clues":[78],"partially-completed":[81],"figure":[84],"out":[85],"most":[90,145],"useful.":[91,146],"user":[93],"not":[95],"required":[97],"formulate":[99],"an":[100],"explicit":[101],"query.":[102],"We":[103,184],"cast":[104],"contextualized":[105],"learning":[110,188],"problem,":[111],"learn":[117],"distribution":[119],"computing":[121,206],"likelihood":[123],"each":[125,159,202],"completes":[128],"and":[131],"propose":[132],"neural":[134,156],"model":[135,157],"for":[136],"predicting":[137],"likely":[142],"Because":[147],"it":[148],"will":[149],"prohibitively":[151],"expensive":[152],"apply":[154],"millions":[165],"billions":[167],"at":[170],"time,":[172],"one":[173],"our":[175],"key":[176],"technical":[177],"concerns":[178],"ensuring":[180],"speedy":[182],"search.":[183],"address":[185],"this":[186],"by":[187],"\"reverse":[190],"encoder\"":[191],"can":[193],"used":[195],"reduce":[197],"problem":[199],"evaluating":[201],"convolution":[208],"two":[210],"normal":[211],"distributions.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-01-23T00:00:00"}
