{"id":"https://openalex.org/W3182535823","doi":"https://doi.org/10.1109/icse-seip55303.2022.9794062","title":"Mining Idioms in the Wild","display_name":"Mining Idioms in the Wild","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W3182535823","doi":"https://doi.org/10.1109/icse-seip55303.2022.9794062","mag":"3182535823"},"language":"en","primary_location":{"id":"doi:10.1109/icse-seip55303.2022.9794062","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icse-seip55303.2022.9794062","pdf_url":"https://ieeexplore.ieee.org/ielx7/9793838/9793543/09794062.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/9793838/9793543/09794062.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070202714","display_name":"Aishwarya Sivaraman","orcid":"https://orcid.org/0000-0002-8074-5517"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aishwarya Sivaraman","raw_affiliation_strings":["UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Abreu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Rui Abreu","raw_affiliation_strings":["Meta Platforms, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013415938","display_name":"Andrew Scott","orcid":"https://orcid.org/0000-0002-6784-5652"},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Andrew Scott","raw_affiliation_strings":["Meta Platforms, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030621214","display_name":"Tobi Akomolede","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Tobi Akomolede","raw_affiliation_strings":["Meta Platforms, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101965118","display_name":"Satish Chandra","orcid":"https://orcid.org/0000-0003-2546-9000"},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Satish Chandra","raw_affiliation_strings":["Meta Platforms, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc","institution_ids":["https://openalex.org/I4210092558","https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"187","last_page":"196"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9858999848365784,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9801999926567078,"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/computer-science","display_name":"Computer science","score":0.8378320932388306},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.7808208465576172},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6381555199623108},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.6198625564575195},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5862110257148743},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5314934253692627},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.457773894071579},{"id":"https://openalex.org/keywords/bytecode","display_name":"Bytecode","score":0.44450944662094116},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.44251981377601624},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.43572449684143066},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.34212300181388855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2964177131652832},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16914233565330505},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.16024893522262573},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.14219531416893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378320932388306},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.7808208465576172},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6381555199623108},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.6198625564575195},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5862110257148743},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5314934253692627},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.457773894071579},{"id":"https://openalex.org/C2779818221","wikidata":"https://www.wikidata.org/wiki/Q837330","display_name":"Bytecode","level":3,"score":0.44450944662094116},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.44251981377601624},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.43572449684143066},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34212300181388855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2964177131652832},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16914233565330505},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.16024893522262573},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.14219531416893005},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icse-seip55303.2022.9794062","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icse-seip55303.2022.9794062","pdf_url":"https://ieeexplore.ieee.org/ielx7/9793838/9793543/09794062.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","raw_type":"proceedings-article"},{"id":"doi:10.1145/3510457.3513046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3510457.3513046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3510457.3513046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.06402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.06402","pdf_url":"https://arxiv.org/pdf/2107.06402","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":"text"},{"id":"mag:3182535823","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2107.06402","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.2107.06402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.06402","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":"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:10.1109/icse-seip55303.2022.9794062","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icse-seip55303.2022.9794062","pdf_url":"https://ieeexplore.ieee.org/ielx7/9793838/9793543/09794062.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3182535823.pdf","grobid_xml":"https://content.openalex.org/works/W3182535823.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W90447038","https://openalex.org/W1503398984","https://openalex.org/W1567790484","https://openalex.org/W1868009147","https://openalex.org/W1975033347","https://openalex.org/W2010452422","https://openalex.org/W2014577207","https://openalex.org/W2041190309","https://openalex.org/W2045656233","https://openalex.org/W2059215200","https://openalex.org/W2060055745","https://openalex.org/W2060610732","https://openalex.org/W2065489029","https://openalex.org/W2073398506","https://openalex.org/W2090111344","https://openalex.org/W2101723202","https://openalex.org/W2112725702","https://openalex.org/W2115733813","https://openalex.org/W2116272605","https://openalex.org/W2121818394","https://openalex.org/W2128782367","https://openalex.org/W2134092629","https://openalex.org/W2138756793","https://openalex.org/W2141422241","https://openalex.org/W2153943889","https://openalex.org/W2157532207","https://openalex.org/W2157874452","https://openalex.org/W2165739648","https://openalex.org/W2166278331","https://openalex.org/W2286236884","https://openalex.org/W2402619042","https://openalex.org/W2790321077","https://openalex.org/W2802401630","https://openalex.org/W2956048495","https://openalex.org/W2962809971","https://openalex.org/W2963371736","https://openalex.org/W2972934903","https://openalex.org/W2979679630","https://openalex.org/W3008999375","https://openalex.org/W3011088748","https://openalex.org/W3014339000","https://openalex.org/W3033748891","https://openalex.org/W3082991350","https://openalex.org/W4232188856","https://openalex.org/W4248681815","https://openalex.org/W4256028358","https://openalex.org/W4301168982","https://openalex.org/W6633995546","https://openalex.org/W6639436161","https://openalex.org/W6668922636","https://openalex.org/W6683195492"],"related_works":["https://openalex.org/W2522278925","https://openalex.org/W3136425480","https://openalex.org/W2295004739","https://openalex.org/W1488625886","https://openalex.org/W2557805692","https://openalex.org/W2008710384","https://openalex.org/W237812766","https://openalex.org/W3014382671","https://openalex.org/W3088089416","https://openalex.org/W3101850750","https://openalex.org/W2780762329","https://openalex.org/W2598968539","https://openalex.org/W2070473038","https://openalex.org/W3174124314","https://openalex.org/W2949271354","https://openalex.org/W2005710769","https://openalex.org/W127275198","https://openalex.org/W2336938009","https://openalex.org/W2287454111","https://openalex.org/W2890042297"],"abstract_inverted_index":{"Existing":[0],"code":[1,7,37,43,68,178,203],"repositories":[2,47],"contain":[3],"numerous":[4],"instances":[5],"of":[6,13,54,66,122,183],"patterns":[8,44,86,102],"that":[9,30,95,133,160,207],"are":[10],"idiomatic":[11,35,67,85],"ways":[12],"accomplishing":[14],"a":[15,137,149,158,180,205],"particular":[16],"programming":[17,21],"task.":[18],"Sometimes,":[19],"the":[20,33,49,55,73,88,123,211],"language":[22],"in":[23,46,82,126,195],"use":[24],"supports":[25],"specific":[26],"operators":[27],"or":[28,58,106],"APIs":[29,57],"can":[31,69,140],"express":[32],"same":[34],"imperative":[36,84],"much":[38],"more":[39,193],"succinctly.":[40],"However,":[41],"those":[42],"linger":[45],"because":[48],"developers":[50],"may":[51],"be":[52,141],"unaware":[53],"new":[56,76,197],"have":[59,210],"not":[60,209],"gotten":[61],"around":[62],"to":[63,72,111,115,155,164,188],"them.":[64],"Detection":[65],"also":[70],"point":[71],"need":[74],"for":[75],"APIs.":[77],"We":[78,93,147],"share":[79],"our":[80],"experiences":[81],"mining":[83],"from":[87,103,136,143,200],"Hack":[89,177],"repo":[90],"at":[91],"Facebook.":[92],"found":[94],"existing":[96],"techniques":[97],"either":[98],"cannot":[99],"identify":[100],"meaningful":[101],"syntax":[104],"trees":[105],"require":[107],"test-suite-based":[108],"dynamic":[109],"analysis":[110],"incorporate":[112],"semantic":[113,134,166],"properties":[114],"mine":[116,165],"useful":[117],"patterns.":[118],"The":[119],"key":[120],"insight":[121],"approach":[124,154],"proposed":[125],"this":[127],"paper":[128],"\u2013":[129,131],"Jezero":[130,175,190],"is":[132,161],"idioms":[135,167],"large":[138],"codebase":[139],"learned":[142],"canonicalized":[144,185],"dataflow":[145,186,212],"trees.":[146],"propose":[148],"scalable,":[150],"lightweight":[151],"static":[152],"analysis-based":[153],"construct":[156],"such":[157],"tree":[159],"well":[162],"suited":[163],"using":[168],"nonparametric":[169],"Bayesian":[170],"methods.":[171],"Our":[172],"experiments":[173],"with":[174],"on":[176],"show":[179],"clear":[181],"advantage":[182],"adding":[184],"information":[187],"ASTs:":[189],"was":[191],"significantly":[192],"effective":[194],"finding":[196],"refactoring":[198],"opportunities":[199],"unannotated":[201],"legacy":[202],"than":[204],"baseline":[206],"did":[208],"augmentation.":[213]},"counts_by_year":[],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}