{"id":"https://openalex.org/W4389208689","doi":"https://doi.org/10.1145/3611643.3616312","title":"HyperDiff: Computing Source Code Diffs at Scale","display_name":"HyperDiff: Computing Source Code Diffs at Scale","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389208689","doi":"https://doi.org/10.1145/3611643.3616312"},"language":"en","primary_location":{"id":"doi:10.1145/3611643.3616312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04189855v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044140918","display_name":"Quentin Le Dilavrec","orcid":"https://orcid.org/0000-0001-7511-8394"},"institutions":[{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Quentin Le Dilavrec","raw_affiliation_strings":["University of Rennes, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)"],"raw_orcid":"https://orcid.org/0000-0001-7511-8394","affiliations":[{"raw_affiliation_string":"University of Rennes, Rennes, France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021471","display_name":"Djamel Eddine Khelladi","orcid":"https://orcid.org/0000-0002-2218-650X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Djamel Eddine Khelladi","raw_affiliation_strings":["CNRS - University of Rennes, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)"],"raw_orcid":"https://orcid.org/0000-0002-2218-650X","affiliations":[{"raw_affiliation_string":"CNRS - University of Rennes, Rennes, France","institution_ids":["https://openalex.org/I56067802","https://openalex.org/I3124938446","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031312202","display_name":"Arnaud Blouin","orcid":"https://orcid.org/0000-0002-5974-9601"},"institutions":[{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arnaud Blouin","raw_affiliation_strings":["INSA Rennes, Rennes, France","INSA Rennes - Institut National des Sciences Appliqu\u00e9es - Rennes (20, avenue des Buttes de Co\u00ebsmes - CS 70839 - 35708 Rennes cedex 7 - France)","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)"],"raw_orcid":"https://orcid.org/0000-0002-5974-9601","affiliations":[{"raw_affiliation_string":"INSA Rennes, Rennes, France","institution_ids":["https://openalex.org/I28221208"]},{"raw_affiliation_string":"INSA Rennes - Institut National des Sciences Appliqu\u00e9es - Rennes (20, avenue des Buttes de Co\u00ebsmes - CS 70839 - 35708 Rennes cedex 7 - France)","institution_ids":["https://openalex.org/I28221208"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069324527","display_name":"Jean\u2010Marc Jez\u00e9qu\u00e9l","orcid":"https://orcid.org/0000-0002-0582-9745"},"institutions":[{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Marc J\u00e9z\u00e9quel","raw_affiliation_strings":["University of Rennes, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)"],"raw_orcid":"https://orcid.org/0000-0002-0582-9745","affiliations":[{"raw_affiliation_string":"University of Rennes, Rennes, France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedes - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044140918"],"corresponding_institution_ids":["https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":1.3453,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86062761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9922999739646912,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9907000064849854,"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":0.8794529438018799},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5549945831298828},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5242536067962646},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.4822443425655365},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4819483458995819},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.48054128885269165},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4773281216621399},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.4335668683052063},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.43045806884765625},{"id":"https://openalex.org/keywords/redundant-code","display_name":"Redundant code","score":0.4231288433074951},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4185551106929779},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4061947464942932},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3449445366859436},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.2646552324295044},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.22358229756355286},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1654006838798523},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15904971957206726},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10034936666488647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8794529438018799},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5549945831298828},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5242536067962646},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.4822443425655365},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4819483458995819},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.48054128885269165},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4773281216621399},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.4335668683052063},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.43045806884765625},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.4231288433074951},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4185551106929779},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4061947464942932},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3449445366859436},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2646552324295044},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.22358229756355286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1654006838798523},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15904971957206726},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10034936666488647},{"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":2,"locations":[{"id":"doi:10.1145/3611643.3616312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3611643.3616312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04189855v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04189855","pdf_url":"https://inria.hal.science/hal-04189855v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ESEC/FSE 2023 - 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, Dec 2023, San Francisco (CA, USA), United States. pp.1-12, &#x27E8;10.1145/3611643.3616312&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04189855v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04189855","pdf_url":"https://inria.hal.science/hal-04189855v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ESEC/FSE 2023 - 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, Dec 2023, San Francisco (CA, USA), United States. pp.1-12, &#x27E8;10.1145/3611643.3616312&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389208689.pdf","grobid_xml":"https://content.openalex.org/works/W4389208689.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2003889154","https://openalex.org/W2004012461","https://openalex.org/W2017404422","https://openalex.org/W2028633384","https://openalex.org/W2033235985","https://openalex.org/W2051742379","https://openalex.org/W2065489029","https://openalex.org/W2136393336","https://openalex.org/W2153150125","https://openalex.org/W2156067883","https://openalex.org/W2400579873","https://openalex.org/W2515936044","https://openalex.org/W2767837303","https://openalex.org/W2842584488","https://openalex.org/W2888158939","https://openalex.org/W2895570420","https://openalex.org/W2900777821","https://openalex.org/W2944738881","https://openalex.org/W2953504043","https://openalex.org/W2962898649","https://openalex.org/W3010730260","https://openalex.org/W3100698844","https://openalex.org/W3100831522","https://openalex.org/W3161504508","https://openalex.org/W3200912930","https://openalex.org/W4206767299","https://openalex.org/W4210896998","https://openalex.org/W4229772528","https://openalex.org/W4241437391","https://openalex.org/W4243013071","https://openalex.org/W4293583930","https://openalex.org/W4308643006","https://openalex.org/W4312497378","https://openalex.org/W6780704300"],"related_works":["https://openalex.org/W4210653322","https://openalex.org/W2390085541","https://openalex.org/W1967199258","https://openalex.org/W3040982692","https://openalex.org/W4399631969","https://openalex.org/W2390554102","https://openalex.org/W3104152981","https://openalex.org/W3202887988","https://openalex.org/W2565892306","https://openalex.org/W4376486317"],"abstract_inverted_index":{"With":[0],"the":[1,62,65,76,83,96,101,153,171,227,241],"advent":[2],"of":[3,64,75,88,95,158,192,230,240,249,258],"fast":[4],"software":[5,146,195],"evolution":[6,28],"and":[7,81,103,109,165,182,197,211,233,244],"multistage":[8],"releases,":[9],"temporal":[10,57],"code":[11,27,31,44,60,89,105,140,159,179],"analysis":[12,58],"is":[13,59],"becoming":[14],"useful":[15],"for":[16,49,226],"various":[17],"purposes,":[18],"such":[19],"as":[20],"bug":[21,24],"cause":[22],"identification,":[23],"prediction":[25],"or":[26,52,68],"analysis.":[29],"Temporal":[30],"analyses":[32],"can":[33,122],"consist":[34],"in":[35,106,206,209,219,237,246],"analyzing":[36,80],"multiple":[37],"Abstract":[38],"Syntax":[39],"Trees":[40],"(ASTs)":[41],"extracted":[42],"from":[43,222],"evolutions,":[45],"e.g.":[46],"one":[47],"AST":[48,252],"each":[50],"commit":[51],"release.":[53],"Core":[54],"feature":[55],"to":[56,144,161,200,224,235,263],"differencing:":[61],"computation":[63,119,232],"so-called":[66],"Diff":[67],"edit":[69],"script":[70],"between":[71,125],"two":[72,107],"given":[73],"versions":[74,87],"code.":[77],"However,":[78],"jointly":[79],"computing":[82],"difference":[84],"on":[85,134,152,188],"thousands":[86],"faces":[90],"scalability":[91,207],"issues.":[92],"Mainly":[93],"because":[94],"cost":[97],"of:":[98],"1)":[99,218],"parsing":[100],"original":[102],"evolved":[104],"source":[108],"target":[110],"ASTs;":[111],"2)":[112,245],"wasting":[113],"resources":[114],"by":[115,169],"not":[116],"reusing":[117],"intermediate":[118,238],"results":[120],"that":[121,138],"be":[123],"shared":[124],"versions.":[126],"This":[127],"paper":[128],"details":[129],"a":[130,155,177,189],"novel":[131,156],"approach":[132,168,187,203,255],"based":[133],"time-oriented":[135],"data":[136],"structures":[137],"makes":[139],"differencing":[141,180],"scale":[142],"up":[143,234],"large":[145,194],"codebases.":[147],"In":[148],"particular,":[149],"we":[150],"leverage":[151],"HyperAST,":[154],"representation":[157],"histories,":[160],"propose":[162],"an":[163,215],"incremental":[164],"memory":[166,247],"efficient":[167],"lazifying":[170],"well":[172],"known":[173],"GumTree":[174],"diffing":[175],"algorithms,":[176],"mainstream":[178],"algorithm":[181],"tool.":[183],"We":[184,213],"evaluated":[185],"our":[186],"curated":[190],"list":[191],"19":[193],"projects":[196],"compared":[198],"it":[199,205],"GumTree.":[201,264],"Our":[202],"outperforms":[204],"both":[208],"time":[210,221,229],"memory.":[212],"observed":[214],"order-of-magnitude":[216],"difference:":[217],"CPU":[220],"x1.2":[223],"x12.7":[225],"total":[228],"diff":[231,242],"x226":[236],"phases":[239],"computation,":[243],"footprint":[248],"x4.5":[250],"per":[251],"node.":[253],"The":[254],"produced":[256],"99.3%":[257],"identical":[259],"diffs":[260],"with":[261],"respect":[262]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
