{"id":"https://openalex.org/W7171996255","doi":"https://doi.org/10.1145/3793302.3793369","title":"Modeling Sampling Workflows for Code Repositories","display_name":"Modeling Sampling Workflows for Code Repositories","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7171996255","doi":"https://doi.org/10.1145/3793302.3793369"},"language":"en","primary_location":{"id":"doi:10.1145/3793302.3793369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793369","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793302.3793369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028297374","display_name":"Romain Lefeuvre","orcid":"https://orcid.org/0009-0008-2019-1058"},"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/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"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":"Romain Lefeuvre","raw_affiliation_strings":["University of Rennes, Inria, CNRS, IRISA, Rennes, France"],"raw_orcid":"https://orcid.org/0009-0008-2019-1058","affiliations":[{"raw_affiliation_string":"University of Rennes, Inria, CNRS, IRISA, Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124114507","display_name":"Ma\u00efwenn Le Goasteller","orcid":null},"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/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"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":"Ma\u00efwenn Le Goasteller","raw_affiliation_strings":["University of Rennes, Inria, CNRS, IRISA, Rennes, France"],"raw_orcid":"https://orcid.org/0009-0001-8504-8139","affiliations":[{"raw_affiliation_string":"University of Rennes, Inria, CNRS, IRISA, Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101553683","display_name":"Jessie Carbonnel","orcid":"https://orcid.org/0000-0002-9868-1814"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jessie Galasso","raw_affiliation_strings":["McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9868-1814","affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079739010","display_name":"Beno\u00eet Combemale","orcid":"https://orcid.org/0000-0002-7104-7848"},"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/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"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":"Benoit Combemale","raw_affiliation_strings":["Inria, University of Rennes, CNRS, IRISA, Rennes, France"],"raw_orcid":"https://orcid.org/0000-0002-7104-7848","affiliations":[{"raw_affiliation_string":"Inria, University of Rennes, CNRS, IRISA, Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069706212","display_name":"Quentin Perez","orcid":"https://orcid.org/0000-0002-1534-4821"},"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/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"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"]},{"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":"Quentin Perez","raw_affiliation_strings":["INSA Rennes, University of Rennes, Inria, CNRS, IRISA, Rennes, France"],"raw_orcid":"https://orcid.org/0000-0002-1534-4821","affiliations":[{"raw_affiliation_string":"INSA Rennes, University of Rennes, Inria, CNRS, IRISA, Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009574640","display_name":"Houari Sahraoui","orcid":"https://orcid.org/0000-0001-6304-9926"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Houari Sahraoui","raw_affiliation_strings":["DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6304-9926","affiliations":[{"raw_affiliation_string":"DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.5888000130653381},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5250999927520752},{"id":"https://openalex.org/keywords/sampling-design","display_name":"Sampling design","score":0.49390000104904175},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.484499990940094},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4325000047683716},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.41510000824928284},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835999727249146},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6205999851226807},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5564000010490417},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.49390000104904175},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4797999858856201},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C52913732","wikidata":"https://www.wikidata.org/wiki/Q857102","display_name":"Software design","level":4,"score":0.2671000063419342},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3793302.3793369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793369","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05478146v2","is_oa":true,"landing_page_url":"https://hal.science/hal-05478146","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"MSR \u201926 - 23rd International Conference on Mining Software Repositories, Apr 2026, Rio de Janeiro, Brazil. pp.423-434, &#x27E8;10.1145/3793302.3793369&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3793302.3793369","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793369","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W821933395","https://openalex.org/W1835740130","https://openalex.org/W2110417468","https://openalex.org/W2140952846","https://openalex.org/W2162739315","https://openalex.org/W2169090130","https://openalex.org/W2322259366","https://openalex.org/W2331675854","https://openalex.org/W2335151507","https://openalex.org/W2570760970","https://openalex.org/W2605897695","https://openalex.org/W2884512787","https://openalex.org/W2917744165","https://openalex.org/W2954266827","https://openalex.org/W3006568433","https://openalex.org/W3047958222","https://openalex.org/W3089816368","https://openalex.org/W3133667557","https://openalex.org/W4200065965","https://openalex.org/W4210644165","https://openalex.org/W4232627933","https://openalex.org/W4239160510","https://openalex.org/W4255375128","https://openalex.org/W4288698636","https://openalex.org/W4382363007","https://openalex.org/W4390829841","https://openalex.org/W4403413397","https://openalex.org/W4412825323","https://openalex.org/W6910082056","https://openalex.org/W6966729743"],"related_works":[],"abstract_inverted_index":{"Empirical":[0],"software":[1,46],"engineering":[2,47],"research":[3,37],"often":[4],"depends":[5],"on":[6,76,113],"datasets":[7],"of":[8,25,36,61,73,110,149],"code":[9,153],"repository":[10,154],"artifacts,":[11],"where":[12],"sampling":[13,40,62,74,92,96,116,139,165],"strategies":[14,27,93,166],"are":[15,28],"employed":[16],"to":[17,55,68,88],"enable":[18],"large-scale":[19],"analyses.":[20],"The":[21],"design":[22,58],"and":[23,59,64,104,127],"evaluation":[24],"these":[26,80],"critical,":[29],"as":[30,122],"they":[31],"directly":[32],"influence":[33],"the":[34,57,66,71,102,105,108,114,120,160,164],"generalizability":[35,109],"findings.":[38],"However,":[39],"remains":[41],"an":[42],"underestimated":[43],"aspect":[44],"in":[45,168],"research:":[48],"we":[49,82],"identify":[50],"two":[51],"main":[52],"challenges":[53],"related":[54],"(1)":[56],"representativeness":[60,132],"approaches,":[63],"(2)":[65],"ability":[67],"reason":[69],"about":[70,107],"implications":[72],"decisions":[75],"generalizability.":[77],"To":[78],"address":[79],"challenges,":[81],"propose":[83],"a":[84,123,146],"Domain-Specific":[85],"Language":[86],"(DSL)":[87],"explicitly":[89],"describe":[90],"complex":[91],"through":[94,145],"composable":[95],"operators.":[97],"This":[98],"formalism":[99],"supports":[100],"both":[101],"specification":[103],"reasoning":[106,133],"results":[111,157],"based":[112],"applied":[115],"strategies.":[117],"We":[118,141],"implement":[119],"DSL":[121,161],"Python-based":[124],"fluent":[125],"API,":[126],"demonstrate":[128],"how":[129],"it":[130],"facilitates":[131],"using":[134],"statistical":[135],"indicators":[136],"extracted":[137],"from":[138],"workflows.":[140],"validate":[142],"our":[143],"approach":[144],"case":[147],"study":[148],"MSR":[150],"papers":[151],"involving":[152],"sampling.":[155],"Our":[156],"show":[158],"that":[159],"can":[162],"model":[163],"reported":[167],"recent":[169],"literature.":[170]},"counts_by_year":[],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2026-08-01T00:00:00"}
