{"id":"https://openalex.org/W4382363007","doi":"https://doi.org/10.1145/3589806.3600043","title":"Fingerprinting and Building Large Reproducible Datasets","display_name":"Fingerprinting and Building Large Reproducible Datasets","publication_year":2023,"publication_date":"2023-06-27","ids":{"openalex":"https://openalex.org/W4382363007","doi":"https://doi.org/10.1145/3589806.3600043"},"language":"en","primary_location":{"id":"doi:10.1145/3589806.3600043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589806.3600043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Conference on Reproducibility and Replicability","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04132604v1/file/Fingerprinting_and_Building_Large_Reproducible_Datasets.pdf","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/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":"Romain Lefeuvre","raw_affiliation_strings":["Inria, University of Rennes, France"],"raw_orcid":"https://orcid.org/0009-0008-2019-1058","affiliations":[{"raw_affiliation_string":"Inria, University of Rennes, France","institution_ids":["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/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":"Jessie Galasso","raw_affiliation_strings":["Department of Computer Science and Operations Research, DIRO, Universit\u00e9 de Montr\u00e9al, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9868-1814","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, DIRO, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"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/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/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]},{"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":["Computer Science Department, University of Rennes, IRISA &amp; Inria, France"],"raw_orcid":"https://orcid.org/0000-0002-7104-7848","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Rennes, IRISA &amp; Inria, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I4210156583","https://openalex.org/I56067802"]}]},{"author_position":"middle","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":["Department of Computer Science and Operations Research, DIRO, Universit\u00e9 de Montr\u00e9al, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6304-9926","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Operations Research, DIRO, Universit\u00e9 de Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006129685","display_name":"Stefano Zacchiroli","orcid":"https://orcid.org/0000-0002-4576-136X"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefano Zacchiroli","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-4576-136X","affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028297374"],"corresponding_institution_ids":["https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":0.8968,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78656519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9987999796867371,"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":0.9987999796867371,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922642230987549},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.7841572165489197},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.620127260684967},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5248465538024902},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5174375176429749},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5053392052650452},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4823448061943054},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4653514325618744},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.45027297735214233},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4476656913757324},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.37371399998664856},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.27892303466796875},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08310535550117493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922642230987549},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7841572165489197},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.620127260684967},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5248465538024902},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5174375176429749},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5053392052650452},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4823448061943054},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4653514325618744},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.45027297735214233},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4476656913757324},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.37371399998664856},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.27892303466796875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08310535550117493},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589806.3600043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589806.3600043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Conference on Reproducibility and Replicability","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04132604v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04132604","pdf_url":"https://hal.science/hal-04132604v1/file/Fingerprinting_and_Building_Large_Reproducible_Datasets.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM REP 2023 - ACM Conference on Reproducibility and Replicability, Jun 2023, Santa Cruz, United States. pp.27-36, &#x27E8;10.1145/3589806.3600043&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04132604v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04132604","pdf_url":"https://hal.science/hal-04132604v1/file/Fingerprinting_and_Building_Large_Reproducible_Datasets.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM REP 2023 - ACM Conference on Reproducibility and Replicability, Jun 2023, Santa Cruz, United States. pp.27-36, &#x27E8;10.1145/3589806.3600043&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382363007.pdf","grobid_xml":"https://content.openalex.org/works/W4382363007.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W821933395","https://openalex.org/W1914969610","https://openalex.org/W1919408037","https://openalex.org/W2066707382","https://openalex.org/W2404313524","https://openalex.org/W2407313496","https://openalex.org/W2789091536","https://openalex.org/W2797862469","https://openalex.org/W2799059383","https://openalex.org/W2891421390","https://openalex.org/W2897442092","https://openalex.org/W2954266827","https://openalex.org/W2969896803","https://openalex.org/W2998064313","https://openalex.org/W3014453155","https://openalex.org/W3091477168","https://openalex.org/W3165454787","https://openalex.org/W4200065965"],"related_works":["https://openalex.org/W2618286804","https://openalex.org/W2329643025","https://openalex.org/W2002770077","https://openalex.org/W3131163342","https://openalex.org/W2092256833","https://openalex.org/W2142369114","https://openalex.org/W2361728394","https://openalex.org/W2166271660","https://openalex.org/W2352631095","https://openalex.org/W3038222916"],"abstract_inverted_index":{"Obtaining":[0],"a":[1],"relevant":[2],"dataset":[3],"is":[4],"central":[5],"to":[6,40,61],"conducting":[7],"empirical":[8,73],"studies":[9],"in":[10,14],"software":[11,19],"engineering.":[12],"However,":[13],"the":[15,21,32,51,68],"context":[16],"of":[17,23,34,53,55,72],"mining":[18,29],"repositories,":[20],"lack":[22,52],"appropriate":[24],"tooling":[25],"for":[26],"large":[27],"scale":[28],"tasks":[30],"hinders":[31],"creation":[33],"new":[35],"datasets.":[36],"Moreover,":[37],"limitations":[38],"related":[39],"data":[41],"sources":[42],"that":[43],"change":[44],"over":[45,64],"time":[46],"(e.g.,":[47],"code":[48],"bases)":[49],"and":[50,70],"documentation":[54],"extraction":[56],"processes":[57],"make":[58],"it":[59],"difficult":[60],"reproduce":[62],"datasets":[63],"time.":[65],"This":[66],"threatens":[67],"quality":[69],"reproducibility":[71],"studies.":[74]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
