{"id":"https://openalex.org/W4414589104","doi":"https://doi.org/10.1007/s10664-025-10717-y","title":"Towards understanding the impact of data bugs on deep learning models in software engineering","display_name":"Towards understanding the impact of data bugs on deep learning models in software engineering","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4414589104","doi":"https://doi.org/10.1007/s10664-025-10717-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-025-10717-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10664-025-10717-y","pdf_url":null,"source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101301241","display_name":"Mehil B. Shah","orcid":"https://orcid.org/0009-0000-3584-0470"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mehil B. Shah","raw_affiliation_strings":["Dalhousie University, Halifax, Canada"],"raw_orcid":"https://orcid.org/0009-0000-3584-0470","affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030616863","display_name":"Mohammad Masudur Rahman","orcid":"https://orcid.org/0000-0003-3821-5990"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad Masudur Rahman","raw_affiliation_strings":["Dalhousie University, Halifax, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3821-5990","affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071052367","display_name":"Foutse Khomh","orcid":"https://orcid.org/0000-0002-5704-4173"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Foutse Khomh","raw_affiliation_strings":["Polytechnique Montreal, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5704-4173","affiliations":[{"raw_affiliation_string":"Polytechnique Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101301241"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":2.018,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90223152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":"6","first_page":null,"last_page":null},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9980000257492065,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6413999795913696},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5964999794960022},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5828999876976013},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5468999743461609},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.5123000144958496},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.47119998931884766},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4099999964237213},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4090999960899353},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4068000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.604200005531311},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5964999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859000086784363},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.5123000144958496},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C139143892","wikidata":"https://www.wikidata.org/wiki/Q7441615","display_name":"Search-based software engineering","level":5,"score":0.35749998688697815},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.34369999170303345},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.29440000653266907},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2776969324","wikidata":"https://www.wikidata.org/wiki/Q613918","display_name":"Software quality assurance","level":5,"score":0.28380000591278076},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.2782000005245209},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.2689000070095062},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.2623000144958496}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10664-025-10717-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10664-025-10717-y","pdf_url":null,"source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:publications.polymtl.ca:68914","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/68914/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article de revue"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1526710119","https://openalex.org/W1966994480","https://openalex.org/W2020458104","https://openalex.org/W2040975718","https://openalex.org/W2061557777","https://openalex.org/W2086123233","https://openalex.org/W2147386665","https://openalex.org/W2162739315","https://openalex.org/W2167460663","https://openalex.org/W2172232422","https://openalex.org/W2767717989","https://openalex.org/W2805001156","https://openalex.org/W2808279976","https://openalex.org/W2885541650","https://openalex.org/W2896671475","https://openalex.org/W2901543039","https://openalex.org/W2952322169","https://openalex.org/W2954276596","https://openalex.org/W2955991060","https://openalex.org/W2962858109","https://openalex.org/W2963640412","https://openalex.org/W2968594320","https://openalex.org/W2981207549","https://openalex.org/W3085062472","https://openalex.org/W3085364681","https://openalex.org/W3090643686","https://openalex.org/W3091588759","https://openalex.org/W3091963033","https://openalex.org/W3098910265","https://openalex.org/W3103334733","https://openalex.org/W3118813946","https://openalex.org/W3121495845","https://openalex.org/W3122473522","https://openalex.org/W3123545166","https://openalex.org/W3125781052","https://openalex.org/W3134770171","https://openalex.org/W3156669901","https://openalex.org/W3178061567","https://openalex.org/W3178469298","https://openalex.org/W3199693282","https://openalex.org/W4205171628","https://openalex.org/W4206238894","https://openalex.org/W4207068100","https://openalex.org/W4226169266","https://openalex.org/W4238404964","https://openalex.org/W4243379839","https://openalex.org/W4284709233","https://openalex.org/W4292121845","https://openalex.org/W4300164480","https://openalex.org/W4304688778","https://openalex.org/W4308641647","https://openalex.org/W4311412320","https://openalex.org/W4312307983","https://openalex.org/W4312436517","https://openalex.org/W4313199266","https://openalex.org/W4313563755","https://openalex.org/W4376606656","https://openalex.org/W4384026501","https://openalex.org/W4384155620","https://openalex.org/W4384302770","https://openalex.org/W4384345694","https://openalex.org/W4384345790","https://openalex.org/W4384572726","https://openalex.org/W4388483492","https://openalex.org/W4389158525","https://openalex.org/W4390187563","https://openalex.org/W4391305812","https://openalex.org/W4394746523","https://openalex.org/W4396773582","https://openalex.org/W4399513333","https://openalex.org/W4400582613","https://openalex.org/W4400681025","https://openalex.org/W4400988474","https://openalex.org/W4404199042","https://openalex.org/W4404609282","https://openalex.org/W4411360056","https://openalex.org/W4411552541","https://openalex.org/W4413611830"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
