{"id":"https://openalex.org/W4405444248","doi":"https://doi.org/10.1145/3708473","title":"Leveraging Data Characteristics for Bug Localization in Deep Learning Programs","display_name":"Leveraging Data Characteristics for Bug Localization in Deep Learning Programs","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405444248","doi":"https://doi.org/10.1145/3708473"},"language":"en","primary_location":{"id":"doi:10.1145/3708473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708473","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","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/A5012837373","display_name":"Ruchira Manke","orcid":"https://orcid.org/0009-0007-4729-8421"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruchira Manke","raw_affiliation_strings":["Department of Computer Science, Tulane University, New Orleans, Louisiana, USA","Department of Computer Science, Tulane University, USA"],"raw_orcid":"https://orcid.org/0009-0007-4729-8421","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, Louisiana, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"Department of Computer Science, Tulane University, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004183493","display_name":"Mohammad Wardat","orcid":"https://orcid.org/0009-0001-0213-725X"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Wardat","raw_affiliation_strings":["Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA","Department of Computer Science and Engineering, Oakland University, USA"],"raw_orcid":"https://orcid.org/0009-0001-0213-725X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Oakland University, USA","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"middle","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 Montr\u00e9al, Montreal, Quebec, Canada","SWAT Lab., Polytechnique Montr\u00e9al, CA"],"raw_orcid":"https://orcid.org/0000-0002-5704-4173","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"SWAT Lab., Polytechnique Montr\u00e9al, CA","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059626072","display_name":"Hridesh Rajan","orcid":"https://orcid.org/0000-0002-9410-9562"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hridesh Rajan","raw_affiliation_strings":["School of Science and Engineering, Tulane University, New Orleans, Louisiana, USA","School of Science and Engineering, Tulane University, USA"],"raw_orcid":"https://orcid.org/0000-0002-9410-9562","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Tulane University, New Orleans, Louisiana, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"School of Science and Engineering, Tulane University, USA","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012837373"],"corresponding_institution_ids":["https://openalex.org/I114832834"],"apc_list":null,"apc_paid":null,"fwci":0.6609,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76782921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"34","issue":"6","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9976000189781189,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8803104758262634},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.538864016532898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4861716628074646},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4562903046607971},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4076460897922516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33664554357528687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8803104758262634},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.538864016532898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4861716628074646},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4562903046607971},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4076460897922516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33664554357528687}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3708473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3708473","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:publications.polymtl.ca:62220","is_oa":false,"landing_page_url":null,"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":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2154516011","display_name":null,"funder_award_id":"CCF-22-23812","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5238564299","display_name":"Collaborative Research: CCRI: ENS: Boa 2.0: Enhancing Infrastructure for Studying Software and its Evolution at a Large Scale","funder_award_id":"2512858","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G537839615","display_name":null,"funder_award_id":"CCF-19-34884","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7568968367","display_name":"SHF:Small: More Modular Deep Learning","funder_award_id":"2512857","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7770872176","display_name":null,"funder_award_id":"CNS-15-13263","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8872482365","display_name":null,"funder_award_id":"CNS-21-20448","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W148396834","https://openalex.org/W1806891645","https://openalex.org/W2017971446","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2140833774","https://openalex.org/W2147800946","https://openalex.org/W2180748755","https://openalex.org/W2194775991","https://openalex.org/W2805595195","https://openalex.org/W2850992922","https://openalex.org/W2887783524","https://openalex.org/W2898868990","https://openalex.org/W2912440308","https://openalex.org/W2914153747","https://openalex.org/W2964024268","https://openalex.org/W2968594320","https://openalex.org/W3000471815","https://openalex.org/W3090643686","https://openalex.org/W3091633490","https://openalex.org/W3134796670","https://openalex.org/W3160349922","https://openalex.org/W3160369295","https://openalex.org/W3161666929","https://openalex.org/W3203969037","https://openalex.org/W4226311503","https://openalex.org/W4229068576","https://openalex.org/W4240768087","https://openalex.org/W4280562623","https://openalex.org/W4284677512","https://openalex.org/W4284681547","https://openalex.org/W4307926351","https://openalex.org/W4362606928","https://openalex.org/W4388483172","https://openalex.org/W6676297131","https://openalex.org/W6713134421","https://openalex.org/W6753064767","https://openalex.org/W6893070773"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W4387369504","https://openalex.org/W3046775127"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"is":[3,66,134],"a":[4,14,135,178,207],"class":[5],"of":[6,17,45,145,171,180,211],"machine":[7],"learning":[8],"algorithms":[9],"that":[10,48,194],"are":[11],"used":[12],"in":[13,32,40,85,88,100,117,201],"wide":[15],"variety":[16],"applications.":[18],"Like":[19],"any":[20],"software":[21],"system,":[22],"DL":[23,33,86,101,118,123,132,184],"programs":[24,119,185],"can":[25],"have":[26,37],"bugs.":[27,78,219],"To":[28,79],"support":[29,80],"bug":[30,81],"localization":[31,84],"programs,":[34,87,204],"several":[35],"tools":[36],"been":[38],"proposed":[39],"the":[41,46,72,104,109,131,143,146,151,157,169,172],"past.":[42],"As":[43],"most":[44],"bugs":[47,58,99,116,141,200,214],"occur":[49],"due":[50],"to":[51,60,70,113,167],"improper":[52],"model":[53],"structure":[54,170],"known":[55],"as":[56],"structural":[57,98,199,213],"lead":[59],"inadequate":[61],"performance":[62],"during":[63],"training,":[64],"it":[65],"challenging":[67],"for":[68],"developers":[69],"identify":[71],"root":[73],"cause":[74],"and":[75,83,96,126,149,160],"address":[76],"these":[77,140],"detection":[82],"this":[89],"article,":[90],"we":[91],"propose":[92],"Theia,":[93],"which":[94,163],"detects":[95,139],"localizes":[97,197,217],"programs.":[102],"Unlike":[103],"previous":[105],"works,":[106],"Theia":[107,138,176,195],"considers":[108],"training":[110,130,147,216],"dataset":[111],"characteristics":[112],"automatically":[114],"detect":[115],"developed":[120],"using":[121],"two":[122],"libraries,":[124],"Keras":[125],"PyTorch":[127],".":[128,190],"Since":[129],"models":[133],"time-consuming":[136],"process,":[137],"at":[142],"beginning":[144],"process":[148],"alerts":[150],"developer":[152],"with":[153],"informative":[154],"messages":[155],"containing":[156],"bug\u2019s":[158],"location":[159],"actionable":[161],"fixes":[162],"will":[164],"help":[165],"them":[166],"improve":[168],"model.":[173],"We":[174],"evaluated":[175],"on":[177],"benchmark":[179],"40":[181,202],"real-world":[182],"buggy":[183,203],"obtained":[186],"from":[187],"Stack":[188],"Overflow":[189],"Our":[191],"results":[192],"show":[193],"successfully":[196],"57/75":[198],"whereas":[205],"NeuraLint,":[206],"state-of-the-art":[208],"approach":[209],"capable":[210],"localizing":[212],"before":[215],"17/75":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
