{"id":"https://openalex.org/W4416083908","doi":null,"title":"A Systematic Survey on Debugging Techniques for Machine Learning Systems","display_name":"A Systematic Survey on Debugging Techniques for Machine Learning Systems","publication_year":2025,"publication_date":"2025-03-05","ids":{"openalex":"https://openalex.org/W4416083908"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.03158","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03158","pdf_url":"https://arxiv.org/pdf/2503.03158","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.03158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010271768","display_name":"Thanh-Dat Nguyen","orcid":"https://orcid.org/0009-0008-8144-969X","observed_orcids":["https://orcid.org/0009-0008-8144-969X"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nguyen, Thanh-Dat","raw_affiliation_strings":["School of Computing and Information Systems , The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397373","display_name":"Haoye Tian","orcid":"https://orcid.org/0000-0002-8049-3997","observed_orcids":["https://orcid.org/0000-0002-8049-3997"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tian, Haoye","raw_affiliation_strings":["School of Computing and Information Systems , The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109801092","display_name":"Bach Le","orcid":"https://orcid.org/0000-0001-5044-1582","observed_orcids":["https://orcid.org/0000-0001-5044-1582"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Le, Bach","raw_affiliation_strings":["School of Computing and Information Systems , The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040320723","display_name":"Patanamon Thongtanunam","orcid":"https://orcid.org/0000-0001-6328-8839","observed_orcids":["https://orcid.org/0000-0001-6328-8839"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thongtanunam, Patanamon","raw_affiliation_strings":["School of Computing and Information Systems , The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043053174","display_name":"Shane McIntosh","orcid":"https://orcid.org/0000-0002-0193-3975","observed_orcids":["https://orcid.org/0000-0002-0193-3975"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"McIntosh, Shane","raw_affiliation_strings":["School of Computer Science , University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9990000128746033,"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/T10260","display_name":"Software Engineering Research","score":0.00039999998989515007,"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":9.999999747378752e-05,"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/machine-learning-software","display_name":"machine learning software","score":0.8579999804496765},{"id":"https://openalex.org/keywords/fault-classification","display_name":"fault classification","score":0.7739999890327454},{"id":"https://openalex.org/keywords/fault-localization","display_name":"fault location","score":0.8330000042915344},{"id":"https://openalex.org/keywords/fault-diagnosis","display_name":"fault diagnosis","score":0.7110000252723694},{"id":"https://openalex.org/keywords/fault-correction","display_name":"fault repair","score":0.6990000009536743},{"id":"https://openalex.org/keywords/developer-interviews","display_name":"developer interviews","score":0.8199999928474426},{"id":"https://openalex.org/keywords/github-issues","display_name":"GitHub issues","score":0.7260000109672546},{"id":"https://openalex.org/keywords/research-gap","display_name":"research gaps","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.9606000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242000102996826},{"id":"https://openalex.org/C136388014","wikidata":"https://www.wikidata.org/wiki/Q17084976","display_name":"Algorithmic program debugging","level":3,"score":0.6007000207901001},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47040000557899475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.40560001134872437},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C24845683","wikidata":"https://www.wikidata.org/wiki/Q178651","display_name":"Interview","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C148609458","wikidata":"https://www.wikidata.org/wiki/Q7021281","display_name":"Nexus (standard)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.25270000100135803},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2503.03158","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03158","pdf_url":"https://arxiv.org/pdf/2503.03158","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.03158","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03158","pdf_url":"https://arxiv.org/pdf/2503.03158","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[{"id":"https://openalex.org/study-designs/systematic-review","display_name":"Systematic Review"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416083908.pdf","grobid_xml":"https://content.openalex.org/works/W4416083908.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W1977362030","https://openalex.org/W2616028256","https://openalex.org/W2767656849","https://openalex.org/W2804337238","https://openalex.org/W2850992922","https://openalex.org/W2888510757","https://openalex.org/W2905631704","https://openalex.org/W2922234936","https://openalex.org/W2948096068","https://openalex.org/W2948367246","https://openalex.org/W2963327228","https://openalex.org/W2988175183","https://openalex.org/W3007157104","https://openalex.org/W3030163527","https://openalex.org/W3090643686","https://openalex.org/W3107864711","https://openalex.org/W3134796670","https://openalex.org/W3135464648","https://openalex.org/W3160369295","https://openalex.org/W3165292502","https://openalex.org/W3170657538","https://openalex.org/W3178469298","https://openalex.org/W3179011554","https://openalex.org/W3184743108","https://openalex.org/W3194120901","https://openalex.org/W4220659214","https://openalex.org/W4224249875","https://openalex.org/W4224884895","https://openalex.org/W4229068576","https://openalex.org/W4280562623","https://openalex.org/W4281706616","https://openalex.org/W4284681547","https://openalex.org/W4284686707","https://openalex.org/W4284687826","https://openalex.org/W4284701600","https://openalex.org/W4284702108","https://openalex.org/W4284708930","https://openalex.org/W4285490447","https://openalex.org/W4285586653","https://openalex.org/W4308641598","https://openalex.org/W4308643012","https://openalex.org/W4384302781","https://openalex.org/W4384345694","https://openalex.org/W4384345721","https://openalex.org/W4389158350"],"related_works":["https://openalex.org/W4389337865","https://openalex.org/W7165540205","https://openalex.org/W4362606928","https://openalex.org/W3183946528","https://openalex.org/W4301626227","https://openalex.org/W2087419855","https://openalex.org/W6885135016","https://openalex.org/W7015813579","https://openalex.org/W4205171628","https://openalex.org/W3083470206"],"abstract_inverted_index":{"Debugging":[0],"ML":[1,40,75,208,251,260,270],"software":[2,17],"(i.e.,":[3],"the":[4,21,43,53,74,93,97,141,164,192,206,267],"detection,":[5],"localization":[6],"and":[7,24,38,238,273],"fixing":[8],"of":[9,26,56,109,137,144,187,205,233,240,269],"faults)":[10],"poses":[11],"unique":[12],"challenges":[13,94,193,210,258],"compared":[14],"to":[15,20,60,134,139,158,190],"traditional":[16],"largely":[18],"due":[19],"probabilistic":[22],"nature":[23],"heterogeneity":[25],"its":[27],"development":[28],"process.":[29],"Various":[30],"methods":[31],"have":[32,70,211],"been":[33,71,212],"proposed":[34],"for":[35,112],"testing,":[36],"diagnosing,":[37],"repairing":[39],"systems.":[41,115],"However,":[42],"big":[44],"picture":[45],"informing":[46],"important":[47],"research":[48,77,249],"directions":[49],"that":[50,78,173,201,230],"really":[51],"address":[52,159],"dire":[54],"needs":[55,81],"developers":[57,80,189],"is":[58],"yet":[59,98],"unfold,":[61],"leaving":[62],"several":[63],"key":[64],"questions":[65],"unaddressed:":[66],"(1)":[67],"What":[68,91],"faults":[69,88,138,161,175],"targeted":[72],"in":[73,82,95,125,148,169,194,243,250,259,276],"debugging":[76,110,123,179,209,271],"fulfill":[79],"practice?":[83],"(2)":[84],"How":[85],"are":[86,92,156,245],"these":[87,132],"addressed?":[89],"(3)":[90],"addressing":[96],"untargeted":[99],"faults?":[100],"In":[101,224],"this":[102],"paper,":[103],"we":[104,152,182,228],"conduct":[105],"a":[106,135,170,263],"systematic":[107],"study":[108,254],"techniques":[111,155],"machine":[113,126],"learning":[114,127],"We":[116,129],"first":[117],"collect":[118],"technical":[119],"papers":[120,133],"focusing":[121],"on":[122,163,236],"components":[124],"software.":[128],"then":[130],"map":[131],"taxonomy":[136,172],"assess":[140],"current":[142],"state":[143],"fault":[145],"resolution":[146,275],"identified":[147,207],"existing":[149],"literature.":[150],"Subsequently,":[151],"analyze":[153],"which":[154],"used":[157],"specific":[160],"based":[162],"collected":[165],"papers.":[166],"This":[167],"results":[168],"comprehensive":[171],"aligns":[174],"with":[176],"their":[177,274],"corresponding":[178],"methods.":[180],"Finally,":[181],"examine":[183],"previously":[184],"released":[185],"transcripts":[186],"interviewing":[188],"identify":[191],"resolving":[195],"unfixed":[196],"faults.":[197],"Our":[198],"analysis":[199],"reveals":[200],"only":[202],"48":[203],"percent":[204,219,232],"explicitly":[213],"addressed":[214],"by":[215,248],"researchers,":[216],"while":[217],"46.9":[218],"remain":[220],"unresolved":[221],"or":[222],"unmentioned.":[223],"real":[225],"world":[226],"applications,":[227],"found":[229],"52.6":[231],"issues":[234,272],"reported":[235],"GitHub":[237],"70.3%":[239],"problems":[241],"discussed":[242],"interviews":[244],"still":[246],"unaddressed":[247],"debugging.":[252],"The":[253],"identifies":[255],"13":[256],"primary":[257],"debugging,":[261],"highlighting":[262],"significant":[264],"gap":[265],"between":[266],"identification":[268],"practice.":[277]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}