{"id":"https://openalex.org/W7215102476","doi":"https://doi.org/10.48550/arxiv.2609.38402","title":"From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning","display_name":"From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7215102476","doi":"https://doi.org/10.48550/arxiv.2609.38402"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38402","pdf_url":"https://arxiv.org/pdf/2609.38402","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.38402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125011452","display_name":"Ankur Garg","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Garg, Ankur","raw_affiliation_strings":["University of Calgary , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calgary , Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116211111","display_name":"Corey Yang-Smith","orcid":"https://orcid.org/0009-0006-5614-3504","observed_orcids":["https://orcid.org/0009-0006-5614-3504"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang-Smith, Corey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114620111","display_name":"Rishav Rishav","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rishav, Rishav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108338171","display_name":"Ahmad Abdellatif","orcid":"https://orcid.org/0000-0003-1863-9147","observed_orcids":["https://orcid.org/0000-0003-1863-9147"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdellatif, Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032466547","display_name":"Samira Ebrahimi Kahou","orcid":"https://orcid.org/0009-0005-6283-3811","observed_orcids":["https://orcid.org/0009-0005-6283-3811"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kahou, Samira Ebrahimi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10260","display_name":"Software Engineering Research","score":0.8535000085830688,"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":0.8535000085830688,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.14550000429153442,"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":0.0003000000142492354,"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/bug-localization","display_name":"bug localization","score":0.9639999866485596},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.7870000004768372},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/codebert","display_name":"CodeBERT","score":0.6779999732971191},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.703000009059906},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.382999986410141},{"id":"https://openalex.org/keywords/python","display_name":"Python","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939000129699707},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.7476000189781189},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.607200026512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3424000144004822},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2778626561","wikidata":"https://www.wikidata.org/wiki/Q6086067","display_name":"Isomap","level":4,"score":0.29429998993873596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38402","pdf_url":"https://arxiv.org/pdf/2609.38402","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38402","doi":"https://doi.org/10.48550/arxiv.2609.38402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38402","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38402","pdf_url":"https://arxiv.org/pdf/2609.38402","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320310537","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215102476.pdf","grobid_xml":"https://content.openalex.org/works/W7215102476.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1950030762","https://openalex.org/W1985947101","https://openalex.org/W2033644368","https://openalex.org/W2514300030","https://openalex.org/W2515360277","https://openalex.org/W2762786131","https://openalex.org/W2905087861","https://openalex.org/W2958754741","https://openalex.org/W3100366369","https://openalex.org/W3195442242","https://openalex.org/W3195681663","https://openalex.org/W4284698368","https://openalex.org/W4386249595","https://openalex.org/W4387360068","https://openalex.org/W4391579639","https://openalex.org/W4392972005","https://openalex.org/W4402040489","https://openalex.org/W4410095576","https://openalex.org/W4411552782","https://openalex.org/W4415991171","https://openalex.org/W6929230376","https://openalex.org/W7131388287"],"related_works":["https://openalex.org/W7171465414","https://openalex.org/W2919796195","https://openalex.org/W3196713798","https://openalex.org/W4298156464","https://openalex.org/W7161728255","https://openalex.org/W4415930160","https://openalex.org/W4413635666","https://openalex.org/W4410553125","https://openalex.org/W4401071349","https://openalex.org/W4407009661"],"abstract_inverted_index":{"We":[0],"introduce":[1],"C2C":[2,38,119,138],"(From":[3],"Codebase":[4],"to":[5,101,105],"Culprit),":[6],"a":[7,48,72,116],"framework":[8,94],"for":[9],"precise":[10],"bug":[11,163],"localization":[12,122,143],"that":[13,137],"progressively":[14],"reduces":[15],"the":[16,77,92,149],"debugging":[17,36],"search":[18,63,90],"space":[19],"across":[20,127],"multiple":[21],"levels":[22],"of":[23,29,56,74,108,151],"granularity:":[24],"files,":[25],"functions,":[26],"and":[27,42,103,133,142,157],"lines":[28,107],"code.":[30,109],"To":[31],"mirror":[32],"developer's":[33],"natural":[34],"top-down":[35],"workflows,":[37],"integrates":[39],"semantic":[40,60],"retrieval":[41,55,140],"Hierarchical":[43],"Reinforcement":[44],"Learning":[45],"(HRL)":[46],"in":[47,160],"two-stage":[49],"process.":[50],"First,":[51],"it":[52],"performs":[53],"recall-oriented":[54],"buggy":[57],"candidates":[58],"via":[59,81],"vector":[61],"similarity":[62],"using":[64],"bug-report":[65],"text,":[66],"including":[67],"available":[68],"stack-trace":[69],"information,":[70],"against":[71],"database":[73],"embeddings,":[75],"where":[76],"embeddings":[78],"are":[79],"fine-tuned":[80],"contrastive":[82],"learning":[83,155],"with":[84],"CodeBERT.":[85],"Building":[86],"on":[87,130],"this":[88],"reduced":[89],"space,":[91],"HRL":[93],"incrementally":[95],"localizes":[96],"bugs,":[97],"reasoning":[98],"from":[99],"files":[100],"functions":[102],"ultimately":[104],"individual":[106],"Unlike":[110],"prior":[111],"approaches":[112],"which":[113],"operate":[114],"at":[115],"single":[117],"granularity,":[118],"enables":[120],"multi-resolution":[121],"while":[123],"maintaining":[124],"contextual":[125],"consistency":[126],"decisions.":[128],"Experiments":[129],"real-world":[131],"Java":[132],"Python":[134],"datasets":[135],"demonstrate":[136],"improves":[139],"precision":[141],"accuracy.":[144],"Ablation":[145],"studies":[146],"further":[147],"highlight":[148],"contributions":[150],"hierarchical":[152],"decomposition,":[153],"structured":[154],"signals,":[156],"reward":[158],"shaping":[159],"advancing":[161],"multi-level":[162],"localization.":[164]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-02T00:00:00"}