{"id":"https://openalex.org/W7204238445","doi":"https://doi.org/10.48550/arxiv.2608.24089","title":"CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval","display_name":"CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204238445","doi":"https://doi.org/10.48550/arxiv.2608.24089"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24089","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24089","pdf_url":"https://arxiv.org/pdf/2608.24089","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148230941","display_name":"Zhen Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhen","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121916823","display_name":"Yuhong Chen","orcid":"https://orcid.org/0009-0000-9073-7038","observed_orcids":["https://orcid.org/0009-0000-9073-7038"]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yuhong","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148248573","display_name":"Wenhao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Wenhao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146923634","display_name":"Xiaodong Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xiaodong","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148326960","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-7342-3467","observed_orcids":["https://orcid.org/0000-0001-7342-3467"]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Hui","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China , Xiamen University Xiamen , China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"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":0.9634000062942505,"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":0.9634000062942505,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.027000000700354576,"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/T10028","display_name":"Topic Modeling","score":0.004699999932199717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual-quantization","display_name":"residual quantization","score":0.9039999842643738},{"id":"https://openalex.org/keywords/hard-negatives","display_name":"hard negatives","score":0.746999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033000230789185},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6384000182151794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3580000102519989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C70992990","wikidata":"https://www.wikidata.org/wiki/Q1681587","display_name":"Systematic code","level":4,"score":0.2831000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24089","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24089","pdf_url":"https://arxiv.org/pdf/2608.24089","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"},{"id":"doi:10.48550/arxiv.2608.24089","doi":"https://doi.org/10.48550/arxiv.2608.24089","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24089","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24089","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24089","pdf_url":"https://arxiv.org/pdf/2608.24089","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204238445.pdf","grobid_xml":"https://content.openalex.org/works/W7204238445.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4312107449","https://openalex.org/W4404574113","https://openalex.org/W7167944412","https://openalex.org/W4391288767","https://openalex.org/W4415004136","https://openalex.org/W4400391132","https://openalex.org/W7160518403","https://openalex.org/W7161536743","https://openalex.org/W4411113095","https://openalex.org/W7218917498"],"abstract_inverted_index":{"Code":[0],"retrieval":[1,28,59,63,91,97,195,210],"models":[2],"have":[3],"predominantly":[4],"relied":[5],"on":[6,110,175],"a":[7,30,34,88,120,198],"flat":[8,100],"matching":[9,102],"paradigm":[10],"that":[11,93,134,181],"treats":[12],"code":[13,25,39,48,62,90,96,137,188,191],"snippets":[14,138],"as":[15],"independent":[16],"candidates,":[17],"making":[18],"them":[19],"less":[20],"capable":[21],"of":[22],"distinguishing":[23],"similar":[24],"candidates.":[26],"Generative":[27],"offers":[29],"solution":[31],"by":[32,125,155,197],"constructing":[33],"learnable":[35],"index":[36,124,154],"over":[37,69],"the":[38,42,61,95],"corpus,":[40],"guiding":[41],"retriever":[43],"to":[44,78,103],"better":[45],"understand":[46],"how":[47],"candidates":[49],"are":[50],"semantically":[51,135],"organized":[52],"and":[53,130,163,170,177,193],"addressed.":[54],"However,":[55],"naively":[56],"applying":[57,126],"generative":[58,89,194],"in":[60,67,201,208],"task":[64,98],"may":[65],"result":[66],"operating":[68],"an":[70],"identifier":[71],"space":[72],"whose":[73],"prefixes":[74,140],"do":[75],"not":[76],"correspond":[77],"meaningful":[79],"code-semantic":[80],"regions.":[81],"In":[82],"this":[83,152],"paper,":[84],"we":[85],"propose":[86],"CodeHID,":[87],"framework":[92],"reformulates":[94],"from":[99],"candidate":[101,168],"coarse-to-fine":[104],"semantic":[105],"address":[106],"generation.":[107],"CodeHID":[108,182],"relies":[109],"two":[111],"core":[112],"components.":[113],"First,":[114],"Pseudo-Neighbor":[115],"Guided":[116],"DocID":[117,147],"Learning":[118],"constructs":[119],"globally":[121],"static":[122],"hierarchical":[123],"multi-level":[127],"residual":[128],"quantization":[129],"$k$-nearest-neighbor":[131],"pseudo-supervision,":[132],"ensuring":[133],"related":[136],"share":[139],"while":[141],"preserving":[142],"target-level":[143],"separability.":[144],"Second,":[145],"Dual-Phase":[146],"Generation":[148],"Guidance":[149],"reliably":[150],"navigates":[151],"fixed":[153],"combining":[156],"training-side":[157],"ranking":[158],"enhancements,":[159],"using":[160],"hard":[161],"negatives":[162],"rank":[164],"distillation,":[165],"with":[166],"inference-side":[167],"constraints":[169],"prefix-aware":[171],"decoding.":[172],"Extensive":[173],"experiments":[174],"CoSQA":[176],"ProCQA":[178],"benchmarks":[179],"demonstrate":[180],"outperforms":[183],"existing":[184],"sparse":[185],"retrieval,":[186,192],"pre-trained":[187],"models,":[189],"dense":[190],"baselines":[196],"large":[199],"margin":[200],"most":[202],"cases,":[203],"achieving":[204],"particularly":[205],"strong":[206],"improvements":[207],"rank-one":[209],"metrics.":[211]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}