{"id":"https://openalex.org/W7129106970","doi":"https://doi.org/10.1145/3773966.3777925","title":"CAT-ID <sup>2</sup> : Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce","display_name":"CAT-ID <sup>2</sup> : Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129106970","doi":"https://doi.org/10.1145/3773966.3777925"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777925","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777925","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0000-0002-9537-7067"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9537-7067","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126082662","display_name":"Fuwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuwei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7711-866X","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051633278","display_name":"Yiqing Wu","orcid":"https://orcid.org/0000-0002-8068-9420"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Wu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8068-9420","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126162043","display_name":"Xinyu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Jia","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9503-2991","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126146808","display_name":"Zenghua Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenghua Xia","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4606-6606","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126073854","display_name":"Fuzhen Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzhen Zhuang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China, China and State Key Laboratory of Complex &amp;#38; Critical Software Environment, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9170-7009","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China, China and State Key Laboratory of Complex &amp;#38; Critical Software Environment, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126132494","display_name":"Zhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China and State Key Laboratory of Complex &amp;#38; Critical Software Environment, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6680-160X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China and State Key Laboratory of Complex &amp;#38; Critical Software Environment, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126092524","display_name":"Fei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Jiang","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7019-140X","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100364629","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0003-2851-820X"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2851-820X","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16659623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4260999858379364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4260999858379364,"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":0.3068000078201294,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.08720000088214874,"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/identifier","display_name":"Identifier","score":0.7342000007629395},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.43290001153945923},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3977000117301941},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100000023841858},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7342000007629395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5730999708175659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3977000117301941},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3777925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777925","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777925","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2421218773","https://openalex.org/W3099700870","https://openalex.org/W3154670582","https://openalex.org/W3168875417","https://openalex.org/W3194782062","https://openalex.org/W4200630919","https://openalex.org/W4252076394","https://openalex.org/W4312974539","https://openalex.org/W4396843633","https://openalex.org/W4400524784","https://openalex.org/W4400909953","https://openalex.org/W4403221739","https://openalex.org/W4403577940","https://openalex.org/W4411630076","https://openalex.org/W4412886996","https://openalex.org/W4412945410"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"retrieval":[1],"(GR)":[2],"has":[3],"gained":[4],"significant":[5],"attention":[6],"as":[7],"an":[8],"effective":[9],"paradigm":[10],"that":[11,164],"integrates":[12],"the":[13,114,152,172,184],"capabilities":[14],"of":[15,23,154,174,186],"large":[16],"language":[17],"models":[18],"(LLMs).":[19],"It":[20],"generally":[21],"consists":[22],"two":[24,61],"stages:":[25],"constructing":[26],"discrete":[27],"semantic":[28,115],"identifiers":[29],"(IDs)":[30],"for":[31,141,203,209],"documents":[32,35,65,167],"and":[33,71,78,92,146,180,207],"retrieving":[34],"by":[36,132],"autoregressively":[37],"generating":[38],"ID":[39,101,143],"tokens.":[40],"The":[41,212],"core":[42],"challenge":[43],"in":[44,94,197],"GR":[45],"is":[46,90,215],"how":[47],"to":[48,127,150,161],"construct":[49],"document":[50,73],"IDs":[51,58,163],"(DocIDS)":[52],"with":[53,189],"strong":[54],"representational":[55],"power.":[56],"Good":[57],"should":[59,66,74],"exhibit":[60],"key":[62,120],"properties:":[63],"similar":[64,69,166],"have":[67],"more":[68,168],"IDs,":[70],"each":[72],"maintain":[75],"a":[76,99,122,136,147,194],"distinct":[77],"unique":[79],"ID.":[80],"However,":[81],"most":[82],"existing":[83],"methods":[84],"ignore":[85],"native":[86],"category":[87,111,129],"information,":[88],"which":[89],"common":[91],"critical":[93],"E-commerce.":[95],"Therefore,":[96],"we":[97],"propose":[98],"novel":[100],"learning":[102],"method,":[103,188],"CAtegory-Tree":[104],"Integrated":[105],"Document":[106],"IDentifier":[107],"(CAT-ID2),":[108],"incorporating":[109],"prior":[110],"information":[112,130],"into":[113],"IDs.":[116],"CAT-ID2":[117,160],"includes":[118],"three":[119],"modules:":[121],"Hierarchical":[123],"Class":[124],"Constraint":[125,139],"Loss":[126,140,149],"integrate":[128],"layer":[131,133],"during":[134],"quantization,":[135],"Cluster":[137],"Scale":[138],"uniform":[142],"token":[144],"distribution,":[145],"Dispersion":[148],"improve":[151],"distinction":[153],"reconstructed":[155],"documents.":[156],"These":[157],"components":[158],"enable":[159],"generate":[162],"make":[165],"alike":[169],"while":[170],"preserving":[171],"uniqueness":[173],"different":[175],"documents'":[176],"representations.":[177],"Extensive":[178],"offline":[179],"online":[181,190],"experiments":[182],"confirm":[183],"effectiveness":[185],"our":[187],"A/B":[191],"tests":[192],"showing":[193],"(0.33%)":[195],"increase":[196],"average":[198],"orders":[199],"per":[200],"thousand":[201],"users":[202],"ambiguous":[204],"intent":[205],"queries":[206],"(0.24%)":[208],"long-tail":[210],"queries.":[211],"source":[213],"code":[214],"available":[216],"at":[217],"https://github.com/lxbdtt/CAT-ID2.":[218]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}