{"id":"https://openalex.org/W7139084441","doi":"https://doi.org/10.48550/arxiv.2603.17387","title":"CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval","display_name":"CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7139084441","doi":"https://doi.org/10.48550/arxiv.2603.17387"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.17387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.17387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130123647","display_name":"Guangzhi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Guangzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130082416","display_name":"Yinghao Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Yinghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129805993","display_name":"Zhi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5130123647"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9222000241279602,"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":0.9222000241279602,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.013100000098347664,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5442000031471252},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4977000057697296},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4431999921798706},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.3880000114440918},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3659000098705292},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3635999858379364},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3474000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906999707221985},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5375000238418579},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.17387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.17387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17387","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"score":0.7191154956817627,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,22,206],"central":[1],"challenge":[2],"of":[3,62],"reasoning-intensive":[4],"retrieval":[5,93,204,221],"lies":[6],"in":[7,43,162],"identifying":[8],"implicitreasoning":[9],"relationships":[10,120],"between":[11,72],"queries":[12,73,175],"and":[13,74,121,159,199],"documents,":[14],"rather":[15],"than":[16],"superficial":[17],"se-mantic":[18],"or":[19,76],"lexical":[20],"similarity.":[21],"contrastive":[23,196],"learning":[24,197],"paradigm":[25],"is":[26,80],"fundamentallya":[27],"static":[28,99,211],"representation":[29],"consolidation":[30],"technique:":[31],"during":[32],"training,":[33],"it":[34,50,135],"encodes":[35],"hier-archical":[36],"relevance":[37,54],"concepts":[38],"into":[39,151],"fixed":[40],"geometric":[41],"structures":[42],"the":[44,58,105,128,132,163,181,188],"vector":[45,152],"space,and":[46],"at":[47],"inference":[48],"time":[49],"cannot":[51],"dynamically":[52],"adjust":[53],"judgments":[55],"accord-ing":[56],"to":[57,82,101,117,143,168],"specific":[59],"reasoning":[60,79,112,119,129,149,216],"demands":[61],"each":[63,115],"query.":[64],"Consequently,":[65],"performancedegrades":[66],"noticeably":[67],"when":[68,77],"vocabulary":[69],"mismatch":[70],"exists":[71],"doc-uments":[75],"implicit":[78],"required":[81],"establish":[83],"relevance.":[84],"This":[85],"pa-per":[86],"proposes":[87],"Thought":[88],"1":[89],"(T1),":[90],"a":[91,124],"generative":[92],"model":[94,167],"that":[95,209],"shifts":[96],"relevancemodeling":[97],"from":[98],"alignment":[100,213],"dynamic":[102,148,215],"reasoning.":[103],"On":[104,131,180],"query":[106,116,190],"side,":[107,134],"T1":[108],"dy-namically":[109],"generates":[110],"intermediate":[111],"trajectories":[113],"for":[114,127,173],"bridgeimplicit":[118],"uses":[122],"as":[123],"semantic":[125],"aggregationpoint":[126],"output.":[130],"document":[133],"employs":[136],"an":[137],"instruction+":[138],"text":[139],"+":[140],"encoding":[141],"format":[142],"support":[144],"high-throughput":[145],"indexing.":[146],"Tointernalize":[147],"capabilities":[150],"representations,":[153],"we":[154],"adopt":[155],"athree-stage":[156],"training":[157],"curriculum":[158],"introduce":[160],"GRPO":[161],"third":[164],"stage,":[165],"enablingthe":[166],"learn":[169],"optimal":[170],"derivation":[171],"strategies":[172],"different":[174],"through":[176],"trial-and-error":[177],"reinforcement":[178],"learning.":[179],"BRIGHT":[182],"benchmark,":[183],"T1-4B":[184],"exhibitsstrong":[185],"performance":[186,201],"under":[187],"original":[189],"setting,":[191],"outperforming":[192],"larger":[193],"modelstrained":[194],"with":[195,214],"overall,":[198],"achieving":[200],"comparableto":[202],"multi-stage":[203],"pipelines.":[205],"results":[207],"demonstrate":[208],"replacing":[210],"rep-resentation":[212],"generation":[217],"can":[218],"effectively":[219],"improvereasoning-intensive":[220],"performance.":[222]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}