{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U4DDMUPTYNZW2GSDXQZ5XCSZHA","short_pith_number":"pith:U4DDMUPT","schema_version":"1.0","canonical_sha256":"a7063651f3c3736d1a43bc33db8a5938184ba6ffb6228d3f05712236946b164e","source":{"kind":"arxiv","id":"2602.00742","version":2},"attestation_state":"computed","paper":{"title":"CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Wang, Xiaoyou Liu, Xinyi Mou, Xuanjing Huang, Zhongyu Wei","submitted_at":"2026-01-31T14:13:06Z","abstract_excerpt":"User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder and a discrete prototype codebook to extract multi-dimensional user traits. This design enables plug-and-play personalization with a small number of t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.00742","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T14:13:06Z","cross_cats_sorted":[],"title_canon_sha256":"c77126d674da0498fe73782693aef9d4665f7fd46300eb544d57e25fefc46cc1","abstract_canon_sha256":"d90e3fb20247bb15c8489f7c4d5e715b7e9a9b80f77003764a3e3227855be2d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:37.606237Z","signature_b64":"D2G8DWxrVDd0ASnGjuYJ4u2CizGrnldgXITEhXoPDItd0RZl9qO0qW07iT/rXNgpbl8lcoGw8fdGj/j0CsLfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7063651f3c3736d1a43bc33db8a5938184ba6ffb6228d3f05712236946b164e","last_reissued_at":"2026-06-02T03:04:37.605711Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:37.605711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Wang, Xiaoyou Liu, Xinyi Mou, Xuanjing Huang, Zhongyu Wei","submitted_at":"2026-01-31T14:13:06Z","abstract_excerpt":"User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large Language Models (LLMs) in contemporary approaches. However, existing methods, whether prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder and a discrete prototype codebook to extract multi-dimensional user traits. This design enables plug-and-play personalization with a small number of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00742","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.00742/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.00742","created_at":"2026-06-02T03:04:37.605769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00742v2","created_at":"2026-06-02T03:04:37.605769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00742","created_at":"2026-06-02T03:04:37.605769+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4DDMUPTYNZW","created_at":"2026-06-02T03:04:37.605769+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4DDMUPTYNZW2GSD","created_at":"2026-06-02T03:04:37.605769+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4DDMUPT","created_at":"2026-06-02T03:04:37.605769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA","json":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA.json","graph_json":"https://pith.science/api/pith-number/U4DDMUPTYNZW2GSDXQZ5XCSZHA/graph.json","events_json":"https://pith.science/api/pith-number/U4DDMUPTYNZW2GSDXQZ5XCSZHA/events.json","paper":"https://pith.science/paper/U4DDMUPT"},"agent_actions":{"view_html":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA","download_json":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA.json","view_paper":"https://pith.science/paper/U4DDMUPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00742&json=true","fetch_graph":"https://pith.science/api/pith-number/U4DDMUPTYNZW2GSDXQZ5XCSZHA/graph.json","fetch_events":"https://pith.science/api/pith-number/U4DDMUPTYNZW2GSDXQZ5XCSZHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA/action/storage_attestation","attest_author":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA/action/author_attestation","sign_citation":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA/action/citation_signature","submit_replication":"https://pith.science/pith/U4DDMUPTYNZW2GSDXQZ5XCSZHA/action/replication_record"}},"created_at":"2026-06-02T03:04:37.605769+00:00","updated_at":"2026-06-02T03:04:37.605769+00:00"}