{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPYAICNF7ZSXOUEP3N7IAUPD7A","short_pith_number":"pith:LPYAICNF","schema_version":"1.0","canonical_sha256":"5bf00409a5fe6577508fdb7e8051e3f82656e717830476040fb070bca9744d0e","source":{"kind":"arxiv","id":"2503.02398","version":2},"attestation_state":"computed","paper":{"title":"PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Min Xu, Qiang Wu, Wujiang Xu, Xing Zi, Yunxiao Shi, Zeqi Zhang","submitted_at":"2025-03-04T08:41:40Z","abstract_excerpt":"User profile embedded in the prompt template of personalized recommendation agents play a crucial role in shaping their decision-making process. High-quality user profiles are essential for aligning agent behavior with real user interests. Typically, these profiles are constructed by leveraging LLMs for user profile modeling (LLM-UM). However, this process faces several challenges: (1) LLMs struggle with long user behaviors due to context length limitations and performance degradation. (2) Existing methods often extract only partial segments from full historical behavior sequence, inevitably d"},"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":"2503.02398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-04T08:41:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77eb689987914bfa80ef4c01e3825e180ff398fd23634ef609305c8ee9a676f5","abstract_canon_sha256":"854afac340fa094f1463266e150e5720bece38919ba9f4ad8ee0787a4f59b3b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:40.535123Z","signature_b64":"T6If1FhtM687n3DT6fjyG8/RVdU3o6wI9k9A2KRRj52/1KhOt8oQ5NZ9ldyXrlnedLxzyidaxQ+QNCdHFmKeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf00409a5fe6577508fdb7e8051e3f82656e717830476040fb070bca9744d0e","last_reissued_at":"2026-07-05T11:08:40.534647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:40.534647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Min Xu, Qiang Wu, Wujiang Xu, Xing Zi, Yunxiao Shi, Zeqi Zhang","submitted_at":"2025-03-04T08:41:40Z","abstract_excerpt":"User profile embedded in the prompt template of personalized recommendation agents play a crucial role in shaping their decision-making process. High-quality user profiles are essential for aligning agent behavior with real user interests. Typically, these profiles are constructed by leveraging LLMs for user profile modeling (LLM-UM). However, this process faces several challenges: (1) LLMs struggle with long user behaviors due to context length limitations and performance degradation. (2) Existing methods often extract only partial segments from full historical behavior sequence, inevitably d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02398","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/2503.02398/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":"2503.02398","created_at":"2026-07-05T11:08:40.534705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02398v2","created_at":"2026-07-05T11:08:40.534705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02398","created_at":"2026-07-05T11:08:40.534705+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPYAICNF7ZSX","created_at":"2026-07-05T11:08:40.534705+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPYAICNF7ZSXOUEP","created_at":"2026-07-05T11:08:40.534705+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPYAICNF","created_at":"2026-07-05T11:08:40.534705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29141","citing_title":"Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09636","citing_title":"PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A","json":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A.json","graph_json":"https://pith.science/api/pith-number/LPYAICNF7ZSXOUEP3N7IAUPD7A/graph.json","events_json":"https://pith.science/api/pith-number/LPYAICNF7ZSXOUEP3N7IAUPD7A/events.json","paper":"https://pith.science/paper/LPYAICNF"},"agent_actions":{"view_html":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A","download_json":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A.json","view_paper":"https://pith.science/paper/LPYAICNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02398&json=true","fetch_graph":"https://pith.science/api/pith-number/LPYAICNF7ZSXOUEP3N7IAUPD7A/graph.json","fetch_events":"https://pith.science/api/pith-number/LPYAICNF7ZSXOUEP3N7IAUPD7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A/action/storage_attestation","attest_author":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A/action/author_attestation","sign_citation":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A/action/citation_signature","submit_replication":"https://pith.science/pith/LPYAICNF7ZSXOUEP3N7IAUPD7A/action/replication_record"}},"created_at":"2026-07-05T11:08:40.534705+00:00","updated_at":"2026-07-05T11:08:40.534705+00:00"}