{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YKQXOSP2TGJP6QUMSRUZCKNNJD","short_pith_number":"pith:YKQXOSP2","schema_version":"1.0","canonical_sha256":"c2a17749fa9992ff428c94699129ad48d3b67c987c57997a6db2886cdbb51565","source":{"kind":"arxiv","id":"2502.14662","version":4},"attestation_state":"computed","paper":{"title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Kai Mei, Kun Wang, Min Xu, Wujiang Xu, Xi Zhu, Xuying Ning, Yongfeng Zhang, Yunxiao Shi, Zujie Liang","submitted_at":"2025-02-20T15:58:25Z","abstract_excerpt":"Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, the defect of recommendation algorithms may put users in very vulnerable positions under this paradigm. First, many sophisticated models are often designed with commercial objectives in mind, focusing on the platform's benefits, which may hinder their ability to protect and capture users' true interests. Second, these models are typically optimized using data from all users, which may overlook individual user's prefere"},"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":"2502.14662","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T15:58:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"95b16a9302470023603ad171b8dc4f86e6345b804261ce379d3bf153c1e5814d","abstract_canon_sha256":"217f3138850187804b194d992f46fb94b449aadd0b2fdbd249aad99483f13d5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:27.919425Z","signature_b64":"fiQ/1K7nHrCOWmg7WP6794iG+kcczSNAAduAo97iiuB+USiIbiBJoHi8LWg5s1MVMxqxqmjNsxo2yPAIZLAnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2a17749fa9992ff428c94699129ad48d3b67c987c57997a6db2886cdbb51565","last_reissued_at":"2026-07-05T11:12:27.918874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:27.918874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Kai Mei, Kun Wang, Min Xu, Wujiang Xu, Xi Zhu, Xuying Ning, Yongfeng Zhang, Yunxiao Shi, Zujie Liang","submitted_at":"2025-02-20T15:58:25Z","abstract_excerpt":"Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, the defect of recommendation algorithms may put users in very vulnerable positions under this paradigm. First, many sophisticated models are often designed with commercial objectives in mind, focusing on the platform's benefits, which may hinder their ability to protect and capture users' true interests. Second, these models are typically optimized using data from all users, which may overlook individual user's prefere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14662","kind":"arxiv","version":4},"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/2502.14662/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":"2502.14662","created_at":"2026-07-05T11:12:27.918939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14662v4","created_at":"2026-07-05T11:12:27.918939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14662","created_at":"2026-07-05T11:12:27.918939+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKQXOSP2TGJP","created_at":"2026-07-05T11:12:27.918939+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKQXOSP2TGJP6QUM","created_at":"2026-07-05T11:12:27.918939+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKQXOSP2","created_at":"2026-07-05T11:12:27.918939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":271,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20858","citing_title":"Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11874","citing_title":"RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2410.02644","citing_title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","ref_index":151,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD","json":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD.json","graph_json":"https://pith.science/api/pith-number/YKQXOSP2TGJP6QUMSRUZCKNNJD/graph.json","events_json":"https://pith.science/api/pith-number/YKQXOSP2TGJP6QUMSRUZCKNNJD/events.json","paper":"https://pith.science/paper/YKQXOSP2"},"agent_actions":{"view_html":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD","download_json":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD.json","view_paper":"https://pith.science/paper/YKQXOSP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14662&json=true","fetch_graph":"https://pith.science/api/pith-number/YKQXOSP2TGJP6QUMSRUZCKNNJD/graph.json","fetch_events":"https://pith.science/api/pith-number/YKQXOSP2TGJP6QUMSRUZCKNNJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD/action/storage_attestation","attest_author":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD/action/author_attestation","sign_citation":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD/action/citation_signature","submit_replication":"https://pith.science/pith/YKQXOSP2TGJP6QUMSRUZCKNNJD/action/replication_record"}},"created_at":"2026-07-05T11:12:27.918939+00:00","updated_at":"2026-07-05T11:12:27.918939+00:00"}