{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZDZUVKR6INJQJXT7I4BLXIGKT6","short_pith_number":"pith:ZDZUVKR6","schema_version":"1.0","canonical_sha256":"c8f34aaa3e435304de7f4702bba0ca9f8ce8803756953cef5906f56f72b49eb6","source":{"kind":"arxiv","id":"2405.03988","version":3},"attestation_state":"computed","paper":{"title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Han Li, Honggang Chen, Jian Jia, Jian Liang, Kun Gai, Peng Jiang, Quan Chen, Xuehan Bai, Yan Li, Yipei Wang, Zhaocheng Liu","submitted_at":"2024-05-07T04:00:30Z","abstract_excerpt":"Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance and poor generalizations. Leveraging the capability of large language models to comprehend and reason about textual content presents a promising avenue for advancing recommendation systems. To achieve this, we propose an Llm-driven knowlEdge Adaptive RecommeNdation (LEARN) framework that synergizes open-world knowledge with "},"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":"2405.03988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-07T04:00:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6652f0282d34e90bae45f74c9eab3e2206ddcd0b6438369071abb3fbedc05681","abstract_canon_sha256":"43e90b05788db4d197bad3b8a101694f6359070909331759e50ebf07966d8b61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:01.878381Z","signature_b64":"yvBTxUNoVTz/L3uRKdku2I024tsrPcJ3P2sSiwngJH+00FtsntwYhNtp4iidV0c8kDjuOSLOK7E0TYXlJhQ4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8f34aaa3e435304de7f4702bba0ca9f8ce8803756953cef5906f56f72b49eb6","last_reissued_at":"2026-07-05T09:54:01.877845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:01.877845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Han Li, Honggang Chen, Jian Jia, Jian Liang, Kun Gai, Peng Jiang, Quan Chen, Xuehan Bai, Yan Li, Yipei Wang, Zhaocheng Liu","submitted_at":"2024-05-07T04:00:30Z","abstract_excerpt":"Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance and poor generalizations. Leveraging the capability of large language models to comprehend and reason about textual content presents a promising avenue for advancing recommendation systems. To achieve this, we propose an Llm-driven knowlEdge Adaptive RecommeNdation (LEARN) framework that synergizes open-world knowledge with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03988","kind":"arxiv","version":3},"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/2405.03988/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":"2405.03988","created_at":"2026-07-05T09:54:01.877914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03988v3","created_at":"2026-07-05T09:54:01.877914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03988","created_at":"2026-07-05T09:54:01.877914+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDZUVKR6INJQ","created_at":"2026-07-05T09:54:01.877914+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDZUVKR6INJQJXT7","created_at":"2026-07-05T09:54:01.877914+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDZUVKR6","created_at":"2026-07-05T09:54:01.877914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17050","citing_title":"Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18146","citing_title":"Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6","json":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6.json","graph_json":"https://pith.science/api/pith-number/ZDZUVKR6INJQJXT7I4BLXIGKT6/graph.json","events_json":"https://pith.science/api/pith-number/ZDZUVKR6INJQJXT7I4BLXIGKT6/events.json","paper":"https://pith.science/paper/ZDZUVKR6"},"agent_actions":{"view_html":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6","download_json":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6.json","view_paper":"https://pith.science/paper/ZDZUVKR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03988&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDZUVKR6INJQJXT7I4BLXIGKT6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDZUVKR6INJQJXT7I4BLXIGKT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6/action/storage_attestation","attest_author":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6/action/author_attestation","sign_citation":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6/action/citation_signature","submit_replication":"https://pith.science/pith/ZDZUVKR6INJQJXT7I4BLXIGKT6/action/replication_record"}},"created_at":"2026-07-05T09:54:01.877914+00:00","updated_at":"2026-07-05T09:54:01.877914+00:00"}