{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RKE3MEWDQGGMJKBWHBBYFA3TEO","short_pith_number":"pith:RKE3MEWD","schema_version":"1.0","canonical_sha256":"8a89b612c3818cc4a83638438283732386eab67f2be300ad06d78b1c0baba044","source":{"kind":"arxiv","id":"2404.00245","version":1},"attestation_state":"computed","paper":{"title":"Aligning Large Language Models with Recommendation Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ed H. Chi, Lichan Hong, Lukasz Heldt, Maheswaran Sathiamoorthy, Nikhil Mehta, Raghunandan Keshavan, Xinyang Yi, Yuwei Cao","submitted_at":"2024-03-30T04:46:16Z","abstract_excerpt":"Large language models (LLMs) have recently been used as backbones for recommender systems. However, their performance often lags behind conventional methods in standard tasks like retrieval. We attribute this to a mismatch between LLMs' knowledge and the knowledge crucial for effective recommendations. While LLMs excel at natural language reasoning, they cannot model complex user-item interactions inherent in recommendation tasks. We propose bridging the knowledge gap and equipping LLMs with recommendation-specific knowledge to address this. Operations such as Masked Item Modeling (MIM) and Ba"},"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":"2404.00245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-30T04:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"377cb8f9dbcc0364174dfcf79926eac6c1ba28808db8e667e869a48c9db829ba","abstract_canon_sha256":"c2e57a36c8d0ad595fa5c8ac785635ebc17638d41fe885add3c0816683c27601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:30.100602Z","signature_b64":"tusIFdDPe1K/AxejUoIXWfO3ZY/ePwJtmAGwHGshhD9QKRb7mRMlp7YDuc/g8qDH9xJEKSZ0WvNpZ87QMoJjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a89b612c3818cc4a83638438283732386eab67f2be300ad06d78b1c0baba044","last_reissued_at":"2026-07-05T08:02:30.100095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:30.100095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Large Language Models with Recommendation Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ed H. Chi, Lichan Hong, Lukasz Heldt, Maheswaran Sathiamoorthy, Nikhil Mehta, Raghunandan Keshavan, Xinyang Yi, Yuwei Cao","submitted_at":"2024-03-30T04:46:16Z","abstract_excerpt":"Large language models (LLMs) have recently been used as backbones for recommender systems. However, their performance often lags behind conventional methods in standard tasks like retrieval. We attribute this to a mismatch between LLMs' knowledge and the knowledge crucial for effective recommendations. While LLMs excel at natural language reasoning, they cannot model complex user-item interactions inherent in recommendation tasks. We propose bridging the knowledge gap and equipping LLMs with recommendation-specific knowledge to address this. Operations such as Masked Item Modeling (MIM) and Ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00245","kind":"arxiv","version":1},"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/2404.00245/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":"2404.00245","created_at":"2026-07-05T08:02:30.100149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00245v1","created_at":"2026-07-05T08:02:30.100149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00245","created_at":"2026-07-05T08:02:30.100149+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKE3MEWDQGGM","created_at":"2026-07-05T08:02:30.100149+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKE3MEWDQGGMJKBW","created_at":"2026-07-05T08:02:30.100149+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKE3MEWD","created_at":"2026-07-05T08:02:30.100149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO","json":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO.json","graph_json":"https://pith.science/api/pith-number/RKE3MEWDQGGMJKBWHBBYFA3TEO/graph.json","events_json":"https://pith.science/api/pith-number/RKE3MEWDQGGMJKBWHBBYFA3TEO/events.json","paper":"https://pith.science/paper/RKE3MEWD"},"agent_actions":{"view_html":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO","download_json":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO.json","view_paper":"https://pith.science/paper/RKE3MEWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00245&json=true","fetch_graph":"https://pith.science/api/pith-number/RKE3MEWDQGGMJKBWHBBYFA3TEO/graph.json","fetch_events":"https://pith.science/api/pith-number/RKE3MEWDQGGMJKBWHBBYFA3TEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO/action/storage_attestation","attest_author":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO/action/author_attestation","sign_citation":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO/action/citation_signature","submit_replication":"https://pith.science/pith/RKE3MEWDQGGMJKBWHBBYFA3TEO/action/replication_record"}},"created_at":"2026-07-05T08:02:30.100149+00:00","updated_at":"2026-07-05T08:02:30.100149+00:00"}