{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIE76GGKH6OXQBO7GOR5GRK4S4","short_pith_number":"pith:LIE76GGK","schema_version":"1.0","canonical_sha256":"5a09ff18ca3f9d7805df33a3d3455c97010bd015e6d5ca90d1827780a5c7eb91","source":{"kind":"arxiv","id":"2410.16458","version":2},"attestation_state":"computed","paper":{"title":"STAR: A Simple Training-free Approach for Recommendations using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Adam Kraft, Dong-Ho Lee, Ed H. Chi, Lichan Hong, Long Jin, Nikhil Mehta, Taibai Xu, Xinyang Yi","submitted_at":"2024-10-21T19:34:40Z","abstract_excerpt":"Recent progress in large language models (LLMs) offers promising new approaches for recommendation system tasks. While the current state-of-the-art methods rely on fine-tuning LLMs to achieve optimal results, this process is costly and introduces significant engineering complexities. Conversely, methods that directly use LLMs without additional fine-tuning result in a large drop in recommendation quality, often due to the inability to capture collaborative information. In this paper, we propose a Simple Training-free Approach for Recommendation (STAR), a framework that utilizes LLMs and can be"},"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":"2410.16458","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-21T19:34:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dde7a38aef38548ff7bfebf5498c4b5fcbdb6612cdb30695bf93464615fc6446","abstract_canon_sha256":"421b0ed38a895070ba6c4f7ce1558ee1927168c7596b509512770a167af0fdea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:12.550116Z","signature_b64":"lSWt1+JFSJkACva3DfWcmATG6RJC4wPY4MDS82MHcYt1B0c+ZKpCxmAc8VEyY/L2b7MaNuqIdznuLgul+e5aDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a09ff18ca3f9d7805df33a3d3455c97010bd015e6d5ca90d1827780a5c7eb91","last_reissued_at":"2026-07-05T10:17:12.549635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:12.549635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAR: A Simple Training-free Approach for Recommendations using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Adam Kraft, Dong-Ho Lee, Ed H. Chi, Lichan Hong, Long Jin, Nikhil Mehta, Taibai Xu, Xinyang Yi","submitted_at":"2024-10-21T19:34:40Z","abstract_excerpt":"Recent progress in large language models (LLMs) offers promising new approaches for recommendation system tasks. While the current state-of-the-art methods rely on fine-tuning LLMs to achieve optimal results, this process is costly and introduces significant engineering complexities. Conversely, methods that directly use LLMs without additional fine-tuning result in a large drop in recommendation quality, often due to the inability to capture collaborative information. In this paper, we propose a Simple Training-free Approach for Recommendation (STAR), a framework that utilizes LLMs and can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16458","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/2410.16458/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":"2410.16458","created_at":"2026-07-05T10:17:12.549693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16458v2","created_at":"2026-07-05T10:17:12.549693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16458","created_at":"2026-07-05T10:17:12.549693+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIE76GGKH6OX","created_at":"2026-07-05T10:17:12.549693+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIE76GGKH6OXQBO7","created_at":"2026-07-05T10:17:12.549693+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIE76GGK","created_at":"2026-07-05T10:17:12.549693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07443","citing_title":"RcLLM: Accelerating Generative Recommendation via Beyond-Prefix KV Caching","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07129","citing_title":"RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4","json":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4.json","graph_json":"https://pith.science/api/pith-number/LIE76GGKH6OXQBO7GOR5GRK4S4/graph.json","events_json":"https://pith.science/api/pith-number/LIE76GGKH6OXQBO7GOR5GRK4S4/events.json","paper":"https://pith.science/paper/LIE76GGK"},"agent_actions":{"view_html":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4","download_json":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4.json","view_paper":"https://pith.science/paper/LIE76GGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16458&json=true","fetch_graph":"https://pith.science/api/pith-number/LIE76GGKH6OXQBO7GOR5GRK4S4/graph.json","fetch_events":"https://pith.science/api/pith-number/LIE76GGKH6OXQBO7GOR5GRK4S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4/action/storage_attestation","attest_author":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4/action/author_attestation","sign_citation":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4/action/citation_signature","submit_replication":"https://pith.science/pith/LIE76GGKH6OXQBO7GOR5GRK4S4/action/replication_record"}},"created_at":"2026-07-05T10:17:12.549693+00:00","updated_at":"2026-07-05T10:17:12.549693+00:00"}