{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TORBHUJLVYK2VLZQ7OKM5X5XGI","short_pith_number":"pith:TORBHUJL","schema_version":"1.0","canonical_sha256":"9ba213d12bae15aaaf30fb94cedfb732312355d442a9fb150613914766e5c031","source":{"kind":"arxiv","id":"2404.00702","version":3},"attestation_state":"computed","paper":{"title":"LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Huifeng Guo, Kuicai Dong, Ruiming Tang, Wenlin Zhang, Xiangyang Li, Xiangyu Zhao, Xinyi Dai, Yichao Wang, Yuhao Wang","submitted_at":"2024-03-31T14:41:49Z","abstract_excerpt":"The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations. To address this problem, Large Language Models (LLMs) can model recommendation tasks as language analysis tasks and provide zero-shot results based on their vast open-world knowledge. However, the large scale of the item corpus poses a challenge to LLMs, leading to substantial token consumption that makes it impractical to deploy in real-world recommendation systems. To tackle this challenge, we introduce a tree-based LLM recommendation fra"},"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":"2404.00702","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-31T14:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"260faa263305a4cc51d05f53c4d44921abd4d53d3b8d805a04563b92902198a7","abstract_canon_sha256":"e67dc586a16757f4e2805264962811e149c0ce9d12a8b2acc72d14db7c8c9c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:40.620409Z","signature_b64":"CxysqrQwaSOAbuYdShkmYvOtUr0OoSrBEvk6mFGHxQoh+1dkcPmKp7W4+Q+qbEOF7jJSyFxk3WaKI6pgW+zsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba213d12bae15aaaf30fb94cedfb732312355d442a9fb150613914766e5c031","last_reissued_at":"2026-07-05T09:53:40.619928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:40.619928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuhan Wu, Huifeng Guo, Kuicai Dong, Ruiming Tang, Wenlin Zhang, Xiangyang Li, Xiangyu Zhao, Xinyi Dai, Yichao Wang, Yuhao Wang","submitted_at":"2024-03-31T14:41:49Z","abstract_excerpt":"The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations. To address this problem, Large Language Models (LLMs) can model recommendation tasks as language analysis tasks and provide zero-shot results based on their vast open-world knowledge. However, the large scale of the item corpus poses a challenge to LLMs, leading to substantial token consumption that makes it impractical to deploy in real-world recommendation systems. To tackle this challenge, we introduce a tree-based LLM recommendation fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00702","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/2404.00702/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":"2404.00702","created_at":"2026-07-05T09:53:40.619988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00702v3","created_at":"2026-07-05T09:53:40.619988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00702","created_at":"2026-07-05T09:53:40.619988+00:00"},{"alias_kind":"pith_short_12","alias_value":"TORBHUJLVYK2","created_at":"2026-07-05T09:53:40.619988+00:00"},{"alias_kind":"pith_short_16","alias_value":"TORBHUJLVYK2VLZQ","created_at":"2026-07-05T09:53:40.619988+00:00"},{"alias_kind":"pith_short_8","alias_value":"TORBHUJL","created_at":"2026-07-05T09:53:40.619988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19500","citing_title":"NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11553","citing_title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI","json":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI.json","graph_json":"https://pith.science/api/pith-number/TORBHUJLVYK2VLZQ7OKM5X5XGI/graph.json","events_json":"https://pith.science/api/pith-number/TORBHUJLVYK2VLZQ7OKM5X5XGI/events.json","paper":"https://pith.science/paper/TORBHUJL"},"agent_actions":{"view_html":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI","download_json":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI.json","view_paper":"https://pith.science/paper/TORBHUJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00702&json=true","fetch_graph":"https://pith.science/api/pith-number/TORBHUJLVYK2VLZQ7OKM5X5XGI/graph.json","fetch_events":"https://pith.science/api/pith-number/TORBHUJLVYK2VLZQ7OKM5X5XGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI/action/storage_attestation","attest_author":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI/action/author_attestation","sign_citation":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI/action/citation_signature","submit_replication":"https://pith.science/pith/TORBHUJLVYK2VLZQ7OKM5X5XGI/action/replication_record"}},"created_at":"2026-07-05T09:53:40.619988+00:00","updated_at":"2026-07-05T09:53:40.619988+00:00"}