{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FFNVGWYHOJ3XF4RSNXMILP3YV","short_pith_number":"pith:2FFNVGWY","schema_version":"1.0","canonical_sha256":"d14ada9ad83b93bb9791936ec42dfbc563f1f7c42a0be7f930d8e2f434d900e5","source":{"kind":"arxiv","id":"2406.14043","version":3},"attestation_state":"computed","paper":{"title":"Taxonomy-Guided Zero-Shot Recommendations with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chen Wang, Kai Shu, Liangwei Yang, Philip S. Yu, Xiongxiao Xu, Yueqing Liang","submitted_at":"2024-06-20T07:06:58Z","abstract_excerpt":"With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of it"},"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":"2406.14043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T07:06:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e5f49c8ff4e98799744f8d02570d1b16ec94e21f1bfbe3a172bd78ee2ddb3036","abstract_canon_sha256":"f6857401010205239f5c6f77bc6fb5ccd050a620476f583410850172217b8c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:09.065474Z","signature_b64":"009zagshYCQzPapqZML85tNHjsFatR+GKjxfBm7V2mKH0EaLECnYchi+KttJlKhdXT+nArSBf/4hDtWWcvy6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d14ada9ad83b93bb9791936ec42dfbc563f1f7c42a0be7f930d8e2f434d900e5","last_reissued_at":"2026-07-05T10:17:09.064981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:09.064981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taxonomy-Guided Zero-Shot Recommendations with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chen Wang, Kai Shu, Liangwei Yang, Philip S. Yu, Xiongxiao Xu, Yueqing Liang","submitted_at":"2024-06-20T07:06:58Z","abstract_excerpt":"With the emergence of large language models (LLMs) and their ability to perform a variety of tasks, their application in recommender systems (RecSys) has shown promise. However, we are facing significant challenges when deploying LLMs into RecSys, such as limited prompt length, unstructured item information, and un-constrained generation of recommendations, leading to sub-optimal performance. To address these issues, we propose a novel method using a taxonomy dictionary. This method provides a systematic framework for categorizing and organizing items, improving the clarity and structure of it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14043","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/2406.14043/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":"2406.14043","created_at":"2026-07-05T10:17:09.065036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14043v3","created_at":"2026-07-05T10:17:09.065036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14043","created_at":"2026-07-05T10:17:09.065036+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FFNVGWYHOJ3","created_at":"2026-07-05T10:17:09.065036+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FFNVGWYHOJ3XF4R","created_at":"2026-07-05T10:17:09.065036+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FFNVGWY","created_at":"2026-07-05T10:17:09.065036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09551","citing_title":"SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07825","citing_title":"Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV","json":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV.json","graph_json":"https://pith.science/api/pith-number/2FFNVGWYHOJ3XF4RSNXMILP3YV/graph.json","events_json":"https://pith.science/api/pith-number/2FFNVGWYHOJ3XF4RSNXMILP3YV/events.json","paper":"https://pith.science/paper/2FFNVGWY"},"agent_actions":{"view_html":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV","download_json":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV.json","view_paper":"https://pith.science/paper/2FFNVGWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14043&json=true","fetch_graph":"https://pith.science/api/pith-number/2FFNVGWYHOJ3XF4RSNXMILP3YV/graph.json","fetch_events":"https://pith.science/api/pith-number/2FFNVGWYHOJ3XF4RSNXMILP3YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV/action/storage_attestation","attest_author":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV/action/author_attestation","sign_citation":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV/action/citation_signature","submit_replication":"https://pith.science/pith/2FFNVGWYHOJ3XF4RSNXMILP3YV/action/replication_record"}},"created_at":"2026-07-05T10:17:09.065036+00:00","updated_at":"2026-07-05T10:17:09.065036+00:00"}