{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7X5UQMFSER4VBB34V7NTLCVTE","short_pith_number":"pith:V7X5UQMF","schema_version":"1.0","canonical_sha256":"afefda41859123ca843be57ed9ac559932b2f0717dfbea21711f6b233f2864e7","source":{"kind":"arxiv","id":"2402.09176","version":2},"attestation_state":"computed","paper":{"title":"Large Language Model Simulator for Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fakhri Karray, Feiran Huang, Hao Chen, Junyi Jiang, Philip S. Yu, Qijie Shen, Senzhang Wang, Yuanchen Bei, Zhenghang Yang","submitted_at":"2024-02-14T13:45:06Z","abstract_excerpt":"Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely solely on content features, limiting their recommendation performance and impacting user experience and revenue. Current models generate synthetic behavioral embeddings from content features but fail to address the core issue: the absence of historical behavior data. To tackle this, we introduce the LLM Simulator framework, which leverages large language models to simulate user interactions for cold items, fundamentally"},"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":"2402.09176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-14T13:45:06Z","cross_cats_sorted":[],"title_canon_sha256":"27fb7c841d6e33e32bba3435d90e1fe3adc684b5e0992edeca8fcd50978e441d","abstract_canon_sha256":"b9f7b773908d8e04b534a322a252467816817190eccfd91a0a7b740754c66c10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:01.136483Z","signature_b64":"Bfoseln6M3ipYfNl0Upq80cGiHsUNHQhENzc9K+SODqlcg/arTe5Q7M48Mkm1M9XqpjxC2Rz8R61wQ0psBsyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afefda41859123ca843be57ed9ac559932b2f0717dfbea21711f6b233f2864e7","last_reissued_at":"2026-07-05T09:54:01.135980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:01.135980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Simulator for Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fakhri Karray, Feiran Huang, Hao Chen, Junyi Jiang, Philip S. Yu, Qijie Shen, Senzhang Wang, Yuanchen Bei, Zhenghang Yang","submitted_at":"2024-02-14T13:45:06Z","abstract_excerpt":"Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely solely on content features, limiting their recommendation performance and impacting user experience and revenue. Current models generate synthetic behavioral embeddings from content features but fail to address the core issue: the absence of historical behavior data. To tackle this, we introduce the LLM Simulator framework, which leverages large language models to simulate user interactions for cold items, fundamentally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09176","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/2402.09176/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":"2402.09176","created_at":"2026-07-05T09:54:01.136042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09176v2","created_at":"2026-07-05T09:54:01.136042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09176","created_at":"2026-07-05T09:54:01.136042+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7X5UQMFSER4","created_at":"2026-07-05T09:54:01.136042+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7X5UQMFSER4VBB3","created_at":"2026-07-05T09:54:01.136042+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7X5UQMF","created_at":"2026-07-05T09:54:01.136042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06779","citing_title":"Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12525","citing_title":"PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14839","citing_title":"Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE","json":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE.json","graph_json":"https://pith.science/api/pith-number/V7X5UQMFSER4VBB34V7NTLCVTE/graph.json","events_json":"https://pith.science/api/pith-number/V7X5UQMFSER4VBB34V7NTLCVTE/events.json","paper":"https://pith.science/paper/V7X5UQMF"},"agent_actions":{"view_html":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE","download_json":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE.json","view_paper":"https://pith.science/paper/V7X5UQMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09176&json=true","fetch_graph":"https://pith.science/api/pith-number/V7X5UQMFSER4VBB34V7NTLCVTE/graph.json","fetch_events":"https://pith.science/api/pith-number/V7X5UQMFSER4VBB34V7NTLCVTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE/action/storage_attestation","attest_author":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE/action/author_attestation","sign_citation":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE/action/citation_signature","submit_replication":"https://pith.science/pith/V7X5UQMFSER4VBB34V7NTLCVTE/action/replication_record"}},"created_at":"2026-07-05T09:54:01.136042+00:00","updated_at":"2026-07-05T09:54:01.136042+00:00"}