{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:47FPNJCKRHFA3YQZEJSAX25ZFH","short_pith_number":"pith:47FPNJCK","schema_version":"1.0","canonical_sha256":"e7caf6a44a89ca0de21922640bebb929f5fa67ffaff616c697832b0652e55dcb","source":{"kind":"arxiv","id":"2509.09066","version":1},"attestation_state":"computed","paper":{"title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Su, Chao Yao, Haowei Yang, Sitao Min, Wei Xu, Yushang Zhao","submitted_at":"2025-09-11T00:13:17Z","abstract_excerpt":"The cold-start user issue further compromises the effectiveness of recommender systems in limiting access to the historical behavioral information. It is an effective pipeline to optimize instructional prompts on a few-shot large language model (LLM) used in recommender tasks. We introduce a context-conditioned prompt formulation method P(u,\\ Ds)\\ \\rightarrow\\ R\\widehat, where u is a cold-start user profile, Ds is a curated support set, and R\\widehat is the predicted ranked list of items. Based on systematic experimentation with transformer-based autoregressive LLMs (BioGPT, LLaMA-2, GPT-4), w"},"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":"2509.09066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-11T00:13:17Z","cross_cats_sorted":[],"title_canon_sha256":"8ec77078e583eb713d9c7ed267b0fb18e6f9bf35f40788512b7aa5ea585351ef","abstract_canon_sha256":"ca9cb8e6f25de0a6e3c57d0d99f054c8c14b83fa29134f53de1ead2fb4b86f51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:28.820995Z","signature_b64":"3i6I+kGkmPtqO3K/BSORMwZsHH3+6PtkHWxtHNNgtdCDDLVgiR1s9DsuV3KMtfY3rDeySNl9DsL4HID0R3NkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7caf6a44a89ca0de21922640bebb929f5fa67ffaff616c697832b0652e55dcb","last_reissued_at":"2026-07-05T12:09:28.820416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:28.820416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Su, Chao Yao, Haowei Yang, Sitao Min, Wei Xu, Yushang Zhao","submitted_at":"2025-09-11T00:13:17Z","abstract_excerpt":"The cold-start user issue further compromises the effectiveness of recommender systems in limiting access to the historical behavioral information. It is an effective pipeline to optimize instructional prompts on a few-shot large language model (LLM) used in recommender tasks. We introduce a context-conditioned prompt formulation method P(u,\\ Ds)\\ \\rightarrow\\ R\\widehat, where u is a cold-start user profile, Ds is a curated support set, and R\\widehat is the predicted ranked list of items. Based on systematic experimentation with transformer-based autoregressive LLMs (BioGPT, LLaMA-2, GPT-4), w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09066","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/2509.09066/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":"2509.09066","created_at":"2026-07-05T12:09:28.820490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09066v1","created_at":"2026-07-05T12:09:28.820490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09066","created_at":"2026-07-05T12:09:28.820490+00:00"},{"alias_kind":"pith_short_12","alias_value":"47FPNJCKRHFA","created_at":"2026-07-05T12:09:28.820490+00:00"},{"alias_kind":"pith_short_16","alias_value":"47FPNJCKRHFA3YQZ","created_at":"2026-07-05T12:09:28.820490+00:00"},{"alias_kind":"pith_short_8","alias_value":"47FPNJCK","created_at":"2026-07-05T12:09:28.820490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH","json":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH.json","graph_json":"https://pith.science/api/pith-number/47FPNJCKRHFA3YQZEJSAX25ZFH/graph.json","events_json":"https://pith.science/api/pith-number/47FPNJCKRHFA3YQZEJSAX25ZFH/events.json","paper":"https://pith.science/paper/47FPNJCK"},"agent_actions":{"view_html":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH","download_json":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH.json","view_paper":"https://pith.science/paper/47FPNJCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09066&json=true","fetch_graph":"https://pith.science/api/pith-number/47FPNJCKRHFA3YQZEJSAX25ZFH/graph.json","fetch_events":"https://pith.science/api/pith-number/47FPNJCKRHFA3YQZEJSAX25ZFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH/action/storage_attestation","attest_author":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH/action/author_attestation","sign_citation":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH/action/citation_signature","submit_replication":"https://pith.science/pith/47FPNJCKRHFA3YQZEJSAX25ZFH/action/replication_record"}},"created_at":"2026-07-05T12:09:28.820490+00:00","updated_at":"2026-07-05T12:09:28.820490+00:00"}