{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDMAGRZDYOZSOHXWM3SFSOQ67U","short_pith_number":"pith:PDMAGRZD","schema_version":"1.0","canonical_sha256":"78d8034723c3b3271ef666e4593a1efd3f4ab51aba30e00e3a4b3c6d33a895e6","source":{"kind":"arxiv","id":"2407.17115","version":2},"attestation_state":"computed","paper":{"title":"Reinforced Prompt Personalization for Recommendation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chongming Gao, Jiancan Wu, Weijian Chen, Wenyu Mao, Xiangnan He, Xiang Wang","submitted_at":"2024-07-24T09:24:49Z","abstract_excerpt":"Designing effective prompts can empower LLMs to understand user preferences and provide recommendations with intent comprehension and knowledge utilization capabilities. Nevertheless, recent studies predominantly concentrate on task-wise prompting, developing fixed prompt templates shared across all users in a given recommendation task (e.g., rating or ranking). Although convenient, task-wise prompting overlooks individual user differences, leading to inaccurate analysis of user interests. In this work, we introduce the concept of instance-wise prompting, aiming at personalizing discrete promp"},"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":"2407.17115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-24T09:24:49Z","cross_cats_sorted":[],"title_canon_sha256":"420ae42544fb24aaf3dfa29af322a81862155d99aef6a60bbed400ec3b673c05","abstract_canon_sha256":"2924b880d969f0480650a8ef754802b2f9fb8ee7134733e790c44fbc59e110be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:53.136230Z","signature_b64":"YAQuQmrgEJ0q0URB8HeqwXh/KHv+5aqBRwFsCa7b0abtmjJOyEwzEr+mQdfBwKtRuWeG6sFgsyga7u/3m5KWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78d8034723c3b3271ef666e4593a1efd3f4ab51aba30e00e3a4b3c6d33a895e6","last_reissued_at":"2026-07-05T10:08:53.135817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:53.135817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced Prompt Personalization for Recommendation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chongming Gao, Jiancan Wu, Weijian Chen, Wenyu Mao, Xiangnan He, Xiang Wang","submitted_at":"2024-07-24T09:24:49Z","abstract_excerpt":"Designing effective prompts can empower LLMs to understand user preferences and provide recommendations with intent comprehension and knowledge utilization capabilities. Nevertheless, recent studies predominantly concentrate on task-wise prompting, developing fixed prompt templates shared across all users in a given recommendation task (e.g., rating or ranking). Although convenient, task-wise prompting overlooks individual user differences, leading to inaccurate analysis of user interests. In this work, we introduce the concept of instance-wise prompting, aiming at personalizing discrete promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17115","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/2407.17115/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":"2407.17115","created_at":"2026-07-05T10:08:53.135874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17115v2","created_at":"2026-07-05T10:08:53.135874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17115","created_at":"2026-07-05T10:08:53.135874+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDMAGRZDYOZS","created_at":"2026-07-05T10:08:53.135874+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDMAGRZDYOZSOHXW","created_at":"2026-07-05T10:08:53.135874+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDMAGRZD","created_at":"2026-07-05T10:08:53.135874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20815","citing_title":"Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U","json":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U.json","graph_json":"https://pith.science/api/pith-number/PDMAGRZDYOZSOHXWM3SFSOQ67U/graph.json","events_json":"https://pith.science/api/pith-number/PDMAGRZDYOZSOHXWM3SFSOQ67U/events.json","paper":"https://pith.science/paper/PDMAGRZD"},"agent_actions":{"view_html":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U","download_json":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U.json","view_paper":"https://pith.science/paper/PDMAGRZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17115&json=true","fetch_graph":"https://pith.science/api/pith-number/PDMAGRZDYOZSOHXWM3SFSOQ67U/graph.json","fetch_events":"https://pith.science/api/pith-number/PDMAGRZDYOZSOHXWM3SFSOQ67U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U/action/storage_attestation","attest_author":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U/action/author_attestation","sign_citation":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U/action/citation_signature","submit_replication":"https://pith.science/pith/PDMAGRZDYOZSOHXWM3SFSOQ67U/action/replication_record"}},"created_at":"2026-07-05T10:08:53.135874+00:00","updated_at":"2026-07-05T10:08:53.135874+00:00"}