{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HOWEAL6G22V6W2T5Y4MT6ILHUV","short_pith_number":"pith:HOWEAL6G","schema_version":"1.0","canonical_sha256":"3bac402fc6d6abeb6a7dc7193f2167a54569bb0c653e0db5030fd21ae8fb0fb0","source":{"kind":"arxiv","id":"2507.21274","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model-Enhanced Reinforcement Learning for Diverse and Novel Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza Bagheri Garakani, Jiin Woo, Tianchen Zhou, Yan Gao, Zhishen Huang","submitted_at":"2025-07-28T19:00:40Z","abstract_excerpt":"In recommendation systems, diversity and novelty are essential for capturing varied user preferences and encouraging exploration, yet many systems prioritize click relevance. While reinforcement learning (RL) has been explored to improve diversity, it often depends on random exploration that may not align with user interests. We propose LAAC (LLM-guided Adversarial Actor Critic), a novel method that leverages large language models (LLMs) as reference policies to suggest novel items, while training a lightweight policy to refine these suggestions using system-specific data. The method formulate"},"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":"2507.21274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-28T19:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"e1b1fee4f7147dfba34641d55c976d4f59a667211f96b209acff134efea88d1f","abstract_canon_sha256":"f4826dc6a8d81ea9e9d5bf05aa6350b67e9bd82696cd8d7690106c1bcba51341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:56.076474Z","signature_b64":"vicO0nPtYHGQrCQRgz0wUvGqiTyWX9g/P0d8fJB5IVFhhOEQJoVMXW6FBdGJUnEh9g1zrj08gIKgNH+5zlPLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bac402fc6d6abeb6a7dc7193f2167a54569bb0c653e0db5030fd21ae8fb0fb0","last_reissued_at":"2026-07-05T11:44:56.076009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:56.076009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model-Enhanced Reinforcement Learning for Diverse and Novel Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza Bagheri Garakani, Jiin Woo, Tianchen Zhou, Yan Gao, Zhishen Huang","submitted_at":"2025-07-28T19:00:40Z","abstract_excerpt":"In recommendation systems, diversity and novelty are essential for capturing varied user preferences and encouraging exploration, yet many systems prioritize click relevance. While reinforcement learning (RL) has been explored to improve diversity, it often depends on random exploration that may not align with user interests. We propose LAAC (LLM-guided Adversarial Actor Critic), a novel method that leverages large language models (LLMs) as reference policies to suggest novel items, while training a lightweight policy to refine these suggestions using system-specific data. The method formulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21274","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/2507.21274/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":"2507.21274","created_at":"2026-07-05T11:44:56.076067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21274v1","created_at":"2026-07-05T11:44:56.076067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21274","created_at":"2026-07-05T11:44:56.076067+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOWEAL6G22V6","created_at":"2026-07-05T11:44:56.076067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOWEAL6G22V6W2T5","created_at":"2026-07-05T11:44:56.076067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOWEAL6G","created_at":"2026-07-05T11:44:56.076067+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/HOWEAL6G22V6W2T5Y4MT6ILHUV","json":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV.json","graph_json":"https://pith.science/api/pith-number/HOWEAL6G22V6W2T5Y4MT6ILHUV/graph.json","events_json":"https://pith.science/api/pith-number/HOWEAL6G22V6W2T5Y4MT6ILHUV/events.json","paper":"https://pith.science/paper/HOWEAL6G"},"agent_actions":{"view_html":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV","download_json":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV.json","view_paper":"https://pith.science/paper/HOWEAL6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21274&json=true","fetch_graph":"https://pith.science/api/pith-number/HOWEAL6G22V6W2T5Y4MT6ILHUV/graph.json","fetch_events":"https://pith.science/api/pith-number/HOWEAL6G22V6W2T5Y4MT6ILHUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV/action/storage_attestation","attest_author":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV/action/author_attestation","sign_citation":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV/action/citation_signature","submit_replication":"https://pith.science/pith/HOWEAL6G22V6W2T5Y4MT6ILHUV/action/replication_record"}},"created_at":"2026-07-05T11:44:56.076067+00:00","updated_at":"2026-07-05T11:44:56.076067+00:00"}