{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJMMFR5RAAKXFQXZNWA3TSOHOY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482"},"schema_version":"1.0","source":{"id":"2501.13816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13816v1","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13816","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"SJMMFR5RAAKX","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"SJMMFR5RAAKXFQXZ","created_at":"2026-07-05T10:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"SJMMFR5R","created_at":"2026-07-05T10:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb","target":"graph","created_at":"2026-07-05T10:04:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.13816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Recommender Systems (RS) have incorporated Reinforcement Learning (RL), framing the recommendation as a Markov Decision Process (MDP). However, offline RL policies trained on static user data are vulnerable to distribution shift when deployed in dynamic online environments. Additionally, excessive focus on exploiting short-term relevant items can hinder exploration, leading to suboptimal recommendations and negatively impacting long-term user gains. Online RL-based RS also face challenges in production deployment, due to the risks of exposing users to untrained or unstab","authors_text":"Alexandros Karatzoglou, Ioannis Arapakis, Jie Wang, Joemon M. Jose","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title":"Large Language Model driven Policy Exploration for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13816","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357","target":"record","created_at":"2026-07-05T10:04:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8873067852e8bd78570e328861564cbbf1bca4691a1a5c2aca2c3f8a232474cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-01-23T16:37:44Z","title_canon_sha256":"c928e8c87ad692780e93c06d3f9c512bdef6b5f9644ae98b5820f93f1b144482"},"schema_version":"1.0","source":{"id":"2501.13816","kind":"arxiv","version":1}},"canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9258c2c7b1001572c2f96d81b9c9c77614229c986fa4a0cbcc18bc2102fb93b7","first_computed_at":"2026-07-05T10:04:34.301027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:34.301027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JDTe5OQT7wHxQyRaJOuEYRFG8fU+fTt/Rm0A9ifGWfYlKift0lByLfrPD1DdDvFm/n+DO/4j7waO/nl3b4bTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:34.301528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32180c1626c2b2a88e4fda9a84333cc54a7af904463c704382af9337dbc2f357","sha256:305095781ed9709df3353308f432defe83cdc60caf5a3e98e57ac5a062b4a9fb"],"state_sha256":"37a17628ba8c7c2031582ce2fa2b5bf20bd561d8bd8aab89d29a8830de2d04f9"}