{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PW6ORIBERNCNO6B3VOMXFGNPA2","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":"b5626776a23965fe87b39eb67f84392957a67b7e08932aed38c03b7208ff3966","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-22T10:28:02Z","title_canon_sha256":"a2e19be2cd072cee554715f4b433329952774ef8a9ad1bc3c79ec035a0218125"},"schema_version":"1.0","source":{"id":"2308.11336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11336","created_at":"2026-07-05T06:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11336v1","created_at":"2026-07-05T06:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11336","created_at":"2026-07-05T06:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"PW6ORIBERNCN","created_at":"2026-07-05T06:43:33Z"},{"alias_kind":"pith_short_16","alias_value":"PW6ORIBERNCNO6B3","created_at":"2026-07-05T06:43:33Z"},{"alias_kind":"pith_short_8","alias_value":"PW6ORIBE","created_at":"2026-07-05T06:43:33Z"}],"graph_snapshots":[{"event_id":"sha256:b5765899acd770df86d140cbe88d225b66dbe95b2606062fbbfa561fc1440b43","target":"graph","created_at":"2026-07-05T06:43:33Z","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/2308.11336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming from its interactive nature. The training of reinforcement learning-based recommender systems demands expensive online interactions to amass adequate trajectories, essential for agents to learn user preferences. This inefficiency renders reinforcement learning-based recommender systems a formidable undertaking, necessitating the exploration of potential solutio","authors_text":"Dietmar Jannach, Julian McAuley, Lina Yao, Siyu Wang, Xiaocong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-22T10:28:02Z","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11336","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":"sha256:01e9d21ad983d70e66c018d1a4b9087833f1b8a33e3df16abdb15d71bf989a63","target":"record","created_at":"2026-07-05T06:43:33Z","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":"b5626776a23965fe87b39eb67f84392957a67b7e08932aed38c03b7208ff3966","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-22T10:28:02Z","title_canon_sha256":"a2e19be2cd072cee554715f4b433329952774ef8a9ad1bc3c79ec035a0218125"},"schema_version":"1.0","source":{"id":"2308.11336","kind":"arxiv","version":1}},"canonical_sha256":"7dbce8a0248b44d7783bab997299af06b3d055c2570c711bc14a9441819bedeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dbce8a0248b44d7783bab997299af06b3d055c2570c711bc14a9441819bedeb","first_computed_at":"2026-07-05T06:43:33.019379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:33.019379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"16lIWSQr1MmIgAcPo82ZnLCZd7ZI83APoEbnSZq6OXWozYdNQfpD4SXad1Gof/FfOXsYQMUL9mD7fnytF865Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:33.019714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01e9d21ad983d70e66c018d1a4b9087833f1b8a33e3df16abdb15d71bf989a63","sha256:b5765899acd770df86d140cbe88d225b66dbe95b2606062fbbfa561fc1440b43"],"state_sha256":"f2ae65d92766259d9c590237889ef922904b2759d75c5ec26831fafb22ebeef3"}