{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ODGHVDVWYR6NOP4ZHXTDGRITCS","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":"b91480dba173c223844b3769dee95b058c2f6d622a9584e6191bae818b89e102","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-01T02:45:35Z","title_canon_sha256":"f5f888dbeff37cdf14d14a0347ff415ca9d4572fb1e74d3bb016852b7b8af65b"},"schema_version":"1.0","source":{"id":"2206.02620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02620","created_at":"2026-07-05T06:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02620v2","created_at":"2026-07-05T06:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02620","created_at":"2026-07-05T06:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"ODGHVDVWYR6N","created_at":"2026-07-05T06:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"ODGHVDVWYR6NOP4Z","created_at":"2026-07-05T06:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"ODGHVDVW","created_at":"2026-07-05T06:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:0e7f5008cc7da4cd148b9ed9d8b16f6e7ff32bfc94d6926f478a33e5907380b9","target":"graph","created_at":"2026-07-05T06:21:12Z","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/2206.02620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-term engagement is preferred over immediate engagement in sequential recommendation as it directly affects product operational metrics such as daily active users (DAUs) and dwell time. Meanwhile, reinforcement learning (RL) is widely regarded as a promising framework for optimizing long-term engagement in sequential recommendation. However, due to expensive online interactions, it is very difficult for RL algorithms to perform state-action value estimation, exploration and feature extraction when optimizing long-term engagement. In this paper, we propose ResAct which seeks a policy that i","authors_text":"Bo An, Dong Zheng, Kun Gai, Peng Jiang, Qingpeng Cai, Ruohan Zhan, Wanqi Xue","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-01T02:45:35Z","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02620","kind":"arxiv","version":2},"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":"sha256:41a896f76880e6d12cddcb1e1c070d44fd0b849148b64d808c40164e48563f11","target":"record","created_at":"2026-07-05T06:21:12Z","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":"b91480dba173c223844b3769dee95b058c2f6d622a9584e6191bae818b89e102","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-01T02:45:35Z","title_canon_sha256":"f5f888dbeff37cdf14d14a0347ff415ca9d4572fb1e74d3bb016852b7b8af65b"},"schema_version":"1.0","source":{"id":"2206.02620","kind":"arxiv","version":2}},"canonical_sha256":"70cc7a8eb6c47cd73f993de6334513149178da6f6330d869089c419ace91718b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70cc7a8eb6c47cd73f993de6334513149178da6f6330d869089c419ace91718b","first_computed_at":"2026-07-05T06:21:12.951100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:12.951100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+4E5LECQ4ERRymfv6ul9ZKwX2WswwKUwM/5xyY1EaXyBIRn/bLx8UepbDY7j5bzqHNGsqenO1qa8compPA4LDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:12.951507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a896f76880e6d12cddcb1e1c070d44fd0b849148b64d808c40164e48563f11","sha256:0e7f5008cc7da4cd148b9ed9d8b16f6e7ff32bfc94d6926f478a33e5907380b9"],"state_sha256":"46666c17672978c1ab250390d75d935144ee318e68483246990977b39d9d512a"}