{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TGKOOKECLEF6X3S75XUI2IQ323","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":"f94492545bd6515d4f56a843771e82e97656d448d330595efe12f7c5dcd6fcac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-04T17:55:38Z","title_canon_sha256":"a2afc469605ec7e1822facc6c3f27b43895f03d208425955ef153464d8511250"},"schema_version":"1.0","source":{"id":"2404.03637","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03637","created_at":"2026-07-05T08:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03637v2","created_at":"2026-07-05T08:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03637","created_at":"2026-07-05T08:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"TGKOOKECLEF6","created_at":"2026-07-05T08:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"TGKOOKECLEF6X3S7","created_at":"2026-07-05T08:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"TGKOOKEC","created_at":"2026-07-05T08:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:5ff38e73f4c863a24f6146d73857d56bb3463cae5f44102866149509bdfbabe5","target":"graph","created_at":"2026-07-05T08:29:25Z","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/2404.03637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the landscape of Recommender System (RS) applications, reinforcement learning (RL) has recently emerged as a powerful tool, primarily due to its proficiency in optimizing long-term rewards. Nevertheless, it suffers from instability in the learning process, stemming from the intricate interactions among bootstrapping, off-policy training, and function approximation. Moreover, in multi-reward recommendation scenarios, designing a proper reward setting that reconciles the inner dynamics of various tasks is quite intricate. In response to these challenges, we introduce DT4IER, an advanced decis","authors_text":"Kesen Zhao, Kun Gai, Lantao Hu, Peng Jiang, Qingpeng Cai, Shuchang Liu, Xiangyu Zhao, Zijian Zhang, Ziru Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-04T17:55:38Z","title":"Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03637","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:a70a621740bd6802a99371f6aefa8de0c083156f87c81fc330a0a06ad0faf674","target":"record","created_at":"2026-07-05T08:29:25Z","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":"f94492545bd6515d4f56a843771e82e97656d448d330595efe12f7c5dcd6fcac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-04T17:55:38Z","title_canon_sha256":"a2afc469605ec7e1822facc6c3f27b43895f03d208425955ef153464d8511250"},"schema_version":"1.0","source":{"id":"2404.03637","kind":"arxiv","version":2}},"canonical_sha256":"9994e72882590bebee5fede88d221bd6f565e45d002e5c5e3e88eaa9547f8e4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9994e72882590bebee5fede88d221bd6f565e45d002e5c5e3e88eaa9547f8e4a","first_computed_at":"2026-07-05T08:29:25.243618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:25.243618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEXEavzpl2eEDc4dpiN8NWVO0ujSZO1HjsY1ksUcaI9v/AHRbJzKbNJLIqOLzn7ChvdyD0iEWz6Z65JUdCGlAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:25.244127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03637","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a70a621740bd6802a99371f6aefa8de0c083156f87c81fc330a0a06ad0faf674","sha256:5ff38e73f4c863a24f6146d73857d56bb3463cae5f44102866149509bdfbabe5"],"state_sha256":"1193048dd2dd6c35c72b74527b561244fad9bc95c24d387ab5e40cba3095827a"}