{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXJLTYHVRGIVNN7QLJYTJZ2W3X","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":"4bca644c24c69251dee5785628c8e5dfd8edf589ff6454e852c5a8a32342f88a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T02:27:27Z","title_canon_sha256":"ff7fc21f0c60ea86cceb6846f829d74e4751b7e0ae70cc3c91a075c770bdbf52"},"schema_version":"1.0","source":{"id":"2607.25207","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25207","created_at":"2026-07-29T00:25:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25207v1","created_at":"2026-07-29T00:25:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25207","created_at":"2026-07-29T00:25:08Z"},{"alias_kind":"pith_short_12","alias_value":"EXJLTYHVRGIV","created_at":"2026-07-29T00:25:08Z"},{"alias_kind":"pith_short_16","alias_value":"EXJLTYHVRGIVNN7Q","created_at":"2026-07-29T00:25:08Z"},{"alias_kind":"pith_short_8","alias_value":"EXJLTYHV","created_at":"2026-07-29T00:25:08Z"}],"graph_snapshots":[{"event_id":"sha256:16e4d5a7fdf7e72c6c526915341415f338d77058087e0a637935f62c7c956bbf","target":"graph","created_at":"2026-07-29T00:25:08Z","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/2607.25207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal policy by combining online interactions with a target environment and offline data from a source environment. A central challenge is that offline data may be collected from outdated environments with shifted transition dynamics, making naive integration of historical data ineffective. To address this, we propose a unified algorithmic framework featuring two algorithms: MIN-UCB-VI for regret minimization and MAX-LCB-VI for best policy identificatio","authors_text":"Fang Kong, Jinhang Zuo, Renjie Zheng, Zenglin Xu, Zheshun Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T02:27:27Z","title":"A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25207","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":"sha256:4778c0d82f84ea315aae56267f9446b550bca5afb47740ad48a822c84506fe84","target":"record","created_at":"2026-07-29T00:25:08Z","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":"4bca644c24c69251dee5785628c8e5dfd8edf589ff6454e852c5a8a32342f88a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T02:27:27Z","title_canon_sha256":"ff7fc21f0c60ea86cceb6846f829d74e4751b7e0ae70cc3c91a075c770bdbf52"},"schema_version":"1.0","source":{"id":"2607.25207","kind":"arxiv","version":1}},"canonical_sha256":"25d2b9e0f5899156b7f05a7134e756dddfbfdeac8ce262938536b0ed37fc695d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25d2b9e0f5899156b7f05a7134e756dddfbfdeac8ce262938536b0ed37fc695d","first_computed_at":"2026-07-29T00:25:08.444075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:08.444075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfW+rkW5hZeMOWLbOqwmdnCuam73gascDSpgrS1Ny1Aswv5ygV0lGfhELvJgkJyKpTjUAVQ2Rc3XM14rHGdTAA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:08.444884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25207","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4778c0d82f84ea315aae56267f9446b550bca5afb47740ad48a822c84506fe84","sha256:16e4d5a7fdf7e72c6c526915341415f338d77058087e0a637935f62c7c956bbf"],"state_sha256":"6b0c1f772606d90e76cc6723895f2e8f3eca2aeb45671441658aad00471b1571"}