{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CG7ZBZFIOMYSTAXX5ZFKNMY3KX","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":"11bc489f9d539d3a895ed745d66e08c70c540469e289fbede25f11b2d8210fcb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-10T08:18:27Z","title_canon_sha256":"8b833861e770c85688edeb56612806732967813773fd077622bc60e719fa574f"},"schema_version":"1.0","source":{"id":"2603.09344","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09344","created_at":"2026-06-19T16:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09344v3","created_at":"2026-06-19T16:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09344","created_at":"2026-06-19T16:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"CG7ZBZFIOMYS","created_at":"2026-06-19T16:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"CG7ZBZFIOMYSTAXX","created_at":"2026-06-19T16:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"CG7ZBZFI","created_at":"2026-06-19T16:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:35ab1ff9c01b3b8ca1f2613c937dc5b036f80e79f61006fd5db482ce7d9bc444","target":"graph","created_at":"2026-06-19T16:11:21Z","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/2603.09344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robu","authors_text":"Dongxu Zhang, Hongqiang Lin, Pengfei Wang, Qixian Huang, Weihao Tang, Yiding Sun, Zhenghui Fu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-10T08:18:27Z","title":"Robust Regularized Policy Iteration under Transition Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09344","kind":"arxiv","version":3},"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":"sha256:6a42d0bae84c99e8d52f9d9999f39ba48677d7a984f448dc84df3b521c36e787","target":"record","created_at":"2026-06-19T16:11:21Z","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":"11bc489f9d539d3a895ed745d66e08c70c540469e289fbede25f11b2d8210fcb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-10T08:18:27Z","title_canon_sha256":"8b833861e770c85688edeb56612806732967813773fd077622bc60e719fa574f"},"schema_version":"1.0","source":{"id":"2603.09344","kind":"arxiv","version":3}},"canonical_sha256":"11bf90e4a873312982f7ee4aa6b31b55cd7a4e8cc92cbfc5c625b86b41d07e29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11bf90e4a873312982f7ee4aa6b31b55cd7a4e8cc92cbfc5c625b86b41d07e29","first_computed_at":"2026-06-19T16:11:21.878541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:21.878541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9lAlwa9W2u4w1TUu6TocJhHIPVIV350f4zftbZMDAH8n8BT7CKl1vF4vrp5MLSacMSbutHexpRXPuFuQNEPBQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:21.878934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.09344","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a42d0bae84c99e8d52f9d9999f39ba48677d7a984f448dc84df3b521c36e787","sha256:35ab1ff9c01b3b8ca1f2613c937dc5b036f80e79f61006fd5db482ce7d9bc444"],"state_sha256":"e6a18da6e9536dc56a4cf0c374f0ae30fadb1b46fda0196942fd0c449f3251b9"}