{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JUCJDEEEH7BXV4L5ZFNOHRZNCA","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":"998cb6acf23b9abaa03b465bb20d41314a9071dffad067e6d098a8320f89988a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T11:35:26Z","title_canon_sha256":"651e47fb971e45c7e974aa9a9271ffac022437cf4583335a1d762d77efa56e39"},"schema_version":"1.0","source":{"id":"2606.00680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00680","created_at":"2026-06-02T01:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00680v1","created_at":"2026-06-02T01:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00680","created_at":"2026-06-02T01:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"JUCJDEEEH7BX","created_at":"2026-06-02T01:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"JUCJDEEEH7BXV4L5","created_at":"2026-06-02T01:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"JUCJDEEE","created_at":"2026-06-02T01:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:14a5f667680ddcee53997551bb6b04813c90984901a8c0306649a7e60d0392a1","target":"graph","created_at":"2026-06-02T01:04:02Z","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/2606.00680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limited data coverage (sample-level) and the ambiguity in identifying transition dynamics from finite data (model-level). To provide a unified quantification of these uncertainties, Bayesian RL has been proposed by treating the dynamics model as a random variable and maintaining a corresponding belief. Despite its theoretical appeal, policy optimization in Bayesian RL remains computationally challenging as it requires solv","authors_text":"Hongqiang Lin, Nenggan Zheng, Pengfei Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T11:35:26Z","title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00680","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:c03522f544a45d097a831ba2529397b3d5195cb13d126f0f2f10868ce92be9a5","target":"record","created_at":"2026-06-02T01:04:02Z","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":"998cb6acf23b9abaa03b465bb20d41314a9071dffad067e6d098a8320f89988a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T11:35:26Z","title_canon_sha256":"651e47fb971e45c7e974aa9a9271ffac022437cf4583335a1d762d77efa56e39"},"schema_version":"1.0","source":{"id":"2606.00680","kind":"arxiv","version":1}},"canonical_sha256":"4d049190843fc37af17dc95ae3c72d1027a397edd2eb45c13a2002ebb913b61a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d049190843fc37af17dc95ae3c72d1027a397edd2eb45c13a2002ebb913b61a","first_computed_at":"2026-06-02T01:04:02.518340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:02.518340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8GdaTZpz4tQzNOmkbvv0+e0bnDZ7aDO8yvynnbMnDcFcPCvFS4QhvZUQy0n0KxgBTu60s4UR+cS0TVWOm/mAA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:02.518790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c03522f544a45d097a831ba2529397b3d5195cb13d126f0f2f10868ce92be9a5","sha256:14a5f667680ddcee53997551bb6b04813c90984901a8c0306649a7e60d0392a1"],"state_sha256":"4c36bf0ff28556130a0ff192474a51e82f2a8dfc4256c70ed375973c3b9b2b28"}