{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JUCJDEEEH7BXV4L5ZFNOHRZNCA","short_pith_number":"pith:JUCJDEEE","schema_version":"1.0","canonical_sha256":"4d049190843fc37af17dc95ae3c72d1027a397edd2eb45c13a2002ebb913b61a","source":{"kind":"arxiv","id":"2606.00680","version":1},"attestation_state":"computed","paper":{"title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hongqiang Lin, Nenggan Zheng, Pengfei Wang","submitted_at":"2026-05-30T11:35:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T11:35:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"651e47fb971e45c7e974aa9a9271ffac022437cf4583335a1d762d77efa56e39","abstract_canon_sha256":"998cb6acf23b9abaa03b465bb20d41314a9071dffad067e6d098a8320f89988a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:02.518790Z","signature_b64":"V8GdaTZpz4tQzNOmkbvv0+e0bnDZ7aDO8yvynnbMnDcFcPCvFS4QhvZUQy0n0KxgBTu60s4UR+cS0TVWOm/mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d049190843fc37af17dc95ae3c72d1027a397edd2eb45c13a2002ebb913b61a","last_reissued_at":"2026-06-02T01:04:02.518340Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:02.518340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hongqiang Lin, Nenggan Zheng, Pengfei Wang","submitted_at":"2026-05-30T11:35:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00680","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.00680/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00680","created_at":"2026-06-02T01:04:02.518397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00680v1","created_at":"2026-06-02T01:04:02.518397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00680","created_at":"2026-06-02T01:04:02.518397+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUCJDEEEH7BX","created_at":"2026-06-02T01:04:02.518397+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUCJDEEEH7BXV4L5","created_at":"2026-06-02T01:04:02.518397+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUCJDEEE","created_at":"2026-06-02T01:04:02.518397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA","json":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA.json","graph_json":"https://pith.science/api/pith-number/JUCJDEEEH7BXV4L5ZFNOHRZNCA/graph.json","events_json":"https://pith.science/api/pith-number/JUCJDEEEH7BXV4L5ZFNOHRZNCA/events.json","paper":"https://pith.science/paper/JUCJDEEE"},"agent_actions":{"view_html":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA","download_json":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA.json","view_paper":"https://pith.science/paper/JUCJDEEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00680&json=true","fetch_graph":"https://pith.science/api/pith-number/JUCJDEEEH7BXV4L5ZFNOHRZNCA/graph.json","fetch_events":"https://pith.science/api/pith-number/JUCJDEEEH7BXV4L5ZFNOHRZNCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA/action/storage_attestation","attest_author":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA/action/author_attestation","sign_citation":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA/action/citation_signature","submit_replication":"https://pith.science/pith/JUCJDEEEH7BXV4L5ZFNOHRZNCA/action/replication_record"}},"created_at":"2026-06-02T01:04:02.518397+00:00","updated_at":"2026-06-02T01:04:02.518397+00:00"}