{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CT44TFHIBAXOVMPVMYS5UXZJD2","short_pith_number":"pith:CT44TFHI","canonical_record":{"source":{"id":"2506.06261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:40:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c319a914840fbac09d1bc1c81fdf51dc9569a387abaa562958ab70a266c851fe","abstract_canon_sha256":"30770a999539b3448e59aa3be0b4acf3e3857d2b8219cefde8e677d96b6a2414"},"schema_version":"1.0"},"canonical_sha256":"14f9c994e8082eeab1f56625da5f291e869fb214cf1595108614fb27f3943512","source":{"kind":"arxiv","id":"2506.06261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06261","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06261v1","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06261","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"CT44TFHIBAXO","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_16","alias_value":"CT44TFHIBAXOVMPV","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_8","alias_value":"CT44TFHI","created_at":"2026-07-05T11:17:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CT44TFHIBAXOVMPVMYS5UXZJD2","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:40:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c319a914840fbac09d1bc1c81fdf51dc9569a387abaa562958ab70a266c851fe","abstract_canon_sha256":"30770a999539b3448e59aa3be0b4acf3e3857d2b8219cefde8e677d96b6a2414"},"schema_version":"1.0"},"canonical_sha256":"14f9c994e8082eeab1f56625da5f291e869fb214cf1595108614fb27f3943512","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:28.304509Z","signature_b64":"bDvUSZ1gC7ZOYM2Grnua5jyBLSmaqtE9/Tvag++hVrS6BJ1JJp7UUUT5SM0zFnZ8/pKrR9MqIQ18dDd26nKoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f9c994e8082eeab1f56625da5f291e869fb214cf1595108614fb27f3943512","last_reissued_at":"2026-07-05T11:17:28.304051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:28.304051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06261","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZ2mM4Ix+fqCCVGPcmkF6+A8PQbLG8+a1f4Nb1SkIHdNNZz9oQS2ELoSKc5LXLy2BF05+uFUmg/yWjjeESsiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:21:00.216746Z"},"content_sha256":"3e09f56a942beef6cefff49d69509aee30ddbf7e3fb4de652fe3b746443477cc","schema_version":"1.0","event_id":"sha256:3e09f56a942beef6cefff49d69509aee30ddbf7e3fb4de652fe3b746443477cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CT44TFHIBAXOVMPVMYS5UXZJD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jihwan Jeong, Jingmin Wang, Pascal Poupart, Scott Sanner, Xiaoyu Wang","submitted_at":"2025-06-06T17:40:12Z","abstract_excerpt":"Offline reinforcement learning (RL) is crucial when online exploration is costly or unsafe but often struggles with high epistemic uncertainty due to limited data. Existing methods rely on fixed conservative policies, restricting adaptivity and generalization. To address this, we propose Reflect-then-Plan (RefPlan), a novel doubly Bayesian offline model-based (MB) planning approach. RefPlan unifies uncertainty modeling and MB planning by recasting planning as Bayesian posterior estimation. At deployment, it updates a belief over environment dynamics using real-time observations, incorporating "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06261","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/2506.06261/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kyRPyhXTtuLvgcFTsS6Ush0mT+2xjuD+ANLvsB1Y65y3app8tlbTVNIBnwRh1tPMMkiozrWxZqqTw/GRtq5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:21:00.217351Z"},"content_sha256":"be2de43a427c57d9227192908d82dd5880bb13ee470cdb5600dd8f4a087320c4","schema_version":"1.0","event_id":"sha256:be2de43a427c57d9227192908d82dd5880bb13ee470cdb5600dd8f4a087320c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/bundle.json","state_url":"https://pith.science/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T20:21:00Z","links":{"resolver":"https://pith.science/pith/CT44TFHIBAXOVMPVMYS5UXZJD2","bundle":"https://pith.science/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/bundle.json","state":"https://pith.science/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CT44TFHIBAXOVMPVMYS5UXZJD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CT44TFHIBAXOVMPVMYS5UXZJD2","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":"30770a999539b3448e59aa3be0b4acf3e3857d2b8219cefde8e677d96b6a2414","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:40:12Z","title_canon_sha256":"c319a914840fbac09d1bc1c81fdf51dc9569a387abaa562958ab70a266c851fe"},"schema_version":"1.0","source":{"id":"2506.06261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06261","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06261v1","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06261","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"CT44TFHIBAXO","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_16","alias_value":"CT44TFHIBAXOVMPV","created_at":"2026-07-05T11:17:28Z"},{"alias_kind":"pith_short_8","alias_value":"CT44TFHI","created_at":"2026-07-05T11:17:28Z"}],"graph_snapshots":[{"event_id":"sha256:be2de43a427c57d9227192908d82dd5880bb13ee470cdb5600dd8f4a087320c4","target":"graph","created_at":"2026-07-05T11:17:28Z","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/2506.06261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is crucial when online exploration is costly or unsafe but often struggles with high epistemic uncertainty due to limited data. Existing methods rely on fixed conservative policies, restricting adaptivity and generalization. To address this, we propose Reflect-then-Plan (RefPlan), a novel doubly Bayesian offline model-based (MB) planning approach. RefPlan unifies uncertainty modeling and MB planning by recasting planning as Bayesian posterior estimation. At deployment, it updates a belief over environment dynamics using real-time observations, incorporating ","authors_text":"Jihwan Jeong, Jingmin Wang, Pascal Poupart, Scott Sanner, Xiaoyu Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:40:12Z","title":"Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06261","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":"sha256:3e09f56a942beef6cefff49d69509aee30ddbf7e3fb4de652fe3b746443477cc","target":"record","created_at":"2026-07-05T11:17:28Z","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":"30770a999539b3448e59aa3be0b4acf3e3857d2b8219cefde8e677d96b6a2414","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-06T17:40:12Z","title_canon_sha256":"c319a914840fbac09d1bc1c81fdf51dc9569a387abaa562958ab70a266c851fe"},"schema_version":"1.0","source":{"id":"2506.06261","kind":"arxiv","version":1}},"canonical_sha256":"14f9c994e8082eeab1f56625da5f291e869fb214cf1595108614fb27f3943512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14f9c994e8082eeab1f56625da5f291e869fb214cf1595108614fb27f3943512","first_computed_at":"2026-07-05T11:17:28.304051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:28.304051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bDvUSZ1gC7ZOYM2Grnua5jyBLSmaqtE9/Tvag++hVrS6BJ1JJp7UUUT5SM0zFnZ8/pKrR9MqIQ18dDd26nKoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:28.304509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e09f56a942beef6cefff49d69509aee30ddbf7e3fb4de652fe3b746443477cc","sha256:be2de43a427c57d9227192908d82dd5880bb13ee470cdb5600dd8f4a087320c4"],"state_sha256":"192c8c6a39436b0a0a265012bfd4eff1da6c69d804fb38e73a678a4d2d809d9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQCVqHM7qRGjETvvnx0PN9azTpdvYSMrxw4OxDPnljZXX5KdlLWQl1QVC0CEAWFo43a3LuGhvZ2capJSjheXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:21:00.221280Z","bundle_sha256":"d18e94542eb39ce0bf2ab6846b6e18ded26bff291dc3251c1a20ecaa4be6e46d"}}