{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FPOKZILQRB7YXVDKVB652LRH7C","short_pith_number":"pith:FPOKZILQ","canonical_record":{"source":{"id":"2309.16973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T04:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"a2a4b1ccd82456dfc32364dec89b2f3792ca5d149200dd6200d7ed7c75414908","abstract_canon_sha256":"c14c4f9b8b31e775987abead278e1136fec309920965db68688edbe4e498281b"},"schema_version":"1.0"},"canonical_sha256":"2bdcaca170887f8bd46aa87ddd2e27f89ce287fa9ed2b486942b7c44de55baf1","source":{"kind":"arxiv","id":"2309.16973","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16973","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16973v2","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16973","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"FPOKZILQRB7Y","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_16","alias_value":"FPOKZILQRB7YXVDK","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_8","alias_value":"FPOKZILQ","created_at":"2026-07-05T09:35:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FPOKZILQRB7YXVDKVB652LRH7C","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T04:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"a2a4b1ccd82456dfc32364dec89b2f3792ca5d149200dd6200d7ed7c75414908","abstract_canon_sha256":"c14c4f9b8b31e775987abead278e1136fec309920965db68688edbe4e498281b"},"schema_version":"1.0"},"canonical_sha256":"2bdcaca170887f8bd46aa87ddd2e27f89ce287fa9ed2b486942b7c44de55baf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:46.310627Z","signature_b64":"48J8FpBADUVZS2dPjM+GwE2IdM3lLBbH7nWb74Kg0QSfk2yn+6bY0U7AWxr4Di5/aGzQocC1CyQFzStaHxA4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdcaca170887f8bd46aa87ddd2e27f89ce287fa9ed2b486942b7c44de55baf1","last_reissued_at":"2026-07-05T09:35:46.310128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:46.310128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16973","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63kn7skqa8WEmtGc503nHWLJBkdNfNuPNNAW/fxJYaXliZrcyeM/E7Olmhpzq1yfaUo4b5HMlFWhzbeG1MxTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:54:23.781956Z"},"content_sha256":"86cf8473f5a12edbb5262c761efcef423478cba2f7da6089efc7b26616365441","schema_version":"1.0","event_id":"sha256:86cf8473f5a12edbb5262c761efcef423478cba2f7da6089efc7b26616365441"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FPOKZILQRB7YXVDKVB652LRH7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Haoyuan Chen, Rui Yang, Xiaoyu Wen, Xudong Yu, Zhen Wang","submitted_at":"2023-09-29T04:42:50Z","abstract_excerpt":"To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which explores informative transitions by interacting with the environment. Offline-to-Online (O2O) RL provides a paradigm for improving an offline trained agent within limited online interactions. However, due to the significant distribution shift between online experiences and offline data, most offline RL algorithms suffer from performance drops and fail to achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16973","kind":"arxiv","version":2},"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/2309.16973/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":"2026-07-05T09:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1M/VoWoJRmqMN5vTmY8yTQSlusCHTxf1NBdXMISUdZq4wxibvda23eRHZI3deZtYzKA1BT3O7+G2jrPVHqQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:54:23.782495Z"},"content_sha256":"3fa521e1a89e1b0496ad6d64285d801e5655802e587b21adbc52c71273e46201","schema_version":"1.0","event_id":"sha256:3fa521e1a89e1b0496ad6d64285d801e5655802e587b21adbc52c71273e46201"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPOKZILQRB7YXVDKVB652LRH7C/bundle.json","state_url":"https://pith.science/pith/FPOKZILQRB7YXVDKVB652LRH7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPOKZILQRB7YXVDKVB652LRH7C/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":"2026-08-12T18:54:23Z","links":{"resolver":"https://pith.science/pith/FPOKZILQRB7YXVDKVB652LRH7C","bundle":"https://pith.science/pith/FPOKZILQRB7YXVDKVB652LRH7C/bundle.json","state":"https://pith.science/pith/FPOKZILQRB7YXVDKVB652LRH7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPOKZILQRB7YXVDKVB652LRH7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FPOKZILQRB7YXVDKVB652LRH7C","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":"c14c4f9b8b31e775987abead278e1136fec309920965db68688edbe4e498281b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T04:42:50Z","title_canon_sha256":"a2a4b1ccd82456dfc32364dec89b2f3792ca5d149200dd6200d7ed7c75414908"},"schema_version":"1.0","source":{"id":"2309.16973","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16973","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16973v2","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16973","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"FPOKZILQRB7Y","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_16","alias_value":"FPOKZILQRB7YXVDK","created_at":"2026-07-05T09:35:46Z"},{"alias_kind":"pith_short_8","alias_value":"FPOKZILQ","created_at":"2026-07-05T09:35:46Z"}],"graph_snapshots":[{"event_id":"sha256:3fa521e1a89e1b0496ad6d64285d801e5655802e587b21adbc52c71273e46201","target":"graph","created_at":"2026-07-05T09:35:46Z","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/2309.16973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which explores informative transitions by interacting with the environment. Offline-to-Online (O2O) RL provides a paradigm for improving an offline trained agent within limited online interactions. However, due to the significant distribution shift between online experiences and offline data, most offline RL algorithms suffer from performance drops and fail to achieve ","authors_text":"Chenjia Bai, Haoyuan Chen, Rui Yang, Xiaoyu Wen, Xudong Yu, Zhen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T04:42:50Z","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16973","kind":"arxiv","version":2},"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":"sha256:86cf8473f5a12edbb5262c761efcef423478cba2f7da6089efc7b26616365441","target":"record","created_at":"2026-07-05T09:35:46Z","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":"c14c4f9b8b31e775987abead278e1136fec309920965db68688edbe4e498281b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-29T04:42:50Z","title_canon_sha256":"a2a4b1ccd82456dfc32364dec89b2f3792ca5d149200dd6200d7ed7c75414908"},"schema_version":"1.0","source":{"id":"2309.16973","kind":"arxiv","version":2}},"canonical_sha256":"2bdcaca170887f8bd46aa87ddd2e27f89ce287fa9ed2b486942b7c44de55baf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bdcaca170887f8bd46aa87ddd2e27f89ce287fa9ed2b486942b7c44de55baf1","first_computed_at":"2026-07-05T09:35:46.310128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:46.310128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48J8FpBADUVZS2dPjM+GwE2IdM3lLBbH7nWb74Kg0QSfk2yn+6bY0U7AWxr4Di5/aGzQocC1CyQFzStaHxA4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:46.310627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16973","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86cf8473f5a12edbb5262c761efcef423478cba2f7da6089efc7b26616365441","sha256:3fa521e1a89e1b0496ad6d64285d801e5655802e587b21adbc52c71273e46201"],"state_sha256":"adfce01b87aa2ac3a22ba97f7823eb404eaced85f629479aead704145a1086bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnXhgpbZq63VMhiwNXS6TIRa0TAbP2d8KpAQmv/p7s3SPi3oCuGo0NHN97aJjG6arEJMsqKoHvlpwX97C3B+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:54:23.786716Z","bundle_sha256":"9df171f65d0d3974e1554ba874552b2e922ddd5854653707fbdd1220c0ee9dce"}}