{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JVKQ2IWNALCEG4VWS5SZEIHMQC","short_pith_number":"pith:JVKQ2IWN","canonical_record":{"source":{"id":"2201.10070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"8978310f64c8fae98db85671e2c0ac4de94326f20858dd72ce186875079149b6","abstract_canon_sha256":"58d47f677e44842c61c9778683b263e578c58325127922efb840a3b76e682233"},"schema_version":"1.0"},"canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","source":{"kind":"arxiv","id":"2201.10070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10070","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10070v1","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10070","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"JVKQ2IWNALCE","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"JVKQ2IWNALCEG4VW","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"JVKQ2IWN","created_at":"2026-07-05T03:51:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JVKQ2IWNALCEG4VWS5SZEIHMQC","target":"record","payload":{"canonical_record":{"source":{"id":"2201.10070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"8978310f64c8fae98db85671e2c0ac4de94326f20858dd72ce186875079149b6","abstract_canon_sha256":"58d47f677e44842c61c9778683b263e578c58325127922efb840a3b76e682233"},"schema_version":"1.0"},"canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:15.180099Z","signature_b64":"pUrWIGqF7kFFaNOvxzx4EVnNzXYp+zXgCfvh92E73HEmfgzIkIGBN0bhP9tXoiVTJAgC1Wl35gjerocRVJdtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","last_reissued_at":"2026-07-05T03:51:15.179684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:15.179684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.10070","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":"2026-07-05T03:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qX2HXza2/Qd2/X7hWzRYqfHG6sanlzUW+4zMApO4gngOrzFcdHG2TQnAveT4N9WQBAHxD1keNdc17UnDrDdXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:19:52.988757Z"},"content_sha256":"f6b79ae059a3d7ba1929f10261802fedce859dd57ba2d3b491ee62289e5484cb","schema_version":"1.0","event_id":"sha256:f6b79ae059a3d7ba1929f10261802fedce859dd57ba2d3b491ee62289e5484cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JVKQ2IWNALCEG4VWS5SZEIHMQC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Wang, Chao Wang, Chongjie Zhang, Yihuan Mao","submitted_at":"2022-01-25T03:14:57Z","abstract_excerpt":"With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast adaptation of the policy plays a vital role in practical online performance improvement. To tackle these challenges, we propose a simple yet efficient algorithm, Model-based Offline-to-Online Reinforcement learning (MOORe), which employs a prioritized sampling scheme that can dynamically adjust the offline and online data for smooth and efficient online adaptation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10070","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/2201.10070/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":"2026-07-05T03:51:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZne/udQUMtVyyHb0R6tLp8+VVGyC2Rtl5PTMN0iE/Yg6oAw+8e4HMAEtmiSLbW9WlrZ0PVxEhDqNJf9SS3xBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:19:52.989184Z"},"content_sha256":"fed8d67d7b23b151567e077f9cbca9bb96b38a8cca296b5cba7d9c7e55ede207","schema_version":"1.0","event_id":"sha256:fed8d67d7b23b151567e077f9cbca9bb96b38a8cca296b5cba7d9c7e55ede207"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/bundle.json","state_url":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/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":"2026-07-13T00:19:52Z","links":{"resolver":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC","bundle":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/bundle.json","state":"https://pith.science/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVKQ2IWNALCEG4VWS5SZEIHMQC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JVKQ2IWNALCEG4VWS5SZEIHMQC","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":"58d47f677e44842c61c9778683b263e578c58325127922efb840a3b76e682233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","title_canon_sha256":"8978310f64c8fae98db85671e2c0ac4de94326f20858dd72ce186875079149b6"},"schema_version":"1.0","source":{"id":"2201.10070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10070","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10070v1","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10070","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"JVKQ2IWNALCE","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"JVKQ2IWNALCEG4VW","created_at":"2026-07-05T03:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"JVKQ2IWN","created_at":"2026-07-05T03:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:fed8d67d7b23b151567e077f9cbca9bb96b38a8cca296b5cba7d9c7e55ede207","target":"graph","created_at":"2026-07-05T03:51:15Z","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/2201.10070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. Besides, fast adaptation of the policy plays a vital role in practical online performance improvement. To tackle these challenges, we propose a simple yet efficient algorithm, Model-based Offline-to-Online Reinforcement learning (MOORe), which employs a prioritized sampling scheme that can dynamically adjust the offline and online data for smooth and efficient online adaptation","authors_text":"Bin Wang, Chao Wang, Chongjie Zhang, Yihuan Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","title":"MOORe: Model-based Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10070","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:f6b79ae059a3d7ba1929f10261802fedce859dd57ba2d3b491ee62289e5484cb","target":"record","created_at":"2026-07-05T03:51:15Z","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":"58d47f677e44842c61c9778683b263e578c58325127922efb840a3b76e682233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T03:14:57Z","title_canon_sha256":"8978310f64c8fae98db85671e2c0ac4de94326f20858dd72ce186875079149b6"},"schema_version":"1.0","source":{"id":"2201.10070","kind":"arxiv","version":1}},"canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d550d22cd02c44372b697659220ec8086a7895e26574dd034f37a016eba4881","first_computed_at":"2026-07-05T03:51:15.179684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:15.179684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pUrWIGqF7kFFaNOvxzx4EVnNzXYp+zXgCfvh92E73HEmfgzIkIGBN0bhP9tXoiVTJAgC1Wl35gjerocRVJdtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:15.180099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6b79ae059a3d7ba1929f10261802fedce859dd57ba2d3b491ee62289e5484cb","sha256:fed8d67d7b23b151567e077f9cbca9bb96b38a8cca296b5cba7d9c7e55ede207"],"state_sha256":"7962e46cf5cf5a3b6cf8b3f12ea797233e4adcb95bde57e2e71d60228833796b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"krFTlHMJWNAC1VGtqFIOxu1AOqlSfH09Km7YUL8p84RDZKvzPgVJT3p49AgqyskQ4SqKTCuIDdpZxcqnxnhPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:19:52.991906Z","bundle_sha256":"eb4b2d05905f599f33f4e42375c92642985175832532bc0cd01284773045a23b"}}