{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3GHXR3ZMC6HKUQ36JLQAB62PSH","short_pith_number":"pith:3GHXR3ZM","canonical_record":{"source":{"id":"2210.13846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T09:08:26Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"92697773e036b50f6d467a249b842f2fbd73fdd50d6278adb585dd267f592e7d","abstract_canon_sha256":"e3d80664e1dd075fca3b63c699978eb90250df2ece16b1f9bf77aa52001c300d"},"schema_version":"1.0"},"canonical_sha256":"d98f78ef2c178eaa437e4ae000fb4f91fc8e48cc26324b9194185bdf4125533b","source":{"kind":"arxiv","id":"2210.13846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13846","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13846v1","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13846","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"3GHXR3ZMC6HK","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"3GHXR3ZMC6HKUQ36","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"3GHXR3ZM","created_at":"2026-07-05T05:10:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3GHXR3ZMC6HKUQ36JLQAB62PSH","target":"record","payload":{"canonical_record":{"source":{"id":"2210.13846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T09:08:26Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"92697773e036b50f6d467a249b842f2fbd73fdd50d6278adb585dd267f592e7d","abstract_canon_sha256":"e3d80664e1dd075fca3b63c699978eb90250df2ece16b1f9bf77aa52001c300d"},"schema_version":"1.0"},"canonical_sha256":"d98f78ef2c178eaa437e4ae000fb4f91fc8e48cc26324b9194185bdf4125533b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:23.247426Z","signature_b64":"NsWklDhSbE6lrsMX1IbxlKv/NlSTrfeyXul4VA3TutvYzK+3ghuX3TFLezwjIvuRwbe49iyPVrd0aV4FB9lXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98f78ef2c178eaa437e4ae000fb4f91fc8e48cc26324b9194185bdf4125533b","last_reissued_at":"2026-07-05T05:10:23.247029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:23.247029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.13846","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":"2026-07-05T05:10:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+kepM/uHCPcr960Q2R4hvpWTVLxaYj17sk/Wn54IuzupcJa4cqmWJdnrxtaDge3alwzEic/WViTSgq+mWrZbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:28:59.274026Z"},"content_sha256":"36758220bf241d6d8a19c60cdf55abfb6d50f4a59812a43270fee380d6d28f01","schema_version":"1.0","event_id":"sha256:36758220bf241d6d8a19c60cdf55abfb6d50f4a59812a43270fee380d6d28f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3GHXR3ZMC6HKUQ36JLQAB62PSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Ilin, Joni Pajarinen, Juho Kannala, Rinu Boney, Yi Zhao","submitted_at":"2022-10-25T09:08:26Z","abstract_excerpt":"Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may have limited performance and would further need to be fine-tuned online by interacting with the environment. During online fine-tuning, the performance of the pre-trained agent may collapse quickly due to the sudden distribution shift from offline to online data. While constraints enforced by offline RL methods such as a behaviour cloning loss prevent this to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13846","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/2210.13846/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":"2026-07-05T05:10:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ILgRewp9y/RmvaZN9936O3IQjcPozikqXffrBgEc5Oes0LRiDfXsX5+rOnnUQTDWEL8TNcCkHOcn8FN4paZlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:28:59.274409Z"},"content_sha256":"b1ab627a5b7c0cd54a1dcb965377df9d9031d03057f7c608e7aa764daaac028a","schema_version":"1.0","event_id":"sha256:b1ab627a5b7c0cd54a1dcb965377df9d9031d03057f7c608e7aa764daaac028a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/bundle.json","state_url":"https://pith.science/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/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":"2026-08-19T05:28:59Z","links":{"resolver":"https://pith.science/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH","bundle":"https://pith.science/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/bundle.json","state":"https://pith.science/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GHXR3ZMC6HKUQ36JLQAB62PSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3GHXR3ZMC6HKUQ36JLQAB62PSH","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":"e3d80664e1dd075fca3b63c699978eb90250df2ece16b1f9bf77aa52001c300d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T09:08:26Z","title_canon_sha256":"92697773e036b50f6d467a249b842f2fbd73fdd50d6278adb585dd267f592e7d"},"schema_version":"1.0","source":{"id":"2210.13846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13846","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13846v1","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13846","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"3GHXR3ZMC6HK","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"3GHXR3ZMC6HKUQ36","created_at":"2026-07-05T05:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"3GHXR3ZM","created_at":"2026-07-05T05:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:b1ab627a5b7c0cd54a1dcb965377df9d9031d03057f7c608e7aa764daaac028a","target":"graph","created_at":"2026-07-05T05:10:23Z","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/2210.13846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may have limited performance and would further need to be fine-tuned online by interacting with the environment. During online fine-tuning, the performance of the pre-trained agent may collapse quickly due to the sudden distribution shift from offline to online data. While constraints enforced by offline RL methods such as a behaviour cloning loss prevent this to a","authors_text":"Alexander Ilin, Joni Pajarinen, Juho Kannala, Rinu Boney, Yi Zhao","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T09:08:26Z","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13846","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":"sha256:36758220bf241d6d8a19c60cdf55abfb6d50f4a59812a43270fee380d6d28f01","target":"record","created_at":"2026-07-05T05:10:23Z","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":"e3d80664e1dd075fca3b63c699978eb90250df2ece16b1f9bf77aa52001c300d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T09:08:26Z","title_canon_sha256":"92697773e036b50f6d467a249b842f2fbd73fdd50d6278adb585dd267f592e7d"},"schema_version":"1.0","source":{"id":"2210.13846","kind":"arxiv","version":1}},"canonical_sha256":"d98f78ef2c178eaa437e4ae000fb4f91fc8e48cc26324b9194185bdf4125533b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98f78ef2c178eaa437e4ae000fb4f91fc8e48cc26324b9194185bdf4125533b","first_computed_at":"2026-07-05T05:10:23.247029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:23.247029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NsWklDhSbE6lrsMX1IbxlKv/NlSTrfeyXul4VA3TutvYzK+3ghuX3TFLezwjIvuRwbe49iyPVrd0aV4FB9lXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:23.247426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36758220bf241d6d8a19c60cdf55abfb6d50f4a59812a43270fee380d6d28f01","sha256:b1ab627a5b7c0cd54a1dcb965377df9d9031d03057f7c608e7aa764daaac028a"],"state_sha256":"cbb98ad864ec3afb344d4d46948a968206c766dbaea845b627eae25f9902884e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9r27ZUttQCWgDCPyrLh1LU8n+fWfvhPu+e2FYSFN0h3Plm5zAd5G52nBve3nhgrvtF+47vHBGFpxb1aarG2qDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:28:59.276699Z","bundle_sha256":"65433ed480c3866a53cb8b41b6e164fdf7f844f1bc62fa3a3f770ca7d0949681"}}