{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CYQQSTDBMMU2CKAA2OMDDWQQ4D","short_pith_number":"pith:CYQQSTDB","canonical_record":{"source":{"id":"2306.06871","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T05:10:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"6c732d0dca417b6137233019b3c0199d57e5a6c05e3aedc67b50c4a95e61bb7e","abstract_canon_sha256":"b168c08b544eacbc8b5a8d4d18e0d3c802f3e93a772fb769be722cb48db5eee0"},"schema_version":"1.0"},"canonical_sha256":"1621094c616329a12800d39831da10e0e98bbebe53b81dffd0c9e66e0b39eb6b","source":{"kind":"arxiv","id":"2306.06871","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06871","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06871v4","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06871","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"CYQQSTDBMMU2","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_16","alias_value":"CYQQSTDBMMU2CKAA","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_8","alias_value":"CYQQSTDB","created_at":"2026-07-05T08:46:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CYQQSTDBMMU2CKAA2OMDDWQQ4D","target":"record","payload":{"canonical_record":{"source":{"id":"2306.06871","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T05:10:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"6c732d0dca417b6137233019b3c0199d57e5a6c05e3aedc67b50c4a95e61bb7e","abstract_canon_sha256":"b168c08b544eacbc8b5a8d4d18e0d3c802f3e93a772fb769be722cb48db5eee0"},"schema_version":"1.0"},"canonical_sha256":"1621094c616329a12800d39831da10e0e98bbebe53b81dffd0c9e66e0b39eb6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:17.379756Z","signature_b64":"KcJ0LRll9iItgDGqv0+EPsqBXZ92gHaHn1S+voj7mZrcPlmINtJJWHShqi5rMVaO82Us6oAboeBNMN+bYOOJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1621094c616329a12800d39831da10e0e98bbebe53b81dffd0c9e66e0b39eb6b","last_reissued_at":"2026-07-05T08:46:17.379311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:17.379311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.06871","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KB/XULv4TGdHPRBK41mF8+DtiKhaW83xkpfNZZIKAwqitK/UMPr6GZmFHrJgnpbBkP+lg2NlZgz3x3inWeSKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:43.930933Z"},"content_sha256":"502d57e5b116158fa196128f3c1ade9ec4741f4e9e39ddf8b8b552b15818672a","schema_version":"1.0","event_id":"sha256:502d57e5b116158fa196128f3c1ade9ec4741f4e9e39ddf8b8b552b15818672a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CYQQSTDBMMU2CKAA2OMDDWQQ4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jianye Hao, Jinyi Liu, Kai Zhao, Yan Zheng, Yi Ma, Zhaopeng Meng","submitted_at":"2023-06-12T05:10:10Z","abstract_excerpt":"Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it, offline-to-online RL combines offline pre-training with online fine-tuning, which enables the agent to further refine its policy by interacting with the environment in real-time. Despite its benefits, existing offline-to-online RL methods suffer from performance degradation and slow improvement during the online phase. To tackle these challenges, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06871","kind":"arxiv","version":4},"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/2306.06871/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":"2026-07-05T08:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KQsn+Aib/1tFUWVGfJRGJBOzmGVUgicqU9MYmc/DlZXrTsuoyX1+dlsHkvjsHlzm477ZPQA6OhHJi9dHqGFdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:43.931425Z"},"content_sha256":"594edf1c2a63e81c0827e3a7303fa0dbcd120c0af87e0e56af0b6f79f4e4183d","schema_version":"1.0","event_id":"sha256:594edf1c2a63e81c0827e3a7303fa0dbcd120c0af87e0e56af0b6f79f4e4183d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/bundle.json","state_url":"https://pith.science/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/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":"2026-08-08T02:54:43Z","links":{"resolver":"https://pith.science/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D","bundle":"https://pith.science/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/bundle.json","state":"https://pith.science/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYQQSTDBMMU2CKAA2OMDDWQQ4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CYQQSTDBMMU2CKAA2OMDDWQQ4D","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":"b168c08b544eacbc8b5a8d4d18e0d3c802f3e93a772fb769be722cb48db5eee0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T05:10:10Z","title_canon_sha256":"6c732d0dca417b6137233019b3c0199d57e5a6c05e3aedc67b50c4a95e61bb7e"},"schema_version":"1.0","source":{"id":"2306.06871","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06871","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06871v4","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06871","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"CYQQSTDBMMU2","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_16","alias_value":"CYQQSTDBMMU2CKAA","created_at":"2026-07-05T08:46:17Z"},{"alias_kind":"pith_short_8","alias_value":"CYQQSTDB","created_at":"2026-07-05T08:46:17Z"}],"graph_snapshots":[{"event_id":"sha256:594edf1c2a63e81c0827e3a7303fa0dbcd120c0af87e0e56af0b6f79f4e4183d","target":"graph","created_at":"2026-07-05T08:46:17Z","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/2306.06871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it, offline-to-online RL combines offline pre-training with online fine-tuning, which enables the agent to further refine its policy by interacting with the environment in real-time. Despite its benefits, existing offline-to-online RL methods suffer from performance degradation and slow improvement during the online phase. To tackle these challenges, we propose a ","authors_text":"Jianye Hao, Jinyi Liu, Kai Zhao, Yan Zheng, Yi Ma, Zhaopeng Meng","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T05:10:10Z","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06871","kind":"arxiv","version":4},"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":"sha256:502d57e5b116158fa196128f3c1ade9ec4741f4e9e39ddf8b8b552b15818672a","target":"record","created_at":"2026-07-05T08:46:17Z","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":"b168c08b544eacbc8b5a8d4d18e0d3c802f3e93a772fb769be722cb48db5eee0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T05:10:10Z","title_canon_sha256":"6c732d0dca417b6137233019b3c0199d57e5a6c05e3aedc67b50c4a95e61bb7e"},"schema_version":"1.0","source":{"id":"2306.06871","kind":"arxiv","version":4}},"canonical_sha256":"1621094c616329a12800d39831da10e0e98bbebe53b81dffd0c9e66e0b39eb6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1621094c616329a12800d39831da10e0e98bbebe53b81dffd0c9e66e0b39eb6b","first_computed_at":"2026-07-05T08:46:17.379311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:17.379311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KcJ0LRll9iItgDGqv0+EPsqBXZ92gHaHn1S+voj7mZrcPlmINtJJWHShqi5rMVaO82Us6oAboeBNMN+bYOOJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:17.379756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06871","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:502d57e5b116158fa196128f3c1ade9ec4741f4e9e39ddf8b8b552b15818672a","sha256:594edf1c2a63e81c0827e3a7303fa0dbcd120c0af87e0e56af0b6f79f4e4183d"],"state_sha256":"1a991b2abc49a7fca1d2579d31a71b9088b683eca746abe258ad5fabdf878cae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6GtxymR0ZITp4tJ0mFowRzvYIJinXyq3PxIIh3iK5h9nlihXNG8ejrD3fU2lGbVCjhqiN0EaedzA7tdlKEeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:54:43.935148Z","bundle_sha256":"91c4ddeb90d950ba2ab5868d701be9feed06cf5ef9a5d7e37422443bed5acc99"}}