{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:53MWVM3DK2PYRI4VA7J6573SNB","short_pith_number":"pith:53MWVM3D","canonical_record":{"source":{"id":"2309.12716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-22T08:58:22Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8a81f44d0260743aef7cbf6186978942fc6d9150eac6247d33606afee7f457dc","abstract_canon_sha256":"94304bdc041b99c7ef151505727479b97b64d1ec5cf944964db645d0636ebabd"},"schema_version":"1.0"},"canonical_sha256":"eed96ab363569f88a39507d3eeff72687581ef623f8d0c231e3139693de15828","source":{"kind":"arxiv","id":"2309.12716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12716","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12716v2","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12716","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"53MWVM3DK2PY","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"53MWVM3DK2PYRI4V","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"53MWVM3D","created_at":"2026-07-05T10:49:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:53MWVM3DK2PYRI4VA7J6573SNB","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-22T08:58:22Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8a81f44d0260743aef7cbf6186978942fc6d9150eac6247d33606afee7f457dc","abstract_canon_sha256":"94304bdc041b99c7ef151505727479b97b64d1ec5cf944964db645d0636ebabd"},"schema_version":"1.0"},"canonical_sha256":"eed96ab363569f88a39507d3eeff72687581ef623f8d0c231e3139693de15828","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:42.681550Z","signature_b64":"FMIEu54OBRa5HXsye/bu36c5SyFv96LlPfkhSzTEb5OJh0PH6PXjtDsKb1F3XCbYWODWbNb42Z6Gj6DCqBJqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed96ab363569f88a39507d3eeff72687581ef623f8d0c231e3139693de15828","last_reissued_at":"2026-07-05T10:49:42.681098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:42.681098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12716","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":"2026-07-05T10:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0bDnRUujVplQn0APpL8/0Uz2JStgtiQBqz73wG5dP3+gBUgeyUGNp5+XBxNYYvJHntaAZ25+Dd6dCyWTPngjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:33:03.671910Z"},"content_sha256":"adbea4341491183d4e3ba6657b09f3b56e92f4da50fd8d9090b8f9de9f4dda54","schema_version":"1.0","event_id":"sha256:adbea4341491183d4e3ba6657b09f3b56e92f4da50fd8d9090b8f9de9f4dda54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:53MWVM3DK2PYRI4VA7J6573SNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bingqi Liu, Guyue Zhou, Haocheng Zhao, Haoyi Niu, Jianming Hu, Jianying Zheng, Pengfei Huang, Tianying Ji, Xiangyu Zhu, Xianyuan Zhan","submitted_at":"2023-09-22T08:58:22Z","abstract_excerpt":"Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can suffer from severe sim-to-real issues. Offline RL approaches although bypass the need for simulators, often pose demanding requirements on the size and quality of the offline datasets. The recently emerged hybrid offline-and-online RL provides an attractive framework that enables joint use of limited offline data and imperfect simulator for transferable policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12716","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/2309.12716/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":"2026-07-05T10:49:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXi3a7vXm/OmQtGGQlhnKenHRyNuWP5jtLIK7UGDGyQwAdHRm3IMCFLqiLejU1KK+qklZn59hWGQ4phSmyciCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:33:03.672335Z"},"content_sha256":"79672eb7383f1957b3f57f597fdd49cffc1e5ab344a5b879d1b8f99220d6cb19","schema_version":"1.0","event_id":"sha256:79672eb7383f1957b3f57f597fdd49cffc1e5ab344a5b879d1b8f99220d6cb19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53MWVM3DK2PYRI4VA7J6573SNB/bundle.json","state_url":"https://pith.science/pith/53MWVM3DK2PYRI4VA7J6573SNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53MWVM3DK2PYRI4VA7J6573SNB/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":"2026-07-06T07:33:03Z","links":{"resolver":"https://pith.science/pith/53MWVM3DK2PYRI4VA7J6573SNB","bundle":"https://pith.science/pith/53MWVM3DK2PYRI4VA7J6573SNB/bundle.json","state":"https://pith.science/pith/53MWVM3DK2PYRI4VA7J6573SNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53MWVM3DK2PYRI4VA7J6573SNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:53MWVM3DK2PYRI4VA7J6573SNB","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":"94304bdc041b99c7ef151505727479b97b64d1ec5cf944964db645d0636ebabd","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-22T08:58:22Z","title_canon_sha256":"8a81f44d0260743aef7cbf6186978942fc6d9150eac6247d33606afee7f457dc"},"schema_version":"1.0","source":{"id":"2309.12716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12716","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12716v2","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12716","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_12","alias_value":"53MWVM3DK2PY","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_16","alias_value":"53MWVM3DK2PYRI4V","created_at":"2026-07-05T10:49:42Z"},{"alias_kind":"pith_short_8","alias_value":"53MWVM3D","created_at":"2026-07-05T10:49:42Z"}],"graph_snapshots":[{"event_id":"sha256:79672eb7383f1957b3f57f597fdd49cffc1e5ab344a5b879d1b8f99220d6cb19","target":"graph","created_at":"2026-07-05T10:49:42Z","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/2309.12716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can suffer from severe sim-to-real issues. Offline RL approaches although bypass the need for simulators, often pose demanding requirements on the size and quality of the offline datasets. The recently emerged hybrid offline-and-online RL provides an attractive framework that enables joint use of limited offline data and imperfect simulator for transferable policy","authors_text":"Bingqi Liu, Guyue Zhou, Haocheng Zhao, Haoyi Niu, Jianming Hu, Jianying Zheng, Pengfei Huang, Tianying Ji, Xiangyu Zhu, Xianyuan Zhan","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-22T08:58:22Z","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12716","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:adbea4341491183d4e3ba6657b09f3b56e92f4da50fd8d9090b8f9de9f4dda54","target":"record","created_at":"2026-07-05T10:49:42Z","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":"94304bdc041b99c7ef151505727479b97b64d1ec5cf944964db645d0636ebabd","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-22T08:58:22Z","title_canon_sha256":"8a81f44d0260743aef7cbf6186978942fc6d9150eac6247d33606afee7f457dc"},"schema_version":"1.0","source":{"id":"2309.12716","kind":"arxiv","version":2}},"canonical_sha256":"eed96ab363569f88a39507d3eeff72687581ef623f8d0c231e3139693de15828","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed96ab363569f88a39507d3eeff72687581ef623f8d0c231e3139693de15828","first_computed_at":"2026-07-05T10:49:42.681098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:42.681098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FMIEu54OBRa5HXsye/bu36c5SyFv96LlPfkhSzTEb5OJh0PH6PXjtDsKb1F3XCbYWODWbNb42Z6Gj6DCqBJqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:42.681550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adbea4341491183d4e3ba6657b09f3b56e92f4da50fd8d9090b8f9de9f4dda54","sha256:79672eb7383f1957b3f57f597fdd49cffc1e5ab344a5b879d1b8f99220d6cb19"],"state_sha256":"054ceee3e8604dac249d25e87884bd94e805a7ee19155f65e75c66d53eee5f69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6ogx3qUQubpaZaUdPj0NDKFqoyE4Kwe7h3shuAMHUe2CzWoD66wkBYT1cHV2yMd53tz7LJP7jMCmqgPnNyFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T07:33:03.674681Z","bundle_sha256":"e83b1eda0a044c4375874043573eef4ad1554b16ad2a937a968ff183e588c4e4"}}