{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JJ2WN62H6UAQZWU2OFJO7XHEIY","short_pith_number":"pith:JJ2WN62H","canonical_record":{"source":{"id":"2212.02125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-05T09:36:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"004171870ec2199a37c1ae7993f60fe0c233478c726bc29e0109ea70467752a4","abstract_canon_sha256":"e74c25bf0ced3bdb10d06b7894342e7394c63676b703689bef42836b0bd17f62"},"schema_version":"1.0"},"canonical_sha256":"4a7566fb47f5010cda9a7152efdce446342d36d4ca08cc0db11a6edd69a8a275","source":{"kind":"arxiv","id":"2212.02125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.02125","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2212.02125v1","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02125","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"JJ2WN62H6UAQ","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"JJ2WN62H6UAQZWU2","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"JJ2WN62H","created_at":"2026-07-05T05:22:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JJ2WN62H6UAQZWU2OFJO7XHEIY","target":"record","payload":{"canonical_record":{"source":{"id":"2212.02125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-05T09:36:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"004171870ec2199a37c1ae7993f60fe0c233478c726bc29e0109ea70467752a4","abstract_canon_sha256":"e74c25bf0ced3bdb10d06b7894342e7394c63676b703689bef42836b0bd17f62"},"schema_version":"1.0"},"canonical_sha256":"4a7566fb47f5010cda9a7152efdce446342d36d4ca08cc0db11a6edd69a8a275","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:20.732942Z","signature_b64":"NapLeQTMyB7LECzrSS/CBC/HVEinN9asBZCxWvC6DpB6rVVywZz865knVzyw8PPsVJeB563UbkJ7tbLP8qnGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7566fb47f5010cda9a7152efdce446342d36d4ca08cc0db11a6edd69a8a275","last_reissued_at":"2026-07-05T05:22:20.732456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:20.732456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.02125","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":"2026-07-05T05:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C5cHzSlRn26zYQLJfPfEfH5hnUqrq7pXTh1SR79C1fcbTO3jia9tW9Co/G9GagcHqavejuRcoAZyr2QBLeDWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:13:31.389370Z"},"content_sha256":"b6d73e5293e1de686453da7c0fc4ff0844bdd2c9babcaf9f6569ec5a354a5e45","schema_version":"1.0","event_id":"sha256:b6d73e5293e1de686453da7c0fc4ff0844bdd2c9babcaf9f6569ec5a354a5e45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JJ2WN62H6UAQZWU2OFJO7XHEIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chuheng Zhang, Jiang Bian, Lei Song, Li Zhao, Tao Qin, Tieyan Liu, Wei Shen, Xuyun Zhang, Yuanying Cai","submitted_at":"2022-12-05T09:36:23Z","abstract_excerpt":"We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02125","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/2212.02125/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":"2026-07-05T05:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A5wUgTw6gddhZ8AcNh7LEedPLmcaSXg4ydM+VDO2HwrovDg2+DNYfK2rLDnd8PjOqkzBCcQlhnD9O5SnLBCjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:13:31.389757Z"},"content_sha256":"7c49444ae6c7cbcf09e8427444539e70e6a1d265d850ef53dbaf53dd2f6fc4a8","schema_version":"1.0","event_id":"sha256:7c49444ae6c7cbcf09e8427444539e70e6a1d265d850ef53dbaf53dd2f6fc4a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/bundle.json","state_url":"https://pith.science/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/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":"2026-08-04T05:13:31Z","links":{"resolver":"https://pith.science/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY","bundle":"https://pith.science/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/bundle.json","state":"https://pith.science/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJ2WN62H6UAQZWU2OFJO7XHEIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JJ2WN62H6UAQZWU2OFJO7XHEIY","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":"e74c25bf0ced3bdb10d06b7894342e7394c63676b703689bef42836b0bd17f62","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-05T09:36:23Z","title_canon_sha256":"004171870ec2199a37c1ae7993f60fe0c233478c726bc29e0109ea70467752a4"},"schema_version":"1.0","source":{"id":"2212.02125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.02125","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2212.02125v1","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02125","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"JJ2WN62H6UAQ","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"JJ2WN62H6UAQZWU2","created_at":"2026-07-05T05:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"JJ2WN62H","created_at":"2026-07-05T05:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:7c49444ae6c7cbcf09e8427444539e70e6a1d265d850ef53dbaf53dd2f6fc4a8","target":"graph","created_at":"2026-07-05T05:22:20Z","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/2212.02125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. Th","authors_text":"Chuheng Zhang, Jiang Bian, Lei Song, Li Zhao, Tao Qin, Tieyan Liu, Wei Shen, Xuyun Zhang, Yuanying Cai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-05T09:36:23Z","title":"TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02125","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:b6d73e5293e1de686453da7c0fc4ff0844bdd2c9babcaf9f6569ec5a354a5e45","target":"record","created_at":"2026-07-05T05:22:20Z","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":"e74c25bf0ced3bdb10d06b7894342e7394c63676b703689bef42836b0bd17f62","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-05T09:36:23Z","title_canon_sha256":"004171870ec2199a37c1ae7993f60fe0c233478c726bc29e0109ea70467752a4"},"schema_version":"1.0","source":{"id":"2212.02125","kind":"arxiv","version":1}},"canonical_sha256":"4a7566fb47f5010cda9a7152efdce446342d36d4ca08cc0db11a6edd69a8a275","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a7566fb47f5010cda9a7152efdce446342d36d4ca08cc0db11a6edd69a8a275","first_computed_at":"2026-07-05T05:22:20.732456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:20.732456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NapLeQTMyB7LECzrSS/CBC/HVEinN9asBZCxWvC6DpB6rVVywZz865knVzyw8PPsVJeB563UbkJ7tbLP8qnGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:20.732942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.02125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6d73e5293e1de686453da7c0fc4ff0844bdd2c9babcaf9f6569ec5a354a5e45","sha256:7c49444ae6c7cbcf09e8427444539e70e6a1d265d850ef53dbaf53dd2f6fc4a8"],"state_sha256":"4a7f1f1fb15b079d95d492353955b5ecc49d9a75262d36d0e9f896a5b1ec4274"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i0SWefWIT63SHrWFCqHpP6aEhW08XI9N1uS1Ct93ppufNfPwFgR5zsTyWWzig9XEqyolJC3vzcI57zSOMRtMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:13:31.392567Z","bundle_sha256":"4e0deafae349c8941dcde2a44c1b8f8a9c39c50500ae7c69938408e78eb4d540"}}