{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:66JHKFWKZ6TCWXUSLJPWJDVGNN","short_pith_number":"pith:66JHKFWK","canonical_record":{"source":{"id":"2203.06662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T14:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"41f26fdd53dc2c1071a7ab1fa2590188d0d1ae6019c91ee7e84844bc029b3978","abstract_canon_sha256":"8f22b227225e05f279b0f80b2960241633b5d4eee9ab450e8671fa3c2e613a5c"},"schema_version":"1.0"},"canonical_sha256":"f7927516cacfa62b5e925a5f648ea66b5c28451891a5d09ff99c13971b5c07d1","source":{"kind":"arxiv","id":"2203.06662","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06662","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06662v1","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06662","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"66JHKFWKZ6TC","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"66JHKFWKZ6TCWXUS","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"66JHKFWK","created_at":"2026-07-05T04:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:66JHKFWKZ6TCWXUSLJPWJDVGNN","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T14:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"41f26fdd53dc2c1071a7ab1fa2590188d0d1ae6019c91ee7e84844bc029b3978","abstract_canon_sha256":"8f22b227225e05f279b0f80b2960241633b5d4eee9ab450e8671fa3c2e613a5c"},"schema_version":"1.0"},"canonical_sha256":"f7927516cacfa62b5e925a5f648ea66b5c28451891a5d09ff99c13971b5c07d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:53.407262Z","signature_b64":"y30BXpNjTRz2IUg39oREhLIppGrPRv6BygH6tFxET89Hp3FX8mDWS+WkcoCi5PFdpVbufBXSGAjIO4fdFftGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7927516cacfa62b5e925a5f648ea66b5c28451891a5d09ff99c13971b5c07d1","last_reissued_at":"2026-07-05T04:04:53.406861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:53.406861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06662","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":"2026-07-05T04:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZQIOTZqR2xCXtj0UTZcgLKYUJP7MugnryKO6BstTolBzjn6IJVnhsJ8Swi+3/RT2+daM0m4QZxPWsdaAT9RCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:18:08.813814Z"},"content_sha256":"aec39d1c001a97bf78089982710b34e6e276e11246ec27c1725e42992df76ed2","schema_version":"1.0","event_id":"sha256:aec39d1c001a97bf78089982710b34e6e276e11246ec27c1725e42992df76ed2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:66JHKFWKZ6TCWXUSLJPWJDVGNN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Hongyin Zhang, Jinxin Liu","submitted_at":"2022-03-13T14:30:55Z","abstract_excerpt":"Offline reinforcement learning algorithms promise to be applicable in settings where a fixed dataset is available and no new experience can be acquired. However, such formulation is inevitably offline-data-hungry and, in practice, collecting a large offline dataset for one specific task over one specific environment is also costly and laborious. In this paper, we thus 1) formulate the offline dynamics adaptation by using (source) offline data collected from another dynamics to relax the requirement for the extensive (target) offline data, 2) characterize the dynamics shift problem in which pri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06662","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/2203.06662/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":"2026-07-05T04:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6U0cF4pOXKFxKtyJiGBQvxb5cB9CIKYuxxy2jK0Pe/b4lKARlae4fp1hHGPTMFKBS8ryeIzitZ6IIn2TpbQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:18:08.814327Z"},"content_sha256":"bb333eb06985edc4b7176b4bc04f1cc782fc005ee2799faff2c3e3d60fc2ee19","schema_version":"1.0","event_id":"sha256:bb333eb06985edc4b7176b4bc04f1cc782fc005ee2799faff2c3e3d60fc2ee19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/bundle.json","state_url":"https://pith.science/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/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":"2026-08-10T11:18:08Z","links":{"resolver":"https://pith.science/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN","bundle":"https://pith.science/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/bundle.json","state":"https://pith.science/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66JHKFWKZ6TCWXUSLJPWJDVGNN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:66JHKFWKZ6TCWXUSLJPWJDVGNN","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":"8f22b227225e05f279b0f80b2960241633b5d4eee9ab450e8671fa3c2e613a5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T14:30:55Z","title_canon_sha256":"41f26fdd53dc2c1071a7ab1fa2590188d0d1ae6019c91ee7e84844bc029b3978"},"schema_version":"1.0","source":{"id":"2203.06662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06662","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06662v1","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06662","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"66JHKFWKZ6TC","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"66JHKFWKZ6TCWXUS","created_at":"2026-07-05T04:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"66JHKFWK","created_at":"2026-07-05T04:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:bb333eb06985edc4b7176b4bc04f1cc782fc005ee2799faff2c3e3d60fc2ee19","target":"graph","created_at":"2026-07-05T04:04:53Z","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/2203.06662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning algorithms promise to be applicable in settings where a fixed dataset is available and no new experience can be acquired. However, such formulation is inevitably offline-data-hungry and, in practice, collecting a large offline dataset for one specific task over one specific environment is also costly and laborious. In this paper, we thus 1) formulate the offline dynamics adaptation by using (source) offline data collected from another dynamics to relax the requirement for the extensive (target) offline data, 2) characterize the dynamics shift problem in which pri","authors_text":"Donglin Wang, Hongyin Zhang, Jinxin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T14:30:55Z","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06662","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:aec39d1c001a97bf78089982710b34e6e276e11246ec27c1725e42992df76ed2","target":"record","created_at":"2026-07-05T04:04:53Z","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":"8f22b227225e05f279b0f80b2960241633b5d4eee9ab450e8671fa3c2e613a5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-13T14:30:55Z","title_canon_sha256":"41f26fdd53dc2c1071a7ab1fa2590188d0d1ae6019c91ee7e84844bc029b3978"},"schema_version":"1.0","source":{"id":"2203.06662","kind":"arxiv","version":1}},"canonical_sha256":"f7927516cacfa62b5e925a5f648ea66b5c28451891a5d09ff99c13971b5c07d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7927516cacfa62b5e925a5f648ea66b5c28451891a5d09ff99c13971b5c07d1","first_computed_at":"2026-07-05T04:04:53.406861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:53.406861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y30BXpNjTRz2IUg39oREhLIppGrPRv6BygH6tFxET89Hp3FX8mDWS+WkcoCi5PFdpVbufBXSGAjIO4fdFftGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:53.407262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aec39d1c001a97bf78089982710b34e6e276e11246ec27c1725e42992df76ed2","sha256:bb333eb06985edc4b7176b4bc04f1cc782fc005ee2799faff2c3e3d60fc2ee19"],"state_sha256":"529496ed2441256a3881d1ab4de60e3893d41e8c1e95f45e58b0b5bc39bfd122"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6A/YjmxkcmYpaLu5Y7yfoF7PfoznZR3qWPQwTHhPWIwdXFPSqO1j1lVECir5ZuD+m0vlDeTXH1N3fA8PkktDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:18:08.817849Z","bundle_sha256":"dcbeb5c7ed049c3c8c62061c26af9751d88ed4bd831121e9399c2fd5e993f120"}}