{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Z2YZHA3DR72BQGVJNZQXMDNVKW","short_pith_number":"pith:Z2YZHA3D","canonical_record":{"source":{"id":"2310.05422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T05:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"324fbc14b58a1645fc6de507cf57a7b732d9cde54be9a5b7fb4551d52e099b7e","abstract_canon_sha256":"081d8654d4a99ab4e2957cdfbf6a859957b2c272e663c234fd6acbea940bd829"},"schema_version":"1.0"},"canonical_sha256":"ceb19383638ff4181aa96e61760db55585cf66768c3dac4424e13bc7e65a908d","source":{"kind":"arxiv","id":"2310.05422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05422","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05422v1","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05422","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"Z2YZHA3DR72B","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"Z2YZHA3DR72BQGVJ","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"Z2YZHA3D","created_at":"2026-07-05T06:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Z2YZHA3DR72BQGVJNZQXMDNVKW","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T05:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"324fbc14b58a1645fc6de507cf57a7b732d9cde54be9a5b7fb4551d52e099b7e","abstract_canon_sha256":"081d8654d4a99ab4e2957cdfbf6a859957b2c272e663c234fd6acbea940bd829"},"schema_version":"1.0"},"canonical_sha256":"ceb19383638ff4181aa96e61760db55585cf66768c3dac4424e13bc7e65a908d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:45.059639Z","signature_b64":"2T8PptvcJhF3xaRZhCUIiAsJGQofLFWZzl2zwkpuri9BIHmDTYOIBc91h++8oE3ATg9f5g6Gv2NwYLuM9Y6jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb19383638ff4181aa96e61760db55585cf66768c3dac4424e13bc7e65a908d","last_reissued_at":"2026-07-05T06:58:45.059112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:45.059112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05422","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":"2026-07-05T06:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"43QZo7jyha4CnMTH8H9P4YFU3oxOsU4Arh3mKijiKKtsLrDGGbb71tgF0g7P7I9gVAgzrtHl+mK2eZbEn9D9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:33:52.348687Z"},"content_sha256":"80a2c2b252393e53948041dc8cd6702d56a5c7f859b58aea93fd4ef062757621","schema_version":"1.0","event_id":"sha256:80a2c2b252393e53948041dc8cd6702d56a5c7f859b58aea93fd4ef062757621"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Z2YZHA3DR72BQGVJNZQXMDNVKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan-Ming Luo, Tian Xu, Xingchen Cao, Yang Yu","submitted_at":"2023-10-09T05:37:58Z","abstract_excerpt":"Learning a precise dynamics model can be crucial for offline reinforcement learning, which, unfortunately, has been found to be quite challenging. Dynamics models that are learned by fitting historical transitions often struggle to generalize to unseen transitions. In this study, we identify a hidden but pivotal factor termed dynamics reward that remains consistent across transitions, offering a pathway to better generalization. Therefore, we propose the idea of reward-consistent dynamics models: any trajectory generated by the dynamics model should maximize the dynamics reward derived from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05422","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/2310.05422/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":"2026-07-05T06:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/c/PQeRsDm/YnmcVnGvEE4EV2U11rGr0UK+BSv1Uq9ruHn1jfhUpvf65LO2sVfsvtNxWVrqmylgmOgtLfFMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:33:52.349177Z"},"content_sha256":"32ed88fcd1c2526256193b9120aceaa261f7a99924b786325f995f500624b96b","schema_version":"1.0","event_id":"sha256:32ed88fcd1c2526256193b9120aceaa261f7a99924b786325f995f500624b96b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/bundle.json","state_url":"https://pith.science/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/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":"2026-08-09T14:33:52Z","links":{"resolver":"https://pith.science/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW","bundle":"https://pith.science/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/bundle.json","state":"https://pith.science/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2YZHA3DR72BQGVJNZQXMDNVKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z2YZHA3DR72BQGVJNZQXMDNVKW","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":"081d8654d4a99ab4e2957cdfbf6a859957b2c272e663c234fd6acbea940bd829","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T05:37:58Z","title_canon_sha256":"324fbc14b58a1645fc6de507cf57a7b732d9cde54be9a5b7fb4551d52e099b7e"},"schema_version":"1.0","source":{"id":"2310.05422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05422","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05422v1","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05422","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"Z2YZHA3DR72B","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"Z2YZHA3DR72BQGVJ","created_at":"2026-07-05T06:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"Z2YZHA3D","created_at":"2026-07-05T06:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:32ed88fcd1c2526256193b9120aceaa261f7a99924b786325f995f500624b96b","target":"graph","created_at":"2026-07-05T06:58:45Z","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/2310.05422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning a precise dynamics model can be crucial for offline reinforcement learning, which, unfortunately, has been found to be quite challenging. Dynamics models that are learned by fitting historical transitions often struggle to generalize to unseen transitions. In this study, we identify a hidden but pivotal factor termed dynamics reward that remains consistent across transitions, offering a pathway to better generalization. Therefore, we propose the idea of reward-consistent dynamics models: any trajectory generated by the dynamics model should maximize the dynamics reward derived from th","authors_text":"Fan-Ming Luo, Tian Xu, Xingchen Cao, Yang Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T05:37:58Z","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05422","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":"sha256:80a2c2b252393e53948041dc8cd6702d56a5c7f859b58aea93fd4ef062757621","target":"record","created_at":"2026-07-05T06:58:45Z","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":"081d8654d4a99ab4e2957cdfbf6a859957b2c272e663c234fd6acbea940bd829","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T05:37:58Z","title_canon_sha256":"324fbc14b58a1645fc6de507cf57a7b732d9cde54be9a5b7fb4551d52e099b7e"},"schema_version":"1.0","source":{"id":"2310.05422","kind":"arxiv","version":1}},"canonical_sha256":"ceb19383638ff4181aa96e61760db55585cf66768c3dac4424e13bc7e65a908d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceb19383638ff4181aa96e61760db55585cf66768c3dac4424e13bc7e65a908d","first_computed_at":"2026-07-05T06:58:45.059112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:45.059112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2T8PptvcJhF3xaRZhCUIiAsJGQofLFWZzl2zwkpuri9BIHmDTYOIBc91h++8oE3ATg9f5g6Gv2NwYLuM9Y6jAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:45.059639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a2c2b252393e53948041dc8cd6702d56a5c7f859b58aea93fd4ef062757621","sha256:32ed88fcd1c2526256193b9120aceaa261f7a99924b786325f995f500624b96b"],"state_sha256":"b036908d3466a93c2bb1a3150f67ae8f29e66c4f6464d64a73c20c0d79fb1810"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlzY6osY3RK1J/DmiE/FQQeuSFN5lbPVvgTV6KSrRB26hFtpg3RIu3jqC572sRm+EylFAo34PIbEebJmJQaECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:33:52.352387Z","bundle_sha256":"77fa3bb80ff36e9dd506bacb7b2cd0db2543b2f186ef146ee969b5d58be87d9a"}}