{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KBS3V4QU2EQW4D2R57T3EE56RZ","short_pith_number":"pith:KBS3V4QU","canonical_record":{"source":{"id":"2302.01244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T17:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"89b403aa6f095d53e0c448478bac7afbaffa4b590186fdc84e2947e437cdcc78","abstract_canon_sha256":"977c48ae6f1d8c6d5cdcea276cff6529babc55306189907971d3ec4515230ba1"},"schema_version":"1.0"},"canonical_sha256":"5065baf214d1216e0f51efe7b213be8e7020af2207992f4de689d4b12080a380","source":{"kind":"arxiv","id":"2302.01244","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01244","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01244v1","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01244","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"KBS3V4QU2EQW","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"KBS3V4QU2EQW4D2R","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"KBS3V4QU","created_at":"2026-07-05T05:38:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KBS3V4QU2EQW4D2R57T3EE56RZ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T17:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"89b403aa6f095d53e0c448478bac7afbaffa4b590186fdc84e2947e437cdcc78","abstract_canon_sha256":"977c48ae6f1d8c6d5cdcea276cff6529babc55306189907971d3ec4515230ba1"},"schema_version":"1.0"},"canonical_sha256":"5065baf214d1216e0f51efe7b213be8e7020af2207992f4de689d4b12080a380","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:24.345044Z","signature_b64":"w5PpZXAt2nj1zayAQLMZ5+CukJfAvkdttJ4Zn+v86yF6RBOdL5dhATY/ptHkowERHumcJdG6mhnIDo0ax/w+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5065baf214d1216e0f51efe7b213be8e7020af2207992f4de689d4b12080a380","last_reissued_at":"2026-07-05T05:38:24.344583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:24.344583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01244","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":"2026-07-05T05:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCFgYPqd111Y+1HUsKfEU6dVM3qWQNrPIQash0lyHNW+zzb1uaz68WmfTBV6BL3AlWnG3JjUqxAkiAhenDL8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:00:52.177362Z"},"content_sha256":"b37a51ed46fc4b56acc9cd8e4c6c04e9820210d604e1fd6f48f712243c66c36e","schema_version":"1.0","event_id":"sha256:b37a51ed46fc4b56acc9cd8e4c6c04e9820210d604e1fd6f48f712243c66c36e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KBS3V4QU2EQW4D2R57T3EE56RZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, Huazhe Xu, Ruijie Zheng, Xiyao Wang","submitted_at":"2023-02-02T17:27:16Z","abstract_excerpt":"Probabilistic dynamics model ensemble is widely used in existing model-based reinforcement learning methods as it outperforms a single dynamics model in both asymptotic performance and sample efficiency. In this paper, we provide both practical and theoretical insights on the empirical success of the probabilistic dynamics model ensemble through the lens of Lipschitz continuity. We find that, for a value function, the stronger the Lipschitz condition is, the smaller the gap between the true dynamics- and learned dynamics-induced Bellman operators is, thus enabling the converged value function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01244","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/2302.01244/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":"2026-07-05T05:38:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWE3wCDL8gY4musL1YYGmWMkKHeTAwhSMhgFNl4H3ViO+G8r6Qb275oS2C6tjRqnku6yWNASY2X8las5EiNcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:00:52.177971Z"},"content_sha256":"bb2a0fa16c49e18153be56dd512c043e303e142cd5411d075e97370cade71529","schema_version":"1.0","event_id":"sha256:bb2a0fa16c49e18153be56dd512c043e303e142cd5411d075e97370cade71529"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/bundle.json","state_url":"https://pith.science/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/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":"2026-08-13T16:00:52Z","links":{"resolver":"https://pith.science/pith/KBS3V4QU2EQW4D2R57T3EE56RZ","bundle":"https://pith.science/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/bundle.json","state":"https://pith.science/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBS3V4QU2EQW4D2R57T3EE56RZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KBS3V4QU2EQW4D2R57T3EE56RZ","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":"977c48ae6f1d8c6d5cdcea276cff6529babc55306189907971d3ec4515230ba1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T17:27:16Z","title_canon_sha256":"89b403aa6f095d53e0c448478bac7afbaffa4b590186fdc84e2947e437cdcc78"},"schema_version":"1.0","source":{"id":"2302.01244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01244","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01244v1","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01244","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_12","alias_value":"KBS3V4QU2EQW","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_16","alias_value":"KBS3V4QU2EQW4D2R","created_at":"2026-07-05T05:38:24Z"},{"alias_kind":"pith_short_8","alias_value":"KBS3V4QU","created_at":"2026-07-05T05:38:24Z"}],"graph_snapshots":[{"event_id":"sha256:bb2a0fa16c49e18153be56dd512c043e303e142cd5411d075e97370cade71529","target":"graph","created_at":"2026-07-05T05:38:24Z","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/2302.01244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Probabilistic dynamics model ensemble is widely used in existing model-based reinforcement learning methods as it outperforms a single dynamics model in both asymptotic performance and sample efficiency. In this paper, we provide both practical and theoretical insights on the empirical success of the probabilistic dynamics model ensemble through the lens of Lipschitz continuity. We find that, for a value function, the stronger the Lipschitz condition is, the smaller the gap between the true dynamics- and learned dynamics-induced Bellman operators is, thus enabling the converged value function ","authors_text":"Furong Huang, Huazhe Xu, Ruijie Zheng, Xiyao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T17:27:16Z","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01244","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:b37a51ed46fc4b56acc9cd8e4c6c04e9820210d604e1fd6f48f712243c66c36e","target":"record","created_at":"2026-07-05T05:38:24Z","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":"977c48ae6f1d8c6d5cdcea276cff6529babc55306189907971d3ec4515230ba1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T17:27:16Z","title_canon_sha256":"89b403aa6f095d53e0c448478bac7afbaffa4b590186fdc84e2947e437cdcc78"},"schema_version":"1.0","source":{"id":"2302.01244","kind":"arxiv","version":1}},"canonical_sha256":"5065baf214d1216e0f51efe7b213be8e7020af2207992f4de689d4b12080a380","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5065baf214d1216e0f51efe7b213be8e7020af2207992f4de689d4b12080a380","first_computed_at":"2026-07-05T05:38:24.344583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:24.344583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w5PpZXAt2nj1zayAQLMZ5+CukJfAvkdttJ4Zn+v86yF6RBOdL5dhATY/ptHkowERHumcJdG6mhnIDo0ax/w+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:24.345044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b37a51ed46fc4b56acc9cd8e4c6c04e9820210d604e1fd6f48f712243c66c36e","sha256:bb2a0fa16c49e18153be56dd512c043e303e142cd5411d075e97370cade71529"],"state_sha256":"cdc063b484fdd1eb3075f4d535f2216a39dcce2f7e6a713ebdc217506bba1c14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nf3tltXOGpU0VoHCI2G7QIXsvGo+iZnuDRxd4DnR6fywiNNrAybNsN6IyTGisyztYERbfK6ZWiE2g/AQ+OhJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:00:52.200700Z","bundle_sha256":"ede56e6e2bd8021fd22230021f5254fc4731ae752dced3fcea71faf0be21d370"}}