{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LVC6JM4HYCTIO2A523Q5EU5NEZ","short_pith_number":"pith:LVC6JM4H","canonical_record":{"source":{"id":"2112.07746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T21:11:27Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"0cfaccbd24c14a0d627c659d2ad478c029a61f8e5b03e036a671112ec5758abc","abstract_canon_sha256":"77dcdb2c2a66a300d729efccbe70f33e0dd11325ef2097b7a00b6cf4bb13ec18"},"schema_version":"1.0"},"canonical_sha256":"5d45e4b387c0a687681dd6e1d253ad2644476b60426b775b989cd7ecafbea037","source":{"kind":"arxiv","id":"2112.07746","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07746","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07746v1","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07746","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_12","alias_value":"LVC6JM4HYCTI","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_16","alias_value":"LVC6JM4HYCTIO2A5","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_8","alias_value":"LVC6JM4H","created_at":"2026-07-05T03:41:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LVC6JM4HYCTIO2A523Q5EU5NEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T21:11:27Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"0cfaccbd24c14a0d627c659d2ad478c029a61f8e5b03e036a671112ec5758abc","abstract_canon_sha256":"77dcdb2c2a66a300d729efccbe70f33e0dd11325ef2097b7a00b6cf4bb13ec18"},"schema_version":"1.0"},"canonical_sha256":"5d45e4b387c0a687681dd6e1d253ad2644476b60426b775b989cd7ecafbea037","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:05.970009Z","signature_b64":"Ou4zAwXGxLfbVJcPDbIVtfKXx6Pcc+RqT8V7juKTL1vQXivSReqjI/rJc8OciIfa9uL/erYgl6Tqj6d7QEFJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d45e4b387c0a687681dd6e1d253ad2644476b60426b775b989cd7ecafbea037","last_reissued_at":"2026-07-05T03:41:05.969602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:05.969602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07746","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":"2026-07-05T03:41:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0qzYB5SufvFWmnqNLBEg1WPzdz530jkVkCCSSBmnJZlSvqgJyykc0OmPyjDyjncvQEdf8nraKJ95lPoIaJfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:20:02.155761Z"},"content_sha256":"574800e462c9eea0466d404e8b18bfcd8108a53f6c1706b25fc049aba6226c09","schema_version":"1.0","event_id":"sha256:574800e462c9eea0466d404e8b18bfcd8108a53f6c1706b25fc049aba6226c09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LVC6JM4HYCTIO2A523Q5EU5NEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Kevin Huang, Sahin Lale, Ugo Rosolia, Yuanyuan Shi","submitted_at":"2021-12-14T21:11:27Z","abstract_excerpt":"Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a large number of trajectory rollouts to select an optimal action, which scales poorly for large prediction horizons or high dimensional action spaces. First-order methods that use the gradients of the rewards with respect to the actions as an update can mitigate this issue, but suffer from local optima due to the non-convex optimization landscape. To overcome t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07746","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/2112.07746/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":"2026-07-05T03:41:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YnwsFcJhjNpw8F/EkCj2/BYYkgbNQvyYn19tYHzyeJEKNSoAHXFrhyl6bapXjibuBd5VOp6oivQ1WlInz4CiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:20:02.156299Z"},"content_sha256":"95dfebefa9ded4933a05b986764d0ba1dc1427bebce390bbed7ea90a41d1135f","schema_version":"1.0","event_id":"sha256:95dfebefa9ded4933a05b986764d0ba1dc1427bebce390bbed7ea90a41d1135f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/bundle.json","state_url":"https://pith.science/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/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":"2026-08-24T03:20:02Z","links":{"resolver":"https://pith.science/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ","bundle":"https://pith.science/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/bundle.json","state":"https://pith.science/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVC6JM4HYCTIO2A523Q5EU5NEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LVC6JM4HYCTIO2A523Q5EU5NEZ","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":"77dcdb2c2a66a300d729efccbe70f33e0dd11325ef2097b7a00b6cf4bb13ec18","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T21:11:27Z","title_canon_sha256":"0cfaccbd24c14a0d627c659d2ad478c029a61f8e5b03e036a671112ec5758abc"},"schema_version":"1.0","source":{"id":"2112.07746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07746","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07746v1","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07746","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_12","alias_value":"LVC6JM4HYCTI","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_16","alias_value":"LVC6JM4HYCTIO2A5","created_at":"2026-07-05T03:41:05Z"},{"alias_kind":"pith_short_8","alias_value":"LVC6JM4H","created_at":"2026-07-05T03:41:05Z"}],"graph_snapshots":[{"event_id":"sha256:95dfebefa9ded4933a05b986764d0ba1dc1427bebce390bbed7ea90a41d1135f","target":"graph","created_at":"2026-07-05T03:41:05Z","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/2112.07746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a large number of trajectory rollouts to select an optimal action, which scales poorly for large prediction horizons or high dimensional action spaces. First-order methods that use the gradients of the rewards with respect to the actions as an update can mitigate this issue, but suffer from local optima due to the non-convex optimization landscape. To overcome t","authors_text":"Anima Anandkumar, Kevin Huang, Sahin Lale, Ugo Rosolia, Yuanyuan Shi","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T21:11:27Z","title":"CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07746","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":"sha256:574800e462c9eea0466d404e8b18bfcd8108a53f6c1706b25fc049aba6226c09","target":"record","created_at":"2026-07-05T03:41:05Z","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":"77dcdb2c2a66a300d729efccbe70f33e0dd11325ef2097b7a00b6cf4bb13ec18","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T21:11:27Z","title_canon_sha256":"0cfaccbd24c14a0d627c659d2ad478c029a61f8e5b03e036a671112ec5758abc"},"schema_version":"1.0","source":{"id":"2112.07746","kind":"arxiv","version":1}},"canonical_sha256":"5d45e4b387c0a687681dd6e1d253ad2644476b60426b775b989cd7ecafbea037","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d45e4b387c0a687681dd6e1d253ad2644476b60426b775b989cd7ecafbea037","first_computed_at":"2026-07-05T03:41:05.969602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:05.969602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ou4zAwXGxLfbVJcPDbIVtfKXx6Pcc+RqT8V7juKTL1vQXivSReqjI/rJc8OciIfa9uL/erYgl6Tqj6d7QEFJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:05.970009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:574800e462c9eea0466d404e8b18bfcd8108a53f6c1706b25fc049aba6226c09","sha256:95dfebefa9ded4933a05b986764d0ba1dc1427bebce390bbed7ea90a41d1135f"],"state_sha256":"5c6492af874b3d4d0e8d96340be3b911d306599b891714c5914c07ea43304103"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T80lQzTbuldFEKROlfaNCXzSsW6YSliAD6trfObURTiBCKUbzWIIkMdA42m7BdiuDZoQdsNTsRh0S6ZUR+MLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:20:02.161311Z","bundle_sha256":"945aa1eca36cfead9aaa36ec58a33c266060a466d9f5204a4acaabb2a552b744"}}