{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7RAM3MHLWQG4JPLYKUPAIYJ6U6","short_pith_number":"pith:7RAM3MHL","schema_version":"1.0","canonical_sha256":"fc40cdb0ebb40dc4bd78551e04613ea7a24c3ea2c5106c6198c0b68fa6fab02f","source":{"kind":"arxiv","id":"2409.04644","version":3},"attestation_state":"computed","paper":{"title":"Second-Order Stein Variational Dynamic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Evangelos A. Theodorou, Peter Lehmamnn, Yuichiro Aoyama","submitted_at":"2024-09-06T22:28:30Z","abstract_excerpt":"We present a novel second-order trajectory optimization algorithm based on Stein Variational Newton's Method and Maximum Entropy Differential Dynamic Programming. The proposed algorithm, called Stein Variational Differential Dynamic Programming, is a kernel-based extension of Maximum Entropy Differential Dynamic Programming that combines the best of the two worlds of sampling-based and gradient-based optimization. The resulting algorithm avoids known drawbacks of gradient-based dynamic optimization in terms of getting stuck to local minima, while it overcomes limitations of sampling-based stoc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.04644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-09-06T22:28:30Z","cross_cats_sorted":[],"title_canon_sha256":"1bca1ce17a44b81470ae6be6edcbeede1f23cfa93d64bfe94cd56126885792dd","abstract_canon_sha256":"99d697fc909b936d59f0c857e62f29cf7780a4cda258dbfcb1b3a964f63c8a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:47.828748Z","signature_b64":"OyzRQr6VwmP5LIr5OHyOajasduibLFrNcWW+eZ0egx5AwVRZaKxR2hq14lJLSmnluT8cbXly5f8lYFEIBwBeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc40cdb0ebb40dc4bd78551e04613ea7a24c3ea2c5106c6198c0b68fa6fab02f","last_reissued_at":"2026-07-05T09:17:47.828309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:47.828309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second-Order Stein Variational Dynamic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Evangelos A. Theodorou, Peter Lehmamnn, Yuichiro Aoyama","submitted_at":"2024-09-06T22:28:30Z","abstract_excerpt":"We present a novel second-order trajectory optimization algorithm based on Stein Variational Newton's Method and Maximum Entropy Differential Dynamic Programming. The proposed algorithm, called Stein Variational Differential Dynamic Programming, is a kernel-based extension of Maximum Entropy Differential Dynamic Programming that combines the best of the two worlds of sampling-based and gradient-based optimization. The resulting algorithm avoids known drawbacks of gradient-based dynamic optimization in terms of getting stuck to local minima, while it overcomes limitations of sampling-based stoc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04644","kind":"arxiv","version":3},"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/2409.04644/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.04644","created_at":"2026-07-05T09:17:47.828379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04644v3","created_at":"2026-07-05T09:17:47.828379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04644","created_at":"2026-07-05T09:17:47.828379+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RAM3MHLWQG4","created_at":"2026-07-05T09:17:47.828379+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RAM3MHLWQG4JPLY","created_at":"2026-07-05T09:17:47.828379+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RAM3MHL","created_at":"2026-07-05T09:17:47.828379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12149","citing_title":"Uncertainty Guided Exploratory Trajectory Optimization for Sampling-Based Model Predictive Control","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6","json":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6.json","graph_json":"https://pith.science/api/pith-number/7RAM3MHLWQG4JPLYKUPAIYJ6U6/graph.json","events_json":"https://pith.science/api/pith-number/7RAM3MHLWQG4JPLYKUPAIYJ6U6/events.json","paper":"https://pith.science/paper/7RAM3MHL"},"agent_actions":{"view_html":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6","download_json":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6.json","view_paper":"https://pith.science/paper/7RAM3MHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04644&json=true","fetch_graph":"https://pith.science/api/pith-number/7RAM3MHLWQG4JPLYKUPAIYJ6U6/graph.json","fetch_events":"https://pith.science/api/pith-number/7RAM3MHLWQG4JPLYKUPAIYJ6U6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6/action/storage_attestation","attest_author":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6/action/author_attestation","sign_citation":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6/action/citation_signature","submit_replication":"https://pith.science/pith/7RAM3MHLWQG4JPLYKUPAIYJ6U6/action/replication_record"}},"created_at":"2026-07-05T09:17:47.828379+00:00","updated_at":"2026-07-05T09:17:47.828379+00:00"}