{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KJEUJPLQHW7EQHENJ5XNQJUAF3","short_pith_number":"pith:KJEUJPLQ","schema_version":"1.0","canonical_sha256":"524944bd703dbe481c8d4f6ed826802eeb111363b2b8e532e3926d3314af2975","source":{"kind":"arxiv","id":"2603.24489","version":2},"attestation_state":"computed","paper":{"title":"Model Predictive Path Integral Control as Preconditioned Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Jiarui Wang, Mahyar Fazlyab, Sina Sharifi","submitted_at":"2026-03-25T16:30:05Z","abstract_excerpt":"Model Predictive Path Integral (MPPI) control is a widely used sampling-based method for trajectory optimization, yet its convergence properties remain only partially understood. This paper provides a direct convergence analysis using variational optimization. By lifting constrained trajectory optimization to a Kullback-Leibler (KL) regularized problem over decision distributions, we derive a reduced free-energy objective defined over a parametric sampling family. For general parametric families, we derive gradient and Hessian representations of this reduced objective and analyze preconditione"},"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":"2603.24489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-03-25T16:30:05Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"b191158cbab3c66b82690cd8bf2d77c11e8e86ab76e8785fa4dfab52f1259500","abstract_canon_sha256":"3c1b52552b5e8777860dd6f90ac54f703ea0afec8f628bfa06e083e92f76681a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:14.727743Z","signature_b64":"BGj5/PyBqA35o4rhHprqpqZ02oCsq8vfTg0QwxBdFbGqJKicvxCpWeAy2WyjxNC4MaUtUEfkzrR0+nhYKCN9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"524944bd703dbe481c8d4f6ed826802eeb111363b2b8e532e3926d3314af2975","last_reissued_at":"2026-05-25T02:02:14.727226Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:14.727226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Predictive Path Integral Control as Preconditioned Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Jiarui Wang, Mahyar Fazlyab, Sina Sharifi","submitted_at":"2026-03-25T16:30:05Z","abstract_excerpt":"Model Predictive Path Integral (MPPI) control is a widely used sampling-based method for trajectory optimization, yet its convergence properties remain only partially understood. This paper provides a direct convergence analysis using variational optimization. By lifting constrained trajectory optimization to a Kullback-Leibler (KL) regularized problem over decision distributions, we derive a reduced free-energy objective defined over a parametric sampling family. For general parametric families, we derive gradient and Hessian representations of this reduced objective and analyze preconditione"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24489","kind":"arxiv","version":2},"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/2603.24489/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":"2603.24489","created_at":"2026-05-25T02:02:14.727288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.24489v2","created_at":"2026-05-25T02:02:14.727288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24489","created_at":"2026-05-25T02:02:14.727288+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJEUJPLQHW7E","created_at":"2026-05-25T02:02:14.727288+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJEUJPLQHW7EQHEN","created_at":"2026-05-25T02:02:14.727288+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJEUJPLQ","created_at":"2026-05-25T02:02:14.727288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3","json":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3.json","graph_json":"https://pith.science/api/pith-number/KJEUJPLQHW7EQHENJ5XNQJUAF3/graph.json","events_json":"https://pith.science/api/pith-number/KJEUJPLQHW7EQHENJ5XNQJUAF3/events.json","paper":"https://pith.science/paper/KJEUJPLQ"},"agent_actions":{"view_html":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3","download_json":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3.json","view_paper":"https://pith.science/paper/KJEUJPLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.24489&json=true","fetch_graph":"https://pith.science/api/pith-number/KJEUJPLQHW7EQHENJ5XNQJUAF3/graph.json","fetch_events":"https://pith.science/api/pith-number/KJEUJPLQHW7EQHENJ5XNQJUAF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3/action/storage_attestation","attest_author":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3/action/author_attestation","sign_citation":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3/action/citation_signature","submit_replication":"https://pith.science/pith/KJEUJPLQHW7EQHENJ5XNQJUAF3/action/replication_record"}},"created_at":"2026-05-25T02:02:14.727288+00:00","updated_at":"2026-05-25T02:02:14.727288+00:00"}