{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CC7UDQC47BAIYOLLDWBRGC7PXU","short_pith_number":"pith:CC7UDQC4","schema_version":"1.0","canonical_sha256":"10bf41c05cf8408c396b1d83130befbd3030fd519b371f6d3383a236c6c6711f","source":{"kind":"arxiv","id":"2412.17118","version":1},"attestation_state":"computed","paper":{"title":"Transformer-Based Model Predictive Path Integral Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Efstathios Bakolas, Shrenik Zinage, Vrushabh Zinage","submitted_at":"2024-12-22T18:15:21Z","abstract_excerpt":"This paper presents a novel approach to improve the Model Predictive Path Integral (MPPI) control by using a transformer to initialize the mean control sequence. Traditional MPPI methods often struggle with sample efficiency and computational costs due to suboptimal initial rollouts. We propose TransformerMPPI, which uses a transformer trained on historical control data to generate informed initial mean control sequences. TransformerMPPI combines the strengths of the attention mechanism in transformers and sampling-based control, leading to improved computational performance and sample efficie"},"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":"2412.17118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-22T18:15:21Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"50b3f361b508488ece14b7a9a66674ff009d54af8b021908c29364546e044b9d","abstract_canon_sha256":"6155dd9805e9aa4dfa3a0e841103d5243f7971cdb4e257acc9598188150a9f9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:17.819701Z","signature_b64":"BefJf1qdQsUsGmd57zqj+K9nEcx2xJemmyDdlAL0odL76AdHbIjaO9+pN9WhUtoz1VBSoUrJ9Gc9wBmNvltKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10bf41c05cf8408c396b1d83130befbd3030fd519b371f6d3383a236c6c6711f","last_reissued_at":"2026-07-05T09:53:17.819222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:17.819222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Based Model Predictive Path Integral Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Efstathios Bakolas, Shrenik Zinage, Vrushabh Zinage","submitted_at":"2024-12-22T18:15:21Z","abstract_excerpt":"This paper presents a novel approach to improve the Model Predictive Path Integral (MPPI) control by using a transformer to initialize the mean control sequence. Traditional MPPI methods often struggle with sample efficiency and computational costs due to suboptimal initial rollouts. We propose TransformerMPPI, which uses a transformer trained on historical control data to generate informed initial mean control sequences. TransformerMPPI combines the strengths of the attention mechanism in transformers and sampling-based control, leading to improved computational performance and sample efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17118","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/2412.17118/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":"2412.17118","created_at":"2026-07-05T09:53:17.819272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17118v1","created_at":"2026-07-05T09:53:17.819272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17118","created_at":"2026-07-05T09:53:17.819272+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC7UDQC47BAI","created_at":"2026-07-05T09:53:17.819272+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC7UDQC47BAIYOLL","created_at":"2026-07-05T09:53:17.819272+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC7UDQC4","created_at":"2026-07-05T09:53:17.819272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03260","citing_title":"Robust Path Tracking for Vehicles via Continuous-Time Residual Learning: An ICODE-MPPI Approach","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU","json":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU.json","graph_json":"https://pith.science/api/pith-number/CC7UDQC47BAIYOLLDWBRGC7PXU/graph.json","events_json":"https://pith.science/api/pith-number/CC7UDQC47BAIYOLLDWBRGC7PXU/events.json","paper":"https://pith.science/paper/CC7UDQC4"},"agent_actions":{"view_html":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU","download_json":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU.json","view_paper":"https://pith.science/paper/CC7UDQC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17118&json=true","fetch_graph":"https://pith.science/api/pith-number/CC7UDQC47BAIYOLLDWBRGC7PXU/graph.json","fetch_events":"https://pith.science/api/pith-number/CC7UDQC47BAIYOLLDWBRGC7PXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU/action/storage_attestation","attest_author":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU/action/author_attestation","sign_citation":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU/action/citation_signature","submit_replication":"https://pith.science/pith/CC7UDQC47BAIYOLLDWBRGC7PXU/action/replication_record"}},"created_at":"2026-07-05T09:53:17.819272+00:00","updated_at":"2026-07-05T09:53:17.819272+00:00"}