{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WL4VOCWR7JGPHSVRRSLA33B4M6","short_pith_number":"pith:WL4VOCWR","schema_version":"1.0","canonical_sha256":"b2f9570ad1fa4cf3cab18c960dec3c678810c976d99a9d5500a3a48af62e6cb4","source":{"kind":"arxiv","id":"2503.09090","version":2},"attestation_state":"computed","paper":{"title":"Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Eiji Uchibe, Hamed Jabbari Asl","submitted_at":"2025-03-12T06:00:16Z","abstract_excerpt":"This paper introduces a novel model-free and a partially model-free algorithm for inverse optimal control (IOC), also known as inverse reinforcement learning (IRL), aimed at estimating the cost function of continuous-time nonlinear deterministic systems. Using the input-state trajectories of an expert agent, the proposed algorithms separately utilize control policy information and the Hamilton-Jacobi-Bellman equation to estimate different sets of cost function parameters. This approach allows the algorithms to achieve broader applicability while maintaining a model-free framework. Also, the mo"},"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":"2503.09090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-03-12T06:00:16Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"27c62d8e070052f397e85aa1bf34c20578206a631b20a11a20ff304a84db111f","abstract_canon_sha256":"82cdc4bf7c5a8e1fc81eacb0f0e5681ba0651646970d541d82e6775b01f07345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:17.514035Z","signature_b64":"USpHgYYUj8C6FgUMTyNiBXbDpwFZLdNUZGIJUX7QbBNX4sLybRGO3nwTM3ATP4Dji7fNwbhvMtnX4pNc6sYgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f9570ad1fa4cf3cab18c960dec3c678810c976d99a9d5500a3a48af62e6cb4","last_reissued_at":"2026-07-05T10:34:17.512858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:17.512858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Eiji Uchibe, Hamed Jabbari Asl","submitted_at":"2025-03-12T06:00:16Z","abstract_excerpt":"This paper introduces a novel model-free and a partially model-free algorithm for inverse optimal control (IOC), also known as inverse reinforcement learning (IRL), aimed at estimating the cost function of continuous-time nonlinear deterministic systems. Using the input-state trajectories of an expert agent, the proposed algorithms separately utilize control policy information and the Hamilton-Jacobi-Bellman equation to estimate different sets of cost function parameters. This approach allows the algorithms to achieve broader applicability while maintaining a model-free framework. Also, the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09090","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/2503.09090/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":"2503.09090","created_at":"2026-07-05T10:34:17.513010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09090v2","created_at":"2026-07-05T10:34:17.513010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09090","created_at":"2026-07-05T10:34:17.513010+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL4VOCWR7JGP","created_at":"2026-07-05T10:34:17.513010+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL4VOCWR7JGPHSVR","created_at":"2026-07-05T10:34:17.513010+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL4VOCWR","created_at":"2026-07-05T10:34:17.513010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08983","citing_title":"Online Learning Control Strategies for Industrial Processes with Application for Loosening and Conditioning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6","json":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6.json","graph_json":"https://pith.science/api/pith-number/WL4VOCWR7JGPHSVRRSLA33B4M6/graph.json","events_json":"https://pith.science/api/pith-number/WL4VOCWR7JGPHSVRRSLA33B4M6/events.json","paper":"https://pith.science/paper/WL4VOCWR"},"agent_actions":{"view_html":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6","download_json":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6.json","view_paper":"https://pith.science/paper/WL4VOCWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09090&json=true","fetch_graph":"https://pith.science/api/pith-number/WL4VOCWR7JGPHSVRRSLA33B4M6/graph.json","fetch_events":"https://pith.science/api/pith-number/WL4VOCWR7JGPHSVRRSLA33B4M6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6/action/storage_attestation","attest_author":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6/action/author_attestation","sign_citation":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6/action/citation_signature","submit_replication":"https://pith.science/pith/WL4VOCWR7JGPHSVRRSLA33B4M6/action/replication_record"}},"created_at":"2026-07-05T10:34:17.513010+00:00","updated_at":"2026-07-05T10:34:17.513010+00:00"}