{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NKKUXQTOCHH7XI3HGNS4JVQTIG","short_pith_number":"pith:NKKUXQTO","schema_version":"1.0","canonical_sha256":"6a954bc26e11cffba3673365c4d6134199acc90fc8cf2d49fe5a01a8bd61731c","source":{"kind":"arxiv","id":"2007.12666","version":5},"attestation_state":"computed","paper":{"title":"Safe Model-Based Reinforcement Learning for Systems with Parametric Uncertainties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Rushikesh Kamalapurkar, Scott A Nivison, S M Nahid Mahmud, Zachary I. Bell","submitted_at":"2020-07-24T17:32:18Z","abstract_excerpt":"Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases. In general, safety guarantees are critical in reinforcement learning when the system is safety-critical and/or task restarts are not practically feasible. In optimal control theory, safety requirements are often expressed in terms of state and/or control constraints. In recent years, reinforcement learning approaches that rely on persistent excitation have "},"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":"2007.12666","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2020-07-24T17:32:18Z","cross_cats_sorted":["cs.SY","math.OC"],"title_canon_sha256":"c43200f7fc48349f4b52c8d7f01ab434fd0855a4b3e96ccc0683cc60c71f982f","abstract_canon_sha256":"5b112059015e550a49c78612b6d30c1d766da33ad0fb81bfcb814af51f9d9078"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:59.239601Z","signature_b64":"SmKhR81ZufgTacQ7OhdEerOeQRWrEyNzIha5Gny7mTsq1pRolzDHsecUblxSuqs6tt1mqBnD+GkuYTpF834sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a954bc26e11cffba3673365c4d6134199acc90fc8cf2d49fe5a01a8bd61731c","last_reissued_at":"2026-07-05T03:19:59.239108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:59.239108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Model-Based Reinforcement Learning for Systems with Parametric Uncertainties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Rushikesh Kamalapurkar, Scott A Nivison, S M Nahid Mahmud, Zachary I. Bell","submitted_at":"2020-07-24T17:32:18Z","abstract_excerpt":"Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases. In general, safety guarantees are critical in reinforcement learning when the system is safety-critical and/or task restarts are not practically feasible. In optimal control theory, safety requirements are often expressed in terms of state and/or control constraints. In recent years, reinforcement learning approaches that rely on persistent excitation have "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12666","kind":"arxiv","version":5},"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/2007.12666/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":"2007.12666","created_at":"2026-07-05T03:19:59.239180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12666v5","created_at":"2026-07-05T03:19:59.239180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12666","created_at":"2026-07-05T03:19:59.239180+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKKUXQTOCHH7","created_at":"2026-07-05T03:19:59.239180+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKKUXQTOCHH7XI3H","created_at":"2026-07-05T03:19:59.239180+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKKUXQTO","created_at":"2026-07-05T03:19:59.239180+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/NKKUXQTOCHH7XI3HGNS4JVQTIG","json":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG.json","graph_json":"https://pith.science/api/pith-number/NKKUXQTOCHH7XI3HGNS4JVQTIG/graph.json","events_json":"https://pith.science/api/pith-number/NKKUXQTOCHH7XI3HGNS4JVQTIG/events.json","paper":"https://pith.science/paper/NKKUXQTO"},"agent_actions":{"view_html":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG","download_json":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG.json","view_paper":"https://pith.science/paper/NKKUXQTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12666&json=true","fetch_graph":"https://pith.science/api/pith-number/NKKUXQTOCHH7XI3HGNS4JVQTIG/graph.json","fetch_events":"https://pith.science/api/pith-number/NKKUXQTOCHH7XI3HGNS4JVQTIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG/action/storage_attestation","attest_author":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG/action/author_attestation","sign_citation":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG/action/citation_signature","submit_replication":"https://pith.science/pith/NKKUXQTOCHH7XI3HGNS4JVQTIG/action/replication_record"}},"created_at":"2026-07-05T03:19:59.239180+00:00","updated_at":"2026-07-05T03:19:59.239180+00:00"}