{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3X4LVQST6YG4XVTHXB4DMZX5D","short_pith_number":"pith:M3X4LVQS","schema_version":"1.0","canonical_sha256":"66efc5d6129fb06e5eb33dc3c1b337e8c9e2381429d8a389c53795333b69f3b1","source":{"kind":"arxiv","id":"2407.09645","version":2},"attestation_state":"computed","paper":{"title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Milan Ganai, Sicun Gao, Sylvia Herbert","submitted_at":"2024-07-12T19:04:39Z","abstract_excerpt":"Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was restricted to verifying low-dimensional dynamical systems primarily because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. In recent years"},"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":"2407.09645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-07-12T19:04:39Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"801ef26fbc6af4f55430adb977b3bea1e4bf81926810adfa3dccaff2e77116a7","abstract_canon_sha256":"99de865c9c4a82b4f529d515e6529888146beee3532f91cb2189751f30bf8466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:57.787728Z","signature_b64":"JzC1Wx3IwY9kOai/B2cXDDrtfcO0ATcVzbuO71V+52W9lC9IXl7MbPHH5wq1QF/dbosI+TJwc0CztGEorPMfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66efc5d6129fb06e5eb33dc3c1b337e8c9e2381429d8a389c53795333b69f3b1","last_reissued_at":"2026-07-05T08:57:57.787312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:57.787312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Milan Ganai, Sicun Gao, Sylvia Herbert","submitted_at":"2024-07-12T19:04:39Z","abstract_excerpt":"Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was restricted to verifying low-dimensional dynamical systems primarily because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. In recent years"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09645","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/2407.09645/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":"2407.09645","created_at":"2026-07-05T08:57:57.787380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09645v2","created_at":"2026-07-05T08:57:57.787380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09645","created_at":"2026-07-05T08:57:57.787380+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3X4LVQST6YG","created_at":"2026-07-05T08:57:57.787380+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3X4LVQST6YG4XVT","created_at":"2026-07-05T08:57:57.787380+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3X4LVQS","created_at":"2026-07-05T08:57:57.787380+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/M3X4LVQST6YG4XVTHXB4DMZX5D","json":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D.json","graph_json":"https://pith.science/api/pith-number/M3X4LVQST6YG4XVTHXB4DMZX5D/graph.json","events_json":"https://pith.science/api/pith-number/M3X4LVQST6YG4XVTHXB4DMZX5D/events.json","paper":"https://pith.science/paper/M3X4LVQS"},"agent_actions":{"view_html":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D","download_json":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D.json","view_paper":"https://pith.science/paper/M3X4LVQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/M3X4LVQST6YG4XVTHXB4DMZX5D/graph.json","fetch_events":"https://pith.science/api/pith-number/M3X4LVQST6YG4XVTHXB4DMZX5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D/action/storage_attestation","attest_author":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D/action/author_attestation","sign_citation":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D/action/citation_signature","submit_replication":"https://pith.science/pith/M3X4LVQST6YG4XVTHXB4DMZX5D/action/replication_record"}},"created_at":"2026-07-05T08:57:57.787380+00:00","updated_at":"2026-07-05T08:57:57.787380+00:00"}