{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:25ELU3DERIA2YQNEJZXV5QRRNS","short_pith_number":"pith:25ELU3DE","schema_version":"1.0","canonical_sha256":"d748ba6c648a01ac41a44e6f5ec2316c9b21222e6b15c41e3fc331709e5e7fd3","source":{"kind":"arxiv","id":"1903.00520","version":3},"attestation_state":"computed","paper":{"title":"A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Kyle D. Julian, Mykel J. Kochenderfer","submitted_at":"2019-03-01T20:14:11Z","abstract_excerpt":"Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing guarantees for deep neural network controllers over multiple time steps using a combination of reachability methods and open source neural network verification tools. By bounding the system dynamics and neural network outputs, the set of reachable states can be over-approximated to provide a guarantee that the system will never reach states outside the set. "},"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":"1903.00520","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2019-03-01T20:14:11Z","cross_cats_sorted":[],"title_canon_sha256":"4bfc975bbf3c166514c840b2ae6fd722965e494ee8821797d360b0327200961b","abstract_canon_sha256":"e68e34733293cfd24c7e60ef74fdd031dc0bd2709b0a2907fe21d6c5957bfb55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.540715Z","signature_b64":"vTVIV3U9BJ3ZbWm1hv8+N8FenfZgKMnvRF2uu5xy+Zx1AcxxP3HD57ngkm06ycmCkGMgjWV5J894g3ktDpxgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d748ba6c648a01ac41a44e6f5ec2316c9b21222e6b15c41e3fc331709e5e7fd3","last_reissued_at":"2026-05-17T23:44:21.540067Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.540067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reachability Method for Verifying Dynamical Systems with Deep Neural Network Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Kyle D. Julian, Mykel J. Kochenderfer","submitted_at":"2019-03-01T20:14:11Z","abstract_excerpt":"Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing guarantees for deep neural network controllers over multiple time steps using a combination of reachability methods and open source neural network verification tools. By bounding the system dynamics and neural network outputs, the set of reachable states can be over-approximated to provide a guarantee that the system will never reach states outside the set. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00520","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.00520","created_at":"2026-05-17T23:44:21.540161+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00520v3","created_at":"2026-05-17T23:44:21.540161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00520","created_at":"2026-05-17T23:44:21.540161+00:00"},{"alias_kind":"pith_short_12","alias_value":"25ELU3DERIA2","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"25ELU3DERIA2YQNE","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"25ELU3DE","created_at":"2026-05-18T12:33:07.085635+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/25ELU3DERIA2YQNEJZXV5QRRNS","json":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS.json","graph_json":"https://pith.science/api/pith-number/25ELU3DERIA2YQNEJZXV5QRRNS/graph.json","events_json":"https://pith.science/api/pith-number/25ELU3DERIA2YQNEJZXV5QRRNS/events.json","paper":"https://pith.science/paper/25ELU3DE"},"agent_actions":{"view_html":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS","download_json":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS.json","view_paper":"https://pith.science/paper/25ELU3DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00520&json=true","fetch_graph":"https://pith.science/api/pith-number/25ELU3DERIA2YQNEJZXV5QRRNS/graph.json","fetch_events":"https://pith.science/api/pith-number/25ELU3DERIA2YQNEJZXV5QRRNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS/action/storage_attestation","attest_author":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS/action/author_attestation","sign_citation":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS/action/citation_signature","submit_replication":"https://pith.science/pith/25ELU3DERIA2YQNEJZXV5QRRNS/action/replication_record"}},"created_at":"2026-05-17T23:44:21.540161+00:00","updated_at":"2026-05-17T23:44:21.540161+00:00"}