{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C6AQHM467TZKBU522KKN2VYIIH","short_pith_number":"pith:C6AQHM46","schema_version":"1.0","canonical_sha256":"178103b39efcf2a0d3bad294dd570841c6e73c5a12c7396f64e28597f5e0aec7","source":{"kind":"arxiv","id":"2410.02904","version":1},"attestation_state":"computed","paper":{"title":"Convergence Guarantees for Neural Network-Based Hamilton-Jacobi Reachability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"William Hofgard","submitted_at":"2024-10-03T18:51:45Z","abstract_excerpt":"We provide a novel uniform convergence guarantee for DeepReach, a deep learning-based method for solving Hamilton-Jacobi-Isaacs (HJI) equations associated with reachability analysis. Specifically, we show that the DeepReach algorithm, as introduced by Bansal et al. in their eponymous paper from 2020, is stable in the sense that if the loss functional for the algorithm converges to zero, then the resulting neural network approximation converges uniformly to the classical solution of the HJI equation, assuming that a classical solution exists. We also provide numerical tests of the algorithm, re"},"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":"2410.02904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2024-10-03T18:51:45Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"8570eb7cf505ef07c3837b684d7a8ead4eadbed605f25f9fdea9e28e4f344de0","abstract_canon_sha256":"ad429fd1212574cbdd8f9a21e0c99c32eeb86421c398af547d0e4151877dcf13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:41.288342Z","signature_b64":"UmhQwoccBFDcnNwQEHEE9e+Cgg2VFU967O7I30IFbhfTvHZ8Y3jXpq0ZOYvQAAW99o2RUU9ShBpN+k18rxv9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"178103b39efcf2a0d3bad294dd570841c6e73c5a12c7396f64e28597f5e0aec7","last_reissued_at":"2026-07-05T09:15:41.287892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:41.287892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Guarantees for Neural Network-Based Hamilton-Jacobi Reachability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"William Hofgard","submitted_at":"2024-10-03T18:51:45Z","abstract_excerpt":"We provide a novel uniform convergence guarantee for DeepReach, a deep learning-based method for solving Hamilton-Jacobi-Isaacs (HJI) equations associated with reachability analysis. Specifically, we show that the DeepReach algorithm, as introduced by Bansal et al. in their eponymous paper from 2020, is stable in the sense that if the loss functional for the algorithm converges to zero, then the resulting neural network approximation converges uniformly to the classical solution of the HJI equation, assuming that a classical solution exists. We also provide numerical tests of the algorithm, re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02904","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/2410.02904/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":"2410.02904","created_at":"2026-07-05T09:15:41.287949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02904v1","created_at":"2026-07-05T09:15:41.287949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02904","created_at":"2026-07-05T09:15:41.287949+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6AQHM467TZK","created_at":"2026-07-05T09:15:41.287949+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6AQHM467TZKBU52","created_at":"2026-07-05T09:15:41.287949+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6AQHM46","created_at":"2026-07-05T09:15:41.287949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03830","citing_title":"Bridging Model Predictive Control and Deep Learning for Scalable Reachability Analysis","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH","json":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH.json","graph_json":"https://pith.science/api/pith-number/C6AQHM467TZKBU522KKN2VYIIH/graph.json","events_json":"https://pith.science/api/pith-number/C6AQHM467TZKBU522KKN2VYIIH/events.json","paper":"https://pith.science/paper/C6AQHM46"},"agent_actions":{"view_html":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH","download_json":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH.json","view_paper":"https://pith.science/paper/C6AQHM46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02904&json=true","fetch_graph":"https://pith.science/api/pith-number/C6AQHM467TZKBU522KKN2VYIIH/graph.json","fetch_events":"https://pith.science/api/pith-number/C6AQHM467TZKBU522KKN2VYIIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH/action/storage_attestation","attest_author":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH/action/author_attestation","sign_citation":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH/action/citation_signature","submit_replication":"https://pith.science/pith/C6AQHM467TZKBU522KKN2VYIIH/action/replication_record"}},"created_at":"2026-07-05T09:15:41.287949+00:00","updated_at":"2026-07-05T09:15:41.287949+00:00"}