{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M4JSBLA7ZOEDYZJHGHRHQR66MC","short_pith_number":"pith:M4JSBLA7","schema_version":"1.0","canonical_sha256":"671320ac1fcb883c652731e27847de608b98d97c8cdaa0f6e5c3caae2ffc1485","source":{"kind":"arxiv","id":"2103.05744","version":1},"attestation_state":"computed","paper":{"title":"Deep neural network approximation for high-dimensional parabolic Hamilton-Jacobi-Bellman equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Lukas Herrmann, Philipp Grohs","submitted_at":"2021-03-09T22:34:13Z","abstract_excerpt":"The approximation of solutions to second order Hamilton--Jacobi--Bellman (HJB) equations by deep neural networks is investigated. It is shown that for HJB equations that arise in the context of the optimal control of certain Markov processes the solution can be approximated by deep neural networks without incurring the curse of dimension. The dynamics is assumed to depend affinely on the controls and the cost depends quadratically on the controls. The admissible controls take values in a bounded 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":"2103.05744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2021-03-09T22:34:13Z","cross_cats_sorted":["cs.LG","cs.NA","stat.ML"],"title_canon_sha256":"eedfc4ea3bd0ef3930ba095c9e5e7cec63aec0ce7464f80afca1e0d1add3d754","abstract_canon_sha256":"23fafd25113e89bc44a7c508eb17ff686fd161458ee323296bada1c86b9e7220"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:57.749896Z","signature_b64":"h9hNwb+7E9v1cvVgofSIGErT0Z5HTdvoExcFglnsNQGf0vSYQBX3y23ffk6bZhM/jUPjCWETUZ21z7c9rD2zDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671320ac1fcb883c652731e27847de608b98d97c8cdaa0f6e5c3caae2ffc1485","last_reissued_at":"2026-07-05T02:21:57.749479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:57.749479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep neural network approximation for high-dimensional parabolic Hamilton-Jacobi-Bellman equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","stat.ML"],"primary_cat":"math.NA","authors_text":"Lukas Herrmann, Philipp Grohs","submitted_at":"2021-03-09T22:34:13Z","abstract_excerpt":"The approximation of solutions to second order Hamilton--Jacobi--Bellman (HJB) equations by deep neural networks is investigated. It is shown that for HJB equations that arise in the context of the optimal control of certain Markov processes the solution can be approximated by deep neural networks without incurring the curse of dimension. The dynamics is assumed to depend affinely on the controls and the cost depends quadratically on the controls. The admissible controls take values in a bounded set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05744","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/2103.05744/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":"2103.05744","created_at":"2026-07-05T02:21:57.749535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05744v1","created_at":"2026-07-05T02:21:57.749535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05744","created_at":"2026-07-05T02:21:57.749535+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4JSBLA7ZOED","created_at":"2026-07-05T02:21:57.749535+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4JSBLA7ZOEDYZJH","created_at":"2026-07-05T02:21:57.749535+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4JSBLA7","created_at":"2026-07-05T02:21:57.749535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.13722","citing_title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC","json":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC.json","graph_json":"https://pith.science/api/pith-number/M4JSBLA7ZOEDYZJHGHRHQR66MC/graph.json","events_json":"https://pith.science/api/pith-number/M4JSBLA7ZOEDYZJHGHRHQR66MC/events.json","paper":"https://pith.science/paper/M4JSBLA7"},"agent_actions":{"view_html":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC","download_json":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC.json","view_paper":"https://pith.science/paper/M4JSBLA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05744&json=true","fetch_graph":"https://pith.science/api/pith-number/M4JSBLA7ZOEDYZJHGHRHQR66MC/graph.json","fetch_events":"https://pith.science/api/pith-number/M4JSBLA7ZOEDYZJHGHRHQR66MC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC/action/storage_attestation","attest_author":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC/action/author_attestation","sign_citation":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC/action/citation_signature","submit_replication":"https://pith.science/pith/M4JSBLA7ZOEDYZJHGHRHQR66MC/action/replication_record"}},"created_at":"2026-07-05T02:21:57.749535+00:00","updated_at":"2026-07-05T02:21:57.749535+00:00"}