{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FTGG3DLQQL7BJGRM5P4JG5X3MV","short_pith_number":"pith:FTGG3DLQ","schema_version":"1.0","canonical_sha256":"2ccc6d8d7082fe149a2cebf89376fb655e271549f034596c5bef003a92a6e688","source":{"kind":"arxiv","id":"1903.06652","version":2},"attestation_state":"computed","paper":{"title":"Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Christoph Reisinger, Yufei Zhang","submitted_at":"2019-03-15T16:42:52Z","abstract_excerpt":"In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum games can be represented by a deep artificial neural network (DNN), whose complexity grows at most polynomially in both the dimension of the state equation and the reciprocal of the required accuracy. Such nonlinear stiff systems may arise, for example, from Galerkin approximations of controlled stochastic partial differential equations (SPDEs), or controlled PDEs with uncertain initial conditions and source terms. This "},"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":"1903.06652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2019-03-15T16:42:52Z","cross_cats_sorted":["cs.LG","cs.NA","math.OC"],"title_canon_sha256":"63a96e1361143bb2bdc585daf8810877907fe3db891552788e8638f1df21336e","abstract_canon_sha256":"23b4c6de622155d88f787dbaf618873cefacdc31af93380ae6ac6c40363b137e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:26.819449Z","signature_b64":"dIZ3Q25AB0RYCKIdSQaTCwNGQ9456mNcGUeuYjwqM/OqLNARg5z6p8lTqT6t37SjSNXu4zVNrg7iFB+vGlTrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ccc6d8d7082fe149a2cebf89376fb655e271549f034596c5bef003a92a6e688","last_reissued_at":"2026-07-05T01:02:26.818819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:26.818819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC"],"primary_cat":"math.NA","authors_text":"Christoph Reisinger, Yufei Zhang","submitted_at":"2019-03-15T16:42:52Z","abstract_excerpt":"In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum games can be represented by a deep artificial neural network (DNN), whose complexity grows at most polynomially in both the dimension of the state equation and the reciprocal of the required accuracy. Such nonlinear stiff systems may arise, for example, from Galerkin approximations of controlled stochastic partial differential equations (SPDEs), or controlled PDEs with uncertain initial conditions and source terms. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06652","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/1903.06652/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":"1903.06652","created_at":"2026-07-05T01:02:26.818893+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.06652v2","created_at":"2026-07-05T01:02:26.818893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06652","created_at":"2026-07-05T01:02:26.818893+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTGG3DLQQL7B","created_at":"2026-07-05T01:02:26.818893+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTGG3DLQQL7BJGRM","created_at":"2026-07-05T01:02:26.818893+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTGG3DLQ","created_at":"2026-07-05T01:02:26.818893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.14523","citing_title":"Deep neural network approximation theory for high-dimensional functions","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV","json":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV.json","graph_json":"https://pith.science/api/pith-number/FTGG3DLQQL7BJGRM5P4JG5X3MV/graph.json","events_json":"https://pith.science/api/pith-number/FTGG3DLQQL7BJGRM5P4JG5X3MV/events.json","paper":"https://pith.science/paper/FTGG3DLQ"},"agent_actions":{"view_html":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV","download_json":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV.json","view_paper":"https://pith.science/paper/FTGG3DLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.06652&json=true","fetch_graph":"https://pith.science/api/pith-number/FTGG3DLQQL7BJGRM5P4JG5X3MV/graph.json","fetch_events":"https://pith.science/api/pith-number/FTGG3DLQQL7BJGRM5P4JG5X3MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV/action/storage_attestation","attest_author":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV/action/author_attestation","sign_citation":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV/action/citation_signature","submit_replication":"https://pith.science/pith/FTGG3DLQQL7BJGRM5P4JG5X3MV/action/replication_record"}},"created_at":"2026-07-05T01:02:26.818893+00:00","updated_at":"2026-07-05T01:02:26.818893+00:00"}