{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALNMOW5OS5JGB4S4BSUIPEYNBV","short_pith_number":"pith:ALNMOW5O","schema_version":"1.0","canonical_sha256":"02dac75bae975260f25c0ca887930d0d5e11a977e8e175afc4957202ff303c6f","source":{"kind":"arxiv","id":"2507.15455","version":2},"attestation_state":"computed","paper":{"title":"Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP"],"primary_cat":"math.NA","authors_text":"Hee Jun Yang, Minjung Gim, Yeoneung Kim","submitted_at":"2025-07-21T10:06:53Z","abstract_excerpt":"We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve high-dimensional, nonconvex Hamilton--Jacobi--Isaacs (HJI) equations arising in stochastic differential games and robust control. The method alternates between solving linear second-order PDEs under fixed feedback policies and updating the controls via pointwise minimax optimization using automatic differentiation. Under standard Lipschitz and uniform ellipticity assumptions, we prove that the value function iterates converge locally uniformly to "},"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":"2507.15455","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2025-07-21T10:06:53Z","cross_cats_sorted":["cs.AI","cs.NA","math.AP"],"title_canon_sha256":"225379d6e1898aa0282f5a692c2eec3cb21004d563f790a657b5156fdd7a9dfd","abstract_canon_sha256":"67e554bfcef9e51c953cca1c94d3825a391bdee97e2217739c868dc309ed628c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:56.039083Z","signature_b64":"L3IFxHUcX2KDlAXztIOMVsWWRH/IMiEAJtOp3Lnu3pnVeNZUKq3w9Yzj7l83IGEyJGq9APHYnqGYirkxkM2EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02dac75bae975260f25c0ca887930d0d5e11a977e8e175afc4957202ff303c6f","last_reissued_at":"2026-07-05T11:41:56.038602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:56.038602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP"],"primary_cat":"math.NA","authors_text":"Hee Jun Yang, Minjung Gim, Yeoneung Kim","submitted_at":"2025-07-21T10:06:53Z","abstract_excerpt":"We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve high-dimensional, nonconvex Hamilton--Jacobi--Isaacs (HJI) equations arising in stochastic differential games and robust control. The method alternates between solving linear second-order PDEs under fixed feedback policies and updating the controls via pointwise minimax optimization using automatic differentiation. Under standard Lipschitz and uniform ellipticity assumptions, we prove that the value function iterates converge locally uniformly to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15455","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/2507.15455/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":"2507.15455","created_at":"2026-07-05T11:41:56.038675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15455v2","created_at":"2026-07-05T11:41:56.038675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15455","created_at":"2026-07-05T11:41:56.038675+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALNMOW5OS5JG","created_at":"2026-07-05T11:41:56.038675+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALNMOW5OS5JGB4S4","created_at":"2026-07-05T11:41:56.038675+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALNMOW5O","created_at":"2026-07-05T11:41:56.038675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07116","citing_title":"Stabilized neural Hamilton--Jacobi--Bellman solvers: Error analysis and applications in model-based reinforcement learning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV","json":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV.json","graph_json":"https://pith.science/api/pith-number/ALNMOW5OS5JGB4S4BSUIPEYNBV/graph.json","events_json":"https://pith.science/api/pith-number/ALNMOW5OS5JGB4S4BSUIPEYNBV/events.json","paper":"https://pith.science/paper/ALNMOW5O"},"agent_actions":{"view_html":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV","download_json":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV.json","view_paper":"https://pith.science/paper/ALNMOW5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15455&json=true","fetch_graph":"https://pith.science/api/pith-number/ALNMOW5OS5JGB4S4BSUIPEYNBV/graph.json","fetch_events":"https://pith.science/api/pith-number/ALNMOW5OS5JGB4S4BSUIPEYNBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV/action/storage_attestation","attest_author":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV/action/author_attestation","sign_citation":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV/action/citation_signature","submit_replication":"https://pith.science/pith/ALNMOW5OS5JGB4S4BSUIPEYNBV/action/replication_record"}},"created_at":"2026-07-05T11:41:56.038675+00:00","updated_at":"2026-07-05T11:41:56.038675+00:00"}