{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCTLFKKUS5MLROWKAQXEFUD4LE","short_pith_number":"pith:GCTLFKKU","schema_version":"1.0","canonical_sha256":"30a6b2a9549758b8baca042e42d07c593962e09b877bcbd8348fd3b92699c4f9","source":{"kind":"arxiv","id":"2605.14643","version":1},"attestation_state":"computed","paper":{"title":"Unbiased and Second-Order-Free Training for High-Dimensional PDEs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Jaemin Seo, Jae Yong Lee, Surin Lee","submitted_at":"2026-05-14T09:59:13Z","abstract_excerpt":"Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not require explicit Hessian evaluations. It has recently been established that the commonly used Euler-Maruyama (EM) time discretization induces an intrinsic bias in BSDE training losses. While high-orde"},"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":"2605.14643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T09:59:13Z","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"title_canon_sha256":"54aa1aa6c210f30cc70792a0024e28b9d9afa707b04f083199aeb7ce56c0a6cc","abstract_canon_sha256":"04c9e30b269b95b80407ce113ac839d5e16453d128e2caa4de04fdf18aaae83a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:03.869388Z","signature_b64":"9kxEFAabcfjUwO+BGVbHx6yMIaHQ29fGSuDkxh06DeBWc9trNT7NrR19a6eedaptpmIgKqjVrXu18jRdPfYIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a6b2a9549758b8baca042e42d07c593962e09b877bcbd8348fd3b92699c4f9","last_reissued_at":"2026-05-17T23:39:03.868701Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:03.868701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unbiased and Second-Order-Free Training for High-Dimensional PDEs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Jaemin Seo, Jae Yong Lee, Surin Lee","submitted_at":"2026-05-14T09:59:13Z","abstract_excerpt":"Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not require explicit Hessian evaluations. It has recently been established that the commonly used Euler-Maruyama (EM) time discretization induces an intrinsic bias in BSDE training losses. While high-orde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14643","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":""},"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":"2605.14643","created_at":"2026-05-17T23:39:03.868808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14643v1","created_at":"2026-05-17T23:39:03.868808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14643","created_at":"2026-05-17T23:39:03.868808+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCTLFKKUS5ML","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCTLFKKUS5MLROWK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCTLFKKU","created_at":"2026-05-18T12:33:37.589309+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/GCTLFKKUS5MLROWKAQXEFUD4LE","json":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE.json","graph_json":"https://pith.science/api/pith-number/GCTLFKKUS5MLROWKAQXEFUD4LE/graph.json","events_json":"https://pith.science/api/pith-number/GCTLFKKUS5MLROWKAQXEFUD4LE/events.json","paper":"https://pith.science/paper/GCTLFKKU"},"agent_actions":{"view_html":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE","download_json":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE.json","view_paper":"https://pith.science/paper/GCTLFKKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14643&json=true","fetch_graph":"https://pith.science/api/pith-number/GCTLFKKUS5MLROWKAQXEFUD4LE/graph.json","fetch_events":"https://pith.science/api/pith-number/GCTLFKKUS5MLROWKAQXEFUD4LE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE/action/storage_attestation","attest_author":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE/action/author_attestation","sign_citation":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE/action/citation_signature","submit_replication":"https://pith.science/pith/GCTLFKKUS5MLROWKAQXEFUD4LE/action/replication_record"}},"created_at":"2026-05-17T23:39:03.868808+00:00","updated_at":"2026-05-17T23:39:03.868808+00:00"}