{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LMABHWB4WBMACZ44ENLJZU5DGJ","short_pith_number":"pith:LMABHWB4","schema_version":"1.0","canonical_sha256":"5b0013d83cb05801679c23569cd3a33279b5c8b90576da24f7d372de0760dcd0","source":{"kind":"arxiv","id":"2603.24002","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A stochastic zeroth-order estimator trains physics-informed neural networks with up to 10 million dimensions using memory and computation costs that stay independent of dimension and derivative order.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huanhuan Gao, Zhangyong Liang","submitted_at":"2026-03-25T07:02:34Z","abstract_excerpt":"Physics-Informed Neural Networks (PINNs) for high-dimensional and high-order partial differential equations (PDEs) are primarily constrained by the $\\mathcal{O}(d^k)$ spatial derivative complexity and the $\\mathcal{O}(P)$ memory overhead of backpropagation (BP). While randomized spatial estimators successfully reduce the spatial complexity to $\\mathcal{O}(1)$, their reliance on first-order optimization still leads to prohibitive memory consumption at scale. Zeroth-order (ZO) optimization offers a BP-free alternative; however, naively combining randomized spatial operators with ZO perturbations"},"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":true},"canonical_record":{"source":{"id":"2603.24002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T07:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"0d1dfed630c218512aec11a4d0fbf3a0e7513e1746b76ccea3a1266d44d3b4c0","abstract_canon_sha256":"35aefff33b98dddb4aabfc15dd074a35d9c24e7e349417c66c60e7238f691209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:04.579759Z","signature_b64":"H4vgtb2UvLgRfOESdSd0Y2U6Kx4l+FrbHYpJEKscLyT7GAOjqIMY68sbWyYQOj9SvJ69IRjmtJkcgd/sgMUWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b0013d83cb05801679c23569cd3a33279b5c8b90576da24f7d372de0760dcd0","last_reissued_at":"2026-05-18T02:45:04.579245Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:04.579245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A stochastic zeroth-order estimator trains physics-informed neural networks with up to 10 million dimensions using memory and computation costs that stay independent of dimension and derivative order.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huanhuan Gao, Zhangyong Liang","submitted_at":"2026-03-25T07:02:34Z","abstract_excerpt":"Physics-Informed Neural Networks (PINNs) for high-dimensional and high-order partial differential equations (PDEs) are primarily constrained by the $\\mathcal{O}(d^k)$ spatial derivative complexity and the $\\mathcal{O}(P)$ memory overhead of backpropagation (BP). While randomized spatial estimators successfully reduce the spatial complexity to $\\mathcal{O}(1)$, their reliance on first-order optimization still leads to prohibitive memory consumption at scale. Zeroth-order (ZO) optimization offers a BP-free alternative; however, naively combining randomized spatial operators with ZO perturbations"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SDZE achieves dimension-independent complexity in both space and memory, enabling the training of 10-million-dimensional PINNs on a single NVIDIA A100 GPU.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Common Random Numbers Synchronization algebraically cancels the O(1/ε²) variance explosion while preserving unbiasedness and convergence of the zeroth-order estimator for the specific randomized spatial operators used in high-order PINNs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SDZE uses common random number synchronization and implicit subspace projection to enable training of 10-million-dimensional PINNs on a single GPU with O(1) space and memory complexity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A stochastic zeroth-order estimator trains physics-informed neural networks with up to 10 million dimensions using memory and computation costs that stay independent of dimension and derivative order.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cce95cab2d91f82cd1c16740df7a1672831a3402336bde2b90944e77972c6a64"},"source":{"id":"2603.24002","kind":"arxiv","version":2},"verdict":{"id":"cc46fed2-606d-433d-991f-557445800809","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:43:08.698061Z","strongest_claim":"SDZE achieves dimension-independent complexity in both space and memory, enabling the training of 10-million-dimensional PINNs on a single NVIDIA A100 GPU.","one_line_summary":"SDZE uses common random number synchronization and implicit subspace projection to enable training of 10-million-dimensional PINNs on a single GPU with O(1) space and memory complexity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Common Random Numbers Synchronization algebraically cancels the O(1/ε²) variance explosion while preserving unbiasedness and convergence of the zeroth-order estimator for the specific randomized spatial operators used in high-order PINNs.","pith_extraction_headline":"A stochastic zeroth-order estimator trains physics-informed neural networks with up to 10 million dimensions using memory and computation costs that stay independent of dimension and derivative order."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"36f8abfc8b0367cd9c9bc65e108737ae6faffc71705ece9f31118bc8b40f6f9a"},"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":"2603.24002","created_at":"2026-05-18T02:45:04.579334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.24002v2","created_at":"2026-05-18T02:45:04.579334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24002","created_at":"2026-05-18T02:45:04.579334+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMABHWB4WBMA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMABHWB4WBMACZ44","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMABHWB4","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":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ","json":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ.json","graph_json":"https://pith.science/api/pith-number/LMABHWB4WBMACZ44ENLJZU5DGJ/graph.json","events_json":"https://pith.science/api/pith-number/LMABHWB4WBMACZ44ENLJZU5DGJ/events.json","paper":"https://pith.science/paper/LMABHWB4"},"agent_actions":{"view_html":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ","download_json":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ.json","view_paper":"https://pith.science/paper/LMABHWB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.24002&json=true","fetch_graph":"https://pith.science/api/pith-number/LMABHWB4WBMACZ44ENLJZU5DGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LMABHWB4WBMACZ44ENLJZU5DGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ/action/storage_attestation","attest_author":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ/action/author_attestation","sign_citation":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ/action/citation_signature","submit_replication":"https://pith.science/pith/LMABHWB4WBMACZ44ENLJZU5DGJ/action/replication_record"}},"created_at":"2026-05-18T02:45:04.579334+00:00","updated_at":"2026-05-18T02:45:04.579334+00:00"}