{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LMABHWB4WBMACZ44ENLJZU5DGJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35aefff33b98dddb4aabfc15dd074a35d9c24e7e349417c66c60e7238f691209","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T07:02:34Z","title_canon_sha256":"0d1dfed630c218512aec11a4d0fbf3a0e7513e1746b76ccea3a1266d44d3b4c0"},"schema_version":"1.0","source":{"id":"2603.24002","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.24002","created_at":"2026-05-18T02:45:04Z"},{"alias_kind":"arxiv_version","alias_value":"2603.24002v2","created_at":"2026-05-18T02:45:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24002","created_at":"2026-05-18T02:45:04Z"},{"alias_kind":"pith_short_12","alias_value":"LMABHWB4WBMA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LMABHWB4WBMACZ44","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LMABHWB4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9cec63de0563a7b4741ddf8e105d0aed1511d4d561bd9ba7e28b4591a858ca26","target":"graph","created_at":"2026-05-18T02:45:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"cce95cab2d91f82cd1c16740df7a1672831a3402336bde2b90944e77972c6a64"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"36f8abfc8b0367cd9c9bc65e108737ae6faffc71705ece9f31118bc8b40f6f9a"},"paper":{"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","authors_text":"Huanhuan Gao, Zhangyong Liang","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T07:02:34Z","title":"Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24002","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T00:43:08.698061Z","id":"cc46fed2-606d-433d-991f-557445800809","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"cc46fed2-606d-433d-991f-557445800809"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:797c456b3a300484b90abff1f84c7cbb758ef6cf69eb7da8ddb33bd640e6372d","target":"record","created_at":"2026-05-18T02:45:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35aefff33b98dddb4aabfc15dd074a35d9c24e7e349417c66c60e7238f691209","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T07:02:34Z","title_canon_sha256":"0d1dfed630c218512aec11a4d0fbf3a0e7513e1746b76ccea3a1266d44d3b4c0"},"schema_version":"1.0","source":{"id":"2603.24002","kind":"arxiv","version":2}},"canonical_sha256":"5b0013d83cb05801679c23569cd3a33279b5c8b90576da24f7d372de0760dcd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b0013d83cb05801679c23569cd3a33279b5c8b90576da24f7d372de0760dcd0","first_computed_at":"2026-05-18T02:45:04.579245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:04.579245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H4vgtb2UvLgRfOESdSd0Y2U6Kx4l+FrbHYpJEKscLyT7GAOjqIMY68sbWyYQOj9SvJ69IRjmtJkcgd/sgMUWCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:04.579759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.24002","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:797c456b3a300484b90abff1f84c7cbb758ef6cf69eb7da8ddb33bd640e6372d","sha256:9cec63de0563a7b4741ddf8e105d0aed1511d4d561bd9ba7e28b4591a858ca26"],"state_sha256":"4f89ae9385554ecf5660f7c50508a7f9a3434ee6a370bfd52e1524aa6d2b019c"}