{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LHV4HDXZPFVM576DATO4D3VCU2","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":"83c2e1738631f768288fbea53d1192eeac1ba37b8a2611377493bb2b60a9d926","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI","cs.CV","physics.ins-det"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T17:59:42Z","title_canon_sha256":"6afb4f1099c43b711fd32d024947eb5205fd26a95e58cea2febfe014dc5dc3f7"},"schema_version":"1.0","source":{"id":"2603.11045","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11045","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11045v2","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11045","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"LHV4HDXZPFVM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LHV4HDXZPFVM576D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LHV4HDXZ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:613f8508c46a81577f5153512701f123646ecda75fb767e8dff50cfb9062e80a","target":"graph","created_at":"2026-05-17T23:39:15Z","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":"Across synthetic 3D benchmarks, NeFTY substantially outperforms soft-constrained PINN variants and a voxel-grid baseline on label-free volumetric recovery, and it transfers to real thermography data, surpassing classical signal-processing baselines in both defect segmentation and depth estimation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a coordinate-based neural network can faithfully represent the unknown diffusivity field while the implicit-Euler discretization with harmonic-mean fluxes exactly captures the continuous PDE on the chosen grid for the materials and time scales of interest."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NeFTY embeds a differentiable implicit-Euler heat solver into neural field optimization to solve the inverse heat conduction problem exactly on the discretization, outperforming soft PINNs and classical baselines on synthetic 3D benchmarks and real thermography data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"NeFTY recovers three-dimensional thermal diffusivity fields exactly by embedding a differentiable heat solver inside neural field optimization."}],"snapshot_sha256":"6a648720bb71fa69e439df0479bcf43f0c10609f25ee8b2734eaa9cae7eca3ca"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dd3b85cb0275db2c8f6dbd926acbe8e46f9321d20cd43546fea7d458276b2ee8"},"paper":{"abstract_excerpt":"Inverse problems for stiff parabolic partial differential equations (PDEs), such as the inverse heat conduction problem (IHCP), are severely ill-posed: the forward map rapidly damps high-frequency interior structure before it reaches the boundary. Soft-constrained physics-informed neural networks (PINNs), which embed the PDE as a residual penalty, suffer from gradient pathology in this regime and tend to fit boundary measurements while leaving the interior field essentially untouched. We propose Neural Field Thermal Tomography (NeFTY), a hard-constrained neural field framework for label-free t","authors_text":"Aditya Sood, Christine Allen-Blanchette, Dongzhe Zheng, Tao Zhong, Yixun Hu","cross_cats":["cond-mat.mtrl-sci","cs.AI","cs.CV","physics.ins-det"],"headline":"NeFTY recovers three-dimensional thermal diffusivity fields exactly by embedding a differentiable heat solver inside neural field optimization.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T17:59:42Z","title":"Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11045","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T13:10:26.159216Z","id":"5f9e308d-1c90-4d46-babe-1fc715628603","model_set":{"reader":"grok-4.3"},"one_line_summary":"NeFTY embeds a differentiable implicit-Euler heat solver into neural field optimization to solve the inverse heat conduction problem exactly on the discretization, outperforming soft PINNs and classical baselines on synthetic 3D benchmarks and real thermography data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"NeFTY recovers three-dimensional thermal diffusivity fields exactly by embedding a differentiable heat solver inside neural field optimization.","strongest_claim":"Across synthetic 3D benchmarks, NeFTY substantially outperforms soft-constrained PINN variants and a voxel-grid baseline on label-free volumetric recovery, and it transfers to real thermography data, surpassing classical signal-processing baselines in both defect segmentation and depth estimation.","weakest_assumption":"The assumption that a coordinate-based neural network can faithfully represent the unknown diffusivity field while the implicit-Euler discretization with harmonic-mean fluxes exactly captures the continuous PDE on the chosen grid for the materials and time scales of interest."}},"verdict_id":"5f9e308d-1c90-4d46-babe-1fc715628603"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0784e95f0962bffc99855e908371ef8a4a2708e12d6b507ed8e84d3e52ab3cb7","target":"record","created_at":"2026-05-17T23:39:15Z","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":"83c2e1738631f768288fbea53d1192eeac1ba37b8a2611377493bb2b60a9d926","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI","cs.CV","physics.ins-det"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T17:59:42Z","title_canon_sha256":"6afb4f1099c43b711fd32d024947eb5205fd26a95e58cea2febfe014dc5dc3f7"},"schema_version":"1.0","source":{"id":"2603.11045","kind":"arxiv","version":2}},"canonical_sha256":"59ebc38ef9796aceffc304ddc1eea2a6b8e6d9e0d82969106f936afabb1766aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59ebc38ef9796aceffc304ddc1eea2a6b8e6d9e0d82969106f936afabb1766aa","first_computed_at":"2026-05-17T23:39:15.807956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:15.807956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2qbKJ25sN05981bjbUNcdBM6kVASd464a9kBZeDs9nK5N0OXxBwH4U81Y23V7pUJq5wyqHZN2+aXaaF7IQA4Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:15.808625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11045","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0784e95f0962bffc99855e908371ef8a4a2708e12d6b507ed8e84d3e52ab3cb7","sha256:613f8508c46a81577f5153512701f123646ecda75fb767e8dff50cfb9062e80a"],"state_sha256":"bbdd91712479d19c385fd220b129203b99fcd8bc3fd073bc6f8fb040b8d9c415"}