{
 "artifacts": null,
 "category": "regularization",
 "description": "Add a differentiable or inference-time projection to mesh and graph neural operators that contracts each predicted nodal state toward a weighted cell anchor. The anchor is the geometry-weighted mean, so the correction preserves the weighted integral exactly, while the contraction parameter is chosen to keep all nodal states inside a convex physical set such as positive density and energy or a probability simplex.",
 "formulas_latex": [
  "$$\\mathbb{W}=wW=wj_{2}\\widehat{U},\\qquad j_{2}:=\\sqrt{\\det(\\gamma_{IJ})},\\qquad \\chi:=wj_{2}.$$",
  "$$\\langle Z\\rangle_{\\chi,K}:=\\frac{\\displaystyle\\sum_{\\boldsymbol{\\ell}}\\mu_{K,\\boldsymbol{\\ell}}\\chi_{\\boldsymbol{\\ell}}Z_{\\boldsymbol{\\ell}}}{\\displaystyle\\sum_{\\boldsymbol{\\ell}}\\mu_{K,\\boldsymbol{\\ell}}\\chi_{\\boldsymbol{\\ell}}},\\qquad \\widehat{U}_{A,K}:=\\langle\\widehat{U}_{h}\\rangle_{\\chi,K}.$$",
  "$$\\sum_{\\boldsymbol{\\ell}}\\mu_{K,\\boldsymbol{\\ell}}\\chi_{\\boldsymbol{\\ell}}\\left[(P_{\\chi,K}^{r}Z)_{\\boldsymbol{\\ell}}-Z_{\\boldsymbol{\\ell}}\\right]V_{\\boldsymbol{\\ell}}=0\\quad\\forall V\\in\\mathbb{Q}_{r}(K).$$",
  "$$\\widehat{U}^{\\mathrm{new}}_{\\boldsymbol{\\ell}}=\\widehat{U}_{A,K}+\\theta_K\\left(\\widehat{U}^{\\mathrm{pred}}_{\\boldsymbol{\\ell}}-\\widehat{U}_{A,K}\\right),\\qquad 0\\leq\\theta_K\\leq1.$$"
 ],
 "id": 2819,
 "implementation": "(1) Integration point: apply this after the final output of a mesh neural operator, graph neural operator, or finite-volume surrogate on each element or local graph neighborhood, before advancing the PDE rollout. The tensor is `U_pred[K,node,channel]`; `chi[K,node]` is the positive geometry or cell-volume weight, and `mu[K,node]` is the quadrature or mass weight. (2) Pseudocode: compute `q = mu * chi`; set `U_anchor = sum(q[...,None] * U_pred, node) / sum(q, node)`; initialize `theta = 1`; for every node and every physical constraint `g(U) \u003e= 0`, find the largest scalar in `[0,1]` satisfying `g(U_anchor + theta*(U_pred-U_anchor)) \u003e= eps`; set `theta_K` to the minimum over all nodes and constraints, multiplied by a safety factor such as `0.99`; return `U_new = U_anchor + theta_K*(U_pred-U_anchor)`. For positivity constraints, bisection on theta for 10-20 iterations is sufficient. For a simplex, enforce channel nonnegativity and verify that the weighted channel sum is conserved. (3) Computed directly from the paper: the weighted anchor, the positive weights, and the conservation identity. Estimated empirically: the feasible intersection along each anchor-to-prediction line; nonlinear constraints can be checked by bisection. Detach theta initially for stable training, then test a differentiable soft minimum. (4) First experiment: train a small graph or Fourier neural operator on 1D or 2D compressible-Euler snapshots with nonuniform cell volumes. Compare no projection, an ordinary unweighted anchor, and this chi-weighted projection. Measure weighted mass and energy drift, invalid-state frequency, one-step validation error, and rollout horizon before NaNs. Success means zero invalid states, much smaller conservation drift, and a longer stable rollout at equal parameter count without harming one-step accuracy.",
 "math_summary": "The paper defines the reduced state by \\(\\mathbb{W}=wW=wj_{2}\\widehat{U}\\), where \\(\\widehat{U}\\) is the local orthonormal conservative state, \\(j_{2}=\\sqrt{\\det(\\gamma_{IJ})}\u003e0\\) is the intrinsic spatial volume factor, and \\(w\u003e0\\) is the physical reduction weight. Define \\(\\chi:=wj_{2}\\). For quadrature nodes \\(\\boldsymbol{\\ell}\\) with positive weights \\(\\mu_{K,\\boldsymbol{\\ell}}\\), equation (139) defines the weighted anchor \\(\\widehat{U}_{A,K}=\\langle\\widehat{U}_{h}\\rangle_{\\chi,K}\\). The paper identifies this anchor as a physical-constraint-preserving anchor and relies on convexity of the admissible set. We adapt the conservative scaling as \\(\\widehat{U}^{\\mathrm{new}}_{\\boldsymbol{\\ell}}=\\widehat{U}_{A,K}+\\theta_K(\\widehat{U}^{\\mathrm{pred}}_{\\boldsymbol{\\ell}}-\\widehat{U}_{A,K})\\), with \\(0\\leq\\theta_K\\leq1\\). Since the anchor is the weighted mean, the weighted integral is unchanged for every \\(\\theta_K\\): \\(\\sum_{\\boldsymbol{\\ell}}\\mu\\chi\\widehat{U}^{\\mathrm{new}}_{\\boldsymbol{\\ell}}=\\sum_{\\boldsymbol{\\ell}}\\mu\\chi\\widehat{U}^{\\mathrm{pred}}_{\\boldsymbol{\\ell}}\\). If the anchor is feasible and the contracted points are feasible, convexity preserves physical admissibility.",
 "math_tags": [
  "geometry",
  "numerical-analysis",
  "convex-analysis",
  "linear-algebra"
 ],
 "ml_areas": [
  "graph-nn",
  "training",
  "world-model",
  "loss"
 ],
 "paper": {
  "arxiv_id": "2608.29229",
  "arxiv_url": "https://arxiv.org/abs/2608.29229",
  "summary_what_math_gives_to_ml": "The paper separates geometry from local physical variables by evolving a weighted state and using a geometry-weighted mean as the admissible anchor. This suggests a transferable postprocessing layer for mesh and graph neural operators: preserve a weighted integral while contracting predicted nodal states toward a feasible anchor. Convexity makes the correction inexpensive and robust, avoiding a general nonlinear constrained optimization at every timestep. The strongest use case is autoregressive neural PDE solvers, where small positivity violations otherwise accumulate into unstable rollouts.",
  "title": "Entropy-Stable and Physical-Constraint-Preserving DGSEM for Symmetry-Reduced General-Relativistic Hydrodynamics on Stationary Spacetimes",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 4,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "stability",
  "accuracy",
  "generalization"
 ],
 "title": "Weighted Conservative Feasibility Projection",
 "url": "https://synthcore.org/idea/2819/weighted-conservative-feasibility-projection",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}