{
 "artifacts": null,
 "category": "architecture",
 "description": "Use cumulative control measures as the input to a neural surrogate instead of the full sequence of control values. For a quasi-static free-boundary system satisfying the paper's average-pressure path-independence assumption, two nonnegative control histories with identical integrals up to time t should produce the same state at t, allowing a smaller training input and fewer distinct control trajectories in the dataset.",
 "formulas_latex": [
  "$$\\int_{0}^{t}a(\\tau)\\,d\\tau=\\int_{0}^{t}b(\\tau)\\,d\\tau \\quad\\Longrightarrow\\quad \\Omega_a(t)=\\Omega_b(t),$$",
  "$$u_j(t)=\\int_0^t p_j(\\tau)\\,d\\tau,\\qquad u(t)=(u_1(t),\\ldots,u_{n_g}(t)),$$",
  "$$\\widehat{x}(t)=F_\\theta\\bigl(u(t),t,c\\bigr),\\qquad \\mathcal{L}(\\theta)=\\sum_k\\left\\|F_\\theta(u_k,t_k,c_k)-x_k\\right\\|^2,$$",
  "$$\\mathcal{L}_{\\mathrm{pc}}=\\left\\|F_\\theta\\!\\left(\\int_0^t p^{(1)}(\\tau)d\\tau,t,c\\right)-F_\\theta\\!\\left(\\int_0^t p^{(2)}(\\tau)d\\tau,t,c\\right)\\right\\|^2,$$"
 ],
 "id": 2832,
 "implementation": "(1) Exact integration point: modify the control-input encoder of a neural surrogate that predicts a spatial state, flow-front mask, saturation field, or terminal completion time. Instead of passing a sequence of gate pressures p[batch,time,gate] through an RNN or Transformer, compute a cumulative trapezoidal integral u[batch,time,gate] and pass u[:,t,:], elapsed time, and static geometry/material features c to an MLP, Fourier-feature MLP, or spatial decoder. Keep the raw sequence available only for the baseline and for detecting violations of the theorem's assumptions.\n\n(2) Pseudocode:\n```python\n# p: [B,T,G], time: [T], static_features: c\nu = torch.zeros_like(p)\nu[:,1:] = torch.cumsum(\n    0.5 * (p[:,1:] + p[:,:-1]) * (time[1:] - time[:-1])[None,:,None], dim=1)\nfor k in range(T):\n    pred[:,k] = surrogate(u[:,k], time[k], c)\nloss = mse(pred, target)\n# optional path-consistency augmentation\nu1 = integrate(p1, time); u2 = integrate(p2, time)\nloss += lam_pc * mse(surrogate(u1[:,k], time[k], c),\n                     surrogate(u2[:,k], time[k], c))\n```\nThe integral in the code is the paper's u_j(t)=\\int_0^t p_j(\\tau)d\\tau; equality of cumulative vectors is used to create paired trajectories with the same target.\n\n(3) Computed from the mathematics: cumulative gate pressure, componentwise equality or distance of cumulative controls, and the path-consistency pairing rule. Estimated empirically: whether equal-integral trajectories actually yield equal states in the dataset, the penalty weight \\lambda_pc, and any residual dependence on pressure ordering. Include non-quasi-static cases, pressure bounds, and abrupt controls to measure theorem mismatch.\n\n(4) First cheap experiment: train on a small 2-D Darcy/free-boundary simulator or an RTM-style synthetic dataset with 2--4 gates. Compare a raw-control Transformer or RNN, a cumulative-control MLP, and a cumulative-plus-raw hybrid at equal parameter count and simulator-data budget. Evaluate front IoU or node saturation error at every time, terminal unfilled-node count, wall-clock training time, and accuracy under unseen pressure waveforms having the same cumulative integral as training waveforms. Success is a 2x reduction in surrogate input-side FLOPs or training time at matched error, improved interpolation across control schedules, and low paired-trajectory error; failure is significant prediction dependence on waveform ordering despite matched integrals.",
 "math_summary": "Theorem 1, Average-pressure path-independence, assumes a bounded Lipschitz domain D, a measurable essentially bounded permeability tensor K:D\\to\\mathbb{R}^{d\\times d} that is uniformly positive definite, constant viscosity \\mu\u003e0 and porosity \\phi\u003e0, and nonnegative gate-pressure histories a,b\\in L^1(0,T;\\mathbb{R}_+^{n_g}) driving the quasi-static Darcy filling problem. Its key premise is $$\\int_0^t a(\\tau)\\,d\\tau=\\int_0^t b(\\tau)\\,d\\tau,$$ componentwise for every gate, under which the corresponding filled regions satisfy \\Omega_a(t)=\\Omega_b(t). Here a(t),b(t)\\in\\mathbb{R}^{n_g} are gate-pressure vectors, n_g is the number of gates, t is elapsed time, and \\Omega_a(t),\\Omega_b(t) are the resin-filled subsets of D. Define the cumulative-control state u(t):=\\int_0^t p(\\tau)d\\tau\\in\\mathbb{R}^{n_g}; the neural surrogate should therefore approximate x(t)=F(u(t),t,c), where c contains static geometry and material features, instead of x(t)=F(p(0:t),t,c). The exact theorem requires the quasi-static Darcy/free-boundary assumptions; outside that regime, cumulative control is a testable inductive bias rather than a guarantee.",
 "math_tags": [
  "pde",
  "control-theory",
  "dynamical-systems",
  "measure-theory"
 ],
 "ml_areas": [
  "mlp",
  "transformer",
  "training",
  "data-augmentation"
 ],
 "paper": {
  "arxiv_id": "2608.29521",
  "arxiv_url": "https://arxiv.org/abs/2608.29521",
  "summary_what_math_gives_to_ml": "The paper contains a constructive reduction for learning controlled free-boundary dynamics: under quasi-static Darcy filling, the filled region at a fixed time depends on the cumulative, rather than pointwise, gate-pressure history. This converts a high-dimensional time-dependent control input into a lower-dimensional path descriptor and can simplify surrogate-model training, especially when controls are piecewise constant or rapidly varying. The transferable asset is the exact sufficient-statistic construction: replace a control trajectory by its time integral and test whether the resulting representation preserves the network target. This is best implemented as an integral-control encoder or cumulative-control tokens, with an explicit ablation against raw time-series conditioning.",
  "title": "Online Gate-Driven Flow Control in Resin Transfer Moulding Using a Neural-Network Surrogate",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 4,
  "novelty": 8,
  "usefulness": 6
 },
 "solves": [
  "speedup",
  "sample-efficiency",
  "scalability"
 ],
 "title": "Cumulative-Control Surrogate Encoder",
 "url": "https://synthcore.org/idea/2832/cumulative-control-surrogate-encoder",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}