{
 "artifacts": null,
 "category": "dynamics",
 "description": "Construct a graph-based latent state whose velocities evolve through free-flight updates and pairwise elastic collision operators. Each collision operator is orthogonal, so total latent kinetic energy is exactly conserved; a connected interaction graph is intended to eliminate unwanted component-wise polynomial invariants and improve long-horizon stability.",
 "formulas_latex": [
  "$$\\dot q=p,\\qquad \\dot p=0,\\qquad f(q+tp,p)=f(q,p)$$",
  "$$R_n p=p-2\\langle p,n\\rangle n,\\qquad R_n^{\\mathsf T}R_n=I$$",
  "$$H(p)=\\frac12\\|p\\|^2,\\qquad H(R_n p)=H(p)$$",
  "$$\\text{connected collision graph}\\ \\Longrightarrow\\ \\text{polynomial first integrals}=\\{P(H):P\\in\\mathbb R[x]\\}$$"
 ],
 "id": 2846,
 "implementation": "1. Integration point: use this as the transition operator of a graph neural state-space model or world model. Split the latent state into positions \\(q_i\\), velocities \\(p_i\\), and unconstrained content variables \\(c_i\\). Decode observations from \\((q,p,c)\\), but update \\((q,p)\\) with the structured dynamics. For each edge \\((i,j)\\), generate a normalized learned interaction direction \\(n_{ij}=u_{ij}/(\\|u_{ij}\\|+\\epsilon)\\), and apply a Householder reflection or a two-node orthogonal rotation to the relative velocity. 2. Pseudocode: initialize \\(q,p,c\\); at every step set \\(q\\leftarrow q+\\Delta t p\\); compute edge directions and gates; for every active edge construct \\(R_{ij}=I-2n_{ij}n_{ij}^{\\mathsf T}\\) in the affected relative-velocity subspace and set \\(p\\leftarrow R_{ij}p\\); update \\(c\\) with an ordinary message-passing block; decode the target. Optionally add \\(L_E=|H_t-H_0|^2\\) only to measure numerical error, not to replace exact orthogonality. 3. Computed from the paper: free-flight invariance, reflection orthogonality, and the connected-graph rigidity prediction. Estimated empirically: interaction directions, edge activation, and graph connectivity. To test invariant collapse, collect many latent trajectories and fit every monomial in \\((q,p)\\) up to degree four to conserved quantities; regress each candidate against \\(1,H,H^2\\). 4. First cheap experiment: train a 4- or 8-node model on synthetic elastic-collision trajectories, comparing an MLP transition, an unconstrained GNN, and this orthogonal-collision model. Measure 500-step rollout error, energy drift, Jacobian spectral growth, and the residual dimension of the fitted polynomial invariant space. The quantitative prediction is machine-precision energy conservation for the structured model and bounded energy over arbitrarily long rollouts. In a connected graph, no independent degree-two invariant beyond \\(H\\) should remain; after removing one edge to create two components, two independent component energies should appear.",
 "math_summary": "The paper uses free flight \\(\\dot q=p\\), \\(\\dot p=0\\), implying the first-integral equation \\(f(q+tp,p)=f(q,p)\\) whenever the segment remains in the free region. At a collision with unit normal \\(n\\), momentum changes by the orthogonal reflection \\(R_n p=p-2\\langle p,n\\rangle n\\), which preserves \\(H(p)=\\frac12\\|p\\|^2\\). For hard balls with connected collision graph, every polynomial-in-momentum first integral is \\(P(H)\\), with \\(P\\) a scalar polynomial. Transfer this by representing node \\(i\\) with latent position \\(q_i\\in\\mathbb R^d\\) and velocity \\(p_i\\in\\mathbb R^d\\), using free drift \\(q_i^+=q_i+\\Delta t p_i\\), and applying pairwise orthogonal operators \\(p^+=R_{ij}p\\). The conserved latent energy is \\(H(z)=\\frac12\\sum_i\\|p_i\\|^2\\). Exact orthogonality gives \\(H(z^+)=H(z)\\), while graph connectivity predicts collapse of low-degree invariant searches to polynomials in \\(H\\).",
 "math_tags": [
  "dynamical-systems",
  "linear-algebra",
  "graph-theory",
  "control-theory"
 ],
 "ml_areas": [
  "world-model",
  "ssm",
  "graph-nn",
  "regularization"
 ],
 "paper": {
  "arxiv_id": "2608.29694",
  "arxiv_url": "https://arxiv.org/abs/2608.29694",
  "summary_what_math_gives_to_ml": "The paper proves a rigidity mechanism for billiard and hard-ball dynamics: free flight forces polynomial first integrals to be position-independent, while elastic collisions restrict momentum dependence through reflection symmetries. For a hard-ball gas with connected collision graph, every polynomial-in-momentum first integral is a polynomial of total kinetic energy, so no additional polynomial conserved quantities survive. A transferable neural construction is an energy-preserving graph latent dynamics model in which propagation is unconstrained between events but pairwise interactions are orthogonal reflections or rotations. The sharp prediction is that connected interaction graphs retain only functions of total latent kinetic energy as low-degree polynomial invariants, while disconnected graphs retain one energy invariant per connected component.",
  "title": "First integrals of dense hard-ball gases",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 6,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "stability",
  "generalization",
  "accuracy"
 ],
 "title": "Connected Collision Energy Latent Dynamics",
 "url": "https://synthcore.org/idea/2846/connected-collision-energy-latent-dynamics",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}