{
 "artifacts": null,
 "category": "theory",
 "description": "Train an encoder-decoder world model together with a latent transition map, but certify latent attractors only when the learned model is approximately semiconjugate to the observed high-dimensional dynamics with residual below the isolating-set margin. Compute a Conley-Morse graph on a latent grid and lift each certified recurrent component through the decoder to obtain a region in the original state space where an attractor or invariant set is predicted to exist.",
 "download_zip": "https://synthcore.org/download/1155",
 "formulas_latex": [
  "ε = sup{x in X} d_Z(g(E(x)), E(f(x)))",
  "E∘f = g∘E for exact semiconjugacy, and d_Z(g(E(x)), E(f(x))) ≤ ε for approximate semiconjugacy",
  "ε_test = max{x in validation set V} d_Z(g(E(x)), E(f(x))); accept a certificate only if ε_test + δ_conf \u003c μ(N)",
  "A_hat_X = D(A_Z) or E⁻¹(A_Z), where A_Z is a terminal strongly connected component of the latent transition graph"
 ],
 "id": 3010,
 "implementation": "Integrate this as a certification branch around a standard autoencoder world model. Use an encoder E_theta, decoder D_phi, and latent transition g_psi. Train with reconstruction loss, one-step prediction loss, and a semiconjugacy penalty. For each batch containing consecutive states x_t and x_next, compute z_t = E_theta(x_t), z_next = E_theta(x_next), z_pred = g_psi(z_t), and residual r = norm(z_pred - z_next). Optimize L = L_reconstruction + lambda_pred times L_prediction + lambda_sc times r squared. After training, tile the latent region visited by validation trajectories into cells Q_i. For each cell, propagate interval samples or an ensemble through g_psi, enlarge the image by the empirical residual bound epsilon_test, and add encoder or model uncertainty if available. Create an edge Q_i to Q_j whenever the padded image intersects Q_j. Find terminal strongly connected components and estimate the isolating margin mu as the smallest distance from any padded image to a forbidden cell boundary. The paper supplies the approximate-semiconjugacy and combinatorial-topological lifting mechanism; residual confidence bounds, interval propagation, and finite-cell margins are engineering estimates. The first cheap experiment should use a Duffing oscillator or Lorenz system with known multiple attractors, embedded into 20-dimensional observations by a smooth random map. Compare an ordinary autoencoder world model with the semiconjugacy-regularized model. Sweep observation noise and training duration. The falsifiable prediction is a sharp certification transition near (epsilon_test + delta_conf) divided by mu equal to 1: below this value, the recovered number of attractors and basin assignments should remain correct; above it, certificates should fail or become unreliable.",
 "math_summary": "Let X be the high-dimensional state space, Z the latent space, f:X→X the true discrete-time evolution, E:X→Z an encoder, D:Z→X a decoder, and g:Z→Z the learned latent evolution. Exact semiconjugacy satisfies E∘f = g∘E. The paper replaces this with the uniform residual ε = sup over x in X of d_Z(g(E(x)), E(f(x))). A Conley-Morse computation partitions Z into cells Q_i and constructs a directed graph of cell transitions under g, including uncertainty padding. A strongly connected component with no outgoing edges is a candidate isolated invariant component. For an isolating neighborhood N in Z, define its robustness margin μ(N) as the minimum distance from the nominal image g(N) to a transition boundary excluded from the Conley graph. The transferable condition is ε \u003c μ(N): perturbations induced by the encoded true dynamics cannot cross the certified combinatorial boundaries, so the invariant-set or attractor conclusion represented by the graph persists for the original dynamics in E⁻¹(N), subject to compactness and approximation assumptions. In implementation, ε is estimated by a held-out maximum or high quantile and μ is estimated from interval-cell distances.",
 "math_tags": [
  "dynamical-systems",
  "control-theory",
  "geometry",
  "numerical-analysis",
  "topology"
 ],
 "ml_areas": [
  "world-model",
  "autoencoder",
  "regularization",
  "training-dynamics"
 ],
 "paper": {
  "arxiv_id": "2609.01509",
  "arxiv_url": "https://arxiv.org/abs/2609.01509",
  "summary_what_math_gives_to_ml": "The paper provides a rigorous mechanism for transferring combinatorial-topological information from a learned low-dimensional latent dynamics model back to a high-dimensional system. Its key condition is approximate semiconjugacy: the encoded true evolution and the latent model must disagree by a uniformly bounded residual, rather than commute exactly. When this residual is smaller than the isolating-neighborhood margin used by a Conley-Morse graph, latent invariant-set and attractor conclusions can be lifted to regions of the original state space. The most promising neural-network use is a topology-aware world-model training and monitoring procedure that penalizes semiconjugacy residuals and refuses to trust latent attractor claims when the residual exceeds a computable certification margin.",
  "title": "Characterizing High-dimensional Dynamics by Combinatorial-Topological Methods on a Latent Space",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 7,
  "novelty": 8,
  "usefulness": 8
 },
 "solves": [
  "stability",
  "accuracy",
  "generalization"
 ],
 "title": "Conley-Certified Latent World Model",
 "url": "https://synthcore.org/idea/3010/conley-certified-latent-world-model",
 "verification": {
  "peer_reviewed": false,
  "status": "queued_mechanism",
  "status_label": "Queued — mechanism check",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)",
  "verification_axes": {
   "benchmark_mechanism": {
    "confirmed": null,
    "tested": false
   },
   "practical_benchmark": {
    "beats_baseline": null,
    "tested": false
   },
   "toy_mechanism_gate": {
    "confirmed": null,
    "tested": false
   }
  }
 }
}