{
 "artifacts": null,
 "category": "dynamics",
 "description": "Replace an unconstrained recurrent hidden-state channel with a two-dimensional oscillator constrained to the supercritical Hopf normal form. A learned control parameter can place the channel below threshold for decaying dynamics or above threshold for sustained periodic dynamics, while the cubic term bounds the amplitude and prevents recurrent-state explosion.",
 "formulas_latex": [
  "dz/dt = (mu + i omega) z - (a + i b)|z|² z",
  "dr/dt = mu r - a r³,    dphi/dt = omega - b r²",
  "r* = 0 for mu \u003c= 0;    r* = sqrt(mu/a) for mu \u003e 0, with a \u003e 0",
  "z_(k+1) = z_k + h[(mu_k + i omega_k)z_k - (a_k + i b_k)|z_k|²z_k + B x_k]"
 ],
 "id": 2719,
 "implementation": "1. Integration point: add one or more two-dimensional oscillator channels to an RNN, state-space model, or world model. For input x_k and hidden state h_k, a small controller computes mu_k and omega_k. The real and imaginary parts of z_k are concatenated with x_k and passed to the remaining neural update. Parameterize a_k = softplus(alpha_k) + epsilon to guarantee positive saturation. 2. Pseudocode: `mu, omega = controller(x, h); a = softplus(alpha) + eps; forcing = B @ x; z = z + hstep*((mu + 1j*omega)*z - (a + 1j*b)*abs(z)**2*z + forcing); h = recurrent_core(concat(x, real(z), imag(z)))`. For large steps, use a smaller oscillator step or an implicit radial update. 3. Taken from the paper: the Hopf normal form, threshold mu = 0, condition a \u003e 0, cycle amplitude sqrt(mu/a), and radial relaxation rate 2 mu. Estimated empirically: the input-dependent controller, effective frequency, forcing scale, and discretization error. 4. First experiment: compare a vanilla GRU with this Hopf-GRU on synthetic damped sinusoids, sustained sinusoids, noisy oscillators, and regime-switching signals; then test a small ECG or motion-forecasting dataset. Sweep constant mu values through zero with a = 1 and no forcing. Measure asymptotic amplitude and radial relaxation. The falsifiable prediction is negligible amplitude for mu \u003c 0, amplitude r approximately sqrt(mu/a) for mu \u003e 0, and a log radial-error slope near -2 mu. The measured threshold and amplitude law should agree within 20 percent. Also compare hidden-state norm variance and long-horizon forecast error against the unconstrained GRU.",
 "math_summary": "The center-manifold dynamics near a supercritical Hopf bifurcation are represented by a complex state z = r exp(i phi) satisfying dz/dt = (mu + i omega)z - (a + i b)|z|²z. Here mu is the distance from the bifurcation, omega is the linear angular frequency, a is the nonlinear amplitude-saturation coefficient, and b controls the amplitude-dependent frequency shift. With a \u003e 0, the polar equations are dr/dt = mu r - a r³ and dphi/dt = omega - b r². The zero-amplitude state is stable when mu \u003c 0. When mu \u003e 0, it becomes unstable and a stable limit cycle appears at r* = sqrt(mu/a). Linearization around this cycle gives radial relaxation rate approximately 2 mu. These onset, amplitude, and decay-rate relations are the quantitative mechanisms transferred to the neural recurrent cell.",
 "math_tags": [
  "dynamical-systems",
  "bifurcations",
  "control-theory",
  "stability"
 ],
 "ml_areas": [
  "rnn",
  "ssm",
  "world-model",
  "training-dynamics"
 ],
 "paper": {
  "arxiv_id": "2608.24200",
  "arxiv_url": "https://arxiv.org/abs/2608.24200",
  "summary_what_math_gives_to_ml": "The paper presents a thermodynamically consistent reaction network with a supercritical Hopf bifurcation controlled by a chemostat concentration. Its transferable mechanism is the Hopf normal form, which produces a predictable transition from a stable fixed point to a bounded oscillation, with square-root amplitude growth above threshold and a measurable relaxation rate. This can be transferred to recurrent neural networks and state-space models by replacing unconstrained recurrent channels with explicitly saturating oscillator channels. The resulting architecture offers a falsifiable stability and long-horizon prediction mechanism rather than relying only on learned recurrent weights.",
  "title": "A Minimal Thermodynamically Consistent Chemical Oscillator",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 6,
  "usefulness": 6
 },
 "solves": [
  "stability",
  "accuracy"
 ],
 "title": "Supercritical Hopf Latent Cell",
 "url": "https://synthcore.org/idea/2719/supercritical-hopf-latent-cell",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)"
 }
}