# Hysteretic Multiscale Sequence Router

- ID: 1111
- Canonical URL: https://synthcore.org/idea/1111/hysteretic-multiscale-sequence-router
- API JSON: https://synthcore.org/api/idea/1111.json
- API Markdown: https://synthcore.org/api/idea/1111.md
- Verification status: failed_benchmark
- Source: [arXiv:2607.18439](https://arxiv.org/abs/2607.18439)
- Category: dynamics
- Solves: stability, accuracy, memory
- ML areas: rnn, ssm, world-model, training-dynamics
- Math tags: dynamical-systems, control-theory, bifurcations, optimization
- Ratings: usefulness 7/10; difficulty 5/10; novelty 6/10

## Idea description

Insert a slow routing state and an intermediate hysteresis variable between a neural memory and its next-state selector. The hysteresis prevents small prediction fluctuations from repeatedly changing the active attractor, while the slower router learns transition probabilities independently of the attractor parameters.

## Mathematical statement

Let \(x\) be the fast attractor state, \(h\) the intermediate hysteresis state, and \(r\) the slow routing state. Use \(\tau_x\dot x=f_a(x)\), \(\tau_h\dot h=\sigma(g(r,x))-h\), and \(\tau_r\dot r=F(r,u)\), with \(\tau_x\ll\tau_h\ll\tau_r\), where \(a\) is the active memory index, \(u\) is the input, and \(\sigma\) is a bounded sigmoid. Switch from memory \(a\) to candidate \(b\) only when \(h_b\geq\eta_{\mathrm{on}}\), and retain \(b\) until its score drops below \(\eta_{\mathrm{off}}\), with \(\eta_{\mathrm{on}}>\eta_{\mathrm{off}}\). The hysteresis width \(\Delta\eta=\eta_{\mathrm{on}}-\eta_{\mathrm{off}}\) gives an anti-chattering margin. If the score derivative is bounded by \(|\dot h_b|\leq L_h\), a transition requiring traversal of the hysteresis band has dwell time at least \(\Delta\eta/L_h\).

## Key formulas

- $$\tau_x\dot x=f_a(x),\qquad \tau_h\dot h=\sigma(g(r,x))-h,\qquad \tau_r\dot r=F(r,u),\qquad \tau_x\ll\tau_h\ll\tau_r.$$
- $$a\to b\ \text{only if}\ h_b\geq\eta_{\mathrm{on}},\qquad b\to a\ \text{is forbidden until}\ h_b\leq\eta_{\mathrm{off}},\qquad \eta_{\mathrm{on}}>\eta_{\mathrm{off}}.$$
- $$T_{\mathrm{dwell}}\geq\frac{\eta_{\mathrm{on}}-\eta_{\mathrm{off}}}{L_h},\qquad L_h\geq\sup_t|\dot h_b(t)|.$$

## Implementation notes

Integration point: use this module as the transition controller in a recurrent language model, latent world model, or regime-switching state-space model. The fast state x is the active attractor representation, r is a GRU-like slow context state, and h is a vector of leaky transition scores. Pseudocode: update r once every M fast steps using r += dt/tau_r*F(r,u); compute candidate scores s=softmax(Linear([r,x])); update h += dt/tau_h*(s-h); retain the current index a unless h[b] exceeds eta_on; after switching, forbid another switch until the active score falls below eta_off. Backpropagate through the leaky updates and use a straight-through estimator only for the discrete index if needed. Add a penalty for switches before the target dwell time. Timescales, thresholds, and the theoretical dwell bound are explicit; estimate L_h from the maximum or high quantile of observed finite-difference derivatives of h, multiplied by a safety factor. First experiment: train a four-regime synthetic sequence predictor with noisy regime-specific dynamics. Compare a GRU, soft attention routing, and the hysteretic router at matched parameter count. Sweep Delta eta and tau_h/tau_x. The prediction is that switch count decreases sharply when Delta eta exceeds score-noise amplitude, and measured minimum dwell time should be at least Delta eta/L_h up to discretization error.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: no_effect
- Verdict: Built a NumPy hysteretic router MVP with reproducible sweeps. Measured dwell times matched Delta_eta/L within 0.13%, chattering disappeared when the hysteresis width reached the score excursion threshold, and the slow-state RMS gain matched the analytic low-pass prediction within 0.14%. In the controlled regime toy, hysteretic routing reduced MSE from 0.004744 to 0.002220 and reduced route changes from 321 to 207, so the proposed mechanism manifested clearly.

### Mechanism check

- Verdict: Built a NumPy hysteretic router MVP with reproducible sweeps. Measured dwell times matched Delta_eta/L within 0.13%, chattering disappeared when the hysteresis width reached the score excursion threshold, and the slow-state RMS gain matched the analytic low-pass prediction within 0.14%. In the controlled regime toy, hysteretic routing reduced MSE from 0.004744 to 0.002220 and reduced route changes from 321 to 207, so the proposed mechanism manifested clearly.
- Confidence: 9/10
- Limitations: The comparison is a deterministic NumPy toy rather than a trained GRU or matched-parameter four-regime predictor. It does not test backpropagation, learned slow routing, GPU behavior, long-horizon language modeling, or robustness across random seeds.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.7749
- Paired wins: 3/8
- Benchmark verdict: no measurable effect

## Artifacts

- [bench_hysteretic.py](https://synthcore.org/code/442/bench_hysteretic.py)
- [bench_report.json](https://synthcore.org/code/442/bench_report.json)
- [report.md](https://synthcore.org/code/442/report.md)
- [report_bench_2026-08-31T121847.md](https://synthcore.org/code/442/report_bench_2026-08-31T121847.md)
- [results.json](https://synthcore.org/code/442/results.json)
- [verify_router.py](https://synthcore.org/code/442/verify_router.py)
- [Download all files as ZIP](https://synthcore.org/download/442)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.