# Excitation-Gated Latent Frame Calibration

- ID: 2047
- Canonical URL: https://synthcore.org/idea/2047/excitation-gated-latent-frame-calibration
- API JSON: https://synthcore.org/api/idea/2047.json
- API Markdown: https://synthcore.org/api/idea/2047.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.09464](https://arxiv.org/abs/2608.09464)
- Category: dynamics
- Solves: stability, accuracy, generalization
- ML areas: training-dynamics, rnn, ssm, world-model, regularization
- Math tags: control-theory, dynamical-systems, linear-algebra, geometry, statistics
- Ratings: usefulness 8/10; difficulty 6/10; novelty 7/10

## Idea description

Add an explicit unknown-frame variable to a recurrent world model or multimodal sensor-fusion network, and train it only on temporal windows whose latent motion provides enough excitation to identify that frame. The model should use a two-view or multi-view consistency loss and an adaptive gate based on the smallest singular value of the window Jacobian, preventing optimization from confidently fitting geometrically ambiguous trajectories.

## Mathematical statement

For observations indexed by k, let q_k be a known or predicted vehicle state, p be a shared latent target, x be an unknown relay translation, R(psi) be a two-dimensional rotation with unknown yaw psi, and ell_k^v, ell_k^t be relay-frame vehicle and target vectors. The measurement equations are q_k=x+R(psi)ell_k^v and p=x+R(psi)ell_k^t. With only one k, translation and yaw remain continuously ambiguous; with two distinct observations k=1,2, the difference q_2-q_1=R(psi)(ell_2^v-ell_1^v) identifies psi when ell_2^v is not equal to ell_1^v. In a neural model, let h_k be its predicted latent pose, y_k its relay-frame observation, and theta=(p,x,psi) latent calibration parameters. Define residual vector r_k(theta)=h_k-x-R(psi)ell_k^v and s_k(theta)=p-x-R(psi)ell_k^t. Let J_W be the Jacobian of all whitened residuals in a window W with respect to theta; the excitation score is sigma_min(J_W), or equivalently the condition number kappa(J_W)=sigma_max(J_W)/sigma_min(J_W). Training updates are downweighted or delayed when sigma_min(J_W) is below a threshold.

## Key formulas

- $$q_k=x+R(\psi)\ell_k^v,\qquad p=x+R(\psi)\ell_k^t,$$
- $$q_2-q_1=R(\psi)(\ell_2^v-\ell_1^v),\qquad \ell_2^v\neq\ell_1^v,$$
- $$J_W=\frac{\partial}{\partial\theta}\begin{bmatrix}W_1^{1/2}r_1(\theta)\\ \vdots\\ W_T^{1/2}r_T(\theta)\\ W_1^{1/2}s_1(\theta)\\ \vdots\\ W_T^{1/2}s_T(\theta)\end{bmatrix},\qquad \kappa_W=\frac{\sigma_{\max}(J_W)}{\sigma_{\min}(J_W)},$$
- $$\mathcal L=\sum_{k\in W}\rho\!\left(\|W_k^{1/2}r_k(\theta)\|^2\right)+\rho\!\left(\|W_k^{1/2}s_k(\theta)\|^2\right)+\lambda\,\max(0,\tau-\sigma_{\min}(J_W))^2,$$

## Implementation notes

1. Integration point: use a small differentiable calibration head on top of an RNN, SSM, or transformer world model. The head predicts a shared latent target p, frame translation x, yaw psi, and per-step relay-frame vectors; the backbone predicts h_k and the calibration residuals are evaluated over sliding windows of length T. 2. Pseudocode: for each window, predict h[1:T], p, x, psi; compute R from psi; form r[k]=h[k]-x-R@ell_v[k] and s[k]=p-x-R@ell_t[k]; compute robust residual loss; obtain J by autodiff or a randomized Jacobian-vector approximation; compute sigma_min; multiply the consistency loss by g=min(1,sigma_min/tau) and add the hinge penalty shown above; update network and calibration parameters jointly. 3. Computed from the paper: the residual geometry, shared-target constraint, and excitation/conditioning criterion. Estimated empirically: the Jacobian uses the current neural model, tau is selected from a calibration set, and residual covariance W is estimated from validation noise. 4. First cheap experiment: train a GRU latent dynamics model on synthetic 2-D trajectories with random unknown rotations and translations and a shared hidden landmark. Compare ordinary consistency training, random-window training, and excitation-gated training. Sweep trajectory spread and record calibration error versus sigma_min and kappa. The quantitative prediction is a sharp failure boundary: windows with kappa above roughly 100 should show substantially higher frame error and occasional divergent training, while windows with kappa below 100 should converge reliably; increasing T or trajectory spread should monotonically increase sigma_min and reduce target error.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: inconclusive
- Verdict: Built a reproducible 2-D latent-frame calibration MVP with autodiff Jacobians, singular-value excitation scoring, and gated versus ordinary consistency optimization. The mechanism manifested clearly: zero motion gave rank 4 versus rank 5 with motion, the small-motion log-log slope was 0.994 (predicted 1), and sigma_min increased monotonically from 0.501 at T=2 to 0.665 at T=8. However, the toy gated optimizer had effectively identical parameter error to baseline at every excitation level, so this is evidence for the identifiability mechanism rather than a demonstrated training improvement.

### Mechanism check

- Verdict: Built a reproducible 2-D latent-frame calibration MVP with autodiff Jacobians, singular-value excitation scoring, and gated versus ordinary consistency optimization. The mechanism manifested clearly: zero motion gave rank 4 versus rank 5 with motion, the small-motion log-log slope was 0.994 (predicted 1), and sigma_min increased monotonically from 0.501 at T=2 to 0.665 at T=8. However, the toy gated optimizer had effectively identical parameter error to baseline at every excitation level, so this is evidence for the identifiability mechanism rather than a demonstrated training improvement.
- Confidence: 8/10
- Limitations: This is a small analytic calibration experiment, not a GRU/world-model integration. The gating comparison optimizes one calibration vector rather than a learned recurrent network and does not test generalization, real sensor noise models, randomized Jacobian approximations, robust losses, or FLOP/speed tradeoffs. The gate is detached from the Jacobian in the toy optimizer, so the result does not establish end-to-end gated training benefit.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.2782
- Paired wins: 4/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/771/bench_report.json)
- [experiment.py](https://synthcore.org/code/771/experiment.py)
- [report.md](https://synthcore.org/code/771/report.md)
- [report_bench_2026-09-01T100357.md](https://synthcore.org/code/771/report_bench_2026-09-01T100357.md)
- [results.json](https://synthcore.org/code/771/results.json)
- [stage2_bench.py](https://synthcore.org/code/771/stage2_bench.py)
- [Download all files as ZIP](https://synthcore.org/download/771)

## Disclaimer

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