# Lipschitz-Inflated Conformal Trajectory Tube

- ID: 2834
- Canonical URL: https://synthcore.org/idea/2834/lipschitz-inflated-conformal-trajectory-tube
- API JSON: https://synthcore.org/api/idea/2834.json
- API Markdown: https://synthcore.org/api/idea/2834.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.29559](https://arxiv.org/abs/2608.29559)
- Category: sampling
- Solves: stability, accuracy, generalization
- ML areas: ssm, rnn, world-model
- Math tags: probability, statistics, dynamical-systems
- Ratings: usefulness 8/10; difficulty 4/10; novelty 7/10

## Idea description

Wrap a neural ODE, recurrent state-space model, or learned world model with a split-conformal prediction tube that is valid between irregularly sampled observations. Calibrate a pointwise residual quantile at observed times and inflate it at an unobserved time according to its distance from the nearest observed time and an estimated bound on the true and predicted trajectory slopes.

## Mathematical statement

Let X:[0,T*] -> R^d be the true trajectory, X_hat(t) the neural predictor, and T_i={t_i1,...,t_iNi} sampled times. Define L_i^cont=sup_{s != t} ||X_i(t)-X_i(s)||/|t-s| and let L_hat upper-bound the test trajectory constant with probability at least 1-alpha_L. For calibration trajectory i, define S_i=max_j ||X_i(t_ij)-X_hat_i(t_ij)|| and let q_(1-alpha) be its split-conformal quantile. If L_hat_pred bounds the predictor slope, the triangle inequality gives ||X(t)-X_hat(t)|| <= q_(1-alpha)+(L_hat+L_hat_pred) delta(t), where delta(t)=min_j |t-t_j|. The resulting tube has approximate failure probability at most alpha+alpha_L, subject to the paper's calibration split and coverage assumptions.

## Key formulas

- $$L_i^{\mathrm{cont}}=\sup_{s,t\in[0,T^*],\,s\neq t}\frac{\|X_i(t)-X_i(s)\|}{|t-s|},\qquad \mathbb P\left(L_{m+1}^{\mathrm{cont}}\le \widehat L\right)\ge 1-\alpha_L.$$
- $$S_i=\max_{j=1,\ldots,N_i}\left\|X_i(t_{ij})-\widehat X_i(t_{ij})\right\|,\qquad q_{1-\alpha}=\operatorname{Quantile}_{\lceil(m+1)(1-\alpha)\rceil}(S_1,\ldots,S_m).$$
- $$\|X(t)-\widehat X(t)\|\le q_{1-\alpha}+\left(\widehat L+\widehat L_{\mathrm{pred}}\right)\delta(t),\qquad \delta(t)=\min_j|t-t_j|.$$
- $$\mathcal C(t)=\left\{y\in\mathbb R^d:\|y-\widehat X(t)\|\le q_{1-\alpha}+\Gamma\delta(t)\right\},\qquad \Gamma=\widehat L+\widehat L_{\mathrm{pred}}.$$

## Implementation notes

Integrate this as an inference-time wrapper around a neural ODE, latent SSM, GRU, or world model. The base model receives irregular observations and produces a continuous prediction function X_hat(t); do not change its weights initially. Split trajectories into training and calibration sets. For every calibration trajectory, evaluate the model at its observed times, compute S_i=max_j ||X_i(t_ij)-X_hat_i(t_ij)||, and store the finite-sample conformal quantile q. Estimate L_hat from a separate high-frequency calibration set by computing the maximum finite-difference slope of the true trajectories, optionally applying a safety multiplier. Estimate L_hat_pred from dense solver evaluations of the neural predictor. At inference, for any requested time t, compute delta(t), the distance to the nearest observed input time, and return center X_hat(t) with radius q+(L_hat+L_hat_pred)delta(t). Pseudocode is: q=conformal_quantile(S); Gamma=L_hat+L_pred_hat; delta=min(abs(t-T_obs)); radius=q+Gamma*delta. The first cheap experiment is a GRU or neural ODE on noisy pendulum trajectories with randomly deleted observation times, comparing pointwise intervals against this tube. The quantitative prediction is dense-grid empirical coverage near 1-alpha-alpha_L, up to finite-sample slack, and approximately linear median radius growth with delta, with fitted slope near Gamma. Artificially using a sublinear gap inflation should cause coverage failures at the largest gaps.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: no_effect
- Verdict: Built a readable Lipschitz-inflated split-conformal trajectory-tube wrapper and numerical verifier. The triangle-inequality bound had zero measured violation, radius slope matched the predicted Gamma (0.9210526) to numerical precision, and the conditional coverage transition occurred exactly at multiplier 1.0; a 0.75 multiplier failed immediately after the largest observation gap. Marginal coverage at the estimated slope quantile was 0.988 versus the predicted slope-event coverage of 0.9, showing the mechanism but also conservatism from the grid/test construction.

### Mechanism check

- Verdict: Built a readable Lipschitz-inflated split-conformal trajectory-tube wrapper and numerical verifier. The triangle-inequality bound had zero measured violation, radius slope matched the predicted Gamma (0.9210526) to numerical precision, and the conditional coverage transition occurred exactly at multiplier 1.0; a 0.75 multiplier failed immediately after the largest observation gap. Marginal coverage at the estimated slope quantile was 0.988 versus the predicted slope-event coverage of 0.9, showing the mechanism but also conservatism from the grid/test construction.
- Confidence: 8/10
- Limitations: This was a deterministic synthetic piecewise-linear toy study with a zero predictor, scalar trajectories, and no neural ODE/GRU training or noisy pendulum experiment. It did not test finite-sample behavior across many independent calibration splits, predictor slope estimation error, multidimensional norms, or irregular observation processes beyond the fixed sparse grid.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 1
- Paired wins: 0/8
- Benchmark verdict: no measurable effect

## Artifacts

- [bench_lipschitz_dynamics.py](https://synthcore.org/code/1067/bench_lipschitz_dynamics.py)
- [bench_report.json](https://synthcore.org/code/1067/bench_report.json)
- [report.md](https://synthcore.org/code/1067/report.md)
- [report_bench_2026-09-01T233554.md](https://synthcore.org/code/1067/report_bench_2026-09-01T233554.md)
- [run_experiment.py](https://synthcore.org/code/1067/run_experiment.py)
- [trajectory_tube.py](https://synthcore.org/code/1067/trajectory_tube.py)
- [Download all files as ZIP](https://synthcore.org/download/1067)

## Disclaimer

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