# Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception

arXiv: https://arxiv.org/abs/2607.01537 · HTML: https://mlsanity.com/paper/2607.01537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 8 of its 8 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 8 of 8)

- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2606.13053/) (2026)
- [Certified World Models: Predictability Across Configuration, Horizon, and Resolution](https://mlsanity.com/paper/2606.13092/) (2026)
- [Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation](https://mlsanity.com/paper/2606.14188/) (2026)
- [Deterministic World Models for Closed-loop Reachability Analysis of End-to-End Vision-based Control](https://mlsanity.com/paper/2512.08991/) (2025)
- [Measurement Simplification in ρ-POMDP with Performance Guarantees](https://mlsanity.com/paper/2309.10701/) (2023)
- [Information-Driven Active Perception for k-step Predictive Safety Monitoring](https://mlsanity.com/paper/2603.23450/) (2026)
- [Belief-Space Control for Personalized Cancer Treatment via Active Inference](https://mlsanity.com/paper/2606.10376/) (2026)

## Built on by (most cited first, 1 of 1)

- [TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views](https://mlsanity.com/paper/2607.21910/) (2026)

## Abstract (arXiv)

Certified world models estimate how long their predictions remain valid. We turn this validity horizon into an operational sensing clock: a rule for when an agent should stop coasting and re-sense. Starting from an audited equivariant world model, we derive a deadline for no-sensing intervals and show that deployable deadlines in learned world models must be drift-aware: on-manifold Lyapunov rates alone overestimate coasting validity, while calibrated native rollout-drift envelopes carry the deployed guarantee. On a frozen 3D VN-JEPA model, the resulting clock controls held-out interval-simultaneous certificate violation across seeds and data shards. In a cue-conditioned theorem-bed (a synthetic bench where all schedulers share the exact model, isolating the scheduling rule), the clock remains valid on the deployment distribution and substantially reduces eventful-tail violations relative to exact-mixture expected-belief scheduling at matched sensing budget. We also report limits: in the short-horizon frozen VN-JEPA regime, empirical conformal horizons match the deployed clock on validity and budget, and a partial-reset exploration finds no clean budget-matched advantage for the spectral term. Thus the contribution is a certified sensing-clock primitive and drift-aware deployment method, not a claim that spectral clocks empirically dominate all non-spectral schedulers.