# Did the Grid Erase the Event? EndoClock for Auditing Medical World-Model Pipelines

arXiv: https://arxiv.org/abs/2608.09266 · HTML: https://mlsanity.com/paper/2608.09266/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and surgical world models, one of 11 directions in World models.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Placed in

- World models / [Medical and surgical world models](https://mlsanity.com/wm/medical-and-surgical-world-models/)

## Builds on (most cited first, 12 of 12)

- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Learning from Irregularly-Sampled Time Series: A Missing Data Perspective](https://mlsanity.com/paper/2008.07599/) (2020)
- [Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis](https://mlsanity.com/paper/2303.12644/) (2023)
- [Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects](https://mlsanity.com/paper/2311.02332/) (2023)
- [Causal Discovery from Subsampled Time Series Data by Constraint Optimization](https://mlsanity.com/paper/1602.07970/) (2016)
- [CoReEcho: Continuous Representation Learning for 2D+time Echocardiography Analysis](https://mlsanity.com/paper/2403.10164/) (2024)
- [MRI Contrast Enhancement Kinetics World Model](https://mlsanity.com/paper/2602.19285/) (2026)

## Abstract (arXiv)

Medical world models commonly learn from multimodal recordings synchronized onto a fixed-rate grid. This preprocessing resamples each native stream onto a shared time axis. Each stream has an observation clock that governs when observations are emitted or updated. When this clock depends on the latent or acquisition state, it is endogenous. In such settings, synchronization may not be neutral and can erase task-relevant evidence before the model sees the data. We introduce a four-regime taxonomy that characterizes where the evidence needed to distinguish a target event or state survives. The relevant witness may remain in the sampled values, in grid-cell update patterns, in native timing, or only in an external acquisition channel. EndoClock operationalizes this taxonomy as a conservative pretraining audit. It reports the lowest witness-bearing representation supported by the available evidence, or unresolved when no regime can be established. We illustrate this failure in echocardiography, where B-mode video write-outs cease during pulsed-wave Doppler acquisition while the corresponding measurement events remain recorded only in an external acquisition log. This work is a preliminary failure alert and executable audit. Its practical message is to preserve the native observation process long enough to determine whether synchronization has erased information required by the intended task.