# DreamLedger: Where to Refuse World-Model Imagination Using Execution-Settled Credit

arXiv: https://arxiv.org/abs/2608.23863 · HTML: https://mlsanity.com/paper/2608.23863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 16 of its 46 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 16 of 16)

- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment](https://mlsanity.com/paper/2502.01828/) (2025)
- [When to Trust Imagination: Adaptive Action Execution for World Action Models](https://mlsanity.com/paper/2605.06222/) (2026)
- [Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots](https://mlsanity.com/paper/2504.16680/) (2025)
- [World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty](https://mlsanity.com/paper/2512.05927/) (2025)
- [Self-Evolving World Models for LLM Agent Planning](https://mlsanity.com/paper/2606.30639/) (2026)
- [Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models](https://mlsanity.com/paper/2604.25416/) (2026)
- [World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications](https://mlsanity.com/paper/2606.00133/) (2026)
- [Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation](https://mlsanity.com/paper/2606.14188/) (2026)
- [Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling](https://mlsanity.com/paper/2607.27511/) (2026)
- [Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators](https://mlsanity.com/paper/2607.07196/) (2026)
- [Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation](https://mlsanity.com/paper/2607.28226/) (2026)
- [ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC](https://mlsanity.com/paper/2605.04709/) (2026)
- [Conformal Orbit-Valid Trust Horizons for Equivariant World Models](https://mlsanity.com/paper/2606.24946/) (2026)
- [When to Personalize Household Object Search: A Rigidity-Gated Hybrid Policy](https://mlsanity.com/paper/2607.00022/) (2026)
- [Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL](https://mlsanity.com/paper/2607.16591/) (2026)

## Abstract (arXiv)

World-model predictions inform robot actions, yet instantaneous reliability signals do not retain the outcomes of comparable past predictions. DreamLedger registers consumed predictions as claims, settles them against execution outcomes, and uses persistent execution history from comparable operating conditions, regions, and prediction horizons to estimate credit before future reliance. Replayable records connect each decision to its supporting evidence and eventual outcome. In ten-seed navigation comparisons at matched refusal volume, removing history features or resetting history increases burn rate, measured as failures per consumed prediction. An independent ten-seed manipulation replication at matched refusal volume finds that, relative to random refusal, DreamLedger lowers burn rate by 4.8 percentage points (95% CI: 0.8-8.7) and uses fewer probes. Randomized audits directly measure higher failure rates among denied candidates, and post-warmup shifts isolate the contribution of newly accumulated settlements. Franka experiments establish online deployment through replay of all 1,062 prediction uses and demonstrate a prospective gate transition: new failures lower previously high credit below a frozen threshold, triggering refusal before the next action. Task completion and verification cost characterize the trade-offs of these interventions.