# Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails

arXiv: https://arxiv.org/abs/2608.14952 · HTML: https://mlsanity.com/paper/2608.14952/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 9 of 9)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022)
- [SoilingNet: Soiling Detection on Automotive Surround-View Cameras](https://mlsanity.com/paper/1905.01492/) (2019)
- [IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research](https://mlsanity.com/paper/2104.13620/) (2021)
- [Self-Supervised Moving Vehicle Detection from Audio-Visual Cues](https://mlsanity.com/paper/2201.12771/) (2022)
- [MVD:A Novel Methodology and Dataset for Acoustic Vehicle Type Classification](https://mlsanity.com/paper/2309.03544/) (2023)

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

- [Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving](https://mlsanity.com/paper/2608.26074/) (2026)

## Abstract (arXiv)

A structured world-state (entities, relations, context, and predictive cues) is designed to preserve prediction-critical content when perception degrades, but it presumes observations to populate it; when the primary visual modality is occluded or degraded, those observations may be missing. We address how to sustain the world model from a complementary modality by treating the absence of expected co-evidence as evidence of a hidden cause. The abductive framework is modality-agnostic; this article instantiates it acoustically. A microphone-array front-end estimates the bearing of engine and tire sources and extracts approach-rate evidence (Doppler when a stable tone exists, a broadband looming readout otherwise); the event "signature present, visual co-evidence absent" then triggers abductive inference of a hidden road user, emitting a calibrated risk advisory rather than a control command. Recoverability of the hidden state is analyzed as an identifiability question separating shared from modality-unique information, and cueing is cast as Neyman-Pearson detection under an explicit false-alarm budget. On real occluded-approach recordings at blind junctions, the method warns a mean 1.7 seconds before line-of-sight entry, matches the sustained-window variant of the published acoustic baseline's detection rate with 42% fewer false alarms, localizes to 3.4 degrees median once in view, is well calibrated (expected calibration error 0.034), and keeps hazard awareness above 0.87 under staged vision degradation that collapses a vision-only channel to 0.03. We also measure the method's limits: calibration transfers to an unseen junction almost losslessly, the signature classifier does not, and moving-ego noise is the binding deployment constraint.