# AcoustiTrace: When Plausible Sound Violates Physics

arXiv: https://arxiv.org/abs/2608.02035 · HTML: https://mlsanity.com/paper/2608.02035/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2026.

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

- [PAWBench: How Far Are We from Probabilistically Aligned World Modeling?](https://mlsanity.com/paper/2608.27345/) (2026)

## Abstract (arXiv)

Recent audio-video generators can produce semantically plausible and apparently synchronized sound, yet may still violate the acoustic processes implied by visible events and environments. Existing benchmarks provide limited support for attributing such violations to particular acoustic processes and quantifying their severity. We introduce AcoustiTrace, a diagnostic benchmark that formalizes acoustic physical realism in audio-video generation. AcoustiTrace organizes text-to-audio-video (T2AV) and image-to-audio-video (I2AV) evaluation around the acoustic process, covering sound generation, propagation environment, and acoustic reception through eight dimensions grounded in measurable acoustic quantities. Based on these evaluation dimensions, we construct a large-scale dataset organized around acoustic mechanisms, comprising real-world audio-video recordings and acoustically annotated RGB-D observations, and use it to develop targeted prompt suites and validated evaluators. Experiments reveal that even leading generators still struggle with fundamental acoustic processes despite producing plausible sound events. Finally, we show that the diagnostics AcoustiTrace provides for specific acoustic relations can guide model refinement toward more physically faithful audio and open new directions for incorporating acoustic principles into training objectives, reward modeling, and candidate selection.