# ESPRIT: Explaining Solutions to Physical Reasoning Tasks

arXiv: https://arxiv.org/abs/2005.00730 · HTML: https://mlsanity.com/paper/2005.00730/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2020.

## Built on by (most cited first, 16 of 16)

- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [ComPhy: Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2205.01089/) (2022)
- [Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties](https://mlsanity.com/paper/2306.15668/) (2023)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [Learning by Self-Explaining](https://mlsanity.com/paper/2309.08395/) (2023)
- [CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering](https://mlsanity.com/paper/2211.03779/) (2022)
- [Compositional Physical Reasoning of Objects and Events from Videos](https://mlsanity.com/paper/2408.02687/) (2024)
- [CLEVRER-Humans: Describing Physical and Causal Events the Human Way](https://mlsanity.com/paper/2310.03635/) (2023)
- [PhysInOne: Visual Physics Learning and Reasoning in One Suite](https://mlsanity.com/paper/2604.09415/) (2026)
- [Physics-IQ Verified](https://mlsanity.com/paper/2606.18943/) (2026)
- [Benchmarks for Physical Reasoning AI](https://mlsanity.com/paper/2312.10728/) (2023)
- [VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction](https://mlsanity.com/paper/2602.13294/) (2026)
- [Deltaynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos](https://mlsanity.com/paper/2605.20576/) (2026)
- [IMBench: A Benchmark for Intuitive Robotic Manipulation](https://mlsanity.com/paper/2607.15641/) (2026)

## Abstract (arXiv)

Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for commonsense reasoning about qualitative physics in natural language that generates interpretable descriptions of physical events. We use a two-step approach of first identifying the pivotal physical events in an environment and then generating natural language descriptions of those events using a data-to-text approach. Our framework learns to generate explanations of how the physical simulation will causally evolve so that an agent or a human can easily reason about a solution using those interpretable descriptions. Human evaluations indicate that ESPRIT produces crucial fine-grained details and has high coverage of physical concepts compared to even human annotations. Dataset, code and documentation are available at https://github.com/salesforce/esprit.