# Neurosymbolic Programming for Science

arXiv: https://arxiv.org/abs/2210.05050 · HTML: https://mlsanity.com/paper/2210.05050/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 10 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Discovering Symbolic Models from Deep Learning with Inductive Biases](https://mlsanity.com/paper/2006.11287/) (2020)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [HOUDINI: Lifelong Learning as Program Synthesis](https://mlsanity.com/paper/1804.00218/) (2018)
- [Learning Differentiable Programs with Admissible Neural Heuristics](https://mlsanity.com/paper/2007.12101/) (2020)
- [Task Programming: Learning Data Efficient Behavior Representations](https://mlsanity.com/paper/2011.13917/) (2020)
- [Data-Efficient Graph Grammar Learning for Molecular Generation](https://mlsanity.com/paper/2203.08031/) (2022)
- [Unsupervised Learning of Neurosymbolic Encoders](https://mlsanity.com/paper/2107.13132/) (2021)
- [Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis](https://mlsanity.com/paper/2111.15186/) (2021)
- [Interpreting Expert Annotation Differences in Animal Behavior](https://mlsanity.com/paper/2106.06114/) (2021)

## Built on by (most cited first, 7 of 7)

- [Grammar Prompting for Domain-Specific Language Generation with Large Language Models](https://mlsanity.com/paper/2305.19234/) (2023)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment](https://mlsanity.com/paper/2403.13798/) (2024)
- [Smoothing Methods for Automatic Differentiation Across Conditional Branches](https://mlsanity.com/paper/2310.03585/) (2023)
- [The Need for Verification in AI-Driven Scientific Discovery](https://mlsanity.com/paper/2509.01398/) (2025)
- [Natural Language Commanding via Program Synthesis](https://mlsanity.com/paper/2306.03460/) (2023)
- [Mapping Uncharted Symmetries: Machine Discovery in Combinatorics](https://mlsanity.com/paper/2605.19063/) (2026)

## Abstract (arXiv)

Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and representations from data, using high-level concepts or known constraints. NP techniques can interface with symbolic domain knowledge from scientists, such as prior knowledge and experimental context, to produce interpretable outputs. We identify opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science: to enable the use of NP broadly for workflows across the natural and social sciences.