# On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigms

arXiv: https://arxiv.org/abs/2502.08932 · HTML: https://mlsanity.com/paper/2502.08932/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Towards Deep Neural Network Architectures Robust to Adversarial Examples](https://mlsanity.com/paper/1412.5068/) (2014)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)
- [Certified Robustness to Label-Flipping Attacks via Randomized Smoothing](https://mlsanity.com/paper/2002.03018/) (2020)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch](https://mlsanity.com/paper/1902.07623/) (2019)
- [Very Deep Convolutional Neural Networks for Raw Waveforms](https://mlsanity.com/paper/1610.00087/) (2016)
- [Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts](https://mlsanity.com/paper/2305.19951/) (2023)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Neurosymbolic Reinforcement Learning with Formally Verified Exploration](https://mlsanity.com/paper/2009.12612/) (2020)
- [How fair can we go in machine learning? Assessing the boundaries of fairness in decision trees](https://mlsanity.com/paper/2006.12399/) (2020)
- [A Survey on AI Assurance](https://mlsanity.com/paper/2111.07505/) (2021)
- [Remote Timing Attacks on Efficient Language Model Inference](https://mlsanity.com/paper/2410.17175/) (2024)
- [Part-Based Models Improve Adversarial Robustness](https://mlsanity.com/paper/2209.09117/) (2022)
- [Safe Neurosymbolic Learning with Differentiable Symbolic Execution](https://mlsanity.com/paper/2203.07671/) (2022)
- [Data-Efficient Learning with Neural Programs](https://mlsanity.com/paper/2406.06246/) (2024)
- [Formal Explanations for Neuro-Symbolic AI](https://mlsanity.com/paper/2410.14219/) (2024)

## Built on by (most cited first, 3 of 3)

- [Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities](https://mlsanity.com/paper/2509.06921/) (2025)
- [Constraint-Aware Neurosymbolic Uncertainty Quantification with Bayesian Deep Learning for Scientific Discovery](https://mlsanity.com/paper/2601.12442/) (2026)
- [Foundation Models for Medical Imaging: Status, Challenges, and Directions](https://mlsanity.com/paper/2602.15913/) (2026)

## Abstract (arXiv)

To create usable and deployable Artificial Intelligence (AI) systems, there requires a level of assurance in performance under many different conditions. Many times, deployed machine learning systems will require more classic logic and reasoning performed through neurosymbolic programs jointly with artificial neural network sensing. While many prior works have examined the assurance of a single component of the system solely with either the neural network alone or entire enterprise systems, very few works have examined the assurance of integrated neurosymbolic systems. Within this work, we assess the assurance of end-to-end fully differentiable neurosymbolic systems that are an emerging method to create data-efficient and more interpretable models. We perform this investigation using Scallop, an end-to-end neurosymbolic library, across classification and reasoning tasks in both the image and audio domains. We assess assurance across adversarial robustness, calibration, user performance parity, and interpretability of solutions for catching misaligned solutions. We find end-to-end neurosymbolic methods present unique opportunities for assurance beyond their data efficiency through our empirical results but not across the board. We find that this class of neurosymbolic models has higher assurance in cases where arithmetic operations are defined and where there is high dimensionality to the input space, where fully neural counterparts struggle to learn robust reasoning operations. We identify the relationship between neurosymbolic models' interpretability to catch shortcuts that later result in increased adversarial vulnerability despite performance parity. Finally, we find that the promise of data efficiency is typically only in the case of class imbalanced reasoning problems.