mlsanityData to 7 Oct 2026

Neurosymbolic Programming for Science

arXiv 2210.05050 ↗First posted 10 Oct 2022cs.AIcited by 7

Not on the map. Why?

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.

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

Builds on

15 of 41 references.

References · 15

  1. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  2. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  3. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  4. 2018Markerless tracking of user-defined features with deep learningcited by 203
  5. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  6. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
  7. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  8. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  9. 2018HOUDINI: Lifelong Learning as Program Synthesiscited by 38
  10. 2020Learning Differentiable Programs with Admissible Neural Heuristicscited by 30
  11. 2020Task Programming: Learning Data Efficient Behavior Representationscited by 27
  12. 2022Data-Efficient Graph Grammar Learning for Molecular Generationcited by 26
3 more
  1. 2021Unsupervised Learning of Neurosymbolic Encoderscited by 8
  2. 2021Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysiscited by 6
  3. 2021Interpreting Expert Annotation Differences in Animal Behaviorcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  2. 2024SymbolicAI: A framework for logic-based approaches combining generative models and solverscited by 15
  3. 2024Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessmentcited by 14
  4. 2023Natural Language Commanding via Program Synthesiscited by 6
  5. 2023Smoothing Methods for Automatic Differentiation Across Conditional Branchescited by 6
  6. 2025The Need for Verification in AI-Driven Scientific Discoverycited by 5
  7. 2026Mapping Uncharted Symmetries: Machine Discovery in Combinatoricscited by 0