mlsanityData to 7 Oct 2026

On scientific understanding with artificial intelligence

arXiv 2204.01467 ↗First posted 4 Apr 2022cs.CY cs.LG physics.chem-phcited by 68

Not on the map. Why?

Abstract (arXiv)

Imagine an oracle that correctly predicts the outcome of every particle physics experiment, the products of every chemical reaction, or the function of every protein. Such an oracle would revolutionize science and technology as we know them. However, as scientists, we would not be satisfied with the oracle itself. We want more. We want to comprehend how the oracle conceived these predictions. This feat, denoted as scientific understanding, has frequently been recognized as the essential aim of science. Now, the ever-growing power of computers and artificial intelligence poses one ultimate question: How can advanced artificial systems contribute to scientific understanding or achieve it autonomously? We are convinced that this is not a mere technical question but lies at the core of science. Therefore, here we set out to answer where we are and where we can go from here. We first seek advice from the philosophy of science to understand scientific understanding. Then we review the current state of the art, both from literature and by collecting dozens of anecdotes from scientists about how they acquired new conceptual understanding with the help of computers. Those combined insights help us to define three dimensions of android-assisted scientific understanding: The android as a I) computational microscope, II) resource of inspiration and the ultimate, not yet existent III) agent of understanding. For each dimension, we explain new avenues to push beyond the status quo and unleash the full power of artificial intelligence's contribution to the central aim of science. We hope our perspective inspires and focuses research towards androids that get new scientific understanding and ultimately bring us closer to true artificial scientists.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 36 of its 137 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

36 of 137 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  5. 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 536
  6. 2019The frontier of simulation-based inferencecited by 490
  7. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  8. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  9. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  10. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  11. 2018Understanding disentangling in β-VAEcited by 332
  12. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
24 more
  1. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  2. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 165
  3. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  4. 2018Discovering physical concepts with neural networkscited by 117
  5. 2021Automatic Symmetry Discovery with Lie Algebra Convolutional Networkcited by 82
  6. 2018The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communitiescited by 78
  7. 2017What Does Explainable AI Really Mean? A New Conceptualization of Perspectivescited by 72
  8. 2022Rediscovering orbital mechanics with machine learningcited by 71
  9. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  10. 2021Machine Learning in the Search for New Fundamental Physicscited by 50
  11. 2021Constructions in combinatorics via neural networkscited by 46
  12. 2017Active learning machine learns to create new quantum experimentscited by 41
  13. 2020Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networkscited by 33
  14. 2019Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physicscited by 24
  15. 2020Machine learning enables completely automatic tuning of a quantum device faster than human expertscited by 23
  16. 2020Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representationscited by 20
  17. 2020Computer-inspired Quantum Experimentscited by 18
  18. 2020Learning models of quantum systems from experimentscited by 16
  19. 2020Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learningcited by 16
  20. 2021Assigning Confidence to Molecular Property Predictioncited by 14
  21. 2021Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Modelscited by 12
  22. 2020Scientific intuition inspired by machine learning generated hypothesescited by 7
  23. 2018Sampling molecular conformations and dynamics in a multi-user virtual reality frameworkcited by 3
  24. 2020Explaining Creative Artifactscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 11; 2024: 24; 2025: 14; 2026: 13.

68 papers.

Sort:

By area:

  1. 2022Graph neural networks for materials science and chemistrycited by 181
  2. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  3. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 96
  4. 2022Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge networkcited by 34
  5. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  6. 2024Forecasting high-impact research topics via machine learning on evolving knowledge graphscited by 21
  7. 2024Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaderscited by 21
  8. 2024Agents for self-driving laboratories applied to quantum computingcited by 18
  9. 2022The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Sciencecited by 14
  10. 2025Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Modelscited by 14
  11. 2024Knowledge-guided Machine Learning: Current Trends and Future Prospectscited by 13
  12. 2024Meta-Designing Quantum Experiments with Language Modelscited by 12
38 more
  1. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  2. 2022Automatic and effective discovery of quantum kernelscited by 10
  3. 2022Quantum Similarity Testing with Convolutional Neural Networkscited by 10
  4. 2023Towards a Benchmark for Scientific Understanding in Humans and Machinescited by 9
  5. 2024Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspectivecited by 9
  6. 2025Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Modelscited by 7
  7. 2025Towards autonomous quantum physics research using LLM agents with access to intelligent toolscited by 7
  8. 2023Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experimentscited by 5
  9. 2024Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligencecited by 5
  10. 2025Building Machine Learning Challenges for Anomaly Detection in Sciencecited by 5
  11. 2025Quantum computing and artificial intelligence: status and perspectivescited by 5
  12. 2025A Multi-Task Evaluation of LLMs' Processing of Academic Text Inputcited by 5
  13. 2024On Tables with Numbers, with Numberscited by 4
  14. 2024Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocolcited by 4
  15. 2025Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?cited by 4
  16. 2026Explainable AI: Learning from the Learnerscited by 4
  17. 2026OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understandingcited by 4
  18. 2024Decoding complexity: how machine learning is redefining scientific discoverycited by 3
  19. 2024Towards a Science Exocortexcited by 3
  20. 2025AI for Scientific Discovery is a Social Problemcited by 3
  21. 2023A Model for Intelligible Interaction Between Agents That Predict and Explaincited by 2
  22. 2023Quantifying the Benefit of Artificial Intelligence for Scientific Researchcited by 2
  23. 2023APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysicscited by 2
  24. 2024Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network modelscited by 2
  25. 2025From Queries to Criteria: Understanding How Astronomers Evaluate LLMscited by 2
  26. 2026Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraintscited by 2
  27. 2026Socratic agents for autonomous scientific discovery in high-dimensional physical systemscited by 2
  28. 2023Probabilistic Regular Tree Priors for Scientific Symbolic Reasoningcited by 1
  29. 2024Autonomous microARPEScited by 1
  30. 2024A theory of understanding for artificial intelligence: composability, catalysts, and learningcited by 1
  31. 2024ViSymRe: Vision Multimodal Symbolic Regressioncited by 1
  32. 2024Discover physical concepts and equations with machine learningcited by 1
  33. 2025Sequence-Model-Guided Measurement Selection for Quantum State Learningcited by 1
  34. 2026Automated near-term quantum algorithm discovery for molecular ground statescited by 1
  35. 2026Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systemscited by 1
  36. 2023Machine learning for discovering laws of naturecited by 0
  37. 2023Re-imagining health and well-being in low resource African settings using an augmented AI system and a 3D digital twincited by 0
  38. 2023AI ensemble for signal detection of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergerscited by 0

50 most cited of 68 All 68 (JSON)