Pith. sign in

REVIEW 13 cited by

Interpretable Machine Learning in Physics: A Review

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.23616 v1 pith:3GXOXWYU submitted 2025-03-30 physics.comp-ph cs.AIcs.LG

classification physics.comp-phcs.AIcs.LG
keywords learningmachinescientificinterpretabilityinterpretablemodelsphysicsdiscoveries
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Machine learning is increasingly transforming various scientific fields, enabled by advancements in computational power and access to large data sets from experiments and simulations. As artificial intelligence (AI) continues to grow in capability, these algorithms will enable many scientific discoveries beyond human capabilities. Since the primary goal of science is to understand the world around us, fully leveraging machine learning in scientific discovery requires models that are interpretable -- allowing experts to comprehend the concepts underlying machine-learned predictions. Successful interpretations increase trust in black-box methods, help reduce errors, allow for the improvement of the underlying models, enhance human-AI collaboration, and ultimately enable fully automated scientific discoveries that remain understandable to human scientists. This review examines the role of interpretability in machine learning applied to physics. We categorize different aspects of interpretability, discuss machine learning models in terms of both interpretability and performance, and explore the philosophical implications of interpretability in scientific inquiry. Additionally, we highlight recent advances in interpretable machine learning across many subfields of physics. By bridging boundaries between disciplines -- each with its own unique insights and challenges -- we aim to establish interpretable machine learning as a core research focus in science.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations

    cs.LG 2025-12 unverdicted novelty 7.0 of 10

    Neural ODEs reproduce 2RDM dynamics from data only when three-particle cumulant correlations are strong, mapping the validity regime of cumulant expansions.

  2. The Ramanujan Challenge For AI

    math.HO 2026-06 accept novelty 6.5 of 10

    A benchmark of new continued fractions, recurrences, series and integrals for classical constants, split into encrypted-proof problems and open conjectures for testing AI mathematical reasoning.

  3. Can AI Follow In Einstein's Footsteps?

    physics.hist-ph 2026-07 conditional novelty 6.0 of 10

    AI for physics has moved from explicit equation discovery to black-box prediction, a trajectory the authors argue reverses the historical progression of human physics, leaving the invention of new mathematical framewo...

  4. Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Unsupervised autoencoders on Ising configurations form magnetization then energy representations in two dynamical regimes, with recursive error flow fields sharing topology across layers.

  5. Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Autoencoders trained on Ising spin configurations learn large-scale magnetization before small-scale energy features; deep models often arrest before the energy stage, and recursive self-application reveals stable lat...

  6. Sequence-Model-Guided Measurement Selection for Quantum State Learning

    quant-ph 2025-07 conditional novelty 6.0 of 10

    A transformer-based 'TGMS' model adaptively chooses quantum measurements and outperforms random selection for property prediction, phase clustering, and tomography, with an emergent preference for boundary measurement...

  7. Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Case study applies SAE probing with enstrophy triage to a continuum-dynamics foundation model and reports intermittent feature consistency that does not align with standard physics while linking some output discrepanc...

  8. Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane

    hep-ph 2026-04 unverdicted novelty 5.0 of 10

    Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across...

  9. KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

    hep-ph 2025-12 conditional novelty 5.0 of 10

    An edge-weighted multi-graph GNN (E-PCN/KIGNet) that encodes four jet kinematic variables improves JetClass jet-tagging accuracy and attributes most predictions to angular separation and transverse momentum.

  10. KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

    hep-ph 2025-12 conditional novelty 5.0 of 10

    E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% ...

  11. Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator

    quant-ph 2025-09 unverdicted novelty 5.0 of 10

    A VAE learns a minimal latent representation from noisy quantum simulator snapshots that correlates with the sine-Gordon equilibrium parameter and detects anomalous post-quench dynamics including frozen-in solitons.

  12. Active Matter as a framework for living systems-inspired Robophysics

    cond-mat.soft 2025-11 unverdicted novelty 3.0 of 10

    Active-matter physics is presented as the organizing framework for robophysics, with robot swarms designed around local interactions, shared purpose, and adaptive feedback.

  13. Artificial intelligence for representing and characterizing quantum systems

    quant-ph 2025-09 unverdicted novelty 1.0 of 10

    A review organizes AI-based quantum system characterization into ML, deep learning, and language model paradigms, covering property prediction and implicit state reconstruction.

Pith tools