REVIEW 8 cited by
AI Feynman: a Physics-Inspired Method for Symbolic Regression
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
read the original abstract
A core challenge for both physics and artificial intellicence (AI) is symbolic regression: finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions of practical interest often exhibit symmetries, separability, compositionality and other simplifying properties. In this spirit, we develop a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques. We apply it to 100 equations from the Feynman Lectures on Physics, and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult test set, we improve the state of the art success rate from 15% to 90%.
Forward citations
Cited by 8 Pith papers
-
A First Observational Assessment of Cosmic Backreaction Over an Extended Redshift Range
First model-light constraints on Ω_R + 3Ω_Q from Pantheon+ and BAO reconstructions are consistent with flat FLRW yet too broad to exclude percent-level backreaction.
-
Inverse-k Primordial Oscillations from a Symbolic Regression Search
Symbolic regression on Planck and Planck+ACT+SPT independently selects an inverse-k primordial oscillation cos(B/k)≈cos(4/k) that weakly outperforms linear and log templates.
-
Diffusion-Based Symbolic Regression
A masked discrete diffusion model trained with token-wise GRPO and a long short-term risk-seeking replay pool improves symbolic regression solution rates and expression simplicity on SRBench.
-
A "Neural" Riemann solver for Relativistic Hydrodynamics
Small neural networks trained on exact solutions can replace the iterative root-finding in a relativistic Riemann solver, giving exact-like accuracy about 14 times faster in 1D tests.
-
From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models
Data-driven models for physical systems share a common structure differing only in model class assumptions, with only mechanism-discovering models capable of generalization.
-
SABER: Symbolic Regression-based Angle of Arrival and Beam Pattern Estimator
AoA can be estimated from a single path loss value by fitting a cos^n inversion with symbolic regression, but the reported accuracy is only demonstrated on the training data and one fixed angle.
-
Data-driven discovery of dynamical models in biology
A review benchmarking regression, network, and decomposition methods on the Oregonator model under the Koopman operator framework, with illustrative experiments on simulated data.
-
Toward Supporting Narrative-Driven Data Exploration: Barriers and Design Opportunities
Clustering particles by mass, spin, lifetime and decay modes with conventional tools reproduces known Standard Model groupings, but the dataset and algorithm choices quietly encode the theory being 'rediscovered'.
Discussion (0). Continue with ORCID to comment.