Pith. sign in

REVIEW 3 cited by

Distilling Wikipedia mathematical knowledge into neural network models

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 2104.05930 v1 pith:UFBKPF6X submitted 2021-04-13 cs.LG cs.AI

classification cs.LGcs.AI
keywords symbolicexpressionslanguagemathematicaltextitusedwikipediadata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of "mathematics as language," we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a $\textit{mathematical}$ $\textit{language}$ $\textit{model}$ trained on this "corpus" of expressions can be used as a prior to improve the performance of neural-guided search for the task of symbolic regression.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Generative Discovery of Partial Differential Equations by Learning from Math Handbooks

    cs.LG 2025-05 conditional novelty 7.0 of 10

    The authors train a GPT-style model on 221 handbook PDE structures and use it to generate and select PDEs from data, including a proposed previously unreported equation for pre-breaking surface gravity waves.

  2. DisCo-DSO: Coupling Discrete and Continuous Optimization for Efficient Generative Design in Hybrid Spaces

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A generative optimization method that jointly samples discrete and continuous design variables outperforms decoupled skeleton-then-optimize baselines in sample efficiency across bitstring, decision-tree, and symbolic ...

  3. Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics

    cs.LG 2025-05 conditional novelty 3.0 of 10

    DSO uses an autoregressive model trained with a risk-seeking policy gradient to search symbolic expressions, and its unified version outperforms baselines on symbolic regression benchmarks.

Pith tools