{"name":"PySR","repo":"astroautomata/PySR","url":"https://midorreal.com/project/astroautomata-pysr","repository":"https://github.com/astroautomata/PySR","description":"Symbolic Learning in Python and Julia","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/astroautomata/PySR","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/astroautomata/PySR","checked":"22 Nov 2026"},"homepage":{"value":"https://pysr.ai","source":"https://pysr.ai","checked":"22 Nov 2026"},"last_release":{"value":"v2.7.2, 19 Oct 2026","source":"https://github.com/astroautomata/PySR/releases","checked":"22 Nov 2026"},"releases":{"value":"114","source":"https://github.com/astroautomata/PySR/releases","checked":"19 Nov 2026"},"contributors":{"value":"50","source":"https://github.com/astroautomata/PySR/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/astroautomata/PySR","checked":"22 Nov 2026"}},"stars":4305.0,"writeup":{"what_it_is":"PySR is an open-source tool for symbolic regression, a machine learning task that searches for an interpretable symbolic expression that optimizes an objective. It is developed alongside the Julia library SymbolicRegression.jl, which serves as its search engine.","audience":"Researchers and practitioners who want interpretable equations fitted to data","claims":[{"kind":"broad","claim":"Engineered to be as high-performance as possible","excerpt":"PySR has been engineered from the ground up to be (1) as high-performance as possible,","status":"too_broad"},{"kind":"broad","claim":"Engineered to be as configurable as possible","excerpt":"(2) as configurable as possible, and (3) easy to use.","status":"too_broad"},{"kind":"specific","claim":"Installable with pip or conda","excerpt":"You can install PySR with pip or conda:","status":"not_checked"},{"kind":"specific","claim":"Provides a scikit-learn style interface with fit and predict","excerpt":"PySR's main interface is in the style of scikit-learn:","status":"not_checked"},{"kind":"specific","claim":"Can convert a neural network into an analytic equation via symbolic distillation","excerpt":"one essentially uses symbolic regression to convert a neural net to an analytic equation.","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-25"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":54,"reality":72,"gap":-17,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-19T19:36:33+00:00","text":"Latest release v2.7.2","source":"https://github.com/astroautomata/PySR/releases"},{"date":"2020-09-21T14:14:47+00:00","text":"First release","source":"https://github.com/astroautomata/PySR/releases"},{"date":"2020-09-14T11:16:09+00:00","text":"Repository created","source":"https://github.com/astroautomata/PySR"}],"cite":"PySR is a GitHub project at https://github.com/astroautomata/PySR written mainly in Python, described there as \"Symbolic Learning in Python and Julia\".","attribution":"Data from Mid or Real, https://midorreal.com/project/astroautomata-pysr, checked 22 November 2026. Attribution with a link is required.","still_real":null}