PySR (including official usage skill) · Agentic Research Directory

Evidence & verification

Source level

Project-documented
Grounded in primary project documentation, not necessarily an empirical evaluation.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-15 (UTC)

Primary-source feature/workflow review only. Performance, uptake and promotional claims are not treated as validated research gains.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

PySR performs symbolic regression to search for interpretable mathematical expressions from data and documents an optional agent skill.

Getting started

Read the installation and examples; fit a small dataset and inspect predictive error and expression complexity before considering agent integration.

Maintenance

Current operational availability and maintenance were not tested; this recommendation rests on the dated source snapshot.

License

Licensing, service terms and rights to input data must be checked before adoption; no independent license audit performed.

Workflow & human oversight

Resource-level classification is intentionally unspecified; instantiated workflows may differ. Humans define objectives, control data access, and check outputs.

Workflow level is not an evidence score; higher is not better evidence.

Approach

A Python interface uses a Julia symbolic-regression engine with configurable operators, objectives and complexity.

Limitations

The page recommends low-dimensional data; fitted expressions are not established scientific laws without validation. The agent skill was not executed or audited.

Reproducibility

Reviewed a stored primary-source extract accessed 2026-10-15. No software, model or claimed outcome was independently reproduced.

Adoption requirements

Python and Julia dependencies, a suitable dataset, candidate operators and held-out validation criteria.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.