[Re] Learning Neural PDE Solvers with Convergence Guarantees ICLR Reproducibility Challenge 2019
A replication of learning-based PDE solvers with convergence guarantees as the target topic.
External publication. Published by its original venue; not published in our journal.
On an evaluator-chosen PDE with an analytic solution, does the observed residual contract over a fixed iteration budget?
Independently compute the PDE residual and solution error; observed convergence on finite cases cannot issue an authoritative formal-proof status.
What you could produce
- Versioned protocol, input and environment manifest, and independent per-case comparison table including uncertainty and incomplete cases.
Before you use it
- PyTorch (current README)
- Conda environment.yml and a main notebook are referenced but not executed or resolved
Limits to keep in view
- No research code was executed; no independent scientific verification has been performed.
- The current qualified pilot is self-contained Python 3.13 with a 90-second author deadline. This article's environment has not been qualified for that path.
- Published source metadata and a historical review do not establish compatibility, successful reproduction, operator independence or current scientific correctness.
- Dependencies named in metadata are not available under the current standard-library-only pilot; a new qualified environment is required.
Source and permission context
Bardi, Francesco; von Baussnern, Samuel; Gjiriti, Emiljano. [Re] Learning Neural PDE Solvers with Convergence Guarantees ICLR Reproducibility Challenge 2019. ReScience C 5(2), #3; 10.5281/zenodo.3162890.
Catalog listing reviewed. This review covers the description and source links displayed here.
ReScience/Zenodo manuscript CC-BY-4.0 evidence; current GPLv3 code text is separately scoped and version-unmatched.
Reviewed 2026-09-14. Copying or adapting source files remains subject to their own terms.
manuscript · CC-BY-4.0
The exact Zenodo record cited by the journal declares cc-by-4.0; the journal separately identifies published manuscripts as CC BY. This records manuscript rights, not separate code/data licenses or archive contents.
Inspect the license evidence ↗code current repository · No SPDX identifier
The current root LICENSE contains GPL version 3 text. A specific GPL-3.0-only versus GPL-3.0-or-later grant and exact article-artifact correspondence were not established, so no precise SPDX identifier is assigned.
Inspect the license evidence ↗Before copying source material
- Data licenses, permissions, consent restrictions and redistribution conditions have not been independently checked.
- Artifacts are referenced only; PDF/archive contents, dependency locks and bytes have not been inspected or executed.
- Current repository license files were inspected, but their equivalence to the journal's DOI/SWH artifact version and all third-party notices remain unresolved.