<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

ZhaoSH980/discrepancy-level-inverse-pinns: v1.0.0 — reproducibility archive

Loading...
Thumbnail Image

Date

Journal Title

Journal ISSN

Volume Title

Publisher

Zenodo

DOI

Abstract

Description

&lt;p&gt;Code and raw per-run records accompanying the manuscript &lt;em&gt;The Level Is the Choice: Reconstruction and Identification Prefer Opposite Discrepancy Levels in Three Misspecified Inverse Physics-Informed Neural Networks&lt;/em&gt;.&lt;/p&gt; &lt;p&gt;Contents:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;code&gt;sandbox/&lt;/code&gt; — problem definitions, the vectorised ensemble trainer, one driver per experiment (w1–w20), and the figure scripts&lt;/li&gt; &lt;li&gt;&lt;code&gt;results/&lt;/code&gt; — raw per-run outputs, one JSON per experiment: every seed, every logged step&lt;/li&gt; &lt;li&gt;&lt;code&gt;scripts/&lt;/code&gt; — the emitters that generate every numeric macro in the manuscript from those records, and the theory verification script&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;All data are synthetic and regenerate deterministically from this code. Seeds fix the collocation and sensor point sets, the noise realisation and the network initialisation, so a seed identifies one run across every arm — which is what makes the reported statistics paired.&lt;/p&gt; &lt;p&gt;Code MIT; recorded outputs CC BY 4.0.&lt;/p&gt;

Keywords

Citation

Collections

Endorsement

Review

Supplemented By

Referenced By

Rights and licensing

info:eu-repo/semantics/openAccess
MIT License
https://opensource.org/licenses/MIT