moju 2.3.1__tar.gz → 2.3.2__tar.gz

{moju-2.3.1 → moju-2.3.2}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: moju
-Version: 2.3.1
-Summary: Physics supervision and audit tools for SciML models, with JAX-native residuals and PyTorch support.
+Version: 2.3.2
+Summary: Physics admissibility auditing for ML surrogates and simulation data: scores how well predicted fields satisfy governing laws and constitutive relations, with implied-parameter checks and admissibility tiers, for JAX and PyTorch.
 Author-email: "Ifimo Lab (Ifimo Global Solutions LLC)" <lab@ifimoanalytics.com>
 Maintainer-email: "Ifimo Global Solutions LLC (dba Ifimo Lab)" <info@ifimoanalytics.com>
 License: MIT
@@ -12,7 +12,7 @@ Project-URL: Paper, https://zenodo.org/records/20519331
 Project-URL: Changelog, https://github.com/IfimoAI/moju/blob/main/CHANGELOG.md
 Project-URL: Citation, https://github.com/IfimoAI/moju/blob/main/CITATION.cff
 Project-URL: Issues, https://github.com/IfimoAI/moju/issues
-Keywords: physics,jax,torch,pytorch,sciml,pinn,dimensionless,cfd,differentiable,residual
+Keywords: physics-informed machine learning,scientific machine learning,surrogate validation,verification and validation,admissibility,JAX,PyTorch,SciML,PINN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
@@ -49,7 +49,7 @@ Dynamic: license-file
 
 # moju
 
-Physics supervision and audit tools for SciML and Physics AI.
+Moju audits predicted fields against governing-law residuals, constitutive and implied-parameter checks, and optional per-region diagnostics. It reports admissibility scores, qualitative tiers, and scoring provenance so you can see how well a state satisfies the physics you stated. It is for people validating ML surrogates or simulation fields. Secondary capabilities include composing laws, models, and dimensionless groups, and using governing-law residuals as a training-time loss.
 
 ```bash
 pip install moju

{moju-2.3.1 → moju-2.3.2}/README.md

@@ -1,6 +1,6 @@
 # moju
 
-Physics supervision and audit tools for SciML and Physics AI.
+Moju audits predicted fields against governing-law residuals, constitutive and implied-parameter checks, and optional per-region diagnostics. It reports admissibility scores, qualitative tiers, and scoring provenance so you can see how well a state satisfies the physics you stated. It is for people validating ML surrogates or simulation fields. Secondary capabilities include composing laws, models, and dimensionless groups, and using governing-law residuals as a training-time loss.
 
 ```bash
 pip install moju

{moju-2.3.1 → moju-2.3.2}/moju/__init__.py

@@ -1,3 +1,3 @@
 """Moju: Physics-AI supervision for engineering-grade simulations."""
 
-__version__ = "2.3.1"
+__version__ = "2.3.2"

{moju-2.3.1 → moju-2.3.2}/moju.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: moju
-Version: 2.3.1
-Summary: Physics supervision and audit tools for SciML models, with JAX-native residuals and PyTorch support.
+Version: 2.3.2
+Summary: Physics admissibility auditing for ML surrogates and simulation data: scores how well predicted fields satisfy governing laws and constitutive relations, with implied-parameter checks and admissibility tiers, for JAX and PyTorch.
 Author-email: "Ifimo Lab (Ifimo Global Solutions LLC)" <lab@ifimoanalytics.com>
 Maintainer-email: "Ifimo Global Solutions LLC (dba Ifimo Lab)" <info@ifimoanalytics.com>
 License: MIT
@@ -12,7 +12,7 @@ Project-URL: Paper, https://zenodo.org/records/20519331
 Project-URL: Changelog, https://github.com/IfimoAI/moju/blob/main/CHANGELOG.md
 Project-URL: Citation, https://github.com/IfimoAI/moju/blob/main/CITATION.cff
 Project-URL: Issues, https://github.com/IfimoAI/moju/issues
-Keywords: physics,jax,torch,pytorch,sciml,pinn,dimensionless,cfd,differentiable,residual
+Keywords: physics-informed machine learning,scientific machine learning,surrogate validation,verification and validation,admissibility,JAX,PyTorch,SciML,PINN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
@@ -49,7 +49,7 @@ Dynamic: license-file
 
 # moju
 
-Physics supervision and audit tools for SciML and Physics AI.
+Moju audits predicted fields against governing-law residuals, constitutive and implied-parameter checks, and optional per-region diagnostics. It reports admissibility scores, qualitative tiers, and scoring provenance so you can see how well a state satisfies the physics you stated. It is for people validating ML surrogates or simulation fields. Secondary capabilities include composing laws, models, and dimensionless groups, and using governing-law residuals as a training-time loss.
 
 ```bash
 pip install moju

{moju-2.3.1 → moju-2.3.2}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "moju"
-version = "2.3.1"
-description = "Physics supervision and audit tools for SciML models, with JAX-native residuals and PyTorch support."
+version = "2.3.2"
+description = "Physics admissibility auditing for ML surrogates and simulation data: scores how well predicted fields satisfy governing laws and constitutive relations, with implied-parameter checks and admissibility tiers, for JAX and PyTorch."
 readme = "README.md"
 authors = [{ name = "Ifimo Lab (Ifimo Global Solutions LLC)", email = "lab@ifimoanalytics.com" }]
 maintainers = [
@@ -13,7 +13,17 @@ maintainers = [
 ]
 license = { text = "MIT" }
 requires-python = ">=3.10"
-keywords = ["physics", "jax", "torch", "pytorch", "sciml", "pinn", "dimensionless", "cfd", "differentiable", "residual"]
+keywords = [
+    "physics-informed machine learning",
+    "scientific machine learning",
+    "surrogate validation",
+    "verification and validation",
+    "admissibility",
+    "JAX",
+    "PyTorch",
+    "SciML",
+    "PINN",
+]
 classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Science/Research",