Address referee feedback: determinism, code cleanup, multi-seed benchmarks

.github/workflows/test.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
 
     steps:
       - uses: actions/checkout@v4
@@ -36,4 +36,4 @@ jobs:
 
       - name: Type check
         run: |
-          mypy src/micro/
+          mypy src/microplex/

README.md

@@ -1,6 +1,6 @@
 # microplex
 
-Microdata synthesis and reweighting using normalizing flows.
+Multi-source microdata synthesis and survey reweighting.
 
 [![PyPI](https://img.shields.io/pypi/v/microplex.svg)](https://pypi.org/project/microplex/)
 [![Tests](https://github.com/CosilicoAI/microplex/actions/workflows/test.yml/badge.svg)](https://github.com/CosilicoAI/microplex/actions/workflows/test.yml)
@@ -74,11 +74,11 @@ print(f"Using {stats['n_nonzero']} of {stats['n_records']} records")
 
 | Feature | microplex | CT-GAN | TVAE | synthpop |
 |---------|-------|--------|------|----------|
-| Conditional generation | ✅ | ❌ | ❌ | ❌ |
+| Multi-source fusion | ✅ | ❌ | ❌ | ❌ |
 | Zero-inflation handling | ✅ | ❌ | ❌ | ⚠️ |
-| Exact likelihood | ✅ | ❌ | ❌ | N/A |
-| Stable training | ✅ | ⚠️ | ✅ | ✅ |
-| Preserves source structure | ✅ | ❌ | ❌ | ⚠️ |
+| Multiple synthesis methods | ✅ (QRF, QDNN, MAF) | ❌ | ❌ | ✅ (CART) |
+| Survey reweighting | ✅ (IPF, entropy, sparse) | ❌ | ❌ | ❌ |
+| PRDC evaluation | ✅ | ❌ | ❌ | ❌ |
 
 ### Use Cases
 
@@ -154,20 +154,20 @@ Full documentation at [cosilicoai.github.io/microplex](https://cosilicoai.github
 
 ## Benchmarks
 
-See [benchmarks/](benchmarks/) for comparisons against:
+See [benchmarks/](benchmarks/) for synthesis method comparisons:
 
-- **CT-GAN**: Conditional Tabular GAN (from SDV)
-- **TVAE**: Tabular VAE (from SDV)
-- **Copulas**: Gaussian copula synthesis (from SDV)
-- **synthpop**: CART-based synthesis (R package, via rpy2)
+- **QRF / ZI-QRF**: Quantile regression forests (with/without zero-inflation)
+- **QDNN / ZI-QDNN**: Quantile deep neural networks
+- **MAF / ZI-MAF**: Masked autoregressive flows
+- **CT-GAN / TVAE**: Deep generative baselines (from SDV)
 
 ## Citation
 
 ```bibtex
-@software{microplex2024,
-  author = {Cosilico},
-  title = {microplex: Microdata synthesis and reweighting using normalizing flows},
-  year = {2024},
+@software{microplex2025,
+  author = {Ghenis, Max},
+  title = {microplex: Multi-source microdata synthesis and survey reweighting},
+  year = {2025},
   url = {https://github.com/CosilicoAI/microplex}
 }
 ```

_build/templates/site/myst/book-theme/book-theme-main/.gitignore

@@ -0,0 +1 @@
+node_modules

_build/templates/site/myst/book-theme/book-theme-main/README.md

@@ -0,0 +1,6 @@
+# Book Theme
+
+> [!NOTE]
+> This repository contains the _build artifacts_ for the MyST Book Theme, it is not meant for editing by humans.
+> - Source code exists at [`github.com/jupyter-book/myst-theme`](https://github.com/jupyter-book/myst-theme). Make edits there, not here.
+> - To report an bug or request a feature, use the [`github.com/jupyter-book/myst-theme/issues`](https://github.com/executablebooks/myst-theme/issues).