docs: add section landing pages and fix broken index links

Author: mkumar73

docs/api/index.md

@@ -0,0 +1,16 @@
+---
+orphan: true
+---
+
+# API Reference
+
+Complete API documentation for DeepTab, organised by module: the public estimators,
+configuration dataclasses, data utilities, distribution families, metrics, and the
+underlying Lightning training modules.
+
+- **[Models](models/index)**: Classifier, Regressor, and LSS classes
+- **[Configs](configs/index)**: Configuration dataclasses
+- **[Data](data/index)**: Datasets, data modules, and schemas
+- **[Distributions](distributions/index)**: LSS distribution families
+- **[Metrics](metrics/index)**: Task-aware metric classes
+- **[Training](training/index)**: Lightning modules for advanced use

docs/core_concepts/index.md

@@ -0,0 +1,18 @@
+---
+orphan: true
+---
+
+# Core Concepts
+
+These pages explain how DeepTab works under the hood: the scikit-learn interface,
+the split-config system, the training and evaluation pipeline, observability, and
+deployment-safe inference.
+
+- **[sklearn API](sklearn_api)**: The fit/predict/evaluate interface
+- **[Model Tiers](model_tiers)**: Stable versus experimental models
+- **[Custom Models](custom_models)**: Building your own architectures
+- **[Config System](config_system)**: Split configuration for model, preprocessing, and training
+- **[Observability](observability)**: Lifecycle events, structured logging, and experiment tracking
+- **[Training and Evaluation](training_and_evaluation)**: The fit pipeline, metrics, and reproducibility
+- **[Model Operations](model_operations)**: Serialisation and inspection
+- **[Inference](inference)**: Deployment-safe prediction with `InferenceModel`

docs/developer_guide/release.md

@@ -217,7 +217,7 @@ git push --follow-tags origin release/vX.Y.Z
 ```
 
 ```{note}
-`--follow-tags` pushes the annotated `vX.Y.ZrcN` tag along with the branch in one step, which triggers `publish-testpypi.yml`. See **[Tag and publish a release candidate](#7-tag-and-publish-a-release-candidate)** below if you prefer to push the tag separately.
+`--follow-tags` pushes the annotated `vX.Y.ZrcN` tag along with the branch in one step, which triggers `publish-testpypi.yml`. See step 7, **Tag and publish a release candidate**, below if you prefer to push the tag separately.
 ```
 
 ### 6b. Stable bump

docs/getting_started/index.md

@@ -0,0 +1,13 @@
+---
+orphan: true
+---
+
+# Getting Started
+
+New to DeepTab? Start here. These pages take you from installation to your first
+trained model, and answer the most common questions along the way.
+
+- **[Overview](overview)**: What DeepTab is and when to use it
+- **[Installation](installation)**: Setup, GPU support, and optional kernels
+- **[Quickstart](quickstart)**: Train your first models in a few minutes
+- **[FAQ](faq)**: Common questions, v1 support, and troubleshooting

docs/model_zoo/index.md

@@ -0,0 +1,15 @@
+---
+orphan: true
+---
+
+# Model Zoo
+
+DeepTab ships 15 stable architectures plus experimental models, all behind the same
+`fit`/`predict`/`evaluate` interface. Use these pages to compare models, understand
+their efficiency trade-offs, and find recommended configurations.
+
+- **[Stable Models](stable/index)**: Production-ready architectures
+- **[Experimental Models](experimental/index)**: Architectures under evaluation for promotion
+- **[Comparison Tables](comparison_tables)**: Side-by-side model comparison and selection guidance
+- **[Efficiency](efficiency)**: Runtime and memory characteristics
+- **[Recommended Configs](recommended_configs)**: Sensible starting configurations per model

docs/tutorials/index.md

@@ -0,0 +1,17 @@
+---
+orphan: true
+---
+
+# Tutorials
+
+End-to-end, runnable walkthroughs covering common modeling workflows with DeepTab.
+Each tutorial is Colab-ready and works through a complete problem from data to results.
+
+- **[Skewed-Target Regression](skewed_regression)**: Regression on a right-skewed target
+- **[Imbalanced Classification](imbalance_classification)**: An end-to-end classification workflow
+- **[Uncertainty Quantification](uncertainty_quantification)**: Prediction intervals with LSS models
+- **[Hyperparameter Optimisation](hpo)**: Tuning models efficiently
+- **[Advanced Training and Inference](advanced_training)**: Optimizers, schedulers, and production inference
+- **[Observability and Logging](observability)**: Run directories and experiment trackers
+- **[Model Efficiency](model_efficiency)**: Runtime and memory benchmarking
+- **[Experimental Models](experimental)**: Working with cutting-edge architectures