# star-ga/nn_universe architecture

> Architecture diagram of the GitHub repository star-ga/nn_universe, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-27). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/star-ga/nn_universe
- Repository: https://github.com/star-ga/nn_universe

## Overview

This repository is a research-experiment suite for measuring and validating the Fisher Information Matrix (FIM) diagonal tier hierarchy across computational substrates. The main workflow is to run substrate- or architecture-specific measurements, compare tier ratios across systems, and test depth-scaling and statistical separation. Major branches cover neural-network scaling and mechanism studies, non-neural and physics controls, modern pretrained architectures, and statistical analysis. The graph follows the README and file tree; unsampled implementations are represented only at their existing directory paths, with uncertain call wiring omitted.

Main entry points: [`experiments/v5_0_dichotomy_stats/dichotomy_stats.py`](https://github.com/star-ga/nn_universe/blob/main/experiments/v5_0_dichotomy_stats/dichotomy_stats.py) (Dichotomy statistics), [`experiments/v6_0_depth_mechanism`](https://github.com/star-ga/nn_universe/tree/main/experiments/v6_0_depth_mechanism) (Depth mechanism), [`experiments/v4_0_uniqueness`](https://github.com/star-ga/nn_universe/tree/main/experiments/v4_0_uniqueness) (Uniqueness panel), [`experiments/v12_partition_invariant`](https://github.com/star-ga/nn_universe/tree/main/experiments/v12_partition_invariant) (Partition analysis)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_scaling["Scaling and mechanism"]
  node_v1_scaling["Initial scaling"]
  node_v12_scaling["Extended scaling"]
  node_depth_mechanism["Depth mechanism"]
  node_mechanism_controls["Mechanism controls"]
end

subgraph group_substrates["Substrate experiments"]
  node_uniqueness["Uniqueness panel"]
  node_qec["QEC experiments"]
  node_symbolic["Symbolic task"]
  node_vision["Vision task"]
  node_u1_lattice["U&#40;1&#41; lattice<br/>[lattice_u1.py]"]
  node_su2_lattice["SU&#40;2&#41; lattice<br/>[lattice_su2.py]"]
  node_tensor_network["Tensor network"]
end

subgraph group_modern["Modern architectures"]
  node_modern_arch["Modern architecture panel"]
  node_production_baselines["Production baselines"]
  node_pythia_moe["MoE measurements"]
end

subgraph group_analysis["Statistical analysis"]
  node_partition_analysis["Partition analysis"]
  node_dichotomy_stats["Dichotomy statistics<br/>[dichotomy_stats.py]"]
  node_statistics["Sensitivity and bootstrap"]
  node_mock_alpha["Mock α-drift<br/>[mock_pipeline.py]"]
  node_real_alpha_stub["α-drift data stub"]
end

node_researcher(("Researcher"))

node_researcher -->|"runs"| node_v1_scaling
node_researcher -->|"runs"| node_v12_scaling
node_researcher -->|"runs"| node_depth_mechanism
node_researcher -->|"runs"| node_uniqueness
node_researcher -->|"runs"| node_modern_arch
node_researcher -->|"runs"| node_production_baselines
node_researcher -->|"runs"| node_qec
node_researcher -->|"runs"| node_u1_lattice
node_researcher -->|"runs"| node_su2_lattice
node_researcher -->|"runs"| node_tensor_network
node_researcher -->|"runs"| node_symbolic
node_researcher -->|"runs"| node_vision
node_researcher -->|"runs"| node_pythia_moe
node_researcher -->|"runs"| node_mock_alpha
node_researcher -->|"runs"| node_real_alpha_stub
node_researcher -->|"runs"| node_partition_analysis
node_researcher -->|"runs"| node_statistics
node_researcher -->|"runs"| node_dichotomy_stats
node_depth_mechanism -->|"tests bounds"| node_mechanism_controls
node_uniqueness -->|"supplies results"| node_dichotomy_stats
node_dichotomy_stats -->|"supports inference"| node_statistics
node_partition_analysis -->|"tests partitioning"| node_dichotomy_stats
node_mock_alpha -.->|"informs protocol"| node_real_alpha_stub

click node_v1_scaling "https://github.com/star-ga/nn_universe/blob/main/experiments/v1_baseline/scaling_experiment.py"
click node_v12_scaling "https://github.com/star-ga/nn_universe/tree/main/experiments/v1_2_scaling"
click node_depth_mechanism "https://github.com/star-ga/nn_universe/tree/main/experiments/v6_0_depth_mechanism"
click node_mechanism_controls "https://github.com/star-ga/nn_universe/tree/main/experiments/v6_0_mechanism"
click node_uniqueness "https://github.com/star-ga/nn_universe/tree/main/experiments/v4_0_uniqueness"
click node_qec "https://github.com/star-ga/nn_universe/tree/main/experiments/v2_1_qec"
click node_symbolic "https://github.com/star-ga/nn_universe/blob/main/experiments/v3_0_task3_symbolic/symbolic_regression.py"
click node_vision "https://github.com/star-ga/nn_universe/blob/main/experiments/v3_0_task4_vision/vision_classification.py"
click node_u1_lattice "https://github.com/star-ga/nn_universe/blob/main/experiments/v5_0_lattice_qcd/lattice_u1.py"
click node_su2_lattice "https://github.com/star-ga/nn_universe/blob/main/experiments/v7_0_lattice_su2/lattice_su2.py"
click node_tensor_network "https://github.com/star-ga/nn_universe/tree/main/experiments/v8_0_tensor_network"
click node_modern_arch "https://github.com/star-ga/nn_universe/tree/main/experiments/v9_modern_arch"
click node_production_baselines "https://github.com/star-ga/nn_universe/tree/main/experiments/v10_baselines"
click node_pythia_moe "https://github.com/star-ga/nn_universe/tree/main/experiments/v11_runpod_pythia_moe"
click node_partition_analysis "https://github.com/star-ga/nn_universe/tree/main/experiments/v12_partition_invariant"
click node_dichotomy_stats "https://github.com/star-ga/nn_universe/blob/main/experiments/v5_0_dichotomy_stats/dichotomy_stats.py"
click node_statistics "https://github.com/star-ga/nn_universe/tree/main/experiments/v4_3_statistics"
click node_mock_alpha "https://github.com/star-ga/nn_universe/blob/main/experiments/v3_1_alpha/mock_pipeline.py"
click node_real_alpha_stub "https://github.com/star-ga/nn_universe/blob/main/experiments/v3_1_alpha/real_data_pipeline.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_v1_scaling,node_v12_scaling,node_depth_mechanism,node_mechanism_controls toneBlue
class node_uniqueness,node_qec,node_symbolic,node_vision,node_u1_lattice,node_su2_lattice,node_tensor_network toneAmber
class node_modern_arch,node_production_baselines,node_pythia_moe toneMint
class node_partition_analysis,node_dichotomy_stats,node_statistics,node_mock_alpha,node_real_alpha_stub toneRose
class node_researcher toneIndigo
```

## Components

### Scaling and mechanism

- [Initial scaling](https://github.com/star-ga/nn_universe/blob/main/experiments/v1_baseline/scaling_experiment.py): `experiments/v1_baseline/scaling_experiment.py`
- [Extended scaling](https://github.com/star-ga/nn_universe/tree/main/experiments/v1_2_scaling): `experiments/v1_2_scaling`
- [Depth mechanism](https://github.com/star-ga/nn_universe/tree/main/experiments/v6_0_depth_mechanism): `experiments/v6_0_depth_mechanism`
- [Mechanism controls](https://github.com/star-ga/nn_universe/tree/main/experiments/v6_0_mechanism): `experiments/v6_0_mechanism`

### Substrate experiments

- [Uniqueness panel](https://github.com/star-ga/nn_universe/tree/main/experiments/v4_0_uniqueness): `experiments/v4_0_uniqueness`
- [QEC experiments](https://github.com/star-ga/nn_universe/tree/main/experiments/v2_1_qec): `experiments/v2_1_qec`
- [Symbolic task](https://github.com/star-ga/nn_universe/blob/main/experiments/v3_0_task3_symbolic/symbolic_regression.py): `experiments/v3_0_task3_symbolic/symbolic_regression.py`
- [Vision task](https://github.com/star-ga/nn_universe/blob/main/experiments/v3_0_task4_vision/vision_classification.py): `experiments/v3_0_task4_vision/vision_classification.py`
- [U(1) lattice](https://github.com/star-ga/nn_universe/blob/main/experiments/v5_0_lattice_qcd/lattice_u1.py): `experiments/v5_0_lattice_qcd/lattice_u1.py`
- [SU(2) lattice](https://github.com/star-ga/nn_universe/blob/main/experiments/v7_0_lattice_su2/lattice_su2.py): `experiments/v7_0_lattice_su2/lattice_su2.py`
- [Tensor network](https://github.com/star-ga/nn_universe/tree/main/experiments/v8_0_tensor_network): `experiments/v8_0_tensor_network`

### Modern architectures

- [Modern architecture panel](https://github.com/star-ga/nn_universe/tree/main/experiments/v9_modern_arch): `experiments/v9_modern_arch`
- [Production baselines](https://github.com/star-ga/nn_universe/tree/main/experiments/v10_baselines): `experiments/v10_baselines`
- [MoE measurements](https://github.com/star-ga/nn_universe/tree/main/experiments/v11_runpod_pythia_moe): `experiments/v11_runpod_pythia_moe`

### Statistical analysis

- [Partition analysis](https://github.com/star-ga/nn_universe/tree/main/experiments/v12_partition_invariant): `experiments/v12_partition_invariant`
- [Dichotomy statistics](https://github.com/star-ga/nn_universe/blob/main/experiments/v5_0_dichotomy_stats/dichotomy_stats.py): `experiments/v5_0_dichotomy_stats/dichotomy_stats.py`
- [Sensitivity and bootstrap](https://github.com/star-ga/nn_universe/tree/main/experiments/v4_3_statistics): `experiments/v4_3_statistics`
- [Mock α-drift](https://github.com/star-ga/nn_universe/blob/main/experiments/v3_1_alpha/mock_pipeline.py): `experiments/v3_1_alpha/mock_pipeline.py`
- [α-drift data stub](https://github.com/star-ga/nn_universe/blob/main/experiments/v3_1_alpha/real_data_pipeline.py): `experiments/v3_1_alpha/real_data_pipeline.py`

### Other components

- **Researcher**

## Connections

- Researcher → Initial scaling: runs
- Researcher → Extended scaling: runs
- Researcher → Depth mechanism: runs
- Researcher → Uniqueness panel: runs
- Researcher → Modern architecture panel: runs
- Researcher → Production baselines: runs
- Researcher → QEC experiments: runs
- Researcher → U(1) lattice: runs
- Researcher → SU(2) lattice: runs
- Researcher → Tensor network: runs
- Researcher → Symbolic task: runs
- Researcher → Vision task: runs
- Researcher → MoE measurements: runs
- Researcher → Mock α-drift: runs
- Researcher → α-drift data stub: runs
- Researcher → Partition analysis: runs
- Researcher → Sensitivity and bootstrap: runs
- Researcher → Dichotomy statistics: runs
- Depth mechanism → Mechanism controls: tests bounds
- Uniqueness panel → Dichotomy statistics: supplies results
- Dichotomy statistics → Sensitivity and bootstrap: supports inference
- Partition analysis → Dichotomy statistics: tests partitioning
- Mock α-drift → α-drift data stub: informs protocol