trustbench 0.2.0__tar.gz

trustbench-0.2.0/PKG-INFO

@@ -0,0 +1,296 @@
+Metadata-Version: 2.4
+Name: trustbench
+Version: 0.2.0
+Summary: TrustBench: Evaluation framework for ML model reliability, robustness, and uncertainty.
+Keywords: machine-learning,evaluation,reliability,robustness,uncertainty,calibration,ood-detection,fairness
+Author: Uni-Creator
+Author-email: Uni-Creator <abhayr24564@gmail.com>
+License-Expression: Apache-2.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: scipy>=1.10.0
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: click>=8.1.0
+Requires-Dist: jinja2>=3.1.6
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: trustbench[torch,storage,api,reporting,onnx] ; extra == 'all'
+Requires-Dist: fastapi>=0.100.0 ; extra == 'api'
+Requires-Dist: uvicorn[standard]>=0.20.0 ; extra == 'api'
+Requires-Dist: jax>=0.4.20 ; extra == 'jax'
+Requires-Dist: onnxruntime>=1.16.0 ; extra == 'onnx'
+Requires-Dist: torch>=2.0.0 ; extra == 'pytorch'
+Requires-Dist: torchvision>=0.15.0 ; extra == 'pytorch'
+Requires-Dist: plotly>=5.0.0 ; extra == 'reporting'
+Requires-Dist: sqlalchemy>=2.0.0 ; extra == 'storage'
+Requires-Dist: tensorflow>=2.15.0 ; extra == 'tensorflow'
+Requires-Dist: torch>=2.0.0 ; extra == 'torch'
+Requires-Dist: torchvision>=0.15.0 ; extra == 'torch'
+Requires-Python: >=3.11
+Provides-Extra: all
+Provides-Extra: api
+Provides-Extra: jax
+Provides-Extra: onnx
+Provides-Extra: pytorch
+Provides-Extra: reporting
+Provides-Extra: storage
+Provides-Extra: tensorflow
+Provides-Extra: torch
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+# TrustBench
+
+**ML Reliability, Robustness, Uncertainty & Fairness Evaluation Framework**
+
+[![PyPI version](https://img.shields.io/badge/pypi-v0.2.0-blue.svg)](https://pypi.org/project/trustbench/)
+[![Python Versions](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue.svg)](https://pypi.org/project/trustbench/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
+[![CI Status](https://img.shields.io/badge/build-passing-brightgreen.svg)](.github/workflows/ci.yml)
+[![Tests](https://img.shields.io/badge/tests-194%20passed-success.svg)](tests/)
+
+</div>
+
+---
+
+TrustBench is a framework-independent machine learning evaluation library designed to measure how reliable models remain under distribution shifts, input corruptions, calibration failures, and algorithmic bias.
+
+Traditional model evaluation focuses almost exclusively on accuracy. TrustBench investigates whether models remain reliable in deployment:
+- **Calibration**: Does predicted confidence reflect the true probability of correctness?
+- **Robustness**: How gracefully does performance degrade under physical, digital, and environmental corruptions?
+- **Uncertainty & Error Detection**: Can predictive entropy and free energy identify incorrect predictions before downstream failures occur?
+- **Selective Prediction**: What error rate is achieved when models defer low-confidence decisions?
+- **Multi-Framework**: Evaluate PyTorch, Scikit-learn, ONNX Runtime, TensorFlow/Keras, and JAX models using identical contracts.
+- **Multi-Task**: Native evaluators for Classification, Regression, Information Retrieval, and Semantic Segmentation.
+
+---
+
+## Architecture Overview
+
+```mermaid
+flowchart TD
+    UserConfig["trustbench.yaml / Python API"] --> TB["TrustBench Orchestrator"]
+    
+    subgraph FrameworkAdapters ["Framework Adapters (Optional)"]
+        Torch["PyTorch (nn.Module)"]
+        SKLearn["Scikit-learn (Estimators)"]
+        ONNX["ONNX Runtime (.onnx)"]
+        Keras["TensorFlow / Keras"]
+        JAX["JAX / Flax"]
+    end
+    
+    subgraph TaskPipelines ["Task-Specific Evaluators"]
+        Cls["Classification\n(Accuracy, Macro-F1, Confusion Matrix)"]
+        Calib["Calibration & Reliability\n(ECE, AdaECE, Brier, Temperature)"]
+        Unc["Uncertainty & Detection\n(Entropy, Energy, AUROC, AUPRC)"]
+        Sel["Selective Prediction\n(Risk-Coverage, AURC)"]
+        Rob["Robustness Suite\n(Noise, Blur, Brightness 1-5)"]
+        Reg["Regression Suite\n(MAE, RMSE, R², 95% PICP)"]
+        Ret["Retrieval Suite\n(Recall@K, MRR, nDCG@K)"]
+        Seg["Segmentation Suite\n(mIoU, Dice, Pixel Acc)"]
+        Fair["Fairness Suite\n(Demographic Parity, Disparate Impact)"]
+    end
+    
+    subgraph StorageReporting ["Storage & Reporting"]
+        FSStore["Filesystem Store\n(Atomic Writes & Checksums)"]
+        SQLiteStore["SQLite & SQLAlchemy\n(Queryable Registry)"]
+        HTMLRep["Interactive HTML Report\n(Zero-Dependency Plotly)"]
+        JSONRep["Versioned JSON Schema\n(v1.0 Lineage)"]
+    end
+
+    FrameworkAdapters --> TB
+    TB --> TaskPipelines
+    TaskPipelines --> StorageReporting
+```
+
+---
+
+## Installation
+
+TrustBench features a lightweight core with optional framework groups:
+
+```bash
+# Core installation (NumPy, SciPy, Scikit-learn, Click, Pydantic)
+pip install trustbench
+
+# For PyTorch model evaluation
+pip install "trustbench[pytorch]"
+
+# For ONNX Runtime inference
+pip install "trustbench[onnx]"
+
+# Full installation (all frameworks, storage, and visualization)
+pip install "trustbench[all]"
+```
+
+See the [Installation Guide](docs/installation.md) for detailed platform requirements.
+
+---
+
+## 5-Minute Quickstart
+
+### 1. Command Line Interface (CLI)
+
+```bash
+# Initialize a starter configuration
+trustbench init
+
+# Validate configuration paths and settings
+trustbench validate trustbench.yaml
+
+# Run evaluation and generate reports
+trustbench evaluate trustbench.yaml
+```
+
+### 2. Python API
+
+```python
+import numpy as np
+from sklearn.linear_model import LogisticRegression
+from trustbench import TrustBench, InMemoryDatasetAdapter
+
+# 1. Train or load your model
+X_train = np.random.randn(200, 4)
+y_train = np.random.randint(0, 2, size=200)
+clf = LogisticRegression().fit(X_train, y_train)
+
+# 2. Prepare test dataset
+X_test = np.random.randn(50, 4)
+y_test = np.random.randint(0, 2, size=50)
+dataset = InMemoryDatasetAdapter(inputs=X_test, labels=y_test)
+
+# 3. Evaluate reliability
+bench = TrustBench(model=clf, dataset=dataset)
+result = bench.evaluate()
+
+print(f"Accuracy:    {result.metrics['classification']['accuracy']:.2%}")
+print(f"Brier Score: {result.metrics['calibration']['brier_score']:.4f}")
+print(f"ECE:         {result.metrics['calibration']['ece']:.4f}")
+```
+
+---
+
+## Multi-Task Evaluation
+
+### Continuous Regression Evaluation
+```python
+from trustbench import evaluate_regression, InMemoryDatasetAdapter
+from sklearn.linear_model import Ridge
+import numpy as np
+
+model = Ridge().fit(X_train, y_train)
+dataset = InMemoryDatasetAdapter(inputs=X_test, labels=y_test)
+
+result = evaluate_regression(model, dataset)
+print(f"MAE:  {result.metrics['mae']:.3f}")
+print(f"RMSE: {result.metrics['rmse']:.3f}")
+print(f"R²:   {result.metrics['r2']:.3f}")
+```
+
+### Information Retrieval Evaluation
+```python
+from trustbench import evaluate_retrieval
+
+ground_truth = {"q1": ["docA", "docB"], "q2": ["docC"]}
+retrieved = {"q1": ["docA", "docX", "docB"], "q2": ["docY", "docC"]}
+
+res = evaluate_retrieval(ground_truth, retrieved, k_list=(1, 3))
+print(f"MRR:      {res.metrics['mrr']:.3f}")
+print(f"Recall@1: {res.metrics['recall@1']:.3f}")
+print(f"nDCG@3:   {res.metrics['ndcg@3']:.3f}")
+```
+
+### Semantic Segmentation Evaluation
+```python
+from trustbench import evaluate_segmentation
+
+result = evaluate_segmentation(segmentation_model, segmentation_dataset, num_classes=21)
+print(f"Mean IoU:       {result.metrics['miou']:.3f}")
+print(f"Dice (F1):      {result.metrics['dice']:.3f}")
+print(f"Pixel Accuracy: {result.metrics['pixel_accuracy']:.2%}")
+```
+
+---
+
+## Key Metrics Reference
+
+| Category | Metrics Implemented |
+|---|---|
+| **Classification** | Accuracy, Balanced Accuracy, Precision, Recall, Macro-F1, Confusion Matrix |
+| **Calibration** | Expected Calibration Error (ECE), Adaptive ECE, Maximum Calibration Error (MCE), Brier Score, NLL |
+| **Uncertainty** | Predictive Shannon Entropy, Maximum Softmax Probability (MSP), Free Energy |
+| **Error Detection** | AUROC, AUPRC, False Positive Rate at 95% TPR (FPR@95%TPR), Minimum Detection Error |
+| **Selective Prediction** | Risk-Coverage Trade-off Curves, Area Under Risk-Coverage (AURC), Excess AURC |
+| **Robustness** | Gaussian Noise, Blur, Brightness, Defocus, Contrast, Corrupted Accuracy Drop |
+| **Regression** | MAE, MSE, RMSE, $R^2$, MedAE, MAPE, Max Error, 95% Interval Coverage (PICP, MPIW) |
+| **Retrieval** | Mean Reciprocal Rank (MRR), Mean Average Precision (MAP), Recall@K, Precision@K, nDCG@K |
+| **Segmentation** | Mean IoU (mIoU), Dice (F1), Pixel Accuracy, Frequency-Weighted IoU (FWIoU) |
+| **Fairness** | Demographic Parity Difference, Disparate Impact Ratio, Equalized Odds Difference |
+
+See [Metrics Documentation](docs/metrics.md) for mathematical derivations.
+
+---
+
+## Tutorials & Examples
+
+Ready-to-run examples are available in the [`examples/`](examples/) directory:
+
+1. **[01_evaluate_pytorch_model.py](examples/01_evaluate_pytorch_model.py)**: Evaluate custom PyTorch `nn.Module`.
+2. **[02_evaluate_cifar10.py](examples/02_evaluate_cifar10.py)**: End-to-end CIFAR-10 ResNet evaluation via configuration.
+3. **[03_robustness_benchmark.py](examples/03_robustness_benchmark.py)**: Evaluate accuracy degradation across noise & corruptions.
+4. **[04_analyze_calibration.py](examples/04_analyze_calibration.py)**: Compute ECE and fit validation temperature scaling.
+5. **[05_evaluate_uncertainty.py](examples/05_evaluate_uncertainty.py)**: Predict error detection AUROC and risk-coverage curves.
+6. **[06_compare_checkpoints.py](examples/06_compare_checkpoints.py)**: Quantify statistical differentials between model checkpoints.
+7. **[07_save_and_reproduce_experiment.py](examples/07_save_and_reproduce_experiment.py)**: Atomic experiment persistence and checksum verification.
+8. **[08_create_custom_metric.py](examples/08_create_custom_metric.py)**: Register custom evaluation scoring functions.
+9. **[09_create_custom_model_adapter.py](examples/09_create_custom_model_adapter.py)**: Implement the runtime `ModelAdapter` protocol.
+
+---
+
+## Documentation
+
+Full documentation is available in the [`docs/`](docs/) directory:
+- [Installation Guide](docs/installation.md)
+- [Quickstart Guide](docs/quickstart.md)
+- [Python API Reference](docs/api.md)
+- [CLI Reference](docs/cli.md)
+- [Configuration Guide](docs/configuration.md)
+- [Model Adapters](docs/model-adapters.md)
+- [Dataset Adapters](docs/dataset-adapters.md)
+- [Metrics Documentation](docs/metrics.md)
+- [Robustness Testing](docs/robustness.md)
+- [Experiment Tracking](docs/experiments.md)
+- [Reporting & Visualization](docs/reporting.md)
+- [Plugin Development](docs/plugins.md)
+- [Troubleshooting & FAQ](docs/troubleshooting.md)
+
+---
+
+## Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) and our [Code of Conduct](CODE_OF_CONDUCT.md).
+
+```bash
+# Run tests
+pytest
+
+# Check code style
+ruff check .
+
+# Static type analysis
+mypy src/trustbench/core src/trustbench/reporting src/trustbench/metrics
+```
+
+---
+
+## License
+
+TrustBench is open-source software licensed under the [Apache License, Version 2.0](LICENSE).

trustbench-0.2.0/README.md

@@ -0,0 +1,249 @@
+<div align="center">
+
+# TrustBench
+
+**ML Reliability, Robustness, Uncertainty & Fairness Evaluation Framework**
+
+[![PyPI version](https://img.shields.io/badge/pypi-v0.2.0-blue.svg)](https://pypi.org/project/trustbench/)
+[![Python Versions](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue.svg)](https://pypi.org/project/trustbench/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
+[![CI Status](https://img.shields.io/badge/build-passing-brightgreen.svg)](.github/workflows/ci.yml)
+[![Tests](https://img.shields.io/badge/tests-194%20passed-success.svg)](tests/)
+
+</div>
+
+---
+
+TrustBench is a framework-independent machine learning evaluation library designed to measure how reliable models remain under distribution shifts, input corruptions, calibration failures, and algorithmic bias.
+
+Traditional model evaluation focuses almost exclusively on accuracy. TrustBench investigates whether models remain reliable in deployment:
+- **Calibration**: Does predicted confidence reflect the true probability of correctness?
+- **Robustness**: How gracefully does performance degrade under physical, digital, and environmental corruptions?
+- **Uncertainty & Error Detection**: Can predictive entropy and free energy identify incorrect predictions before downstream failures occur?
+- **Selective Prediction**: What error rate is achieved when models defer low-confidence decisions?
+- **Multi-Framework**: Evaluate PyTorch, Scikit-learn, ONNX Runtime, TensorFlow/Keras, and JAX models using identical contracts.
+- **Multi-Task**: Native evaluators for Classification, Regression, Information Retrieval, and Semantic Segmentation.
+
+---
+
+## Architecture Overview
+
+```mermaid
+flowchart TD
+    UserConfig["trustbench.yaml / Python API"] --> TB["TrustBench Orchestrator"]
+    
+    subgraph FrameworkAdapters ["Framework Adapters (Optional)"]
+        Torch["PyTorch (nn.Module)"]
+        SKLearn["Scikit-learn (Estimators)"]
+        ONNX["ONNX Runtime (.onnx)"]
+        Keras["TensorFlow / Keras"]
+        JAX["JAX / Flax"]
+    end
+    
+    subgraph TaskPipelines ["Task-Specific Evaluators"]
+        Cls["Classification\n(Accuracy, Macro-F1, Confusion Matrix)"]
+        Calib["Calibration & Reliability\n(ECE, AdaECE, Brier, Temperature)"]
+        Unc["Uncertainty & Detection\n(Entropy, Energy, AUROC, AUPRC)"]
+        Sel["Selective Prediction\n(Risk-Coverage, AURC)"]
+        Rob["Robustness Suite\n(Noise, Blur, Brightness 1-5)"]
+        Reg["Regression Suite\n(MAE, RMSE, R², 95% PICP)"]
+        Ret["Retrieval Suite\n(Recall@K, MRR, nDCG@K)"]
+        Seg["Segmentation Suite\n(mIoU, Dice, Pixel Acc)"]
+        Fair["Fairness Suite\n(Demographic Parity, Disparate Impact)"]
+    end
+    
+    subgraph StorageReporting ["Storage & Reporting"]
+        FSStore["Filesystem Store\n(Atomic Writes & Checksums)"]
+        SQLiteStore["SQLite & SQLAlchemy\n(Queryable Registry)"]
+        HTMLRep["Interactive HTML Report\n(Zero-Dependency Plotly)"]
+        JSONRep["Versioned JSON Schema\n(v1.0 Lineage)"]
+    end
+
+    FrameworkAdapters --> TB
+    TB --> TaskPipelines
+    TaskPipelines --> StorageReporting
+```
+
+---
+
+## Installation
+
+TrustBench features a lightweight core with optional framework groups:
+
+```bash
+# Core installation (NumPy, SciPy, Scikit-learn, Click, Pydantic)
+pip install trustbench
+
+# For PyTorch model evaluation
+pip install "trustbench[pytorch]"
+
+# For ONNX Runtime inference
+pip install "trustbench[onnx]"
+
+# Full installation (all frameworks, storage, and visualization)
+pip install "trustbench[all]"
+```
+
+See the [Installation Guide](docs/installation.md) for detailed platform requirements.
+
+---
+
+## 5-Minute Quickstart
+
+### 1. Command Line Interface (CLI)
+
+```bash
+# Initialize a starter configuration
+trustbench init
+
+# Validate configuration paths and settings
+trustbench validate trustbench.yaml
+
+# Run evaluation and generate reports
+trustbench evaluate trustbench.yaml
+```
+
+### 2. Python API
+
+```python
+import numpy as np
+from sklearn.linear_model import LogisticRegression
+from trustbench import TrustBench, InMemoryDatasetAdapter
+
+# 1. Train or load your model
+X_train = np.random.randn(200, 4)
+y_train = np.random.randint(0, 2, size=200)
+clf = LogisticRegression().fit(X_train, y_train)
+
+# 2. Prepare test dataset
+X_test = np.random.randn(50, 4)
+y_test = np.random.randint(0, 2, size=50)
+dataset = InMemoryDatasetAdapter(inputs=X_test, labels=y_test)
+
+# 3. Evaluate reliability
+bench = TrustBench(model=clf, dataset=dataset)
+result = bench.evaluate()
+
+print(f"Accuracy:    {result.metrics['classification']['accuracy']:.2%}")
+print(f"Brier Score: {result.metrics['calibration']['brier_score']:.4f}")
+print(f"ECE:         {result.metrics['calibration']['ece']:.4f}")
+```
+
+---
+
+## Multi-Task Evaluation
+
+### Continuous Regression Evaluation
+```python
+from trustbench import evaluate_regression, InMemoryDatasetAdapter
+from sklearn.linear_model import Ridge
+import numpy as np
+
+model = Ridge().fit(X_train, y_train)
+dataset = InMemoryDatasetAdapter(inputs=X_test, labels=y_test)
+
+result = evaluate_regression(model, dataset)
+print(f"MAE:  {result.metrics['mae']:.3f}")
+print(f"RMSE: {result.metrics['rmse']:.3f}")
+print(f"R²:   {result.metrics['r2']:.3f}")
+```
+
+### Information Retrieval Evaluation
+```python
+from trustbench import evaluate_retrieval
+
+ground_truth = {"q1": ["docA", "docB"], "q2": ["docC"]}
+retrieved = {"q1": ["docA", "docX", "docB"], "q2": ["docY", "docC"]}
+
+res = evaluate_retrieval(ground_truth, retrieved, k_list=(1, 3))
+print(f"MRR:      {res.metrics['mrr']:.3f}")
+print(f"Recall@1: {res.metrics['recall@1']:.3f}")
+print(f"nDCG@3:   {res.metrics['ndcg@3']:.3f}")
+```
+
+### Semantic Segmentation Evaluation
+```python
+from trustbench import evaluate_segmentation
+
+result = evaluate_segmentation(segmentation_model, segmentation_dataset, num_classes=21)
+print(f"Mean IoU:       {result.metrics['miou']:.3f}")
+print(f"Dice (F1):      {result.metrics['dice']:.3f}")
+print(f"Pixel Accuracy: {result.metrics['pixel_accuracy']:.2%}")
+```
+
+---
+
+## Key Metrics Reference
+
+| Category | Metrics Implemented |
+|---|---|
+| **Classification** | Accuracy, Balanced Accuracy, Precision, Recall, Macro-F1, Confusion Matrix |
+| **Calibration** | Expected Calibration Error (ECE), Adaptive ECE, Maximum Calibration Error (MCE), Brier Score, NLL |
+| **Uncertainty** | Predictive Shannon Entropy, Maximum Softmax Probability (MSP), Free Energy |
+| **Error Detection** | AUROC, AUPRC, False Positive Rate at 95% TPR (FPR@95%TPR), Minimum Detection Error |
+| **Selective Prediction** | Risk-Coverage Trade-off Curves, Area Under Risk-Coverage (AURC), Excess AURC |
+| **Robustness** | Gaussian Noise, Blur, Brightness, Defocus, Contrast, Corrupted Accuracy Drop |
+| **Regression** | MAE, MSE, RMSE, $R^2$, MedAE, MAPE, Max Error, 95% Interval Coverage (PICP, MPIW) |
+| **Retrieval** | Mean Reciprocal Rank (MRR), Mean Average Precision (MAP), Recall@K, Precision@K, nDCG@K |
+| **Segmentation** | Mean IoU (mIoU), Dice (F1), Pixel Accuracy, Frequency-Weighted IoU (FWIoU) |
+| **Fairness** | Demographic Parity Difference, Disparate Impact Ratio, Equalized Odds Difference |
+
+See [Metrics Documentation](docs/metrics.md) for mathematical derivations.
+
+---
+
+## Tutorials & Examples
+
+Ready-to-run examples are available in the [`examples/`](examples/) directory:
+
+1. **[01_evaluate_pytorch_model.py](examples/01_evaluate_pytorch_model.py)**: Evaluate custom PyTorch `nn.Module`.
+2. **[02_evaluate_cifar10.py](examples/02_evaluate_cifar10.py)**: End-to-end CIFAR-10 ResNet evaluation via configuration.
+3. **[03_robustness_benchmark.py](examples/03_robustness_benchmark.py)**: Evaluate accuracy degradation across noise & corruptions.
+4. **[04_analyze_calibration.py](examples/04_analyze_calibration.py)**: Compute ECE and fit validation temperature scaling.
+5. **[05_evaluate_uncertainty.py](examples/05_evaluate_uncertainty.py)**: Predict error detection AUROC and risk-coverage curves.
+6. **[06_compare_checkpoints.py](examples/06_compare_checkpoints.py)**: Quantify statistical differentials between model checkpoints.
+7. **[07_save_and_reproduce_experiment.py](examples/07_save_and_reproduce_experiment.py)**: Atomic experiment persistence and checksum verification.
+8. **[08_create_custom_metric.py](examples/08_create_custom_metric.py)**: Register custom evaluation scoring functions.
+9. **[09_create_custom_model_adapter.py](examples/09_create_custom_model_adapter.py)**: Implement the runtime `ModelAdapter` protocol.
+
+---
+
+## Documentation
+
+Full documentation is available in the [`docs/`](docs/) directory:
+- [Installation Guide](docs/installation.md)
+- [Quickstart Guide](docs/quickstart.md)
+- [Python API Reference](docs/api.md)
+- [CLI Reference](docs/cli.md)
+- [Configuration Guide](docs/configuration.md)
+- [Model Adapters](docs/model-adapters.md)
+- [Dataset Adapters](docs/dataset-adapters.md)
+- [Metrics Documentation](docs/metrics.md)
+- [Robustness Testing](docs/robustness.md)
+- [Experiment Tracking](docs/experiments.md)
+- [Reporting & Visualization](docs/reporting.md)
+- [Plugin Development](docs/plugins.md)
+- [Troubleshooting & FAQ](docs/troubleshooting.md)
+
+---
+
+## Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) and our [Code of Conduct](CODE_OF_CONDUCT.md).
+
+```bash
+# Run tests
+pytest
+
+# Check code style
+ruff check .
+
+# Static type analysis
+mypy src/trustbench/core src/trustbench/reporting src/trustbench/metrics
+```
+
+---
+
+## License
+
+TrustBench is open-source software licensed under the [Apache License, Version 2.0](LICENSE).

trustbench-0.2.0/pyproject.toml

@@ -0,0 +1,82 @@
+[project]
+name = "trustbench"
+version = "0.2.0"
+description = "TrustBench: Evaluation framework for ML model reliability, robustness, and uncertainty."
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.11"
+keywords = [
+    "machine-learning",
+    "evaluation",
+    "reliability",
+    "robustness",
+    "uncertainty",
+    "calibration",
+    "ood-detection",
+    "fairness",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "numpy>=1.24.0",
+    "scipy>=1.10.0",
+    "scikit-learn>=1.3.0",
+    "pydantic>=2.0.0",
+    "pyyaml>=6.0",
+    "click>=8.1.0",
+    "jinja2>=3.1.6",
+    "pillow>=10.0.0",
+]
+
+[[project.authors]]
+name = "Uni-Creator"
+email = "abhayr24564@gmail.com"
+
+[project.optional-dependencies]
+torch = [
+    "torch>=2.0.0",
+    "torchvision>=0.15.0",
+]
+pytorch = [
+    "torch>=2.0.0",
+    "torchvision>=0.15.0",
+]
+storage = ["sqlalchemy>=2.0.0"]
+api = [
+    "fastapi>=0.100.0",
+    "uvicorn[standard]>=0.20.0",
+]
+reporting = ["plotly>=5.0.0"]
+onnx = ["onnxruntime>=1.16.0"]
+tensorflow = ["tensorflow>=2.15.0"]
+jax = ["jax>=0.4.20"]
+all = ["trustbench[torch,storage,api,reporting,onnx]"]
+
+[project.scripts]
+trustbench = "trustbench.cli.main:app"
+
+[build-system]
+requires = ["uv_build>=0.12.15,<0.13.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "httpx>=0.28.1",
+    "mypy>=2.4.0",
+    "pytest>=9.1.1",
+    "ruff>=0.17.2",
+    "fastapi>=0.100.0",
+    "sqlalchemy>=2.0.0",
+    "torch>=2.0.0",
+    "torchvision>=0.15.0",
+]
+
+[tool.ruff.lint]
+ignore = ["B008"]