Spaces:
Sleeping
Sleeping
docs: add Model Card | GitHub navigation header
Browse files
README.md
CHANGED
|
@@ -12,14 +12,12 @@ short_description: Order-Equivariant Probabilistic Decision Model
|
|
| 12 |
|
| 13 |
# InvariantOne — Permutation-Equivariant Decision Model Demo
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
|
| 18 |
-
- **GitHub Repository:** [tradertanmay/InvariantOne](https://github.com/tradertanmay/InvariantOne)
|
| 19 |
-
- **PyPI Package:** [`invariantone==1.0.2`](https://pypi.org/project/invariantone/)
|
| 20 |
|
| 21 |
### Key Characteristics
|
| 22 |
- **Candidate-Independent Scoring:** Each candidate option is encoded independently with context, eliminating position and option-order biases.
|
| 23 |
- **Analytic Distributional Equivariance:** Exact permutation equivariance holds by construction in real arithmetic.
|
| 24 |
-
- **Calibrated Softmax Readout:** Outputs probabilities normalized by frozen calibration temperature
|
| 25 |
-
- **Dynamic Options (
|
|
|
|
| 12 |
|
| 13 |
# InvariantOne — Permutation-Equivariant Decision Model Demo
|
| 14 |
|
| 15 |
+
[Model Card](https://huggingface.co/TanmaySah/InvariantOne-v1) | [GitHub](https://github.com/tradertanmay/InvariantOne)
|
| 16 |
|
| 17 |
+
Interactive demonstration of **InvariantOne-v1**, an order-equivariant probabilistic decision model for runtime multiple-choice action selection.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
### Key Characteristics
|
| 20 |
- **Candidate-Independent Scoring:** Each candidate option is encoded independently with context, eliminating position and option-order biases.
|
| 21 |
- **Analytic Distributional Equivariance:** Exact permutation equivariance holds by construction in real arithmetic.
|
| 22 |
+
- **Calibrated Softmax Readout:** Outputs probabilities normalized by frozen calibration temperature τ* = 1.0091.
|
| 23 |
+
- **Dynamic Options (K ≥ 2):** Supports arbitrary numbers of runtime candidate actions (empirical benchmarks evaluated on K = 4).
|