Update README.md

README.md

@@ -30,16 +30,17 @@ Benchmarked on 120,000 samples across six input magnitude ranges. Metrics: MAE,
 
 Precision degrades for extremely large magnitude inputs (e.g., >500,000), indicated by increased MAE/MSE, although R2 remains high.
 
-## Important Disclaimer, Safety Warning, & Liability Limitation
+## Crucial Safety Warning, Disclaimers, & Liability Limitation
 
-This model is provided strictly "as is" and "with all faults," without warranty of any kind, express or implied.
+This model is an experimental statistical prototype provided strictly "as is" and "with all faults." The developers, distributors, and contributors disclaim all warranties, express or implied, including but not limited to any implied warranties of merchantability, fitness for a particular purpose, or non-infringement.
 
-*   **Statistical Approximation vs. Exact Arithmetic:** This is a statistical machine learning model, not a hardware-level Arithmetic Logic Unit (ALU). Although optimized using double precision (`torch.float64`), it operates via continuous regression approximation. It **does not** guarantee exact mathematical results. Even with the reduced error rates in v2.0, the absolute error (MAE of 0.706 at high ranges) represents an incorrect mathematical sum. Under no circumstances should this model be deployed in accounting, financial ledgers, navigation, structural engineering, or medical dosage systems where exact addition is mandatory.
-*   **Strict Double Precision (`torch.float64`) Requirement:** This model's weights are configured specifically for double precision. Feeding standard single-precision tensors (`torch.float32`) will result in runtime casting errors, model exceptions, or severe degradation of accuracy. Users are solely responsible for ensuring input compliance.
-*   **Scale Limits and Degradation:** Despite optimization, the model continues to exhibit accuracy degradation as input scale increases, particularly beyond 500,000. It is highly susceptible to extrapolation errors when presented with out-of-distribution values.
-*   **Metric Misinterpretation ($R^2$ Illusion):** The $R^2$ value of `1.000` is a mathematical side effect of high variance at scale and does not mean the model's predictions are error-free. Absolute error metrics (MAE/MSE) must be reviewed to understand actual operational deviations.
-*   **Deserialization Security Risk:** Like all PyTorch models saved as serialized state dictionaries, there is an inherent risk of arbitrary code execution upon loading. When importing the model parameters, users are strongly advised to enforce strict security practices by specifying `weights_only=True` in the PyTorch load call:
+*   **Approximation vs. Deterministic Arithmetic:** Despite utilizing double-precision float optimization (`torch.float64`), this model remains a statistical regression estimator. It does not perform hardware-level or logical arithmetic. Even at its lowest error rates, the model produces mathematically incorrect results (e.g., an absolute error of 0.706 at scale). Under no circumstances should this model be deployed in accounting, critical infrastructure, flight systems, medical dosage software, or any environment where a non-zero margin of mathematical error is unacceptable.
+*   **Strict Precision and Type Constraints:** This model is strictly compiled for double precision (`torch.float64`). Providing standard single-precision tensors (`torch.float32`) or integers will result in casting mismatches, runtime exceptions, or silent, extreme numerical corruption of the output. The responsibility for input validation and strict type casting rests entirely on the user.
+*   **Unpredictable Boundary and Edge-Case Behavior:** The model’s behavior on extreme mathematical boundaries (such as zero, negative values, infinity, subnormal numbers, or NaN inputs) has not been audited or verified. The model may yield highly unstable or volatile outputs when exposed to these values.
+*   **Computational and Operational Overhead:** Performing basic arithmetic operations via a neural network introduces severe computational, memory, and runtime latency overhead compared to native CPU/ALU instructions. It also introduces a massive attack and failure surface, requiring heavy dependencies (such as Python, PyTorch, C++ runtimes, and specific CUDA drivers), all of which can fail independently.
+*   **Statistical Metric Deception ($R^2$):** Users are explicitly warned that the reported $R^2$ score of `1.000` is a statistical artifact of scale variance. It is mathematically deceptive and must not be used to justify the model’s safety, precision, or operational readiness.
+*   **Arbitrary Code Execution (Security Vulnerability):** The serialized model file is saved in PyTorch's default pickle-based format. Loading untrusted `.pt` or `.pth` files can execute arbitrary, malicious code on your system. To mitigate the risk of remote code execution (RCE) and system compromise, you must enforce strict sandboxing and use `weights_only=True`:
     ```python
     torch.load("model.pth", map_location=device, weights_only=True)
     ```
-*   **Assumption of Risk:** The end-user assumes all liability, financial or otherwise, arising from the utilization, deployment, or integration of this model into any hardware or software system.
+*   **Complete Assumption of Risk:** The end-user assumes 100% of the risk associated with integrating this model into any system. The creators shall not be held liable for any direct, indirect, incidental, special, or consequential damages (including but not limited to financial loss, hardware damage, or system downtime) arising from its use.