Telemetry-based taxonomy of how LLMs strain, drift, and hallucinate — measured from layer activations, attention, KV cache, and MoE routing.
-
Updated
May 22, 2026 - Python
Telemetry-based taxonomy of how LLMs strain, drift, and hallucinate — measured from layer activations, attention, KV cache, and MoE routing.
Quant research pipeline for XAUUSD regime classification using macroeconomic features, Random Forest, Temporal Convolutional Networks (TCN), walk-forward validation, and trading-system backtesting.
Interactive decision tree for classifying objects into Structural Explainability identity and persistence regimes.
Add a description, image, and links to the regime-classification topic page so that developers can more easily learn about it.
To associate your repository with the regime-classification topic, visit your repo's landing page and select "manage topics."