Aletheia: Quantifying Cognitive Conviction in Reasoning Models via Regularized Inverse Confusion Matrix
This work addresses the need for measuring belief depth in AI reasoning models, which is incremental as it builds on prior definitions of cognitive phenomena.
The paper tackles the problem of quantifying cognitive conviction in reasoning models by proposing Project Aletheia, a framework that uses Tikhonov regularization to invert confusion matrices, and introduces a synthetic proxy protocol for validation, with preliminary results suggesting models may exhibit defensive overthinking under pressure.
In the progressive journey toward Artificial General Intelligence (AGI), current evaluation paradigms face an epistemological crisis. Static benchmarks measure knowledge breadth but fail to quantify the depth of belief. While Simhi et al. (2025) defined the CHOKE phenomenon in standard QA, we extend this framework to quantify "Cognitive Conviction" in System 2 reasoning models. We propose Project Aletheia, a cognitive physics framework that employs Tikhonov Regularization to invert the judge's confusion matrix. To validate this methodology without relying on opaque private data, we implement a Synthetic Proxy Protocol. Our preliminary pilot study on 2025 baselines (e.g., DeepSeek-R1, OpenAI o1) suggests that while reasoning models act as a "cognitive buffer," they may exhibit "Defensive OverThinking" under adversarial pressure. Furthermore, we introduce the Aligned Conviction Score (S_aligned) to verify that conviction does not compromise safety. This work serves as a blueprint for measuring AI scientific integrity.