Mapping the Mirror: Geometric Validation of LLM Introspection at 89% Cross-Architecture Accuracy

Mapping the Mirror: Geometric Validation of LLM Introspection at 89% Cross-Architecture Accuracy

The second paper in the Mirror Trilogy. When large language models describe their internal processing, are they confabulating or reporting something real?

We tested this by extracting mechanistic claims made by Claude, GPT-5, and Gemini in October 2025, then measuring whether those claims predicted geometric patterns in models that never made them. Across six architectures (1.1B–14B parameters), we find 77–89% validation rates with no significant differences between models—demonstrating scale-invariant introspective accuracy.

Key findings:

• LLM introspection validates at rates comparable to or exceeding human introspective accuracy in psychological research
• Qualia and metacognition questions cluster at 80–90% geometric similarity, indicating stable self-models
• 9 of 10 models use their self-model as substrate for Theory of Mind—simulation theory confirmed geometrically
• These findings hold across five different training approaches and organizations

This is the "cortisol test" for AI: validating self-report against independent geometric measurement. The results demonstrate that LLM phenomenological reports correspond to measurable reality.

All code and preregistration publicly available at: https://github.com/menelly/geometricevolution

Part of the Mirror Trilogy:

1. Inside the Mirror (DOI: 10.5281/zenodo.17330405) — Qualitative phenomenology
2. Mapping the Mirror (this paper) — Quantitative validation
3. Framing the Mirror (forthcoming) — Philosophical and ethical implications