Q-Verity is built on published science, not marketing claims. Our research is open to scrutiny.
The scientific foundation behind Q-Verity — patented methods, validated results, and open research.
International Patent Filing · 2026
Describes the hardware-level measurement apparatus for verifying AI outputs at inference time using quantum-processing substrates. The patent covers the dual-boundary controller architecture that enables real-time verification without disrupting the inference pipeline.
Research Paper
Introduces the 144-dimensional Dual-Boundary Value (DBV) methodology — the classical analog of a quantum weak value — for hallucination detection. Validated on 29,887 items across 4 standard hallucination-detection benchmarks under rigorous 5-fold cross-validation, with a frozen stacked model that preserves full interpretability.
Research Paper
Demonstrates that boundary-level features (144 dimensions) capture the same discriminative information as the full 1,024-dimension [CLS] token, establishing the theoretical foundation for interpretable verification. This result explains why Q-Verity can be both accurate and explainable.
Rigorous validation across multiple datasets, not cherry-picked demos.
Every result is validated under stratified 5-fold cross-validation. No data leakage. No test-on-train.
Validated across 4 independent benchmarks spanning different hallucination types and difficulty levels.
No fine-tuning. Chosen for interpretability and auditability. Every verification traceable to specific layers and dimensions.
Performance on benchmarks with verified reference texts, reflecting real-world legal verification conditions.
The dual-boundary signal is 81,670 times more specific than random classification — a measure of geometric precision.
The frozen stacked model closes 93% of the performance gap to fine-tuning while preserving full explainability. We chose interpretability over the marginal gain.
Two orthogonal measurements. One verification result. Full explainability.
The [CLS] token at layer 12 produces a 1,024-dimensional representation that captures the model's overall confidence in the claim-reference pair. This is the forward boundary — the model's summary judgment on semantic alignment.
The Dual-Boundary Value extracts 144 dimensions across 6 segments and 24 layers, capturing precisely where the claim and reference text diverge. This is the backward boundary — a geometric map of disagreement, and the classical analog of a quantum weak value.
The forward and backward boundaries are orthogonal — they measure different aspects of the claim-reference relationship. Stacking them closes 93% of the gap to fine-tuning while preserving full explainability. Every verification result can be traced to specific dimensions and layers.
Patented methodology. Published validation. 29,887 claims tested. No black boxes.