compositional anomaly detection
FidelityAI trains a quantum fidelity kernel offline, hands off a projection matrix T, and runs real-time one-class inference on classical hardware — no QPU required at deployment.
Two orthogonal infringement profiles — quantum discovery and classical deployment — with a single serialized handoff artifact.
k-fold amplitude encoding → SWAP-test fidelity matrix F → eigendecomposition → projection matrix T → serialize T
QPU required. Infringement: running quantum discovery.
Receive T (no QPU) → project z = TTx → one-class SVM score → anomaly alert
No quantum hardware. Infringement: deploying T.
Qubit allocation: n = k·⌈log₂(v)⌉ + 2 · k compositional roles, v per-role vocabulary
For amplitude-encoded states, F_ij = cos²(θ_ij) mathematically — but classical eigendecomposition of the cosine²-similarity matrix achieves 73% higher FNR. The formula equivalence does not imply computational equivalence. The SWAP test encodes correlations from the full 2n-dimensional Hilbert space.
Any domain whose records can be structured as k-fold semantic tuples (k ≥ 2 roles).
API grammar violations, zero-day malware — no labeled attacks needed
Contradictory obligations, missing required clauses, deontic violations
Adverse drug events, genomic anomalies, clinical trial integrity
AV, grid, ICS, and manufacturing control-sequence violations
AML, smart-contract exploits, access-control violations