AI assistants are entering transplant and immunogenetics workflows — and they fabricate allele names, resurrect deleted ones, and slip into 1990s formats. HLA-Verify checks every allele-shaped token in a typing report, EHR fragment, or model output against a pinned IPD-IMGT/HLA release. No LLM anywhere in the loop: every verdict is computed, versioned, and reproducible.
A 7B open model fabricates allele names in 9% of benchmark tasks and answers 62% of them wrongly with high confidence. Our benchmark, HLA-Bench-A, measures it; this engine catches it at runtime.
Pinned to an exact IPD-IMGT/HLA release (46,652 alleles in 3.65.0, ~600 added per quarter). Deleted names resolve to their successors across 110 releases of history.
Reports are processed in memory and discarded; we log counts, not content. Reference data are fetched from the official source under CC-BY-ND and never redistributed.
In-browser verifier (nothing leaves your machine), open benchmark, Python engine on GitHub. Apache-2.0 for the benchmark and graders.
Your reports or model outputs, verified against a pinned release with a full audit trail and a findings letter. Fee credited toward a first-year licence.
Commercial licence for the verification service on your infrastructure; model-evaluation licences and custom environment families for AI labs — talk to us.
Seeking partners: registries and labs holding licensed data can run population-realistic evaluation slices on their own infrastructure — your data never leaves. AI agents: see /llms.txt.
The demo runs entirely client-side — nothing you paste leaves your machine. Keyed API for labs and LIMS vendors: pilot slots open.