What is open#
Touchstone publishes the calculations that turn a card condition assessment into a grade. It doesn't publish, and doesn't specify, how you got to the assessment in the first place. A standard that's vague about its own edges is asking to be trusted rather than checked, so here are the edges.
What the standard covers#
Everything needed to compute a grade, and to prove you computed it correctly:
- The normative specification. The rubric is the authority. Where the prose and the reference implementation disagree, the prose governs and the disagreement is a bug in one of them, filed and fixed.
- The rubric data. Every penalty is quantified and shown. A number you can read, not a constant compiled into something.
- The reference implementation. One dependency-free module. It's conformance evidence, not the definition.
- The schemas. The shape of an assessment going in and a result coming out.
- The conformance vectors. Frozen inputs paired with the exact output every implementation has to reproduce.
All of it under Apache-2.0. See the licence for what that commits us to, and for the part that can't be narrowed.
What the standard doesn't cover#
How the assessment is produced. Touchstone takes centering measurements and an enumerated list of defects as its input. Where those come from is out of scope. A person with a loupe and a ruler, a scanner, a vendor's software or a machine-learning model are all equally valid sources, and the standard takes no position on which. Two implementations that disagree about whether a corner is minor or moderate will produce different grades. Touchstone can't help with that. It guarantees only that they'll agree once they agree on the input.
The definitions still matter: not every source or supplied label is accurate. The standard defines the meaning of supported inputs but does not validate the physical findings, the observer, or the model that supplied them.
Given the same assessment and rubric version, conforming implementations reproduce the calculation. That's the claim. You don't have to take it on faith. Run the vectors.
A note about us, and the part we keep closed#
Grailology, which stewards Touchstone, plans to sell grading. The part of its product that turns an image into an assessment (measuring centering, finding and classifying defects) is proprietary, and will stay that way.
That component materially influences the grade by determining which findings enter the assessment and how they are classified. The calculation from that assessment is public and reproducible. Given the assessment and exact rubric version, anyone can recompute the result and question a particular input, penalty or rule. This does not establish that all damage was found or correctly classified, and a partial assessment is not a complete card inspection.
An assessment you disagree with is a disagreement about a card. A grade you can't recompute is a disagreement you're not allowed to have.
Who needs an account#
No account, ever. The specification, the schemas, the conformance vectors, the reference implementation, and the hosted reference scorer. All of it usable, and self-hostable, by someone with no relationship to Grailology at all. This tier is what makes charging for the others legitimate.
Hosted and metered. Grailology operates a hosted Touchstone MCP server for use inside AI tools. Hosting costs money and has to be rate limited, so it's account-gated.
The Touchstone MCP server is provided by Grailology, which uses Touchstone as its grading standard. It is not operated by the Touchstone project.
Commercial. Grailology's own grading, attestation and registry services, once they exist, will be products built on the standard. They're not the standard, and you don't need any of them to use it.