Name: etb-scan
Author: Authensor

Question 1

What is Authensor?

Accepted Answer

Authensor is a research-led evaluation integrity firm. We audit the instruments the AI industry measures itself with: evaluation harnesses, benchmarks, judges, leaderboards, and scoring pipelines. Every defect we report is proven with a running reproduction, and every audit ends in an attestation with a scope, a standard version, and an expiry date.

Question 2

What is an evaluation integrity audit?

Accepted Answer

A fixed-scope read of the scoring path that produces your published number: dataset residency, answer extraction, judge parsing, aggregation, and reporting. We read the code line by line, run adversarial reproductions against it, and re-grade your headline result under an instrument that fails closed.

Question 3

What is an attestation?

Accepted Answer

A signed statement that a named instrument, at a named commit, survived a named standard on a named date. It has a scope, a standard version, and an expiry date, so your buyers can file it in procurement and know exactly what it does and does not cover.

Question 4

What is a claim check?

Accepted Answer

A free 48-hour verification of one published number. You give us the claim and the artifact behind it; we tell you whether the number survives contact with the grading code that produced it. If it does, you can say so. If it does not, you know before your buyer does.

Question 5

What is the evaluator trust boundary?

Accepted Answer

The evaluator trust boundary (ETB) is the line between the system being measured and the instrument doing the measuring. Our research shows that line is crossed in specific, repeatable ways: candidate text reaches the judge unparsed, ground truth lives where the evaluated system can read it, and parse failures silently shrink denominators. The ETB taxonomy catalogs 75 defect classes found across the most-used evaluation repositories.

Question 6

Who is this for?

Accepted Answer

Three buyers. AI labs that publish numbers and need them to survive diligence. Enterprises procuring AI who want a third party to verify vendor claims before signature. And investors or insurers whose models price the risk those numbers describe.

Self-Play Adversary

Request a scoped evaluation. Exclusive licensing available where wanted.