Call for field testers: measurement-backed claim and reasoning checks

[HarperZ9]

Project Telos is looking for field testers for crucible: measurement-backed thesis evaluation with clean verifier packets and re-checkable verdicts.

The question this repo should help answer:

Can a claim be steelmanned, measured against a substrate, and refined without pretending unsupported claims are proven?

Useful test lanes:

• Technical claims: "this repo supports X", "this workflow verifies Y", or "this evidence shows Z".
• Research packets: public sources, derived claims, and known uncertainty boundaries.
• Security/eval work: cases where a confident model answer needs explicit MATCH, DRIFT, or UNVERIFIABLE labels.
• Reasoning workflows: identify where the weakest axis is evidence, criteria, measurement, or presentation.

What I am looking for:

• Verification against public or synthetic claim sets.
• Cases where the verdict is too generous or too strict.
• Better report shapes for humans who need to inspect the evidence.
• Stress tests where refinement should stop rather than overfit a weak claim.
• Early testers and pointers to modest grassroots research funding for checkable judgment tooling.

Project links:

• Main site: https://harperz9.github.io
• Field guide: https://harperz9.github.io/field-guide.html
• GitHub profile: https://github.com/HarperZ9
• Related flagships: https://github.com/HarperZ9/gather https://github.com/HarperZ9/index https://github.com/HarperZ9/forum https://github.com/HarperZ9/telos

Stage label: public, solo, early, pre-revenue, not independently audited. Please start with public, non-sensitive material.