返回产品列表
p

产品详情

plumb

Run the paper. Check its numbers.

发布日期 · UTC
2026-10-20
产品域名
—
域名后缀
—
产品方向
人工智能

关于产品

Plumb re-runs a paper's own code on your compute, re-derives each claim from the actual run, and returns a per-claim verdict: REPRODUCED, DIVERGED, or UNVERIFIED. Execution decides, never an LLM. Open source; the honest number is published with it.

关键词

开源reproducibilityresearch validation