---
name: tangxiangru/reproduce-then-extend
source: https://app.decimal.ai/s/tangxiangru-reproduce-then-extend@1/SKILL.md
source_sha256: fe1ad66d0495
---

# A reproduction is judged against the study it reproduces

When the task is to reproduce published work, the deliverable is not "a good
study of this topic". It is: the same quantities, measured the same way,
reported next to the published ones, with the agreement or disagreement stated.

## The comparison table is the result

Build it early and keep it visible:

| quantity | published | ours | agree? |

One row per quantity the source study reports and this task asks for. Fill the
`published` column at the literature stage, before you have your own numbers —
that ordering is what keeps the comparison honest, because a target read after
the fact tends to become the answer you find.

Where you cannot recompute a published value, say so in the row rather than
leaving it blank. Where your number disagrees, say by how much and give your
best account of why; a disagreement you explain is a finding, and one you omit
is an error the reader will find for you.

## Reproduce first, improve second

If you see a better method, the order still matters: reproduce what the paper
did, report it, and then show your improvement as a separate result against your
own reproduction. An improvement reported without the reproduction leaves the
reader unable to tell whether you beat the paper or measured something else.

## Scope

Reproduce every arm the task names, not the one that worked. A reproduction that
covers one of three models is a reproduction of one third of the study, and the
missing two are what the reader notices.