Home / uchicago-dsi / ai-sci-skills · skills/leakage-and-splits/SKILL.md · GitHub

leakage-and-splits skillA

leakage-and-splits is agent-read markdown (skill) from uchicago-dsi/ai-sci-skills: Keep held-out data genuinely held out: assign split eligibility to whole source groups, count independent units rather than rows, and check whether a split was already exposed by earlier fitting. Use when defining, reusing, or claiming a train/validation/test split, or when reporting an n..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Leakage And Splits

The vocabulary below is generic on purpose. A "source group" is whatever repeats:
a participant, a site, an animal, a batch, a sensor, a time period, a physical
specimen.

## Hold Out Whole Groups, Not Rows

- A unit reported as held out must contribute neither gradient nor
  model/optimizer/checkpoint selection. If an outer objective uses data excluded
  only from an inner solve, call it adaptation or outer-training data and reserve a
  separate untouched evaluation split.
- For longitudinal or repeated-measure analyses, assign split eligibility to the
  whole participant/source group before forming pairs. If any visit is held out,
  exclude every visit in that group from training. Define sufficiency, permutation,
  and holdout counts in independent groups rather than in visits or pair
  combinations.
- Treat raw source identity, not an analysis-row identifier, as the unit. When rows
  or annotations reuse a source, record that identity, keep splits source-exclusive,
  report within-source envelopes, and balance cohort summaries over sources.

## Do Not Inflate The Denominator

- Do not count overlapping windows, crops, augmentations, repeated rows, or
…

Read the whole file at its exact version.

How to install

Latest version
mdr add uchicago-dsi/ai-sci-skills/leakage-and-splits@git:20260921.9b3de7c
Exact content
mdr add uchicago-dsi/ai-sci-skills/leakage-and-splits@sha256:518eb2699511e207

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d7vrdn4sbpoy52o5.svg)](https://markdownregistry.com/a/art_d7vrdn4sbpoy52o5)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.9b3de7c latest2026-09-21 9b3de7c 4,171 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4171 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d7vrdn4sbpoy52o5
GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/leakage-and-splits
GET https://markdownregistry.com/api/v1/blob/518eb2699511e2071acf3f558bf0fc2cab3d4ca411b8e396880a311a9d628451

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from uchicago-dsi/ai-sci-skills

agentcomm skill
uchicago-dsi/ai-sci-skills · skills/agentcomm/SKILL.md · Coordinate agents through the AgentComm mailbox - installing it, binding a durable name, how Codex and Claude hooks…
git:20260922.0776e0f · audit A · 20 stars
bounded-auto-loop skill
uchicago-dsi/ai-sci-skills · skills/bounded-auto-loop/SKILL.md · Run a short, bounded autonomous loop of debugging or experiments before checking back in. Use when the user wants the…
git:20260728.3acf544 · audit A · 20 stars
claude-code-worker skill
uchicago-dsi/ai-sci-skills · skills/claude-code-worker/SKILL.md · Delegate a bounded coding, review, or research subtask from Codex to Claude Code in an isolated Git worktree, then…
git:20260922.608ac59 · audit A · 20 stars
decision-gates skill
uchicago-dsi/ai-sci-skills · skills/decision-gates/SKILL.md · Separate a scientific gate that decides promotion, continuation, stopping, or retirement from a mechanical check you…
git:20260921.9b3de7c · audit A · 20 stars
experiment-design skill
uchicago-dsi/ai-sci-skills · skills/experiment-design/SKILL.md · Design the smallest useful experiment matrix that separates important hypotheses and changes a decision. Use when the…
git:20260921.9b3de7c · audit A · 20 stars
handoff skill
uchicago-dsi/ai-sci-skills · skills/handoff/SKILL.md · Create a restart-ready handoff so a fresh agent or future turn can resume work without rereading the full conversation…
git:20260320.999ac68 · audit A · 20 stars
humanize skill
uchicago-dsi/ai-sci-skills · skills/humanize/SKILL.md · Edit prose so it sounds like the author and reads plainly - stripping formulaic AI phrasing and replacing jargon with…
v2.1.0 · audit A · 20 stars
job-babysitting skill
uchicago-dsi/ai-sci-skills · skills/job-babysitting/SKILL.md · Directly monitor long-running jobs or pipelines, classify them as healthy, waiting, stalled, failed, completed, or…
git:20260921.9b3de7c · audit A · 20 stars
lab-notebook skill
uchicago-dsi/ai-sci-skills · skills/lab-notebook/SKILL.md · Record work in a lab notebook so it is both a literal activity log and an efficient re-entry aid. Use when the agent is…
git:20260921.9b3de7c · audit A · 20 stars
maintenance-pass skill
uchicago-dsi/ai-sci-skills · skills/maintenance-pass/SKILL.md · Run safe, high-yield codebase maintenance passes that trim dead code, vestiges, duplicate implementations, stale…
git:20260921.9b3de7c · audit A · 20 stars
mission-control skill
uchicago-dsi/ai-sci-skills · skills/mission-control/SKILL.md · Coordinate multiple long-running agents or workers while preserving the global goal, current evidence, and timely…
git:20260921.9b3de7c · audit A · 20 stars
paper-structure skill
uchicago-dsi/ai-sci-skills · skills/paper-structure/SKILL.md · Organize a scientific manuscript for a specific venue: fix the claim it argues, load the venue's own section skeleton…
git:20260921.27eae4c · audit A · 20 stars

Every file in uchicago-dsi/ai-sci-skills

Browse by kind, by grade A, or by owner.