Home / cuhk-aim-group / neurodiscovery · GitHub

ibgnn SKILL.md skillA

ibgnn from cuhk-aim-group/neurodiscovery is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cuhk-aim-group/neurodiscovery/ibgnn@git:20260519.c62dcfb

Pins git:20260519.c62dcfb in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cuhk-aim-group/neurodiscovery
Path: skills/ibgnn/SKILL.md
Versions recorded: 1
Latest version: git:20260519.c62dcfb, committed May 19, 2026
Size: 5,587 bytes
Repository stars: 93
License: MIT

Use this model doc whenever the user wants to run IBGNN (Interpretable Brain Graph Neural Network) for fMRI phenotype prediction. IBGNN is a PyG-based GNN with a learnable MLP message function over [x_i, x_j, edge_attr], designed for connectome-based brain disorder analysis with post-hoc edge-mask explainer support.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# IBGNN Model Doc

## Overview
IBGNN (Interpretable Brain Graph Neural Network) 是面向脑连接组分析的可解释 GNN。核心组件是 MPConv —— 在 GCN 归一化基础上，将消息计算从简单加权聚合改为 `MLP([x_i, x_j, edge_attr])` 学习消息函数。模型与 post-hoc 边遮罩 explainer 配合使用，可提取对预测重要的边子图。

- Paper: Cui et al., 2022, "Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis"，MICCAI
- Official code: https://github.com/HennyJie/IBGNN
- NeuroClaw reimplementation: `models/ibgnn/`（移除 explainer 用的 edge_flag 机制，仅保留 encoder）
- Primary input: PyG Data graph（与 BrainGNN 共享数据格式）
- Primary output: phenotype prediction（可选 attention/重要边解释）

**Research use only.**

---

## NeuroClaw 实现要点

1. **MPConv 核心**：每条边的消息 = `Linear([x_i, x_j, edge_attr])`，比 GCN 多一层非线性表达。
2. **GCN 归一化**：边权 |corr| 经过对称归一化（与 GCN 相同），再注入 self-loop。
3. **去除 edge_flag**：原版用于 explainer 屏蔽边，普通 forward 中 edge_flag 是全 1 tensor，NeuroClaw 直接砍掉以简化代码。
4. **正边权约束**：`edge_attr.abs()` 后传入，与 BrainGNN 同样做法（softmax 类操作需要非负）。
5. **任务统一接口**：classification (`nclass=N`) 与 regression (`nclass=1, task='regression'`) 一套代码。
6. **PyG 2.7 兼容**：`torch_scatter.scatter_add` 已被 `torch_geometric.utils.scatter(reduce='sum')` 替代。
7. **数据复用**：直接复用 BrainGNN 的 `NeuroClawFCDataset`，无需额外预处理。

---
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/ibgnn@sha256:183de7657d7f3928

The line at the top of this page pins the label git:20260519.c62dcfb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_6aqvingfacv3ela6.svg)](https://markdownregistry.com/a/art_6aqvingfacv3ela6)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 19, 2026.

version	committed	commit	size	audit
git:20260519.c62dcfb latest	2026-05-19	c62dcfb	5,587 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (5587 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

cuhk-aim-group/neurodiscovery · 93 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6aqvingfacv3ela6
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/ibgnn
GET https://markdownregistry.com/api/v1/blob/183de7657d7f39286a177432daabc1223eed2ebd657b0f00a6974fddc383ec24

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.