Home / cuhk-aim-group / neurodiscovery · GitHub

bnt SKILL.md skillA

bnt 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/bnt@git:20261023.f74c2bd

Pins git:20261023.f74c2bd 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/bnt/SKILL.md
Versions recorded: 2
Latest version: git:20261023.f74c2bd, committed Oct 23, 2026
First version recorded: May 15, 2026
Size: 6,942 bytes
Repository stars: 93
License: MIT

Use this model doc whenever the user wants to run BrainNetworkTransformer for fMRI phenotype prediction, including data loading, training, and evaluation. BNT uses dense FC matrices (no PyG dependency) with DEC pooling + interpretable transformer encoder.

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

# BrainNetworkTransformer (BNT) Model Doc

## Overview
BrainNetworkTransformer 是一种基于 Transformer 的脑网络分析模型，使用 DEC (Deep Embedded Clustering) 池化实现可解释的节点聚类。

- Paper: Kan et al., 2022, BrainNetworkTransformer
- Official code: https://github.com/Wayfear/BrainNetworkTransformer
- NeuroRuntime reimplementation: `models/bnt/` (无 hydra/omegaconf 依赖，纯 argparse)
- Primary input: ROI-level FC 矩阵（dense [N, N]，非 PyG 图格式）
- Primary output: phenotype prediction (classification/regression) + attention weights + DEC assignments

**Research use only.**

---

## NeuroRuntime 实现要点

NeuroRuntime 版本对原始 BNT 做了以下关键改动：

1. **去除 hydra/omegaconf 依赖**：原始代码使用 hydra 配置系统，NeuroRuntime 改为纯 argparse，降低依赖复杂度。
2. **纯 PyTorch Dataset**：不依赖 PyG，使用标准 `torch.utils.data.Dataset` + `DataLoader`，输入为 dense FC matrix [B, N, N]。
3. **Fisher-z 反变换**：与 BrainGNN 一致，存储的 fc_matrix 是 Fisher-z，加载时用 `torch.tanh()` 还原为 Pearson r，对角线置零。
4. **nhead 自动适配**：当 forward_dim (N + pos_embed_dim) 不能被 nhead 整除时，自动降低 nhead 到最大兼容值。
5. **支持 classification + regression 双任务**：regression 时 nclass=1，输出 raw scalar，用 MSELoss。
6. **可选 T1 GM volume 融合**：`--include-t1` 将 z-scored GM volume 作为额外 1 维拼接到 FC 行末尾（node feature dim 从 N 变为 N+1）。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/bnt@sha256:28eddf9b7554d1b7

The line at the top of this page pins the label git:20261023.f74c2bd, 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_dg7cat74jlzx5hfl.svg)](https://markdownregistry.com/a/art_dg7cat74jlzx5hfl)

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

Versions

The registry has recorded 2 versions of this file, between May 15, 2026 and Oct 23, 2026, about one every 161 days.

version	committed	commit	size	audit
git:20261023.f74c2bd latest	2026-10-23	f74c2bd	6,942 B	A	view · diff
git:20260515.bfd8dae	2026-05-15	bfd8dae	6,918 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 (6942 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_dg7cat74jlzx5hfl
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/bnt
GET https://markdownregistry.com/api/v1/blob/28eddf9b7554d1b78879e4611fd06cfbdc0e10a31ecc8611e38f815ae558cc2c

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.