Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images/logo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,115 @@
+---
+language:
+- zh
+- en
+datasets:
+- MMFact/MMFact
+tags:
+- mmfact
+- multimodal
+- fake-news-detection
+---
+<h1 align="center" style="text-align: center; font-size: 40px;">MMFact-CKPT</h1>
+
+<p align="center">
+  <img src="images/logo.png" alt="MMFact logo" width="280">
+</p>
+
+<p align="center" style="text-align: center;">
+  <strong>Model Checkpoints for Multimodal Fake News Detection</strong>
+</p>
+
+<p align="center">
+  <a href="https://arxiv.org/abs/2610.34162"><img src="https://img.shields.io/badge/arXiv-2610.34162-B31B1B?style=flat&amp;logo=arxiv&amp;logoColor=white" alt="arXiv: 2610.34162" height="20"></a>
+  <a href="https://github.com/yuchenmiao04/MMFact"><img src="https://img.shields.io/badge/GitHub-MMFact-181717?style=flat&amp;logo=github&amp;logoColor=white" alt="GitHub: MMFact" height="20"></a>
+  <a href="https://huggingface.co/datasets/MMFact/MMFact"><img src="https://img.shields.io/badge/Hugging%20Face-Dataset-D4A017?style=flat&amp;logo=huggingface&amp;logoColor=FFD21E" alt="Hugging Face: Dataset" height="20"></a>
+</p>
+
+**English** | [简体中文](https://huggingface.co/MMFact/MMFact-CKPT/blob/main/README_zh.md)
+
+MMFact-CKPT is the model checkpoint repository for [MMFact](https://github.com/yuchenmiao04/MMFact), supporting reproducible experiments on Weibo-17, Weibo-21<sup>†</sup>, and GossipCop.
+
+This repository contains checkpoints for **47 methods**, including **24 methods with separate ResNet and ViT variants**, covering three datasets and three random seeds for a total of **639 checkpoints**. Checkpoints are organized by dataset, method, variant, and seed to support evaluation and comparison using the MMFact toolbox.
+
+## Checkpoint Coverage
+
+| Method group | Methods | Variants | Checkpoints per method | Total |
+|---|---:|---|---:|---:|
+| Methods with a single variant | 23 | `default` | 9 | 207 |
+| Methods with two visual variants | 24 | `resnet`, `vit` | 18 | 432 |
+| **Total** | **47** | — | — | **639** |
+
+Each variant has one checkpoint for each combination of the following datasets and random seeds:
+
+| Setting | Values |
+|---|---|
+| Datasets | `weibo17`, `weibo21`, `gossipcop` |
+| Random seeds | `0`, `42`, `2026` |
+| Checkpoint filename | `checkpoint.pt` |
+
+The `default` variant identifies methods without separate ResNet and ViT versions in this collection.
+
+<sup>†</sup> Weibo-21 refers to the reconstructed version provided by MMFact, based on the [original paper](https://doi.org/10.1145/3459637.3482139), with a fixed 8:1:1 train/validation/test split. See the [dataset repository](https://huggingface.co/datasets/MMFact/MMFact) for details.
+
+## Organization and Usage
+
+All checkpoints follow a consistent directory structure:
+
+```text
+<dataset>/<method_slug>/<variant>/seed-<seed>/checkpoint.pt
+```
+
+For example, the EANN directory layout is as follows:
+
+```text
+weibo17/
+└── eann/
+    ├── resnet/
+    │   ├── seed-0/
+    │   │   └── checkpoint.pt
+    │   ├── seed-42/
+    │   │   └── checkpoint.pt
+    │   └── seed-2026/
+    │       └── checkpoint.pt
+    └── vit/
+        ├── seed-0/
+        │   └── checkpoint.pt
+        ├── seed-42/
+        │   └── checkpoint.pt
+        └── seed-2026/
+            └── checkpoint.pt
+```
+
+Download an individual checkpoint using `huggingface_hub`:
+
+```python
+from huggingface_hub import hf_hub_download
+
+checkpoint_path = hf_hub_download(
+    repo_id="MMFact/MMFact-CKPT",
+    repo_type="model",
+    filename="weibo17/eann/resnet/seed-0/checkpoint.pt",
+)
+
+print(checkpoint_path)
+```
+
+Change the filename to select a checkpoint for another dataset, method, variant, or random seed.
+
+Use the corresponding model implementation and configuration in the [MMFact toolbox](https://github.com/yuchenmiao04/MMFact) to load and evaluate the checkpoint. Dataset definitions, preprocessing resources, and precomputed features are documented in the [MMFact dataset repository](https://huggingface.co/datasets/MMFact/MMFact).
+
+## Citation
+
+If you use these checkpoints or other MMFact resources in your research, please cite our paper:
+
+```bibtex
+@misc{miao2026mmfactsimplifyingmultimodalmisinformation,
+  title={MMFact: Simplifying Multimodal Misinformation Detection with Shared Resources and Tools},
+  author={Yuchen Miao and Zijun Wang and Mingtai Zhang and Xiaoyi Chen and Sihan Deng and Xianglin Ding},
+  year={2026},
+  eprint={2610.34162},
+  archivePrefix={arXiv},
+  primaryClass={cs.MM},
+  url={https://arxiv.org/abs/2610.34162},
+}
+```

README_zh.md

@@ -0,0 +1,104 @@
+<h1 align="center" style="text-align: center; font-size: 40px;">MMFact-CKPT</h1>
+
+<p align="center">
+  <img src="images/logo.png" alt="MMFact logo" width="280">
+</p>
+
+<p align="center" style="text-align: center;">
+  <strong>面向多模态虚假新闻检测的模型检查点</strong>
+</p>
+
+<p align="center">
+  <a href="https://arxiv.org/abs/2610.34162"><img src="https://img.shields.io/badge/arXiv-2610.34162-B31B1B?style=flat&amp;logo=arxiv&amp;logoColor=white" alt="arXiv: 2610.34162" height="20"></a>
+  <a href="https://github.com/yuchenmiao04/MMFact"><img src="https://img.shields.io/badge/GitHub-MMFact-181717?style=flat&amp;logo=github&amp;logoColor=white" alt="GitHub: MMFact" height="20"></a>
+  <a href="https://huggingface.co/datasets/MMFact/MMFact"><img src="https://img.shields.io/badge/Hugging%20Face-Dataset-D4A017?style=flat&amp;logo=huggingface&amp;logoColor=FFD21E" alt="Hugging Face: Dataset" height="20"></a>
+</p>
+
+[English](https://huggingface.co/MMFact/MMFact-CKPT) | **简体中文**
+
+MMFact-CKPT 是 [MMFact](https://github.com/yuchenmiao04/MMFact) 的模型检查点仓库，用于支持在 Weibo-17、Weibo-21<sup>†</sup> 和 GossipCop 上开展可复现的实验。
+
+本仓库收录 **47 个方法**的模型检查点，其中 **24 个方法分别提供 ResNet 和 ViT 两个版本**，覆盖三个数据集和三个随机种子，共计 **639 个检查点**。检查点按照数据集、方法、版本和随机种子组织，便于结合 MMFact 工具箱进行评估与比较。
+
+## 检查点覆盖范围
+
+| 方法类别 | 方法数量 | 版本 | 每个方法的检查点数量 | 总数 |
+|---|---:|---|---:|---:|
+| 单版本方法 | 23 | `default` | 9 | 207 |
+| 双视觉版本方法 | 24 | `resnet`、`vit` | 18 | 432 |
+| **合计** | **47** | — | — | **639** |
+
+每个版本在以下数据集与随机种子的每一种组合下，分别对应一个检查点：
+
+| 设置 | 取值 |
+|---|---|
+| 数据集 | `weibo17`、`weibo21`、`gossipcop` |
+| 随机种子 | `0`、`42`、`2026` |
+| 检查点文件名 | `checkpoint.pt` |
+
+`default` 表示该方法在本仓库中不单独区分 ResNet 和 ViT 两个版本。
+
+<sup>†</sup> 此处的 Weibo-21 指 MMFact 根据[原始论文](https://doi.org/10.1145/3459637.3482139)重建的数据版本，采用固定的 8:1:1 训练集、验证集和测试集划分。详情请参阅[数据集仓库](https://huggingface.co/datasets/MMFact/MMFact)。
+
+## 目录结构与使用方法
+
+所有检查点采用统一的目录格式：
+
+```text
+<数据集>/<方法目录名>/<版本>/seed-<随机种子>/checkpoint.pt
+```
+
+例如，EANN 的目录结构如下：
+
+```text
+weibo17/
+└── eann/
+    ├── resnet/
+    │   ├── seed-0/
+    │   │   └── checkpoint.pt
+    │   ├── seed-42/
+    │   │   └── checkpoint.pt
+    │   └── seed-2026/
+    │       └── checkpoint.pt
+    └── vit/
+        ├── seed-0/
+        │   └── checkpoint.pt
+        ├── seed-42/
+        │   └── checkpoint.pt
+        └── seed-2026/
+            └── checkpoint.pt
+```
+
+使用 `huggingface_hub` 下载单个检查点：
+
+```python
+from huggingface_hub import hf_hub_download
+
+checkpoint_path = hf_hub_download(
+    repo_id="MMFact/MMFact-CKPT",
+    repo_type="model",
+    filename="weibo17/eann/resnet/seed-0/checkpoint.pt",
+)
+
+print(checkpoint_path)
+```
+
+修改文件路径，可以选择其他数据集、方法、版本或随机种子的检查点。
+
+请使用 [MMFact 工具箱](https://github.com/yuchenmiao04/MMFact)中对应的模型实现和配置加载、评估检查点。数据集定义、预处理资源及预计算特征的说明见 [MMFact 数据集仓库](https://huggingface.co/datasets/MMFact/MMFact)。
+
+## 引用
+
+如果您在研究中使用了这些检查点或其他 MMFact 资源，请引用我们的论文：
+
+```bibtex
+@misc{miao2026mmfactsimplifyingmultimodalmisinformation,
+  title={MMFact: Simplifying Multimodal Misinformation Detection with Shared Resources and Tools},
+  author={Yuchen Miao and Zijun Wang and Mingtai Zhang and Xiaoyi Chen and Sihan Deng and Xianglin Ding},
+  year={2026},
+  eprint={2610.34162},
+  archivePrefix={arXiv},
+  primaryClass={cs.MM},
+  url={https://arxiv.org/abs/2610.34162},
+}
+```