README / README.md
ekmpa's picture
Update README
8ef127e verified
---
title: CrediNet
colorFrom: indigo
colorTo: purple
sdk: static
pinned: false
short_description: Network-based Credibility Modelling
---
<div align="center">
<h1>CrediNet</h1>
<img src="https://cdn-uploads.huggingface.co/production/uploads/681e3663829118a837bbaeb3/Mz_vqAW1rlfEDkx2Mv4fd.png" alt="credinet" width="150"/>
**CrediNet** is set of tools that use graph machine learning and computational methods for credibility modelling on the web.
We develop billion-scale data webgraphs and use them to assess credibility levels of websites, which can be used downstream to augment Retrieval-Augmented Generation robustness and fact-checking.
This involves large-scale web scraping and text processing, and developing model architectures to interpret the different types of signals we can find on the web (including structural, temporal and linguistic cues).
<p>
<a href="https://github.com/credi-net">See also: our Github codebases</a>
</p>
</div>
---
# Projects
- **CrediBench**: benchmark of billion-scale temporal webgraphs on a monthly granularity, sourced from Common Crawl. For the corresponding graph construction pipeline refer to [CrediGraph - GitHub](https://github.com/credi-net/CrediGraph).
- **CrediPred**: inferred scores from our developed model (for more details on the model architecture, refer to [CrediPred - GitHub](https://github.com/credi-net/CrediPred)).
- **CrediText**: text embeddings extracted from scraped web content. Find the corresponding scraping and embedding pipelines on [CrediText - GitHub](https://github.com/credi-net/CrediText).
- **CrediNet**: API set-up to query CrediPred scores easily on the client side (for more details on the API set up and examples usages, refer to [CrediNet - GitHub](https://github.com/credi-net/CrediNet)).
<div align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/681e3663829118a837bbaeb3/gAED3hY_AVkER7mLblJ4u.png" alt="suite" width="600"/>
</div>
---