The rapid growth of open-source software has made GitHub a central platform for studying large-scale collaboration for software development. Existing datasets and event logs are typically limited to individual projects or user–repository collaboration at the GitHub level. We introduce GONets, a publicly available dataset that provides a direct bipartite representation of user–repository interactions at the organisational level. GONets comprises over 230K GitHub organisations, 2.52M unique users, 4.37M repositories, and nearly 30M contribution edges, enriched with detailed organisational metadata including organisation size, creation date and follower count. We present an automated data collection pipeline that retrieves organisational and membership information via GitHub's API, aggregates user-repository contribution data, and constructs large-scale bipartite networks suitable for network analysis and modelling. Using this dataset, we conduct the first large-scale characterisation of the GitHub organisational ecosystem, analysing organisational attributes and user-repository contribution patterns across a diverse range of organisations. We release the complete dataset and collection pipeline to support reproducible research and facilitate future studies on topics including code reuse diffusion, collaboration dynamics and the security ecosystem of GitHub organisations. The entire dataset can be accessed at: https://zenodo.org/records/18472549.

Large Language Models (LLMs) have become integral to human decision-making processes. However, their outputs are not always reliable, often requiring users to assess the accuracy of the information provided manually. This issue is exacerbated by hallucinated responses, which are frequently presented with convincing but incorrect explanations, leading to trust concerns among users. To address this challenge, we propose GE-Chat, a knowledge Graph-enhanced retrieval-augmented generation framework designed to deliver Evidence-based responses. Specifically, when users upload a document, GE-Chat constructs a knowledge graph to support a retrieval-augmented agent, enriching the agent's responses with external knowledge beyond its training data. We further incorporate Chain-of-Thought (CoT) reasoning, n-hop subgraph searching, and entailment-based sentence generation to ensure accurate evidence retrieval. Experimental results demonstrate that our approach improves the ability of existing models to identify precise evidence in free-form contexts, offering a reliable mechanism for verifying LLM-generated conclusions and enhancing trustworthiness.