GRN · German Reproducibility Network

Wikipedia:Reliable sources/Perennial sources

This is a non-exhaustive list of sources whose reliability and use on Wikipedia are frequently discussed. This list summarizes prior consensus and consolidates links to the most in-depth and recent discussions from the reliable sources noticeboard and elsewhere on Wikipedia.

Home | Bellingcat's Online Investigation Toolkit

A toolkit for open source researchers

The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale

Sir Isaac Newton famously wrote, “If I have seen further, it is by standing on the shoulders of giants”. Scientific contributions are rarely developed in isolation, but build upon prior contributions, such as problem framings, experimental methods, and empirical findings. Understanding these prerequisite relationships is important for studying scientific progress, and for automated scientific discovery systems that must reason about which existing capabilities can be used to develop new ones (e.g. Lu et al., 2024; Jansen et al., 2025b; Baek et al., 2025).

Related work | Data Counterfactuals

Adjacent research areas and starting papers, curated in Semble and synced into the site.

About CRDTs • Conflict-free Replicated Data Types

Resources and community around CRDT technology — papers, blog posts, code and more.

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?

Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generated hypotheses. We study KG-guided hypothesis generation for battery materials across Mistral-7B, Llama-3.1-70B, and Gemini 2.5 Flash. We perturb local KGs by varying density, ontology richness, topology, and control structure, and evaluate outputs with both provided-graph and fixed-reference metrics. Across models, KG utility is selective and model-dependent: graph context changes outputs, but no-KG outputs also recover substantial graph content from model priors. Compact top-kk subgraphs often approximate full-KG behavior, including when claimed-outcome triples are held out. At the same time, compression is not unique to one semantic ranking rule, random and topology-based subsets can also recover much of the signal. These results support a redundancy-aware Compressive KG hypothesis: useful KG signal is often recoverable from compact, scientifically structured subgraphs rather than requiring the full local graph.

InVID Verification Plugin - InVID project

A verification “Swiss army knife” helping journalists to save time and be more efficient in their fact-checking and debunking tasks on social networks.

The GDELT Project

The GDELT Project

Identify trusted publishers for your research • Think. Check. Submit.

Tools and practical resources, aiming to educate researchers, promote integrity, and build trust in credible research and publications.

KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

Maintaining comprehensive and up-to-date knowledge graphs (KGs) is critical for modern AI systems, but manual curation struggles to scale with the rapid growth of scientific literature. This paper presents KARMA, a novel framework employing multi-agent large language models (LLMs) to automate KG enrichment through structured analysis of unstructured text. Our approach employs nine collaborative agents, spanning entity discovery, relation extraction, schema alignment, and conflict resolution that iteratively parse documents, verify extracted knowledge, and integrate it into existing graph structures while adhering to domain-specific schema. Experiments on 1,200 PubMed articles from three different domains demonstrate the effectiveness of KARMA in knowledge graph enrichment, with the identification of up to 38,230 new entities while achieving 83.1% LLM-verified correctness and reducing conflict edges by 18.6% through multi-layer assessments.

Center for Open Science

At the Center for Open Science, our mission is to increase openness, integrity, and reproducibility of scholarly research. Promoting these practices within the research funding and publishing communities accelerates scientific progress

Thomas Kuhn Foundation | Science Intelligence for the New World

The world's first science intelligence engine capable of monitoring scientific progress in real time

Semble — A social knowledge network for research

Follow your peers' research trails. Surface and discover new connections. Built on ATProto so you own your data.

ZKPROV: A Zero-Knowledge Approach to Dataset Provenance for Large Language Models

As large language models (LLMs) are used in sensitive fields, accurately verifying their computational provenance without disclosing their training datasets poses a significant challenge, particularly in regulated sectors such as healthcare, which have strict requirements for dataset use. Traditional approaches either incur substantial computational cost to fully verify the entire training process or leak unauthorized information to the verifier. Therefore, we introduce ZKPROV, a novel cryptographic framework allowing users to verify that the LLM's responses to their prompts are trained on datasets certified by the authorities that own them. Additionally, it ensures that the dataset's content is relevant to the users' queries without revealing sensitive information about the datasets or the model parameters. ZKPROV offers a unique balance between privacy and efficiency by binding training datasets, model parameters, and responses, while also attaching zero-knowledge proofs to the responses generated by the LLM to validate these claims. Our experimental results demonstrate sublinear scaling for generating and verifying these proofs, with end-to-end overhead under 3.3 seconds for models up to 8B parameters, presenting a practical solution for real-world applications. We also provide formal security guarantees, proving that our approach preserves dataset confidentiality while ensuring trustworthy dataset provenance.

Search LibGen, the Pirated-Books Database That Meta Used to Train AI

Millions of books and scientific papers are captured in the collection’s current iteration.