OpenScholar releases code, models, and research corpus
On November 19, 2024, the OpenScholar project announced code, model checkpoints, a corpus of over 45 million papers, and the ScholarQABench benchmark.
Published on November 19, 2024, the OpenScholar announcement describes the release of code, model checkpoints, ScholarQABench, and a datastore containing over 45 million scientific papers, covering publications through October 2024. The project presents it as a research assistant for finding, summarizing, and analyzing scientific evidence.
The material may interest readers studying open research systems and scientific-answer evaluation. To check the scope, resources, and findings, consult the project’s original page and inspect the published materials and benchmark directly; do not infer performance beyond what those materials document.