Resource library
Explore our complete library of resources including blogs, benchmarks, research papers, and more.
Grok 4.5 Testing Results: How SpaceXAI’s New Model Performs on Real Professional Work
Why coding agents need better data, evals, and environments
Closing the Evaluation Gap in Agentic AI
Announcing a $3M commitment to launch Open Benchmarks Grants
Evaluating coding agent capabilities with Terminal-Bench: Snorkel’s role in building the next generation benchmark
Building FinQA: An Open RL Environment for Financial Reasoning Agents
The science of rubric design
Introducing FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches and requires fewer assumptions
We love meeting people in the data science and machine learning community. Here are a few upcoming events where you can meet Snorkelers.
This paper proposes cross-modal data programming (XMDP) for machine learning (ML) in medicine.
This paper provides a series of results studying how performance scales with changes in source coverage, source accuracy, and the Lipschitzness of label distributions in the embedding space, and compare this rate to standard weak supervision.
Presenting Trove, a framework for weakly supervised entity classification using medical ontologies and expert-generated rules.
There’s a lot of excitement about the potential for AI to improve healthcare. This is driven by compelling advances across a wide range of applications including drug discovery, radiology, pathology, electronic medical record (EMR) intelligence, clinical trials, and more. There are also many challenges for development and deployment of AI for healthcare.
Background: The aortic valve is an important determinant of cardiovascular physiology and anatomic location of common human diseases. Methods: From a sample of 34 287 white British ancestry participants, we estimated functional aortic valve area by planimetry from prospectively obtained cardiac magnetic resonance imaging sequences of the aortic valve. Aortic valve area measurements were submitted to genome-wide association testing, followed by…
In this paper, we propose a learning algorithm for training deep neural networks when there is not sufficient labeled data. To improve the generalization capabilities of the deep model, we adopt a learning scheme to train two related tasks simultaneously. One is the original task (target), and the other is an auxiliary task (source). In order to create a related…
We are inventing a new way to build enterprise AI applications. Taking a data-centric approach, we are making machine learning iterable, faster to deploy, and ultimately more practical.That is a fantastic opportunity, but it also presents one of our biggest challenges – figuring out how to bridge the gap between developers at the vanguard of machine learning and business leaders…
