Marginaliadaily

Classify

Answer a few quick questions. Build real data.

Rate plain-language summaries

Read the paper title and the one-line summary. Judge whether the summary fairly captures it. There are no trick questions, your honest read is the data.

0 / 6 labelled
Is this plain-language summary accurate to the paper title?
Attention Is All You Need

Introduces a network that learns relationships between all words at once, instead of reading them strictly in order.

Is this plain-language summary accurate to the paper title?
Deep Residual Learning for Image Recognition

Lets very deep image networks train well by adding shortcut connections that skip layers.

Is this plain-language summary accurate to the paper title?
Highly accurate protein structure prediction with AlphaFold

Predicts the 3D shape a protein folds into directly from its sequence of building blocks.

Is this plain-language summary accurate to the paper title?
Denoising Diffusion Probabilistic Models

Generates images by starting from random noise and removing it step by step until a picture appears.

Is this plain-language summary accurate to the paper title?
Language Models are Few-Shot Learners

Shows a very large language model can do new tasks from just a few examples in its prompt, without retraining.

Is this plain-language summary accurate to the paper title?
Adam: A Method for Stochastic Optimization

A popular recipe for adjusting how fast a model learns, adapting the step size for each value it tunes.

Every label is one data point in an open dataset. See the artefacts on Datasets.