Orientation

A working glossary for the site

Use this when you want a quick definition without leaving the thread of the argument. The explanations lean on the grid metaphor whenever it helps, but keep the wording practical.

Find a term fast

Search or jump

19 terms

  • Data counterfactual

    A "what if" question about training data. What would happen to model performance if we trained on different data? The grid visualization shows all possible counterfactuals: each row is a possible training set, each column is an evaluation point.

  • Influence function

    A technique for estimating how much a single training example affects a model's predictions, without retraining. Approximates what would happen if you removed or upweighted that point.

  • Data Shapley

    A method for assigning value to each training point based on its average marginal contribution across all possible subsets. Borrowed from cooperative game theory. Computationally expensive but theoretically principled.

  • Leave-one-out

    The simplest data counterfactual: compare performance with and without a single data point. In the grid, this means comparing two rows that differ by exactly one point.

  • Coreset

    A small subset of training data that approximates training on the full dataset. The goal is to find a much smaller row in the grid that lands in roughly the same performance region.

  • Data poisoning

    Deliberately corrupting training data to cause targeted model failures. Expands the grid dramatically; every possible perturbation creates new rows with potentially different outcomes.

  • Backdoor attack

    A type of data poisoning where a trigger pattern causes the model to misclassify inputs containing that trigger, while behaving normally otherwise.

  • Data strike

    Coordinated withholding of data by creators to reduce model performance and exert leverage over AI operators. A strategic move to a less favorable row in the grid.

  • Data leverage

    The power that data creators have over AI systems by virtue of controlling training data. Leverage depends on how much performance drops when data is withheld or degraded.

  • Scaling law

    An empirical relationship describing how model performance changes with data size, model size, or compute. In grid terms, a regression over average performance across rows grouped by size.

  • Differential privacy

    A mathematical framework for limiting how much any single data point can affect model outputs. It constrains how far the model can move in the grid when one point changes.

  • Memorization

    When a model stores training data too literally rather than learning general patterns. That can enable extraction attacks that recover private examples from model outputs.

  • Machine unlearning

    Efficiently updating a model as if a data point was never in the training set, moving from one row to another without full retraining.

  • Active learning

    Choosing which data points to label next under a limited labeling budget. In grid language, it is a strategy for deciding which rows become available for training.

  • Data augmentation

    Creating synthetic variations of training data such as crops, rotations, or noise. It effectively adds nearby rows to the grid.

  • Curriculum learning

    Training on examples in a meaningful order, often from easy to hard. It changes how you move through the grid over time, not just which row you end on.

  • Membership inference

    Trying to determine whether a specific example was in a model's training set by exploiting differences between seen and unseen data.

  • Training set

    The data used to train a model. In the grid, each row represents one possible training set.

  • Evaluation set

    The data used to measure model performance. In the grid, each column represents one possible evaluation point or slice.