Glossary · Term

R-squared

← all terms

Definition

Plain language

A score for how well data fits a curve — near one means the points sit right on it, near zero means a shapeless cloud.

As stated in the literature

The coefficient of determination, the fraction of variance in an outcome explained by a predictor; can go negative when the predictor is worse than the mean baseline, as raw token-count measures do on real agent traces in the Effective Feedback Compute analysis.

Also called:

Why it matters: It tells you how much a model actually explains, and a negative value is a red flag that the model is worse than just guessing the average.

For example, an R-squared near one means a fitted line passes right through the data points, while near zero means the points scatter like a shapeless cloud.

Heard on the show

“Variance explained, R-squared — a zero-to-one number for how much the input measure determines the output measure.”
Episode 241 — Swapping the Name Did Nothing, But Hedging Moved Every Model

Mentioned in 4 episodes

  1. 241
    Swapping the Name Did Nothing, But Hedging Moved Every Model
  2. 152
    Training a Model to Mean What It Says, And Why That Isn't the Same as Being Good
  3. 108
    The Reasoning Cliff: Why Thinking Longer Makes Models Worse at Exact Step-by-Step Tasks
  4. 097
    Same Tokens, Same Cost, Wildly Different Results: What Actually Scales in AI Agents

Related terms