**BIMAN**, or **Bot Identification by commit Message, commit Association, and author Name**, is a technique to detect bots that commit code. It is comprised of three methods that consider independent aspects of the commits made by a particular author: 1) Commit Message: Identify if commit messages are being generated from templates; 2) Commit Association: Predict if an author is a bot using a random forest model, with features related to files and projects associated with the commits as predictors; and 3) Author Name: Match author’s name and email to common bot patterns.

**Latent Optimisation** is a technique used for generative adversarial networks to refine the sample quality of $z$. Specifically, it exploits knowledge from the discriminator $D$ to refine the latent source $z$. Intuitively, the gradient $\nabla\_{z}f\left(z\right) = \delta{f}\left(z\right)\delta{z}$ points in the direction that better satisfies the discriminator $D$, which implies better samples. Therefore, instead of using the randomly sampled $z \sim p\left(z\right)$, we uses the optimised latent:

$$ \Delta{z} = \alpha\frac{\delta{f}\left(z\right)}{\delta{z}} $$

$$ z' = z + \Delta{z} $$

Source: [LOGAN](https://paperswithcode.com/method/logan)
.

Latent Optimisation

Deep Compressed Sensing

BIMAN

Detecting and Characterizing Bots that Commit Code

**Adaptive Input Embeddings** extend the [adaptive softmax](https://paperswithcode.com/method/adaptive-softmax) to input word representations. The factorization assigns more capacity to frequent words and reduces the capacity for less frequent words with the benefit of reducing overfitting to rare words.

Source	Detecting and Characterizing Bots that Commit Code
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com