Skip to content

Competition Solution

arc_baseline

What it is

This repository provides a Dockerized baseline solution for the ARCathon competition, which uses a brute-force approach with image transformations to solve abstract reasoning tasks. The core solving code is copied from a public Kaggle notebook, with added preprocessing, postprocessing, and containerization.

Scored ate260e1c14 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
Computer Vision: 72.7%Data Science: 27.3%
  • Computer Vision73%
  • Data Science27%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths2

  • Provides a runnable solution via Docker, making it easy to deploy and execute.
  • Includes the necessary code to process competition data and generate a submission file.

Limitations

The owner keeps this project's limitations private.

Around it on the Computer Vision board

Whole board
  1. 16ButterflyClassifierML Application · Python43.3/100ImplementationMohamed Khayat
  2. 17background-subtractionEducational Implementation · Jupyter Notebook42.1/100ImplementationPop Alexandru
  3. 18, shared ranksteel-defect-classifier-railcomputeML Application · Python41.4/100ImplementationAditya Ray
  4. 18, shared rankarc_baselineCompetition Solution41.4/100ImplementationSimon Strandgaard
  5. 20face-lock-promptsEducational Implementation41.1/100Implementationkarims

More from Simon Strandgaard