Participant GuideConcepts
Concepts — Why this challenge exists
Sourced from whest-starterkit @
aaa3882.
Concepts — Why this challenge exists
Background reading. These three docs explain the problem framing, the scoring metric, and how ground truth is generated. Helpful before you start tuning; essential before debating leaderboard outcomes.
| Doc | What it covers |
|---|---|
| problem-setup.md | The MLP architecture, He initialization, and the research framing — why "competing with sampling" is the milestone this challenge targets. Includes a "Further reading" pointer to the relevant ARC posts and papers. |
| scoring-model.md | How the leaderboard score is computed: ASCII pipeline diagram, explicit equation block for adjusted_final_layer_score and all_layers_mse, behavior when the FLOP budget is exceeded, and a calibration table from the bundled examples. |
| ground-truth.md | How the evaluator generates the reference values you're scored against — Monte-Carlo sampling, sample counts, the inherent noise floor. |
Read in order if you want the full picture. At minimum, skim scoring-model.md — it's what drives every number you'll obsess over.
➡️ Where to look next
- Ready to write code? → Tutorial: Stage 1, How-to: write-an-estimator.
- Want the exact API contract? → Reference: estimator-contract.