NARC

What is NARC?

NARC is a new kind of abstract reasoning puzzle. Each puzzle presents a sequence of colored grids that tell a visual "story." One or more grids in the sequence are hidden, and your goal is to reconstruct them pixel-perfectly.

The catch: the grids alone aren't enough. Each puzzle comes with a short narrative clue. Without it, the missing grid is ambiguous — multiple answers seem plausible. With the clue, exactly one answer is correct.

This is the NARC property: neither the grids nor the narrative suffice alone, but together they uniquely determine the answer.

How to play

1. Look at the grid sequence. Each grid uses a 10-color palette. One or more grids are hidden, shown as a ? placeholder.
2. Try to guess what the missing grid looks like from the visual pattern alone. You can submit a guess before seeing the clue.
3. Reveal the clue. A short narrative provides the key insight that disambiguates the puzzle.
4. Draw your answer. Set the colors of each cell in the missing grid and submit.

Why does this matter?

NARC investigates a fundamental question: how does narrative transform visual reasoning?

Abstract grid patterns that look meaningless can become instantly comprehensible when accompanied by the right story. This "narrative augmentation" works differently for humans and AI systems — and studying where they diverge reveals something deep about how each processes language and vision together.

NARC is a sibling project to MARC2 (Metaphor Abstraction and Reasoning Corpus), which explored how figurative language helps AI solve abstract reasoning tasks from the ARC-AGI benchmark.

The puzzle corpus

Puzzles span literary classics (Hemingway, Kafka, Shelley), scientific concepts (natural selection, entropy, plate tectonics), philosophical thought experiments (the trolley problem, Plato's cave, the ship of Theseus), and more.

Each puzzle is rated on two axes: human difficulty and AI difficulty (1–5), creating a spectrum from puzzles that are easy for humans but hard for AI, to puzzles where AI excels but humans struggle.

Research context

NARC draws on insights from:

• ARC-AGI — abstract visual reasoning as an intelligence benchmark
• MARC — figurative language as a bridge between human and machine reasoning
• Econarratology — Erin James's framework for how narratives construct "storyworlds" that organize spatial and temporal understanding
• Focalization — how the same story told from different characters' perspectives changes what information is foregrounded

Get involved

You can:

• Browse and solve existing puzzles
• Create and submit your own puzzles
• Inspect how AI models perform across puzzles and narrative variants