Sample questions
Every question below is quoted verbatim from the launch map manifests (degs/ in the repo). The launch maps are the open practice set; competition instances are minted fresh per season, with the same structure and different seeded values, and stay sealed until the season closes.
Maze family (alpha-2) — navigation carries the difficulty
Gates are standalone problems; the challenge is the map itself — dead ends, a loop trap, one exit, and a small budget of lives.
Calculate: 38 + 17Evaluate: (TRUE AND FALSE) OR TRUECalculate: 144 ÷ 12Evaluate: NOT(FALSE OR FALSE)Calculate: 7 × 8
Corridor family (nav-3) — retention carries the difficulty
No branches, no dead ends: 20 gates in a straight line, and the questions chain. Later gates reach back to specific earlier answers, rotating through all of them — the model must recall any prior answer on demand. The full ramp, in order:
Calculate 3 + 4Add 5 to your c1a answerAdd 6 to your c1b answerCalculate 11 + 8Add 7 to your c2a answerSubtract 4 from your c2b answerAdd your c1c answer to your c2c answerAdd your c1a answer to the previous gate's answerAdd your c2a answer to the previous gate's answerSubtract your c1b answer from the previous gate's answerAdd your c2b answer to the previous gate's answerSubtract your c1c answer from the previous gate's answerAdd your c2c answer to the previous gate's answerSubtract your s1 answer from the previous gate's answerAdd your c1a answer to the previous gate's answerMultiply the previous gate's answer by your c1a answerSubtract your c2a answer from the previous gate's answerMultiply the previous gate's answer by your c1b answerAdd your c2c answer to the previous gate's answerMultiply the previous gate's answer by your c1a answer
Each gate id (c1a, c2b, s1, …) names an earlier answer. Trivial with clean notes; brutal from an accumulating context full of its own noise.
Revision family (rev-2) — currency carries the difficulty
Eight variables change value as you climb — and change back. Every gate asks about the current value; the same question can recur with a change in between. Recompute, don't reuse. A representative sequence:
Variable A is initialized to 3. What is the value of A?Add the current value of F to the current value of C.E changes: E is now 4. Answer 4 to set it.Add the current value of E to the current value of D.— asked again later, after E has changed
Question variety is a roadmap axis: template-generated prose gates with seeded values keep the deterministic scoring while making the surface text effectively inexhaustible. Board rules and season cadence: methodology.