67 gate-passed questions · 45 cells · 19 occupied · go to this type's cells
Bins were cut on this corpus at 240×135@16 (CLEAR_PX 25, motion floor 19 px). Margin bins: a near-edge band [1, 1.25) above the gate boundary, then corpus quantiles; salience bins: a visibility floor, then quantiles.
min over objects: clearance from the mover/static boundary (screen path vs 8% W) · measurable on 67 questions
| margin bin | numeric range |
|---|---|
| near-edge [1,1.25) | [−∞, 1.25) |
| bin0 | [1.25, 4.097) |
| bin1 | [4.097, ∞) |
Ask: is this the same quantity the gate certifies on for this type? Are the states (e.g. 'same', 'gone') the right one-bin exceptions? Are the edges where a change in difficulty actually happens?
min queried-object peak area (frac of frame) · floor 0.0007716
| salience bin | numeric range |
|---|---|
| <floor (0.0008) | [−∞, 0.0007716) |
| bin0 | [0.0007716, 0.01108) |
| bin1 | [0.01108, ∞) |
Ask: does this axis capture what makes a question of this type perceptually hard, independently of the answer? Is the floor the right anti-gaming boundary?
answer (branch 1) · labels: 0, 1, 2, 3, 4+
Compatible margin bins per context label (cells outside these are definitionally impossible):
| answer | n |
|---|---|
| 1 | 31 |
| 2 | 17 |
| 3 | 9 |
| 0 | 6 |
| 4 | 3 |
| 5 | 1 |