131 gate-passed questions · 48 cells · 31 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.
start lead (px) / 8% W · measurable on 131 questions
| margin bin | numeric range |
|---|---|
| near-edge [1,1.25) | [−∞, 1.25) |
| bin0 | [1.25, 2.578) |
| bin1 | [2.578, ∞) |
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, 0.01451) |
| bin1 | [0.01451, 0.02784) |
| bin2 | [0.02784, ∞) |
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: in the left third of the frame, in the middle third of the frame, in the right third of the frame, no longer visible
Compatible margin bins per context label (cells outside these are definitionally impossible):
| answer | n |
|---|---|
| in the middle third of the frame | 46 |
| in the left third of the frame | 33 |
| no longer visible | 29 |
| in the right third of the frame | 23 |