FA-98194 / Attention mask construction / Member archive
Dilated attention includes every intermediate key · case 04
Dilated attention includes every intermediate key.
Case contract
Query i sees key j iff j<=i and (i-j) is divisible by positive dilation D.
Why this case matters
A small explicit visibility matrix makes sequence-attention boundary behavior reviewable.
One recorded failure
Sample boundary fixtureThis sample comes from the broken implementation of a controlled reproducer.
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| stride two | [[true, false, false, false, false, false, false], [true, true, false, false, false, false, false], [false, true, true, false, false, false, false], [false, false, true, true, false, false, false], [false, false, false, true, true, false, false], [false, false, false, false, true, true, false], [false, false, false, false, false, true, true]] | [[true, false, false, false, false, false, false], [false, true, false, false, false, false, false], [true, false, true, false, false, false, false], [false, true, false, true, false, false, false], [true, false, true, false, true, false, false], [false, true, false, true, false, true, false], [true, false, true, false, true, false, true]] | Failed |
MEMBER ARCHIVE
The complete case is available to members.
This record includes three runnable implementations, regression fixtures, execution results, and source hashes.
Member access is invitation-based. Sign in with your invited account to inspect the sources.
Sign in to the archive ↗