FA-98124 / Sequence batch packing / Member archive
Loss mask includes prompt tokens · case 04
Loss mask includes prompt tokens.
Case contract
Concatenate prompt and response tokens; return a mask of zero for prompt positions and one for response positions.
Why this case matters
This deterministic toy packing rule models a common boundary in preparing bounded training sequences.
One recorded failure
Sample boundary fixtureThis sample comes from the broken implementation of a controlled reproducer.
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| one response | [[4, 8, 12], [1, 1, 1]] | [[4, 8, 12], [0, 0, 1]] | 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 ↗