FA-98438 / Token sampling filters / Member archive
Token sampling: Prompt history is included in repetition adjustment · case 03
Prompt history is included in repetition adjustment.
Case contract
The penalty history is prompt followed by generated tokens; apply the presence penalty once to every scored token in that combined history.
Why this case matters
A finite, deterministic token-selection contract isolates one decoding operation from model inference and runtime behavior.
One recorded failure
Sample boundary fixtureThis sample comes from the broken implementation of a controlled reproducer.
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| prompt token penalized | {"a": 4.0, "b": 3.0} | {"a": 3.0, "b": 3.0} | 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 ↗