FA-100084 / Preference pair construction / Member archive
Preference pairs: weights are normalized across unrelated prompts · case 04
weights are normalized across unrelated prompts.
Case contract
Rows are [prompt,id,weight]. Return [prompt,id,numerator,denominator] for positive weights normalized by prompt sum, preserving input order.
Why this case matters
A small deterministic preference-data transform makes pair semantics inspectable without a training framework.
One recorded failure
Sample boundary fixtureThis sample comes from the broken implementation of a controlled reproducer.
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| separate denominators | [["p4", "a", 4, 16], ["p4", "b", 4, 16], ["q4", "c", 8, 16]] | [["p4", "a", 1, 2], ["p4", "b", 1, 2], ["q4", "c", 1, 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 ↗