Repository navigation
Register metadata-driven RUL scorer with strict label checks - #673
Open
DhavalRepo18 wants to merge 3 commits into
Open
DhavalRepo18 wants to merge 3 commits into
DhavalRepo18 wants to merge 3 commits into
Conversation
Signed-off-by: Dhaval Patel <pateldha@us.ibm.com>
DhavalRepo18
force-pushed
the
codex/register-rul-scorer
branch
from
November 1, 2026 16:23
eb057a9 to
b756899
Compare
Signed-off-by: Dhaval Patel <pateldha@us.ibm.com>
Signed-off-by: Dhaval Patel <pateldha@us.ibm.com>
DhavalRepo18
changed the title
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Registers
rul_numeric_v1in AOB's existing scorer registry so Harbor's standard verifier can dispatch to the RUL checker after rebuilding the runtime.A submission passes only when both
label_passandnumerical_passare true. Labels require the correct asset and cutoff, exact sorted failed/ongoing fleets, and a genuine boolean horizon decision that matches the outcome and is consistent with the submitted RUL. Numerical accuracy uses the inclusive relative-error tolerance supplied by privatescenario_meta.json. The per-case results expose both checks andoverall_passseparately.The horizon is read from the question and cross-checked against its output comparison; there is no default horizon or extra required metadata. Invalid predictions fail; invalid evaluator configuration or ground truth raises a harness error. No dataset-specific values or fixed tolerance are bundled.
Validation:
python -m pytest src/evaluation/tests -q— 262 passed, including independent synthetic fixtures for numerical boundaries, label failures, missing fields, nondefault horizons, inclusive equality, horizon-crossing forecasts, invalid configuration/gold, and native evaluator dispatch. Changes remain limited to the scorer, registration and tests.