fix(validate): widen the dataset leak check beyond the gold ECCN (description + item_name, EAR99 rows included) - #1
Open
isaac-maya wants to merge 1 commit into
Conversation
… description and item_name, EAR99 rows included
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Discovery. Found while running the validator (scripts/build_dataset.py) on my own candidate file. Enforces the curation rule already stated in data/schema.md.
What it does: widens the dataset validator's leak check so it catches what mine caught:
Why: the story is in the data PR. The validator passed my file, and my own stricter check then caught two of my descriptions leaking: one named a related entry (3A090.a against a 4A090.a gold), one ended with "no license is required under the 4A003 note". A leak turns the question into a lookup, which data/schema.md says the benchmark must not become. This makes the tooling enforce the rule the docs already state.
Benign phrases like "numerically controlled oscillator" do not trigger it. 50 tests pass (two new integration tests pin that
validatenow exits nonzero on a leaking file, not just prints), and the 34 published questions (data/questions.jsonl) come back clean. No false alarms.