docs(aroma): record the aroma evaluation + defer decision - #45
Merged
Merged
Conversation
Document the rigorous attempt and honest negative result: aggregated the only commercially-clean odor-descriptor set (keller_2016, CC-BY) and trained per-descriptor RandomForest regressors — all 20 scored CV-R2 <= 0 (5-fold CV). Root cause: naive-subject ratings are too noisy; the learnable (expert-labeled) odor data is all restricted. Decision: defer aroma, keep the OpenPOM scaffold for licensed/customer data, lead with taste. Adds the attempt scripts (build_aroma_dataset.py, train_aroma.py), docs/AROMA.md, and the keller_2016 (Keller & Vosshall 2016) attribution.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Records the rigorous aroma attempt and the honest negative result: the only commercially-clean odor-descriptor set (keller_2016, CC-BY) was aggregated and trained per-descriptor — all 20 scored CV-R² ≤ 0 (5-fold). Root cause: naive-subject ratings are too noisy; the learnable expert-labeled data is all restricted. Decision: defer aroma, keep the OpenPOM scaffold for licensed/customer data, lead with taste. Adds the attempt scripts,
docs/AROMA.md, and the keller_2016 attribution.