Repository navigation
A: configurable fusion weights + held-out R@1/R@3 - #4
Merged
Merged
Conversation
Expose lexical/vector fusion weights via Config and env overrides (defaults stay 0.75/0.25). Add a deterministic synthetic held-out harness so weight changes can be checked without overfitting.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Config(fusion_lexical_weight/fusion_vector_weight) and envSTRATA_FUSION_LEXICAL_WEIGHT/STRATA_FUSION_VECTOR_WEIGHT.recall._hybrid_relevanceto use config weights.tests/test_fusion_eval.py) reporting R@1 / R@3.Held-out (synthetic, defaults)
out/fusion-heldout-summary.json)Test plan
pytesttargeted fusion/recall: 20 passed (3.12) / 12 passed (3.11 subset)test_local_without_extra_uses_hashing_embedderassertshashingbut env hasfastembed; same failure on cleanmain, unrelated to this PR