feat(reranker): add opt-in usage/time memory axis to hybrid reranker#6
Merged
Conversation
SonAIengine
force-pushed
the
feature/reranker-memory-axis
branch
from
3ce1fd8 to
cb361da
Compare
Wire the existing ResonanceScorer (importance/recency/vitality) into the EvidenceSearch ranking path as a fifth reranker signal, so retrieval evolves as nodes are reinforced/decayed — which a static index cannot do. RerankerWeights.memory defaults to 0.0 (OFF, zero behaviour change). ScoredCandidate.memory exposes the per-candidate axis. HybridReranker blends importance/recency/vitality (relevance omitted, already covered by lexical+semantic). SynapticGraph plumbs reranker_weights to EvidenceSearch and exposes a runtime-settable reranker_weights property. Verified: reinforcing a result reorders graph.search() rankings while a dense baseline stays frozen; 1312 unit tests pass (axis defaults off).
SonAIengine
force-pushed
the
feature/reranker-memory-axis
branch
from
cb361da to
d1121c1
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Wire the existing ResonanceScorer (importance/recency/vitality) into the EvidenceSearch ranking path as a fifth reranker signal, so retrieval evolves as nodes are reinforced/decayed — which a static index cannot do.
RerankerWeights.memory defaults to 0.0 (OFF, zero behaviour change). ScoredCandidate.memory exposes the per-candidate axis. HybridReranker blends importance/recency/vitality (relevance omitted, already covered by lexical+semantic). SynapticGraph plumbs reranker_weights to EvidenceSearch and exposes a runtime-settable reranker_weights property.
Verified: reinforcing a result reorders graph.search() rankings while a dense baseline stays frozen; 1312 unit tests pass (axis defaults off).