research(nightly): matryoshka-hnsw — dimension-adaptive cascade vector search#467
Draft
ruvnet wants to merge 1 commit into
Draft
research(nightly): matryoshka-hnsw — dimension-adaptive cascade vector search#467ruvnet wants to merge 1 commit into
ruvnet wants to merge 1 commit into
Conversation
Adds ADR-194 topic selection, SOTA research for Matryoshka Representation Learning (MRL, arXiv:2205.13147) and dimension-adaptive cascade search as the 2026-05-16 nightly RuVector research topic. Research loop passes: 3 (Discover → Deepen → Critique) Selected slug: matryoshka-hnsw Final score: 4.65 (highest of 8 evaluated candidates)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Nightly RuVector research: Matryoshka HNSW
Adds the 2026-05-16 nightly research for dimension-adaptive multi-resolution vector search using Matryoshka cascade.
What is included
Working Rust PoC —
crates/ruvector-matryoshkaMatryoshkaIndextrait (3 implementations)FullScan(baseline),CoarseScan(fast/lossy),CascadeSearch(Matryoshka cascade)matryoshka-benchADR —
docs/adr/ADR-194-matryoshka-hnsw.mdResearch document —
docs/research/nightly/2026-05-16-matryoshka-hnsw/README.mdSEO gist —
docs/research/nightly/2026-05-16-matryoshka-hnsw/gist.mdReal benchmark results (x86-64 Linux, rustc 1.87+, N=5 000, D=128, K=10)
Acceptance: recall@10 = 1.0000 ≥ 0.90 → PASS ✓. 2.28× throughput gain over FullScan.
Quick start
cargo build --release -p ruvector-matryoshka cargo test -p ruvector-matryoshka cargo run --release -p ruvector-matryoshkaResearch doc:
docs/research/nightly/2026-05-16-matryoshka-hnsw/README.mdADR:
docs/adr/ADR-194-matryoshka-hnsw.mdThis branch should either become a production RuVector capability or a falsified research path with useful evidence.
Generated by Claude Code