feat(ADR-261 M2): multi-bit + large-N ANN scaling study — measured, no crossover (refutes M1 prediction)#1066
Merged
Merged
Conversation
…ng harness
Generalize the SymphonyQG-style quantized-traversal HNSW from 1-bit Hamming to a
b-bit-per-dimension code (b ∈ {1,2,4}), mirroring ADR-156 §10's multi-bit RaBitQ
scheme (rotate via FHT Pass-2, uniform mid-rise scalar quantizer over [-3,3],
ranked by per-dim L1). b=1 is byte-for-byte the original construction (codes in
{0,1} ⇒ L1 == Hamming), pinned by one_bit_build_bits_matches_legacy_build.
Bytes/node scales linearly: 128-d → 16/32/64 B for b=1/2/4.
- hnsw_quantized.rs: QuantizedHnswIndex::build_bits(...,bits,...), bits()/
bytes_per_node() accessors, code-L1 greedy+beam traversal. build(...) kept as
the b=1 backward-compatible entry point. +4 tests (multi-bit recall regression,
bits clamp, bytes/node, legacy parity).
- ann_measure.rs: build_indices_bits / build_quant_bits / run_scaling_study +
best_float_op / best_quant_op; scaling_report (#[ignore], --release) and a
CI-safe scaling_study_small_is_consistent.
- ann_bench.rs: 2-bit and 4-bit quant criterion benches over the shared graph.
ruvector lib 151 → 156 passed, 0 failed, 1 ignored (scaling_report).
Co-Authored-By: claude-flow <ruv@ruv.net>
…over (refutes M1 prediction)
Multi-bit (b∈{1,2,4}) quantized HNSW traversal + N∈{10k,100k,250k} scaling study,
measured on this box. No crossover at any (N,b): at 10k more bits help (ratio
0.19→0.48×, b≥2 reaches 0.90 recall) but quant stays slower than float HNSW at
equal recall; at 100k/250k quant recall collapses (b=4: 1.0→0.788→0.624, never
≥0.90) while float holds ≥0.92. The predicted large-N crossover moved the wrong
way. Published negative with the mechanism explained. ADR-261 §11.
Co-Authored-By: claude-flow <ruv@ruv.net>
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.
Summary
ADR-261 Milestone-2 — completes the SymphonyQG investigation by building the two levers M1 predicted would produce a crossover (multi-bit codes + large N) and measuring them. The prediction is refuted with data: a published negative with the mechanism explained.
Built
hnsw_quantized.rs): generalized from 1-bit tob-bit-per-dimension (b ∈ {1,2,4}, 16/32/64 bytes/node) over the Pass-2 rotated coordinates — same quantizer as ADR-156 §10'smeasure_multibit.ann_measure.rs):run_scaling_study/best_float_op/best_quant_op+ ascaling_report(#[ignore],--release) and a CI-safescaling_study_small_is_consistent.MEASURED (dim=128, K=10, L2, M=16, ef_construction=200, seeded,
--release, target recall ≥ 0.90)Verdict — NO crossover, prediction refuted
Validation
cargo test --workspace --no-default-features→ exit 0, 0 failed. ruvector lib 151→156 (+5 multi-bit/scaling tests).python archive/v1/data/proof/verify.py→ VERDICT: PASS (off the proof path).scaling_reporttest (ANN_BENCH_N-tunable) — reproducible.🤖 Generated with claude-flow