| title | Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings |
|---|---|
| authors | Stanislav Kirdey, Clark Labs Inc |
| date | 2026-05-27 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.28034 |
| links | abs pdf hf code |
| abstract | Clark Hash is a small method for storing neural embeddings in less space. It normalizes each database vector, applies a deterministic sparse signed Johnson-Lindenstrauss projection, clips the result, and stores a fixed-width scalar-quantized code. Queries stay in floating point and are scored against the stored sketches. In the default 384-dimensional sentence-embedding setting, Clark Hash stores a cosine-search vector in 48 bytes instead of 1536 bytes for dense f32 storage. This is 32x smaller. The method does not need a training pass, learned codebooks, rotations, or corpus statistics before new vectors can be stored. We describe the codec, the Rust implementation, and a multilingual sentence-similarity evaluation on 9,304 labeled pairs from 29 subsets. With a multilingual MiniLM encoder, the 48-byte sketches reached 0.910 and 0.946 macro Pearson correlation with dense cosine scores on STS17 and STS22. Clark Hash is not a new Johnson-Lindenstrauss theorem and it is not a replacement for approximate nearest-neighbor indexes. It is a simple stateless codec for compact embedding storage. |
cite
@misc{kirdey2026clark,
title={Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings},
author={Stanislav Kirdey and Clark Labs Inc},
year={2026},
eprint={2605.28034},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.28034}
}