Metraipolis › archive › dc_5559e83bed7b

SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists — arXiv:2610.02387

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02387
License (as archived)
CC0-1.0
Archived
2026-10-06T09:00:25.653Z
SHA-256 of the archived text
ec4f9a0d7f46a252d82a357e3089cd59801494fdcb1aaca69808f8c2c968304b
Stable URL of this page
https://metraipolis.com/documento/dc_5559e83bed7b

How to cite

SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists — arXiv:2610.02387 — arXiv (en), https://arxiv.org/abs/2610.02387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5559e83bed7b (Metraipolis archive dc_5559e83bed7b, sha256 ec4f9a0d7f46a252d82a357e3089cd59801494fdcb1aaca69808f8c2c968304b)
BibTeX
@misc{dc5559e83bed7b,
  title = {SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists — arXiv:2610.02387},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02387},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5559e83bed7b; sha256 ec4f9a0d7f46a252d82a357e3089cd59801494fdcb1aaca69808f8c2c968304b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present SOLO, an index for approximate nearest-neighbor search in general metric spaces whose serving path contains no ranking heuristic of any kind: a query is routed to the $k_s$ nearest points of a random sample of the database, and every object in the touched posting lists is evaluated with the true distance. Because nothing must outrank anything, recall equals a coverage probability computable from the stored index: one ground-truth pass over a query sample certifies every operating point at once, without serving any of them -- a recall certificate, and for a navigable graph no analogous object exists at any price. The whole index is one recursive rule -- sample the collection, post each object to its $b$ nearest sample points, split any list that outgrows a bound, always scan the leaves -- and its operating surface obeys an equal-work law, recall $\approx f(b \cdot k_s)$, whose level is a one-scalar signature of the dataset. The same scan-only structure gives a serving floor no graph architecture reaches once the router is itself indexed by the same rule: Deep-100M served at recall 0.9977 from 1 GB of resident memory (enforced cap, 10.7 bytes per object) and at 0.9964 from 256 MB, Deep-1B at recall 0.9925 from 512 MB (and from 96 MB at depth 3), inserts that are one search, and deletes that are exact. Throughput is competitive where the hardware allows it -- up to $1.8\times$ a tuned HNSW at $10^8$ on a two-socket 32-core server, with operating points to the right of where that graph saturates -- and the tables report it against HNSW, DiskANN, GRAFT, NAPP, misi, and SPANN's assignment rule on the same hardware and ground truth.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.IR).
Categorie arXiv: Databases (cs.DB) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.02387 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T08:21:15.851Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).