Metraipolis › archive › dc_4f65e7803bee

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps — arXiv:2608.16309

Source

arXiv (en)

Original

https://arxiv.org/abs/2608.16309

License (as archived)

CC0-1.0

Archived

2026-10-18T18:07:08.418Z

SHA-256 of the archived text

c6a05a8f601b4fe147acb7ccf1c1287bcbec1296ddc23d73cbd85a040902fae4

Stable URL of this page

https://metraipolis.com/documento/dc_4f65e7803bee

How to cite

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps — arXiv:2608.16309 — arXiv (en), https://arxiv.org/abs/2608.16309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f65e7803bee (Metraipolis archive dc_4f65e7803bee, sha256 c6a05a8f601b4fe147acb7ccf1c1287bcbec1296ddc23d73cbd85a040902fae4)

@misc{dc4f65e7803bee,
  title = {Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps — arXiv:2608.16309},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16309},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f65e7803bee; sha256 c6a05a8f601b4fe147acb7ccf1c1287bcbec1296ddc23d73cbd85a040902fae4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms. We present the first cross-engine pruning portability study, evaluating static pruning strategies across three engines - a controlled C++ pipeline (exhaustive inverted index), BMP (block-max pruning), and SEISMIC (clustered inverted indexes) - on two benchmarks (MS MARCO, Natural Questions) with two encoders spanning opposite query-density regimes (SPLADE: 44 avg. query terms; V3-GTE: 7 avg. query terms), totaling 1,140 experimental configurations, with an additional deep-judgment validation on TREC DL 2019/2020. We find that index-side pruning (document and posting-list) is portable: it consistently reduces latency (1.2-6.6$\times$) and index size (18-82%) across all engines because sparse retrieval is memory-bound - a conclusion we support with cache-miss, TLB, and IPC profiling. In contrast, query pruning is already internalized by modern engines: it yields 4-11$\times$ speedup on the exhaustive pipeline but is subsumed by BMP's $\beta$ and SEISMIC's query_cut. Static pruning complements dynamic pruning: on BMP, combining document and query reduction yields 2.5$\times$ speedup with NDCG@10 within 0.003 of the exact baseline. Finally, NDCG@10 saturates while Recall@10 is still in the ${\sim}$85-95% range across all three engines, providing a portable stopping criterion: practitioners can push pruning to this knee without visible ranking degradation. Together, these findings answer what transfers (index-side pruning), what breaks (query pruning), and what still helps (static atop dynamic pruning).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16309 — 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 2026-10-18T16:29:14.103Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).