# Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps

arXiv: https://arxiv.org/abs/2608.16309 · HTML: https://mlsanity.com/paper/2608.16309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [CEDR: Contextualized Embeddings for Document Ranking](https://mlsanity.com/paper/1904.07094/) (2019)
- [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques](https://mlsanity.com/paper/2106.14807/) (2021)
- [Learning Passage Impacts for Inverted Indexes](https://mlsanity.com/paper/2104.12016/) (2021)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [A Static Pruning Study on Sparse Neural Retrievers](https://mlsanity.com/paper/2304.12702/) (2023)
- [Let's measure run time! Extending the IR replicability infrastructure to include performance aspects](https://mlsanity.com/paper/1907.04614/) (2019)
- [Faster Learned Sparse Retrieval with Block-Max Pruning](https://mlsanity.com/paper/2405.01117/) (2024)
- [Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers](https://mlsanity.com/paper/2411.04403/) (2024)
- [Faster Learned Sparse Retrieval with Guided Traversal](https://mlsanity.com/paper/2204.11314/) (2022)
- [Optimizing Guided Traversal for Fast Learned Sparse Retrieval](https://mlsanity.com/paper/2305.01203/) (2023)

## Abstract (arXiv)

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×) 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× speedup on the exhaustive pipeline but is subsumed by BMP's β and SEISMIC's querycut. Static pruning complements dynamic pruning: on BMP, combining document and query reduction yields 2.5× speedup with NDCG@10 within 0.003 of the exact baseline. Finally, NDCG@10 saturates while Recall@10 is still in the ~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).