Metraipolis › archive › dc_272bd45afcd4

ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science — arXiv:2610.41396

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41396
License (as archived)
CC0-1.0
Archived
2026-11-03T08:02:48.960Z
SHA-256 of the archived text
348f58e3de4666105f739b29d9a50a8b6cd85dc527cdfa1843d81b2b17a7d3c8
Stable URL of this page
https://metraipolis.com/documento/dc_272bd45afcd4

How to cite

ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science — arXiv:2610.41396 — arXiv (en), https://arxiv.org/abs/2610.41396 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_272bd45afcd4 (Metraipolis archive dc_272bd45afcd4, sha256 348f58e3de4666105f739b29d9a50a8b6cd85dc527cdfa1843d81b2b17a7d3c8)
BibTeX
@misc{dc272bd45afcd4,
  title = {ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science — arXiv:2610.41396},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41396},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_272bd45afcd4; sha256 348f58e3de4666105f739b29d9a50a8b6cd85dc527cdfa1843d81b2b17a7d3c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41396. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In AI for Science scenarios, experimental design and method reproduction require retrieving protocols that satisfy multiple interdependent constraints, yet existing benchmarks lack systematic evaluation of this capability. To address this gap, we introduce ProSearch, a benchmark for multi-constraint protocol retrieval in experimental science. ProSearch has three key features: (1) realism, with queries grounded in real experimental records and expert-defined templates; (2) complexity, with 60 experimental fields and their dependencies; and (3) diagnosticity, with 3-5 explicit constraints per query, including numerical and negation constraints. We construct ProSearch through LLM-based extraction, data-driven constraint selection, controlled query generation, and evidence-based relevance validation. The resulting benchmark contains 1,515 queries across six experimental science domains. We conduct extensive experiments on ProSearch with 19 representative retrievers and complementary analyses. The best-performing retriever achieves an average nDCG@10 of only 0.290, which improves to 0.474 with reranking. Structured diagnostic analysis shows that explicit constraint matching provides a strong ranking signal, while manual error analysis identifies joint constraint binding as a key bottleneck. ProSearch provides a testbed for systematically evaluating scientific retrieval systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41396 — 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 2026-11-03T07:59:38.803Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).