Metraipolis › archive › dc_ff3250000cdb
R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing — arXiv:2610.00700
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00700
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:02:42.820Z
- SHA-256 of the archived text
c7122817dc6ebbb2ea545cfa8f83ad1a8e746a556f92db2c7f5c58b293197ba6- Stable URL of this page
https://metraipolis.com/documento/dc_ff3250000cdb
How to cite
R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing — arXiv:2610.00700 — arXiv (en), https://arxiv.org/abs/2610.00700 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff3250000cdb (Metraipolis archive dc_ff3250000cdb, sha256 c7122817dc6ebbb2ea545cfa8f83ad1a8e746a556f92db2c7f5c58b293197ba6)
BibTeX
@misc{dcff3250000cdb,
title = {R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing — arXiv:2610.00700},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00700},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff3250000cdb; sha256 c7122817dc6ebbb2ea545cfa8f83ad1a8e746a556f92db2c7f5c58b293197ba6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00700. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in AI for scientific discovery enable molecular understandingand design, yet reasoning over incomplete chemical representations this http URL structures, which encode molecular families through variable R-groupplaceholders (\textit{R\textsubscript{1}}, \textit{R\textsubscript{2}}, \textit{X}, etc.), are ubiquitous in pharmaceutical patents and requiregrounding across molecular, textual, and chemical this http URL , existing molecule-language benchmarks focus on fully specifiedmolecules, leaving R-group grounding largely this http URL introduce R-GroundBench:, a diagnostic benchmark built from real patent Markushstructures, featuring a Multiple-Choice (VQA) track with controlled difficultyand modality splits, and an open-ended Generation this http URL results reveal a substantial gap between recognition andmolecular this http URL models achieve over 90\% accuracy on Easy VQA, performance drops to56--66\% on Hard VQA when shortcuts are this http URL -domain VLMs also remain unreliable, achieving only 25.7--46.2\% on HardVQA despite domain-specific this http URL , Generation Exact Match remains below 20\% for most models and below8\% when visual input is this http URL findings reveal that current AI systems lack reliable grounding andexecution for Markush editing, highlighting challenges for AI-drivenscientific discovery.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.00700 — 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 2026-10-06T10:21:27.883Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).