Metraipolis › archive › dc_e14ae3a67104

Reaction precedents extend retrosynthetic prediction beyond training coverage — arXiv:2610.40249

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40249
License (as archived)
CC0-1.0
Archived
2026-10-31T06:10:45.860Z
SHA-256 of the archived text
6da4d788ce9a616ce93412ce863afd824a9c17af7b1012cae1ce977bc2515506
Stable URL of this page
https://metraipolis.com/documento/dc_e14ae3a67104

How to cite

Reaction precedents extend retrosynthetic prediction beyond training coverage — arXiv:2610.40249 — arXiv (en), https://arxiv.org/abs/2610.40249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e14ae3a67104 (Metraipolis archive dc_e14ae3a67104, sha256 6da4d788ce9a616ce93412ce863afd824a9c17af7b1012cae1ce977bc2515506)
BibTeX
@misc{dce14ae3a67104,
  title = {Reaction precedents extend retrosynthetic prediction beyond training coverage — arXiv:2610.40249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e14ae3a67104; sha256 6da4d788ce9a616ce93412ce863afd824a9c17af7b1012cae1ce977bc2515506},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reaction precedents guide retrosynthesis, but how far they can compensate for gaps in task-specific training coverage remains unclear. Using 2.71 million reactions, we restricted training and retrieval coverage by transformation or time, then expanded only the retrieval corpus with model parameters fixed. For transformations excluded from training, mean Top-1 accuracy increased from 13.0% to 58.0% on a historical test set and from 4.9% to 23.1% on a temporally held-out test set. For temporal coverage gaps, retrieval expansion enabled a model trained on records before 2017 to match or exceed a non-retrieval model trained on records before 2025 on both test sets. Without task-specific fine-tuning, precedents improved all 14 representative general-purpose models on both test sets and USPTO-50K; the strongest with precedents surpassed all eight representative specialized models. These findings show that inference-time reaction precedents can extend retrosynthetic prediction beyond task-specific training coverage without parameter updates.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.40249 — 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 2026-10-31T06:07:08.556Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).