前驱体基因组：用于固态合成的成对反应数据集
The Precursor Genome: A Pairwise Reaction Dataset for Solid-State Synthesis
浏览论文内容
中文总结 AI 辅助
针对固态反应缺乏相关数据集阻碍合成科学发展的问题，通过A-Lab自动驾驶实验室生成前驱体基因组数据集，涵盖多种反应、元素及元数据，经自动精修和人工验证，为固态反应性预测模型提供可重复使用的基准。
中文摘要 AI 辅助
固态反应仍是无机材料的主要制备途径，但尚无大型、机器可读数据集报告其具有一致来源的实验方案和结果，这阻碍了合成科学的第一性原理、数据驱动和机器学习方法。本文展示了前驱体基因组，这是一个由A-Lab自动驾驶实验室自主生成的包含1035个成对固态反应的数据集，涵盖46种前驱体和39种元素。每个反应都与其完整实验元数据一起报告，包括测量的热曲线、前驱体和回收质量以及仪器配置。通过Dara框架的自动Rietveld精修从原始X射线衍射（1351次扫描）中识别每个产物混合物，产生1950个精修案例，并由人类专家在三层质量尺度上独立验证。原始模式文件、序列化精修对象和审阅者注释通过经Pydantic验证的JSON账本分发，保留从每个前驱体对到其最终相分配的完整可追溯性。前驱体基因组为训练和评估固态反应性预测模型建立了一个公平、可重复使用的基准。
英文摘要
Solid-state reactions remain the dominant route to inorganic materials, yet no large, machine-readable dataset reports their experimental protocols and outcomes with consistent provenance; this gap obstructs first-principles, data-driven, and machine-learning approaches to synthesis science. Here, we present the Precursor Genome, a dataset of 1,035 pairwise solid-state reactions generated autonomously by the A-Lab self-driving laboratory, spanning 46 precursors and 39 elements. Every reaction is reported together with its full experimental metadata, including measured thermal profiles, precursor and recovered masses, and instrument configuration. Every product mixture is identified from raw X-ray diffraction (1,351 scans) through automated Rietveld refinement with the Dara framework, yielding 1,950 refinement cases that are independently validated by human experts on a three-tier quality scale. Raw pattern files, serialized refinement objects, and reviewer annotations are distributed through a Pydantic-validated JSON ledger, preserving full traceability from each precursor pair to its final phase assignment. The Precursor Genome establishes a FAIR, reusable benchmark for training and evaluating predictive models of solid-state reactivity.
