/
划分小节”,那如果是从原文里提取的语句作为小节标题?不对,那也属于拆分,但内容不变。哦不对,等下看原文的结构,是不是可以拆分段落?比如第一段讲问题:从开头到“rather than appearing as explicit outliers.” 这是一段,讲背景和存在的问题。然后接下来从“In this paper, we propose...”到“provides historical reference scoring.” 这是第二段,讲提出的方法框架。然后接下来从“Experiments on 23 ODDS benchmark datasets...”到最后,是第三段,讲实验结果。对,这样拆分段落,每个用p包裹,然后重要的内容比如“confidence-based materials data quality assessment framework”“nine-dimensional feature-quality prior”“duplicate-aware sample initialization”“sample-feature bipartite graph propagation”“weakly supervised graph attention”“Memory-GAT module”这些重要的术语用strong?还有代码相关的,比如mp\_20,还有$R^2$?不对,规则里说代码用pre code,那mp_20还有那些公式里的符号?等下看,原文里的mp\_20,还有$R^2$,$0.538\pm0.008$这些,是不是属于代码或者公式?不对,用户说代码用pre code,那这些是不是可以放在code里?等下看原文里的“mp\_20”还有那些数学符号,比如$R^2$,还有数值带±的?不对,先仔细看:首先,原文里的“mp\_20”,还有“$R^2$”,还有那些带$的公式,应该用code标签包裹对吧?因为是代码/公式类的?然后重要的内容,比如提出的框架名称,方法模块,这些用strong。那现在组织内容:首先第一段,背景和问题:
The rapid development of materials machine learning relies on large-scale, heterogeneous datasets, yet model reliability is often compromised by imperfect data from diverse experiments, simulations, and database integration. Real-world materials databases may contain measurement errors, failed calculations, missing or duplicate records, and hidden violations of physicochemical constraints. Such problems are difficult to identify because corrupted samples may remain statistically plausible rather than appearing as explicit outliers.
然后第二段,提出的方法:In this paper, we propose a confidence-based materials data quality assessment framework that integrates domain knowledge with graph-structured learning. Data quality is formulated as a continuous confidence estimation problem rather than a binary anomaly identification task, enabling sample-level assessment and historical-reference-based batch comparison. A nine-dimensional feature-quality prior and duplicate-aware sample initialization are calibrated using materials domain rules and statistical evidence. Confidence is further refined through sample-feature bipartite graph propagation and weakly supervised graph attention, while a Memory-GAT module provides historical reference scoring.
然后第三段,实验结果:Experiments on 23 ODDS benchmark datasets show that the generic module achieves an average AUC-ROC of 0.866. In five repeated mixed-contamination experiments on
mp\_20, rule calibration improves
HistGradientBoostingRegressor test
$R^2$ from
$0.538\pm0.008$ to
$0.616\pm0.014$. Graph refinement increases average precision from
$0.943\pm0.004$ to
0.953\pm0.004, while the rule-calibrated configuration has the highest mean test
$R^2$ among the evaluated screening configurations. Five repeated
MACE subset experiments further show an increase in
$R^2$ from
$0.590\pm0.053$ to
$0.880\pm0.027$ after rule-based screening.
不对,等下pre标签是不是不能嵌套在p里?哦对,pre是块级元素,放在p里是不合法的,p里不能放块级元素。哦,那怎么办?那这些代码/公式的内容,是不是可以用code标签就行?不对,规则里说代码用pre code,那如果是行内的代码,是不是用code?不对,规则3说“代码用
”,那行内的怎么办?哦,等下看原文里的这些术语,比如mp_20,HistGradientBoostingRegressor,还有公式,是不是属于代码/公式,行内的话可以用code,但是如果是pre的话是块级,那如果放在段落里的话,是不是可以用而不是pre?不对,再看规则3的描述:“列表内容用- ,引用用
,代码用,重要句子可用”,哦,那如果是行内代码的话,是不是也可以用pre?不对,pre是预格式化块,那如果放在段落里的话,会换行?不对,那有没有可能这些术语是行内的,用就够了?不对,规则说代码用pre code,那是不是需要调整?哦,不对,等下,比如mp_20是数据集名称,是不是不算代码?哦,那公式的话,是不是用code?不对,再想想,规则说不要增删改内容,那首先,段落拆分是对的,因为原文的内容可以分成三个自然段:背景问题、方法、实验,这样每个p包裹。然后重要的内容,比如提出的框架、各个模块、方法,用strong,这个是允许的。然后里面的专业术语,比如mp\_20,HistGradientBoostingRegressor,MACE,还有$R^2$,还有那些数值带$的,是不是可以用包裹?不对,规则说代码用pre code,那如果是行内的,是不是可以用?哦,可能规则里的代码包括行内