`包裹,长文用`
`/`
`划分小节。 3. 列表内容用`
- `,引用用`
`,代码用`
`,重要句子可用``。
4. 保留原文所有信息,不得增删改内容。
5. 不要输出``/``/``等文档级标签。
正文内容:
Deep learning models that combine genotypes with neuroimaging predict neurological diseases more accurately than either modality alone. Their clinical use, however, requires identifying which genetic variants a prediction is based on. Path-based attribution methods like Integrated Gradients address this by integrating the model's gradient from a baseline to the input. These methods assume the model accepts any point along that path as a valid input. Genotype models violate this assumption. They map the three discrete allele dosages \{0,1,2\} to vectors through a learned embedding defined only at those values, so a straight line passes through fractional genotypes at which no embedding, and therefore no gradient, exists. Attribution must therefore proceed in embedding space where the choice of path can affect the resulting attribution. We show that the commonly used per-variant estimator does not generally satisfy completeness. Additive separability guarantees completeness for this estimator, but interactions between variants generally break that property. Instead, we integrate along piecewise-linear embedding-space paths connecting genotype waypoints observed in the training cohort. Each path satisfies completeness in the continuum although the interiors of its segments are not necessarily observed. Our method improves faithfulness over Integrated Gradients and discretized Integrated Gradients under both perturbation protocols, achieves the strongest results for Parkinson's disease classification under support-preserving perturbations, and is competitive with a support-background Shapley baseline under per-variant perturbations. It also shows higher seed stability and better recovery of planted non-additive effects in a synthetic benchmark.
分析正文,这是一个学术摘要/新闻正文,没有明显的列表、引用或代码。需要划分小节吗?可以划分为几个部分,比如背景与问题、方法、实验结果。或者就当作一个长段落,加几个小标题。
原文本其实是一个连续的段落。为了符合“长文用/
划分小节”的规则,我可以适当添加小标题来划分结构,但规则4要求“保留原文所有信息,不得增删改内容”。添加小标题算不算“增改内容”?
通常,添加结构性标题如果不改变原文文字,是允许的,但为了严格遵守“不得增删改内容”,最好不添加额外的文字作为标题,或者把原文的句子作为标题?不行,标题通常是总结性的。
如果不添加标题,直接用`
`包裹整个段落,也是可以的,因为规则说“长文用
`,代码用``,重要句子可用``。 4. 保留原文所有信息,不得增删改内容。 5. 不要输出``/``/``等文档级标签。 正文内容: Deep learning models that combine genotypes with neuroimaging predict neurological diseases more accurately than either modality alone. Their clinical use, however, requires identifying which genetic variants a prediction is based on. Path-based attribution methods like Integrated Gradients address this by integrating the model's gradient from a baseline to the input. These methods assume the model accepts any point along that path as a valid input. Genotype models violate this assumption. They map the three discrete allele dosages \{0,1,2\} to vectors through a learned embedding defined only at those values, so a straight line passes through fractional genotypes at which no embedding, and therefore no gradient, exists. Attribution must therefore proceed in embedding space where the choice of path can affect the resulting attribution. We show that the commonly used per-variant estimator does not generally satisfy completeness. Additive separability guarantees completeness for this estimator, but interactions between variants generally break that property. Instead, we integrate along piecewise-linear embedding-space paths connecting genotype waypoints observed in the training cohort. Each path satisfies completeness in the continuum although the interiors of its segments are not necessarily observed. Our method improves faithfulness over Integrated Gradients and discretized Integrated Gradients under both perturbation protocols, achieves the strongest results for Parkinson's disease classification under support-preserving perturbations, and is competitive with a support-background Shapley baseline under per-variant perturbations. It also shows higher seed stability and better recovery of planted non-additive effects in a synthetic benchmark. 分析正文,这是一个学术摘要/新闻正文,没有明显的列表、引用或代码。需要划分小节吗?可以划分为几个部分,比如背景与问题、方法、实验结果。或者就当作一个长段落,加几个小标题。 原文本其实是一个连续的段落。为了符合“长文用/
划分小节”的规则,我可以适当添加小标题来划分结构,但规则4要求“保留原文所有信息,不得增删改内容”。添加小标题算不算“增改内容”? 通常,添加结构性标题如果不改变原文文字,是允许的,但为了严格遵守“不得增删改内容”,最好不添加额外的文字作为标题,或者把原文的句子作为标题?不行,标题通常是总结性的。 如果不添加标题,直接用`
`包裹整个段落,也是可以的,因为规则说“长文用
/
划分小节”,如果不算长文或者不适合划分,可以直接用`
`。但为了体现排版能力,可以把原文按语义分成几个段落,或者提取句子做小标题? “不得增删改内容”意味着不能添加原文没有的字词。如果我不添加小标题,只使用`
`,是安全的。原文本只有一个自然段。我可以直接用一个`
`包裹,或者将原文按句群拆分成几个`
`,但不要添加标题,以免违反“不得增删改内容”。 等等,原文本中有一个数学符号 `\{0,1,2\}`,这可以放在`
`或者直接放在文本中。由于它是行内的数学公式表示,直接放在``里或者用``包裹行内的 `{0,1,2}` 都可以。原文是 `\{0,1,2\}`,保留原样。
让我们仔细看看原文:
"Deep learning models that combine genotypes with neuroimaging predict neurological diseases more accurately than either modality alone. Their clinical use, however, requires identifying which genetic variants a prediction is based on. Path-based attribution methods like Integrated Gradients address this by integrating the model's gradient from a baseline to the input. These methods assume the model accepts any point along that path as a valid input. Genotype models violate this assumption. They map the three discrete allele dosages \{0,1,2\} to vectors through a learned embedding defined only at those values, so a straight line passes through fractional genotypes at which no embedding, and therefore no gradient, exists. Attribution must therefore proceed in embedding space where the choice of path can affect the resulting attribution. We show that the commonly used per-variant estimator does not generally satisfy completeness. Additive separability guarantees completeness for this estimator, but interactions between variants generally break that property. Instead, we integrate along piecewise-linear embedding-space paths connecting genotype waypoints observed in the training cohort. Each path satisfies completeness in the continuum although the interiors of its segments are not necessarily observed. Our method improves faithfulness over Integrated Gradients and discretized Integrated Gradients under both perturbation protocols, achieves the strongest results for Parkinson's disease classification under support-preserving perturbations, and is competitive with a support-background Shapley baseline under per-variant perturbations. It also shows higher seed stability and better recovery of planted non-additive effects in a synthetic benchmark."
可以把它分成几个段落,例如:
段落1:介绍深度学习模型和临床应用需求。
段落2:介绍基于路径的归因方法及其在基因型模型上的假设违反。
段落3:介绍现有估计器的问题和本文的方法。
段落4:介绍实验结果。
分段落不改变内容,只是改变了换行。
例如:
Deep learning models that combine genotypes with neuroimaging predict neurological diseases more accurately than either modality alone. Their clinical use, however, requires identifying which genetic variants a prediction is based on. Path-based attribution methods like Integrated Gradients address this by integrating the model's gradient from a baseline to the input. These methods assume the model accepts any point along that path as a valid input.
Genotype models violate this assumption. They map the three discrete allele dosages \{0,1,2\} to vectors through a learned embedding defined only at those values, so a straight line passes through fractional genotypes at which no embedding, and therefore no gradient, exists. Attribution must therefore proceed in embedding space where the choice of path can affect the resulting attribution.
We show that the commonly used per-variant estimator does not generally satisfy completeness. Additive separability guarantees completeness for this estimator, but interactions between variants generally break that property. Instead, we integrate along piecewise-linear embedding-space paths connecting genotype waypoints observed in the training cohort. Each path satisfies completeness in the continuum although the interiors of its segments are not necessarily observed.
Our method improves faithfulness over Integrated Gradients and discretized Integrated Gradients under both perturbation protocols, achieves the strongest results for Parkinson's disease classification under support-preserving perturbations, and is competitive with a support-background Shapley baseline under per-variant perturbations. It also shows higher seed stability and better recovery of planted non-additive effects in a synthetic benchmark.
关于 `/
`,如果不添加标题,是否违反规则2?规则2说“长文用
/
划分小节”,这意味着如果是长文,应该用。但添加标题会违反规则4“不得增删改内容”。为了权衡,我可以把原文的第一句或者某些句子提取出来作为标题?不,这改变了内容。或者我不加标题,因为规则说“长文用...”,如果不算严格的长文(只是一段摘要),可以不用。或者,我可以把段落分成几块,不加标题,只使用 `
`。
其实,很多类似的任务中,如果不添加标题,只使用 `
` 也是可以的,因为“不得增删改内容”是硬性要求,而“长文用”是条件性要求(如果是长文才用)。这里只有约200词,不算长文。
检查代码标签:`\{0,1,2\}` 可以用 `\{0,1,2\}` 包裹,或者直接输出。用 `` 更符合“代码用
”或者行内代码的语义。这里用 `\{0,1,2\