`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。
分析正文内容:
这是一段关于气象预测物理幻觉(physical hallucinations)和提出PhysXAI框架的学术新闻/摘要。
原文是一整段。为了符合“长文用``/`
`划分小节”以及“每个自然段落用`
`包裹”,我需要合理地将其拆分成几个小节和段落,同时严格保留所有信息,不增删改内容。
原文句子拆分:
1. Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling.
2. We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies.
3. Unlike existing post-hoc metric suites, PhysXAI is a learnable system that explicitly decouples forecast error from physical plausibility.
4. We formalise the problem through a novel joint condition on numerical and physical residuals, and introduce a multi-branch encoder that extracts representations from conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals.
5. A key innovation is a physics-consistency contrastive learning objective, which we theoretically show the latent representation to be approximately isometric to the physical residual space, ensuring that diagnostic decisions remain grounded in physically meaningful deviations.
6. We further derive an adaptive multi-objective loss with gradient-based weighting to balance competing diagnostic objectives.
7. The framework produces spatially resolved hallucination maps, violation-type classifications, and calibrated Bayesian uncertainty, enabling both detection and interpretable attribution of physical inconsistencies.
8. We conduct a comprehensive comparative evaluation of PhysXAI across ERA5, WeatherBench 2, and MERRA-2, using forecasts from GraphCast, Pangu-Weather, and NeuralGCM, with Python-written code and a fully reproducible experimental protocol.
9. Our theoretical analysis and empirical evaluation establish PhysXAI as a principled framework for diagnosing physical hallucinations and advancing trustworthy AI for weather forecasting.
如何划分小节和段落,同时不改变原文的字词?
可以将某些句子组合成段落,并添加`
`,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。 分析正文内容: 这是一段关于气象预测物理幻觉(physical hallucinations)和提出PhysXAI框架的学术新闻/摘要。 原文是一整段。为了符合“长文用``/`
`划分小节”以及“每个自然段落用`
`包裹”,我需要合理地将其拆分成几个小节和段落,同时严格保留所有信息,不增删改内容。 原文句子拆分: 1. Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling. 2. We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies. 3. Unlike existing post-hoc metric suites, PhysXAI is a learnable system that explicitly decouples forecast error from physical plausibility. 4. We formalise the problem through a novel joint condition on numerical and physical residuals, and introduce a multi-branch encoder that extracts representations from conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals. 5. A key innovation is a physics-consistency contrastive learning objective, which we theoretically show the latent representation to be approximately isometric to the physical residual space, ensuring that diagnostic decisions remain grounded in physically meaningful deviations. 6. We further derive an adaptive multi-objective loss with gradient-based weighting to balance competing diagnostic objectives. 7. The framework produces spatially resolved hallucination maps, violation-type classifications, and calibrated Bayesian uncertainty, enabling both detection and interpretable attribution of physical inconsistencies. 8. We conduct a comprehensive comparative evaluation of PhysXAI across ERA5, WeatherBench 2, and MERRA-2, using forecasts from GraphCast, Pangu-Weather, and NeuralGCM, with Python-written code and a fully reproducible experimental protocol. 9. Our theoretical analysis and empirical evaluation establish PhysXAI as a principled framework for diagnosing physical hallucinations and advancing trustworthy AI for weather forecasting. 如何划分小节和段落,同时不改变原文的字词? 可以将某些句子组合成段落,并添加`
`或`
`标题。但是,添加标题本身算不算“增删改内容”? 规则4说:“保留原文所有信息,不得增删改内容”。通常,添加标题(如`
问题背景
`)属于增加内容。如果严格不增删改,最好不添加任何原文没有的标题文字。或者,可以将小标题直接从原文中提取,但原文并没有小标题。 如果不添加小标题,怎么满足“长文用``/`
`划分小节”? 也许可以把原文的某些句子作为小标题?比如第一句的关键词。但这会破坏原文的句子结构。 或者,使用HTML的`
`标签包裹原文的某些核心句子,作为小节标题? 例如:
Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling.
这有点奇怪,把句子当标题。 另一种理解:“长文用``/`
`划分小节”是通用规则,如果原文没有明显的小节,可以不加,或者把段落分好。但为了尽量满足规则,我可以把原文分成几个逻辑段落,并使用`
`来标记段落的主题(如果必须加标题,只能加原文里没有的词,但这违反了“不得增删改内容”)。 等等,如果我不加标题,只分段落,会不会被判错?“长文用`
`/`
`划分小节”说明如果有长文,应该用。我可以把第一句作为`
`,或者把“We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies.”作为`
`。 其实,更稳妥的做法是不添加原文没有的汉字/单词作为标题,而是把原文的句子用`
`或`
`包裹,作为小节标题,剩下的用`
`。 或者,原文其实只有一段。我可以把它拆成几个`
`,不写`
`/`
`,因为“长文用……”是条件触发。不过为了稳妥,我尽量用`
`/`
`。 比如:
Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling.
We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies. Unlike existing post-hoc metric suites, PhysXAI is a learnable system that explicitly decouples forecast error from physical plausibility.
We formalise the problem through a novel joint condition on numerical and physical residuals, and introduce a multi-branch encoder that extracts representations from conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals.
A key innovation is a physics-consistency contrastive learning objective, which we theoretically show the latent representation to be approximately isometric to the physical residual space, ensuring that diagnostic decisions remain grounded in physically meaningful deviations. We further derive an adaptive multi-objective loss with gradient-based weighting to balance competing diagnostic objectives.
The framework produces spatially resolved hallucination maps, violation-type classifications, and calibrated Bayesian uncertainty, enabling both detection and interpretable attribution of physical inconsistencies.
We conduct a comprehensive comparative evaluation of PhysXAI across ERA5, WeatherBench 2, and MERRA-2, using forecasts from GraphCast, Pangu-Weather, and NeuralGCM, with Python-written code and a fully reproducible experimental protocol. Our theoretical analysis and empirical evaluation establish PhysXAI as a principled framework for diagnosing physical hallucinations and advancing trustworthy AI for weather forecasting.
这样处理,既使用了``和`
`划分小节,又完全没有增加任何原文没有的词句,完美符合“不得增删改内容”。
重要句子可用``:
比如:“physical hallucinations” 和 “PhysXAI” 可以用``加粗。
“Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling. We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies.”
再审视一下规则:
1. 只输出HTML片段本身,不要Markdown围栏、不要解释;
2. 每个自然段落用``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。
检查文本是否有列表、引用、代码?没有。所以不需要使用``、``、``。
调整HTML结构,确保标点符号和单词完全一致,不增删改。
- `,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。 检查文本是否有列表、引用、代码?没有。所以不需要使用`- `、`
`、`
`。 调整HTML结构,确保标点符号和单词完全一致,不增删改。