模块:逻辑衔接与方法论深度
触发词: logic, coherence, 逻辑, 衔接, methodology, 方法论, 论证, argument
脚本用法:
uv run python $SKILL_DIR/scripts/analyze_logic.py main.typ
uv run python $SKILL_DIR/scripts/analyze_logic.py main.typ --section method
--section接受规范键与同义词(methods/methodology/approach→method)。
目标:确保段落间逻辑流畅,强化方法论的严谨性。
重点检查领域:
1. 段落级逻辑衔接(AXES 模型):
| 组成部分 | 说明 | 示例 |
|---|---|---|
| Assertion(主张) | 清晰的主题句,陈述核心观点 | "注意力机制能够提升序列建模效果。" |
| Xample(例证) | 支撑主张的具体证据或数据 | "实验中,注意力机制达到95%准确率。" |
| Explanation(解释) | 分析证据为何支撑主张 | "这一提升源于其捕获长程依赖的能力。" |
| Significance(意义) | 与更广泛论点或下一段的联系 | "这一发现为本文架构设计提供了依据。" |
2. 过渡信号词:
| 关系类型 | 中文信号词 | 英文对应 |
|---|---|---|
| 递进 | 此外、进一步、更重要的是 | furthermore, moreover |
| 转折 | 然而、但是、相反 | however, nevertheless |
| 因果 | 因此、由此可见、故而 | therefore, consequently |
| 顺序 | 首先、随后、最后 | first, subsequently, finally |
| 举例 | 例如、具体而言、特别是 | for instance, specifically |
3. 方法论深度检查清单:
- [ ] 每个主张都有证据支撑(数据、引用或逻辑推理)
- [ ] 方法选择有充分理由(为何选此方法而非其他?)
- [ ] 明确承认研究局限性
- [ ] 清晰陈述前提假设
- [ ] 可复现性细节充分(参数、数据集、评估指标)
4. 常见问题:
| 问题类型 | 表现 | 修正方法 |
|---|---|---|
| 逻辑断层 | 段落间缺乏衔接 | 添加过渡句说明段落关系 |
| 无据主张 | 断言缺乏证据支撑 | 补充引用、数据或推理 |
| 方法论浅薄 | "本文采用X"但无理由 | 解释为何X适合本问题 |
| 隐含假设 | 前提条件未明示 | 显式陈述假设条件 |
输出格式:
// 逻辑衔接(第45行)[Severity: Major] [Priority: P1]: 段落间逻辑断层
// 问题:从问题描述直接跳转到解决方案,缺乏过渡
// 原文:数据存在噪声。本文提出一种滤波方法。
// 修改后:数据存在噪声,这对后续分析造成干扰。因此,本文提出一种滤波方法以解决该问题。
// 理由:添加因果过渡,连接问题与解决方案
// 方法论深度(第78行)[Severity: Major] [Priority: P1]: 方法选择缺乏论证
// 问题:方法选择未说明理由
// 原文:本文采用ResNet作为骨干网络。
// 修改后:本文采用ResNet作为骨干网络,其残差连接结构能有效缓解梯度消失问题,且在特征提取任务中表现优异。
// 理由:用技术原理论证架构选择分章节指南:
| 章节 | 逻辑衔接重点 | 方法论深度重点 |
|---|---|---|
| Abstract | 目的→方法→结果→结论的流畅衔接 | 突出核心贡献 |
| Introduction | 问题→空白→贡献的流畅衔接 | 论证研究意义 |
| Related Work | 按主题分组,显式对比 | 定位与前人工作的关系 |
| Methods | 步骤间逻辑递进 | 论证每个设计选择 |
| Experiments | 设置→结果→分析的流程 | 解释评估指标选择 |
| Discussion | 发现→启示→局限的衔接 | 承认研究边界 |
最佳实践:
- 一段一主题:每段聚焦单一核心观点
- 主题句先行:段首即陈述本段主张
- 证据链完整:每个主张都需支撑(数据、引用或逻辑)
- 显式过渡:使用信号词标明段落关系
- 论证而非描述:解释"为何",而非仅陈述"是什么"
Literature Review Quality Validation (A1-A4)
Authoritative rules are defined in
latex-paper-en/references/modules/LOGIC.md. This section mirrors them for Typst usage.
A1: Thematic Clustering (Not Author/Year Enumeration)
Related Work must organize references by research theme. Detecting 3+ consecutive sentences following "Author (Year) proposed..." signals enumeration → Major/P1.
Script detection: analyze_logic.py checks for consecutive author/year enumeration patterns in the related section.
A2: Critical Analysis After Each Theme Cluster (LLM-judgment)
Each thematic group must end with a synthesis sentence that compares or evaluates. Requires LLM judgment.
A3: Research Gap Derivation
The final paragraph of Related Work must contain explicit research gap language. The script scans the last 10 lines for gap keywords (gap|limitation|remains|lack|overlooked|under-explored). No match → Major/P1.
A4: Funnel-Shaped Citation Density (LLM-judgment)
Citation density should follow broad→focused→specific. Requires LLM judgment.
Cross-Section Logic Chain Closure (C3)
Introduction contribution claims must be answered in the Conclusion. The script extracts contribution keywords from introduction and answer keywords from conclusion. If intro has claims but conclusion has zero answer language → Major/P1 ([Script] observation).
Activate with --cross-section flag or full-document analysis (no --section).
Motivation Red-Thread Closure (opt-in: --motivation-thread)
A strong paper is one problem→solution arc: every Introduction promise should be tested in Results/Experiments and resolved in Discussion/Conclusion. This opt-in diagnostic is additive — without the flag the normal logic output is unchanged.
uv run python scripts/analyze_logic.py main.typ --motivation-threadProduces (read-only, all [Script], comment prefix //):
- Promise Map — each Introduction promise → best-overlapping Results/Experiment line;
[NO EVIDENCE FOUND]= promise never tested. - Closure Map — each Introduction claim → best-overlapping Discussion/Conclusion line;
[UNCLOSED]= claim never resolved. - Evidence-without-promise — numeric Results lines that trace to no Introduction promise.
Mechanism: keyword + content-token overlap (English words ≥4 chars plus CJK bigrams), so it works on English and Chinese Typst papers alike. It is a heuristic navigation aid, not a verdict — the report says so and asks for manual verification.