Anchor Sheet (evidence → write hooks) [NO PROSE]
Purpose: make “what to actually say” explicit:
- - select quantitative snippets (numbers/percentages)
- select evaluation anchors (benchmarks/datasets/metrics)
- select limitations/failure hooks
This prevents the writer from producing paragraph-shaped but content-poor prose.
Inputs
Outputs
Output format (outline/anchor_sheet.jsonl)
JSONL (one object per H3 subsection).
Required fields:
- -
sub_id, INLINECODE5 - INLINECODE6 (list; each anchor has
hook_type, text, citations, and optional paper_id/evidence_id/pointer)
Workflow
- 1. Read
outline/evidence_drafts.jsonl. - Prefer anchors that contain:
- a number (%, counts, scores)
- an explicit benchmark/dataset/metric name
- an explicit limitation/failure statement
- 3. Filter anchors to only citation keys present in
citations/ref.bib. - Write
outline/anchor_sheet.jsonl.
Quality checklist
- - [ ] Every H3 has >=10 cite-backed anchors (A150++ hard target).
- [ ] At least 1 anchor contains digits when the evidence pack contains digits.
- [ ] No placeholders (
TODO/…/(placeholder)).
Consumption policy (for C5 writers)
Anchors are intended to prevent “long but empty” prose. Treat them as must-use hooks, not optional ideas.
Recommended minimums per H3 (A150++):
- - >=3 protocol anchors (benchmark/dataset/metric/budget/tool access)
- >=3 limitation/failure hooks (concrete, not generic “future work”)
- If digits exist in the evidence pack: include >=1 cited numeric anchor (digit + citation in the same paragraph)
Note:
- - Anchor text is trimmed for readability and does not include ellipsis markers (to reduce accidental leakage into prose).
Script
Quick Start
- - INLINECODE17
- INLINECODE18
All Options
- - INLINECODE19
- INLINECODE20
- INLINECODE21
- INLINECODE22
- INLINECODE23
Examples
-
python scripts/run.py --workspace workspaces/<ws>
- INLINECODE25
Refinement marker (recommended; prevents churn)
When you are satisfied with anchor facts (and they are actually subsection-specific), create:
This is an explicit "I reviewed/refined this" signal:
- - prevents scripts from regenerating and undoing your work
- (in strict runs) can be used as a completion signal before writing
锚点表(证据 → 撰写钩子)[无散文]
目的:明确实际要写什么:
- - 选择量化片段(数字/百分比)
- 选择评估锚点(基准/数据集/指标)
- 选择局限性/失败钩子
这可以防止作者写出段落形状但内容贫乏的散文。
输入
- - outline/evidence_drafts.jsonl
- citations/ref.bib
输出
- - outline/anchor_sheet.jsonl
输出格式(outline/anchor_sheet.jsonl)
JSONL(每个H3子节一个对象)。
必填字段:
- - subid,title
- anchors(列表;每个锚点包含hooktype、text、citations,以及可选的paperid/evidenceid/pointer)
工作流程
- 1. 读取outline/evidence_drafts.jsonl。
- 优先选择包含以下内容的锚点:
- 数字(百分比、计数、分数)
- 明确的基准/数据集/指标名称
- 明确的局限性/失败陈述
- 3. 将锚点过滤为仅存在于citations/ref.bib中的引用键。
- 写入outline/anchor_sheet.jsonl。
质量检查清单
- - [ ] 每个H3包含>=10个引用支持的锚点(A150++硬目标)。
- [ ] 当证据包包含数字时,至少1个锚点包含数字。
- [ ] 无占位符(TODO/…/(placeholder))。
使用策略(针对C5撰写者)
锚点旨在防止长而空的散文。将其视为必须使用的钩子,而非可选的思路。
每个H3的推荐最低数量(A150++):
- - >=3个协议锚点(基准/数据集/指标/预算/工具访问)
- >=3个局限性/失败钩子(具体,而非泛泛的未来工作)
- 如果证据包中存在数字:包含>=1个带引用的数字锚点(同一段落中的数字+引用)
注意:
- - 锚点文本经过修剪以提高可读性,不包含省略号标记(以减少意外泄漏到散文中)。
脚本
快速开始
- - python scripts/run.py --help
- python scripts/run.py --workspace workspaces/
所有选项
- - --workspace
- --unit-id
- --inputs <分号分隔>
- --outputs <分号分隔>
- --checkpoint
示例
- python scripts/run.py --workspace workspaces/
- python scripts/run.py --workspace workspaces/ --inputs outline/evidencedrafts.jsonl;citations/ref.bib --outputs outline/anchorsheet.jsonl
精炼标记(推荐;防止反复修改)
当您对锚点事实满意(且它们确实是子节特定的)时,创建:
- - outline/anchor_sheet.refined.ok
这是一个明确的我已审查/精炼此内容信号:
- - 防止脚本重新生成并撤销您的工作
- (在严格运行中)可在撰写前用作完成信号