superlab 0.1.25 → 0.1.27

package/README.md

@@ -255,7 +255,7 @@ Stages should follow that file rather than guess language locally.
 - Python 3.10+
 - Git
 
-`/lab:write` ships with vendored paper-writing references and the upstream example bank for `abstract`, `introduction`, and `method` under the installed `lab` skill, so it does not depend on an extra runtime skill installation.
+`/lab:write` ships with vendored paper-writing references, the upstream example bank for `abstract`, `introduction`, and `method`, and local manuscript-delivery examples for `related work`, `experiments`, and `conclusion` under the installed `lab` skill, so it does not depend on an extra runtime skill installation.
 
 ## Command Set
 
@@ -311,7 +311,10 @@ See the source command docs in [commands/codex/lab.md](/Users/zhouhao119/coding/
 - `docs/research/main-tables.md`
 - `docs/research/artifact-status.md`
 - `docs/research/paper/main.tex`
+- `docs/research/paper/references.bib`
 - `docs/research/paper/sections/*.tex`
+- `docs/research/paper/tables/*.tex`
+- `docs/research/paper/figures/*.tex`
 
 Internal writing-control artifacts stay under:
 
@@ -323,6 +326,7 @@ If `paper_template_root` is configured, `/lab:write` should inspect that templat
 If no template is configured, the first manuscript-writing round should ask once whether to continue with the managed default LaTeX scaffold or attach a template directory first.
 If the user approves the default scaffold, persist that choice in `.lab/config/workflow.json` and stop asking on ordinary rounds.
 At the final export or final-draft boundary, if the project is still on the default scaffold and no attached template exists, ask one final reminder question before finalizing.
+For final-draft or export rounds, `/lab:write` should materialize real LaTeX tables, figure placeholders with figure intent, a non-empty `references.bib`, and pass `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before stopping.
 
 `/lab` treats `.lab/` as the workflow-control layer only. Durable outputs should use natural project roots:
 
@@ -336,6 +340,7 @@ At the final export or final-draft boundary, if the project is still on the defa
 - `scripts/eval_report.py` normalizes metrics into a comparable summary.
 - `scripts/summarize_iterations.py` rolls multiple iteration summaries into one file.
 - `scripts/validate_results.py` verifies required report fields before publication.
+- `scripts/validate_manuscript_delivery.py` verifies that the paper deliverable contains basic manuscript-ready tables, figures, citations, and bibliography.
 
 ## Packaging
 

package/README.zh-CN.md

@@ -253,7 +253,7 @@ superlab init --lang en
 - Python 3.10+
 - Git
 
-`/lab:write` 自带 vendored 的 paper-writing 章节参考，以及 `abstract`、`introduction`、`method` 对应的 upstream example bank，不再依赖额外安装一个运行时写作 skill。
+`/lab:write` 自带 vendored 的 paper-writing 章节参考、`abstract`、`introduction`、`method` 对应的 upstream example bank，以及为 `related work`、`experiments`、`conclusion` 补齐的 manuscript-delivery examples，不再依赖额外安装一个运行时写作 skill。
 
 ## 命令集合
 
@@ -296,7 +296,10 @@ Codex 和 Claude 的命令入口不一样：
 - `docs/research/main-tables.md`
 - `docs/research/artifact-status.md`
 - `docs/research/paper/main.tex`
+- `docs/research/paper/references.bib`
 - `docs/research/paper/sections/*.tex`
+- `docs/research/paper/tables/*.tex`
+- `docs/research/paper/figures/*.tex`
 
 内部写作控制工件放在：
 
@@ -308,6 +311,7 @@ Codex 和 Claude 的命令入口不一样：
 如果没有配置模板，第一次进入论文 `.tex` 写作时应先追问一次：继续使用内置默认 LaTeX scaffold，还是先接入模板目录。
 如果用户确认先用默认 scaffold，就把这个决定持久化到 `.lab/config/workflow.json`，后续普通轮次不再重复追问。
 但在最终导出或最终定稿节点，如果项目仍在使用默认 scaffold 且没有接入模板，应再提醒一次，给用户最后切换模板的机会。
+在最终定稿或导出轮次里，`/lab:write` 还应物化真正的 LaTeX 表格、带图意图的 figure placeholders、非空的 `references.bib`，并在停止前通过 `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper`。
 
 `/lab` 把 `.lab/` 视为工作流控制层，不是正式结果目录。持久输出应按自然根目录放置：
 
@@ -321,7 +325,7 @@ Codex 和 Claude 的命令入口不一样：
 - `package-assets/` 是 npm 安装时真正分发到目标项目的命令与 skill 资产。
 - `skills/lab/` 是仓库开发时使用的共享 workflow 定义。
 - `templates/` 是研究工件模板。
-- `scripts/` 是运行登记、评估汇总和结果校验脚本。
+- `scripts/` 是运行登记、评估汇总和结果校验脚本，其中也包括论文交付校验器。
 - `results/` 和 `figures/` 是默认的自然结果目录。
 - `tests/` 是脚本与安装器测试。
 - `examples/` 是最小端到端示例。

package/lib/i18n.cjs

@@ -60,7 +60,7 @@ const ZH_CONTENT = {
   [path.join(".codex", "prompts", "lab-write.md")]: codexPrompt(
     "把验证过的研究工件转成论文 section，并按小步方式修订",
     "section or writing target",
-    "使用已安装的 `lab` 技能：`.codex/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `/lab:write`，不要只推荐别的 `/lab` 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 `/lab:write` 阶段。它必须先有来自 `/lab:framing` 的已批准 framing artifact，再读取 `.codex/skills/lab/references/paper-writing/` 下与当前 section 对应的参考文件；如果当前是 `abstract`、`introduction` 或 `method`，还必须继续读取 `.codex/skills/lab/references/paper-writing/examples/index.md`、对应的 examples index，以及 1-2 个具体 example 文件。然后结合 `paper-review.md` 与 `does-my-writing-flow-source.md`，先写 mini-outline，再只修改一个 section。第一次进入会产出论文 `.tex` 的路径时，如果 `paper_template_root` 为空，必须先问一次：继续使用默认 LaTeX scaffold，还是先接入模板目录。"
+    "使用已安装的 `lab` 技能：`.codex/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `/lab:write`，不要只推荐别的 `/lab` 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 `/lab:write` 阶段。它必须先有来自 `/lab:framing` 的已批准 framing artifact，再读取 `.codex/skills/lab/references/paper-writing/` 下与当前 section 对应的参考文件；如果当前 section 有 bundled example bank，还必须继续读取 `.codex/skills/lab/references/paper-writing/examples/index.md`、对应的 examples index，以及 1-2 个具体 example 文件。然后结合 `paper-review.md` 与 `does-my-writing-flow-source.md`，先写 mini-outline，先规划该 section 需要的表、图和 citation，再只修改一个 section。在起草 `method`、`experiments`、`related work` 或 `conclusion` 之前，必须先运行 `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`。最终定稿或导出轮次必须运行 `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper`。第一次进入会产出论文 `.tex` 的路径时，如果 `paper_template_root` 为空，必须先问一次：继续使用默认 LaTeX scaffold，还是先接入模板目录。"
   ),
   [path.join(".claude", "commands", "lab-idea.md")]: claudeCommand(
     "lab-idea",
@@ -925,9 +925,10 @@ const ZH_SKILL_FILES = {
 
 ## 目标
 
-- Venue or audience:
-- Paper status:
+- 目标会议或读者:
+- 论文状态:
 - 一句话主线：
+- 已批准 framing artifact:
 - Terminology lock:
 
 ## Section 状态
@@ -946,6 +947,60 @@ const ZH_SKILL_FILES = {
 - Limitation sources:
 - 哪些 claim 还缺证据：
 
+## 表计划
+
+- 主结果表:
+  - 资产文件:
+  - 作用章节:
+  - 作用:
+  - 证据:
+  - 状态:
+- 消融表:
+  - 资产文件:
+  - 作用章节:
+  - 作用:
+  - 证据:
+  - 状态:
+
+## 图计划
+
+- 方法总览图:
+  - 资产文件:
+  - 作用章节:
+  - 图意图:
+  - 证据:
+  - 状态:
+- 结果总览图:
+  - 资产文件:
+  - 作用章节:
+  - 图意图:
+  - 证据:
+  - 状态:
+
+## 引用计划
+
+- 背景锚点:
+  - 引用或来源锚点:
+  - 作用章节:
+  - 为什么重要:
+  - 状态:
+- 最接近前作:
+  - 引用或来源锚点:
+  - 作用章节:
+  - 为什么重要:
+  - 状态:
+- 指标或 benchmark 来源:
+  - 引用或来源锚点:
+  - 作用章节:
+  - 为什么重要:
+  - 状态:
+
+## 章节到资产映射
+
+- 方法:
+- 实验:
+- 相关工作:
+
 ## 写作顺序
 
 1. 第一优先 section:
@@ -1583,8 +1638,23 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "write.md")] = `# \`/l
 - 如果用户在最终提醒里仍确认继续使用默认 scaffold，就把 \`paper_template_final_reminder_acknowledged\` 持久化为 \`true\`。
 - 只加载当前 section guide，不要一次加载全部章节参考。
 - 如果当前 section 是 \`abstract\`、\`introduction\` 或 \`method\`，还必须继续读取本地 example bank：\`references/paper-writing/examples/index.md\`、对应的 examples index，以及 1-2 个具体 example 文件。
+- 如果当前 section 是 \`related work\`、\`experiments\` 或 \`conclusion\`，也要读取对应的本地 example bank：\`references/paper-writing/examples/index.md\`、对应的 examples index，以及 1-2 个具体 example 文件。
 - 例子只能复用结构、段落角色和句法逻辑，不能直接复用原句。
 - 先写 mini-outline 再写 prose。
+- 如果当前 section 带方法、实验、相关工作或结论 claim，先规划需要的表格、figure placeholders 和 citations，再写 prose。
+- 在起草 \`method\`、\`experiments\`、\`related work\` 或 \`conclusion\` 之前，必须先运行 \`.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md\`。
+- 如果 \`paper-plan\` 校验失败，就先补 \`.lab/writing/plan.md\`，不能直接跳去写 prose。
+- 最终定稿或导出轮次里，必须维护非空的 \`references.bib\`，并把关键实验结果物化成真正的 LaTeX 表格：
+  - \`<deliverables_root>/paper/tables/main-results.tex\`
+  - \`<deliverables_root>/paper/tables/ablations.tex\`
+- 方法或实验章节还必须物化带 caption、label 和图意图的 figure placeholders：
+  - \`<deliverables_root>/paper/figures/method-overview.tex\`
+  - \`<deliverables_root>/paper/figures/results-overview.tex\`
+- 只要论文资产发生变化，就同步更新 \`.lab/writing/plan.md\` 里的表计划、图计划、引用计划和章节到资产映射。
+- 不要把纯 prose section 当成论文交付完成。
+- 论文源码里不要出现绝对本地路径、workflow provenance、shell 日志或 \`+/-\` 这类工程记法；应改成 paper-facing LaTeX 表达。
+- 在最终定稿或导出轮次结束前，必须运行 \`.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper\`；如果失败，就继续补表、图、引用和正文。
+- 如果本地有 LaTeX 工具链，就再跑一次 compile smoke test；如果没有，也要在 write iteration artifact 里记录该限制。
 - 如果缺少 framing artifact，不要继续写作，直接回到 \`/lab:framing\`。
 - 如果某个 claim 没有证据支撑，就削弱或删除。
 
@@ -1594,7 +1664,12 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "write.md")] = `# \`/l
 - \`.lab/writing/plan.md\`
 - \`.lab/writing/iterations/<n>.md\`
 - \`<deliverables_root>/paper/main.tex\`
+- \`<deliverables_root>/paper/references.bib\`
 - \`<deliverables_root>/paper/sections/<section>.tex\`
+- \`<deliverables_root>/paper/tables/main-results.tex\`
+- \`<deliverables_root>/paper/tables/ablations.tex\`
+- \`<deliverables_root>/paper/figures/method-overview.tex\`
+- \`<deliverables_root>/paper/figures/results-overview.tex\`
 `;
 
 ZH_CONTENT[path.join(".claude", "skills", "lab", "stages", "write.md")] =

package/package-assets/claude/commands/lab-write.md

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `write` stage of the lab workflow. It requires an approved framing artifact from the `framing` stage, must read the matching section reference from `.claude/skills/lab/references/paper-writing/`, and for `abstract`, `introduction`, or `method` it must also read `.claude/skills/lab/references/paper-writing/examples/index.md` plus the matching examples index and 1-2 concrete example files. Then it should run `paper-review.md` and `does-my-writing-flow-source.md`, build a mini-outline, and revise only one section.
+This command runs the `write` stage of the lab workflow. It requires an approved framing artifact from the `framing` stage, must read the matching section reference from `.claude/skills/lab/references/paper-writing/`, and for any section with a bundled example bank it must also read `.claude/skills/lab/references/paper-writing/examples/index.md` plus the matching examples index and 1-2 concrete example files. Then it should run `paper-review.md` and `does-my-writing-flow-source.md`, build a mini-outline, plan the section's paper-facing tables/figures/citations, and revise only one section. Before drafting `method`, `experiments`, `related work`, or `conclusion`, it must run `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`. Final-draft or export rounds must run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before stopping.

package/package-assets/claude/commands/lab.md

@@ -58,7 +58,9 @@ Use the same repository artifacts and stage boundaries every time.
 - `iterate` requires a normalized summary from `scripts/eval_report.py`.
 - `run`, `iterate`, `auto`, and `report` should all follow `.lab/context/eval-protocol.md`, including its recorded sources for metrics and comparison implementations.
 - `write` requires an approved framing artifact from the `framing` stage.
-- `write` requires stable report artifacts, a mini-outline, the active section guide, `paper-review.md`, and `does-my-writing-flow-source.md`, and should only change one section per round.
+- `write` requires stable report artifacts, a mini-outline, the active section guide, the matching bundled examples when available, `paper-review.md`, and `does-my-writing-flow-source.md`, and should only change one section per round.
+- Before drafting `method`, `experiments`, `related work`, or `conclusion`, `write` should validate `.lab/writing/plan.md` with `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`.
+- Final-draft or export rounds in `write` should materialize paper-facing tables, figure placeholders, a non-empty `references.bib`, and pass `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper`.
 
 ## How to Ask for `/lab auto`
 

package/package-assets/codex/prompts/lab-write.md

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:write` stage. It requires an approved framing artifact from `/lab:framing`, must read the matching section reference from `.codex/skills/lab/references/paper-writing/`, and for `abstract`, `introduction`, or `method` it must also read `.codex/skills/lab/references/paper-writing/examples/index.md` plus the matching examples index and 1-2 concrete example files. Then it should run `paper-review.md` and `does-my-writing-flow-source.md`, build a mini-outline, and revise only one section.
+This command runs the `/lab:write` stage. It requires an approved framing artifact from `/lab:framing`, must read the matching section reference from `.codex/skills/lab/references/paper-writing/`, and for any section with a bundled example bank it must also read `.codex/skills/lab/references/paper-writing/examples/index.md` plus the matching examples index and 1-2 concrete example files. Then it should run `paper-review.md` and `does-my-writing-flow-source.md`, build a mini-outline, plan the section's paper-facing tables/figures/citations, and revise only one section. Before drafting `method`, `experiments`, `related work`, or `conclusion`, it must run `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`. Final-draft or export rounds must run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before stopping.

package/package-assets/codex/prompts/lab.md

@@ -52,7 +52,9 @@ argument-hint: workflow question or stage choice
 - `/lab:iterate` requires a normalized summary from `scripts/eval_report.py`.
 - `/lab:run`, `/lab:iterate`, `/lab:auto`, and `/lab:report` should all follow `.lab/context/eval-protocol.md`, including its recorded sources for metrics and comparison implementations.
 - `/lab:write` requires an approved framing artifact from `/lab:framing`.
-- `/lab:write` requires stable report artifacts, a mini-outline, the active section guide, `paper-review.md`, and `does-my-writing-flow-source.md`, and should only change one section per round.
+- `/lab:write` requires stable report artifacts, a mini-outline, the active section guide, the matching bundled examples when available, `paper-review.md`, and `does-my-writing-flow-source.md`, and should only change one section per round.
+- Before drafting `method`, `experiments`, `related work`, or `conclusion`, `/lab:write` should validate `.lab/writing/plan.md` with `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`.
+- Final-draft or export rounds in `/lab:write` should materialize paper-facing tables, figure placeholders, a non-empty `references.bib`, and pass `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper`.
 
 ## How to Ask for `/lab:auto`
 

package/package-assets/shared/lab/.managed/scripts/validate_manuscript_delivery.py

@@ -0,0 +1,175 @@
+#!/usr/bin/env python3
+import argparse
+import re
+import sys
+from pathlib import Path
+
+
+ABSOLUTE_PATH_MARKERS = ("/Users/", "/home/", "/tmp/", "/private/tmp/")
+REQUIRED_TABLE_FILES = ("main-results.tex", "ablations.tex")
+REQUIRED_FIGURE_FILES = ("method-overview.tex", "results-overview.tex")
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="Validate that a paper delivery contains basic manuscript-ready assets."
+    )
+    parser.add_argument("--paper-dir", required=True, help="Path to the paper deliverable root")
+    return parser.parse_args()
+
+
+def read_text(path: Path) -> str:
+    return path.read_text(encoding="utf-8")
+
+
+def check_exists(path: Path, issues: list[str], label: str):
+    if not path.exists():
+        issues.append(f"missing required file: {label} ({path})")
+
+
+def check_bibliography(paper_dir: Path, issues: list[str]):
+    bib_path = paper_dir / "references.bib"
+    check_exists(bib_path, issues, "references.bib")
+    if not bib_path.exists():
+        return
+    text = read_text(bib_path)
+    if "TODO" in text or "todo" in text or "Add bibliography entries" in text or "@" not in text:
+        issues.append("missing a non-empty references.bib")
+
+
+def check_global_tex(paper_dir: Path, issues: list[str]):
+    tex_files = sorted(paper_dir.rglob("*.tex"))
+    combined = "\n".join(read_text(path) for path in tex_files)
+
+    if r"\cite{" not in combined:
+        issues.append("missing citation commands in manuscript tex files")
+    if "+/-" in combined:
+        issues.append("replace '+/-' with LaTeX \\pm formatting")
+    if any(marker in combined for marker in ABSOLUTE_PATH_MARKERS):
+        issues.append("manuscript tex files must not contain absolute local paths")
+
+
+def check_table_file(path: Path, issues: list[str], label: str):
+    if not path.exists():
+        if label == "tables/main-results.tex":
+            issues.append("missing a main results table")
+        elif label == "tables/ablations.tex":
+            issues.append("missing an ablation table")
+        else:
+            issues.append(f"missing required file: {label} ({path})")
+        return
+    text = read_text(path)
+    if r"\begin{table}" not in text:
+        issues.append(f"{label} must contain a table environment")
+    if r"\caption{" not in text or r"\label{" not in text:
+        issues.append(f"{label} must contain both caption and label")
+    if not all(token in text for token in (r"\toprule", r"\midrule", r"\bottomrule")):
+        issues.append(f"{label} must use booktabs structure")
+
+
+def check_figure_file(path: Path, issues: list[str], label: str):
+    if not path.exists():
+        if label == "figures/method-overview.tex":
+            issues.append("missing a method figure placeholder")
+        elif label == "figures/results-overview.tex":
+            issues.append("missing an experiments figure placeholder")
+        else:
+            issues.append(f"missing required file: {label} ({path})")
+        return
+    text = read_text(path)
+    if r"\begin{figure}" not in text:
+        issues.append(f"{label} must contain a figure environment")
+    if r"\caption{" not in text or r"\label{" not in text:
+        issues.append(f"{label} must contain both caption and label")
+    if "Figure intent:" not in text and "图意图：" not in text:
+        issues.append(f"{label} must explain figure intent")
+
+
+def check_experiments_section(paper_dir: Path, issues: list[str]):
+    experiments = paper_dir / "sections" / "experiments.tex"
+    check_exists(experiments, issues, "sections/experiments.tex")
+    if not experiments.exists():
+        return
+    text = read_text(experiments)
+    has_table = any(
+        token in text
+        for token in (
+            r"\input{tables/main-results}",
+            r"\input{tables/ablations}",
+            r"\begin{table}",
+        )
+    )
+    has_figure = any(
+        token in text
+        for token in (
+            r"\input{figures/results-overview}",
+            r"\begin{figure}",
+        )
+    )
+    if not has_table:
+        issues.append("experiments section is missing a main results table")
+    if not has_figure:
+        issues.append("experiments section is missing an experiments figure placeholder")
+
+
+def check_method_section(paper_dir: Path, issues: list[str]):
+    method = paper_dir / "sections" / "method.tex"
+    check_exists(method, issues, "sections/method.tex")
+    if not method.exists():
+        return
+    text = read_text(method)
+    has_figure = any(
+        token in text
+        for token in (
+            r"\input{figures/method-overview}",
+            r"\begin{figure}",
+        )
+    )
+    if not has_figure:
+        issues.append("method section is missing a method figure placeholder")
+
+
+def check_main_tex(paper_dir: Path, issues: list[str]):
+    main_tex = paper_dir / "main.tex"
+    check_exists(main_tex, issues, "main.tex")
+    if not main_tex.exists():
+        return
+    text = read_text(main_tex)
+    if r"\bibliography{references}" not in text:
+        issues.append("main.tex must include the references bibliography")
+
+
+def main():
+    args = parse_args()
+    paper_dir = Path(args.paper_dir)
+    issues: list[str] = []
+
+    if not paper_dir.exists():
+        print(f"paper directory does not exist: {paper_dir}", file=sys.stderr)
+        return 1
+
+    check_main_tex(paper_dir, issues)
+    check_bibliography(paper_dir, issues)
+    check_global_tex(paper_dir, issues)
+    check_method_section(paper_dir, issues)
+    check_experiments_section(paper_dir, issues)
+
+    tables_dir = paper_dir / "tables"
+    check_table_file(tables_dir / REQUIRED_TABLE_FILES[0], issues, "tables/main-results.tex")
+    check_table_file(tables_dir / REQUIRED_TABLE_FILES[1], issues, "tables/ablations.tex")
+
+    figures_dir = paper_dir / "figures"
+    check_figure_file(figures_dir / REQUIRED_FIGURE_FILES[0], issues, "figures/method-overview.tex")
+    check_figure_file(figures_dir / REQUIRED_FIGURE_FILES[1], issues, "figures/results-overview.tex")
+
+    if issues:
+        for issue in issues:
+            print(issue, file=sys.stderr)
+        return 1
+
+    print("manuscript delivery artifacts are valid")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/package-assets/shared/lab/.managed/scripts/validate_paper_plan.py

@@ -0,0 +1,228 @@
+#!/usr/bin/env python3
+import argparse
+import re
+import sys
+from pathlib import Path
+
+
+REQUIRED_SECTIONS = {
+    "Target": [r"^##\s+Target\s*$", r"^##\s+目标\s*$"],
+    "Section Status": [r"^##\s+Section Status\s*$", r"^##\s+Section 状态\s*$"],
+    "Evidence Map": [r"^##\s+Evidence Map\s*$", r"^##\s+证据地图\s*$"],
+    "Table Plan": [r"^##\s+Table Plan\s*$", r"^##\s+表计划\s*$"],
+    "Figure Plan": [r"^##\s+Figure Plan\s*$", r"^##\s+图计划\s*$"],
+    "Citation Plan": [r"^##\s+Citation Plan\s*$", r"^##\s+引用计划\s*$"],
+    "Section-to-Asset Map": [r"^##\s+Section-to-Asset Map\s*$", r"^##\s+章节到资产映射\s*$"],
+    "Writing Order": [r"^##\s+Writing Order\s*$", r"^##\s+写作顺序\s*$"],
+    "Five-Dimension Self-Review Status": [
+        r"^##\s+Five-Dimension Self-Review Status\s*$",
+        r"^##\s+五维自评状态\s*$",
+    ],
+}
+
+TARGET_FIELDS = (
+    "Venue or audience",
+    "Paper status",
+    "Core story in one sentence",
+    "Approved framing artifact",
+    "Terminology lock",
+    "目标会议或读者",
+    "论文状态",
+    "一句话主线",
+    "已批准 framing artifact",
+    "术语锁",
+)
+
+SECTION_STATUS_FIELDS = (
+    "Abstract",
+    "Introduction",
+    "Related Work",
+    "Method",
+    "Experiments",
+    "Conclusion",
+)
+
+EVIDENCE_FIELDS = (
+    "Main result sources",
+    "Ablation sources",
+    "Limitation sources",
+    "Claims that still need more evidence",
+    "主结果来源",
+    "消融来源",
+    "限制来源",
+    "还缺更多证据的 claim",
+)
+
+TABLE_DETAIL_FIELDS = (
+    "Asset file",
+    "Section",
+    "Message",
+    "Evidence",
+    "Status",
+    "资产文件",
+    "作用章节",
+    "作用",
+    "证据",
+    "状态",
+)
+FIGURE_DETAIL_FIELDS = (
+    "Asset file",
+    "Section",
+    "Figure intent",
+    "Evidence",
+    "Status",
+    "资产文件",
+    "作用章节",
+    "图意图",
+    "证据",
+    "状态",
+)
+CITATION_DETAIL_FIELDS = (
+    "Citation or source anchor",
+    "Section",
+    "Why it matters",
+    "Status",
+    "引用或来源锚点",
+    "作用章节",
+    "为什么重要",
+    "状态",
+)
+SECTION_MAP_FIELDS = ("Method", "Experiments", "Related Work", "方法", "实验", "相关工作")
+WRITING_ORDER_FIELDS = (
+    "First section target",
+    "Second section target",
+    "Deferred sections",
+    "第一优先 section",
+    "第二优先 section",
+    "延后 section",
+)
+SELF_REVIEW_FIELDS = (
+    "Contribution",
+    "Writing clarity",
+    "Experimental strength",
+    "Evaluation completeness",
+    "Method design soundness",
+)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="Validate that the managed paper plan contains concrete asset planning before prose drafting."
+    )
+    parser.add_argument("--paper-plan", required=True, help="Path to .lab/writing/plan.md")
+    return parser.parse_args()
+
+
+def read_text(path: Path) -> str:
+    return path.read_text(encoding="utf-8")
+
+
+def extract_section_body(text: str, patterns: list[str]) -> str:
+    for pattern in patterns:
+        match = re.search(pattern, text, flags=re.MULTILINE)
+        if not match:
+            continue
+        start = match.end()
+        next_heading = re.search(r"^##\s+", text[start:], flags=re.MULTILINE)
+        end = start + next_heading.start() if next_heading else len(text)
+        return text[start:end].strip()
+    return ""
+
+
+def missing_sections(text: str) -> list[str]:
+    missing = []
+    for section_name, patterns in REQUIRED_SECTIONS.items():
+        if not any(re.search(pattern, text, flags=re.MULTILINE) for pattern in patterns):
+            missing.append(section_name)
+    return missing
+
+
+def has_filled_field(body: str, field_labels: tuple[str, ...]) -> bool:
+    for label in field_labels:
+        pattern = re.compile(rf"^\s*(?:-|\d+\.)\s*{re.escape(label)}:[ \t]*([^\n]+?)\s*$", flags=re.MULTILINE)
+        for match in pattern.finditer(body):
+            value = match.group(1).strip()
+            if value and value not in {"TBD", "TODO", "待补", "待定"}:
+                return True
+    return False
+
+
+def count_filled_fields(body: str, field_labels: tuple[str, ...]) -> int:
+    count = 0
+    for label in field_labels:
+        pattern = re.compile(rf"^\s*(?:-|\d+\.)\s*{re.escape(label)}:[ \t]*([^\n]+?)\s*$", flags=re.MULTILINE)
+        for match in pattern.finditer(body):
+            value = match.group(1).strip()
+            if value and value not in {"TBD", "TODO", "待补", "待定"}:
+                count += 1
+    return count
+
+
+def validate_filled_fields(text: str) -> list[str]:
+    issues: list[str] = []
+
+    target_body = extract_section_body(text, REQUIRED_SECTIONS["Target"])
+    if not has_filled_field(target_body, TARGET_FIELDS):
+        issues.append("paper plan is missing filled target fields")
+
+    section_status_body = extract_section_body(text, REQUIRED_SECTIONS["Section Status"])
+    if count_filled_fields(section_status_body, SECTION_STATUS_FIELDS) < 6:
+        issues.append("paper plan is missing filled section-status entries")
+
+    evidence_body = extract_section_body(text, REQUIRED_SECTIONS["Evidence Map"])
+    if not has_filled_field(evidence_body, EVIDENCE_FIELDS):
+        issues.append("paper plan is missing filled evidence-map entries")
+
+    table_body = extract_section_body(text, REQUIRED_SECTIONS["Table Plan"])
+    if count_filled_fields(table_body, TABLE_DETAIL_FIELDS) < 10:
+        issues.append("paper plan must fill both required table-asset blocks")
+
+    figure_body = extract_section_body(text, REQUIRED_SECTIONS["Figure Plan"])
+    if count_filled_fields(figure_body, FIGURE_DETAIL_FIELDS) < 10:
+        issues.append("paper plan must fill both required figure-asset blocks")
+
+    citation_body = extract_section_body(text, REQUIRED_SECTIONS["Citation Plan"])
+    if count_filled_fields(citation_body, CITATION_DETAIL_FIELDS) < 12:
+        issues.append("paper plan must fill all required citation-plan blocks")
+
+    section_map_body = extract_section_body(text, REQUIRED_SECTIONS["Section-to-Asset Map"])
+    if not has_filled_field(section_map_body, SECTION_MAP_FIELDS):
+        issues.append("paper plan is missing filled section-to-asset mappings")
+
+    writing_order_body = extract_section_body(text, REQUIRED_SECTIONS["Writing Order"])
+    if count_filled_fields(writing_order_body, WRITING_ORDER_FIELDS) < 3:
+        issues.append("paper plan is missing filled writing-order entries")
+
+    self_review_body = extract_section_body(text, REQUIRED_SECTIONS["Five-Dimension Self-Review Status"])
+    if count_filled_fields(self_review_body, SELF_REVIEW_FIELDS) < 5:
+        issues.append("paper plan is missing filled self-review status entries")
+
+    return issues
+
+
+def main():
+    args = parse_args()
+    plan_path = Path(args.paper_plan)
+    if not plan_path.exists():
+        print(f"paper plan does not exist: {plan_path}", file=sys.stderr)
+        return 1
+
+    text = read_text(plan_path)
+    issues = []
+
+    missing = missing_sections(text)
+    if missing:
+        issues.append(f"paper plan is missing required sections: {', '.join(missing)}")
+    issues.extend(validate_filled_fields(text))
+
+    if issues:
+        for issue in issues:
+            print(issue, file=sys.stderr)
+        return 1
+
+    print("paper plan is valid")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/package-assets/shared/lab/.managed/templates/paper-figure.tex

@@ -0,0 +1,6 @@
+\begin{figure}[t]
+\centering
+\fbox{\rule{0pt}{1.2in}\rule{0.9\linewidth}{0pt}}
+\caption{Figure title. Figure intent: explain what this figure should show and why the reader needs it.}
+\label{fig:placeholder}
+\end{figure}

package/package-assets/shared/lab/.managed/templates/paper-plan.md

@@ -24,6 +24,60 @@
 - Limitation sources:
 - Claims that still need more evidence:
 
+## Table Plan
+
+- Main results table:
+  - Asset file:
+  - Section:
+  - Message:
+  - Evidence:
+  - Status:
+- Ablation table:
+  - Asset file:
+  - Section:
+  - Message:
+  - Evidence:
+  - Status:
+
+## Figure Plan
+
+- Method overview figure:
+  - Asset file:
+  - Section:
+  - Figure intent:
+  - Evidence:
+  - Status:
+- Results overview figure:
+  - Asset file:
+  - Section:
+  - Figure intent:
+  - Evidence:
+  - Status:
+
+## Citation Plan
+
+- Background anchor:
+  - Citation or source anchor:
+  - Section:
+  - Why it matters:
+  - Status:
+- Closest prior work:
+  - Citation or source anchor:
+  - Section:
+  - Why it matters:
+  - Status:
+- Metric or benchmark source:
+  - Citation or source anchor:
+  - Section:
+  - Why it matters:
+  - Status:
+
+## Section-to-Asset Map
+
+- Method:
+- Experiments:
+- Related Work:
+
 ## Writing Order
 
 1. First section target:

package/package-assets/shared/lab/.managed/templates/paper-references.bib

@@ -0,0 +1,9 @@
+% Add paper-facing bibliography entries here.
+% Keep keys stable with the manuscript's \cite{...} usage.
+
+@article{placeholder2026,
+  title = {Replace with a real cited work before finalizing},
+  author = {Placeholder, Example},
+  journal = {Placeholder Venue},
+  year = {2026}
+}

package/package-assets/shared/lab/.managed/templates/paper-table.tex

@@ -0,0 +1,13 @@
+\begin{table}[t]
+\caption{One-sentence message of the table and the evaluation protocol.}
+\label{tab:placeholder}
+\centering
+\begin{tabular}{lcc}
+\toprule
+Method & Metric 1 $\uparrow$ & Metric 2 $\uparrow$ \\
+\midrule
+Ours & 0.0000 & 0.0000 \\
+Baseline & 0.0000 & 0.0000 \\
+\bottomrule
+\end{tabular}
+\end{table}

package/package-assets/shared/skills/lab/SKILL.md

@@ -172,14 +172,19 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - Write one paper section or one explicit subproblem per round.
 - Bind each claim to evidence from `report`, iteration reports, or normalized summaries.
 - Write planning artifacts with `.lab/.managed/templates/paper-plan.md`, `.lab/.managed/templates/paper-section.md`, and `.lab/.managed/templates/write-iteration.md`.
-- Write final manuscript artifacts with `.lab/.managed/templates/paper.tex` and `.lab/.managed/templates/paper-section.tex`.
+- Write final manuscript artifacts with `.lab/.managed/templates/paper.tex`, `.lab/.managed/templates/paper-section.tex`, `.lab/.managed/templates/paper-table.tex`, `.lab/.managed/templates/paper-figure.tex`, and `.lab/.managed/templates/paper-references.bib`.
 - Use the vendored paper-writing references under `skills/lab/references/paper-writing/`.
-- For `abstract`, `introduction`, and `method`, also use the vendored example-bank files under `skills/lab/references/paper-writing/examples/`.
+- For any section with a bundled example bank, also use the vendored example-bank files under `skills/lab/references/paper-writing/examples/`.
 - Load only the current section guide, the matching examples index when one exists, 1-2 matching concrete example files, plus `paper-review.md` and `does-my-writing-flow-source.md`.
 - Build a compact mini-outline before prose.
+- Build the paper asset plan before prose when the section carries method or experiments claims.
 - For each subsection, explicitly cover motivation, design, and technical advantage when applicable.
 - Keep terminology stable across rounds and sections.
 - If a claim is not supported by evidence, weaken or remove it.
+- Treat tables, figures, citations, and bibliography as core manuscript content rather than optional polish.
+- Keep paper-facing LaTeX free of absolute local paths, rerun ids, shell transcripts, and internal workflow provenance.
+- Materialize real LaTeX tables and figure placeholders instead of leaving all evidence inside prose paragraphs.
+- Run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before accepting a final-draft or export round.
 - Before finalizing a round, append and answer the five-dimension self-review checklist and revise unresolved items.
 - Apply paper-writing discipline without changing experimental truth.
 - If the evidence is insufficient, stop and route back to `review` or `iterate`.
@@ -194,7 +199,7 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - No unconstrained auto mode. Every `/lab:auto` campaign must declare allowed stages, stop conditions, and a promotion policy in `.lab/context/auto-mode.md`.
 - No auto start without an explicit autonomy level and `Approval status: approved`.
 - No final report without validated normalized results.
-- No paper-writing round without stable report artifacts, an approved framing artifact, evidence links, and LaTeX manuscript output.
+- No paper-writing round without stable report artifacts, an approved framing artifact, evidence links, LaTeX manuscript output, and a passing manuscript-delivery validation for final-draft or export rounds.
 
 ## References
 
@@ -212,7 +217,7 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - Write stage guide: `.codex/skills/lab/stages/write.md` or `.claude/skills/lab/stages/write.md`
 - Paper-writing integration: `.codex/skills/lab/references/paper-writing-integration.md` or `.claude/skills/lab/references/paper-writing-integration.md`
 - Vendored paper-writing references: `.codex/skills/lab/references/paper-writing/{abstract,introduction,related-work,method,experiments,conclusion,paper-review,does-my-writing-flow-source}.md` or `.claude/skills/lab/references/paper-writing/{abstract,introduction,related-work,method,experiments,conclusion,paper-review,does-my-writing-flow-source}.md`
-- Vendored paper-writing example bank: `.codex/skills/lab/references/paper-writing/examples/{index,abstract-examples,introduction-examples,method-examples}.md` or `.claude/skills/lab/references/paper-writing/examples/{index,abstract-examples,introduction-examples,method-examples}.md`, plus the matching section subdirectories
+- Vendored paper-writing example bank: `.codex/skills/lab/references/paper-writing/examples/{index,abstract-examples,introduction-examples,method-examples,related-work-examples,experiments-examples,conclusion-examples}.md` or `.claude/skills/lab/references/paper-writing/examples/{index,abstract-examples,introduction-examples,method-examples,related-work-examples,experiments-examples,conclusion-examples}.md`, plus the matching section subdirectories
 - Command adapters: the installed `/lab:*` command assets
 - Shared workflow config: `.lab/config/workflow.json`
 - Shared project context: `.lab/context/{mission,state,decisions,evidence-index,open-questions,data-decisions,eval-protocol,auto-mode,auto-status}.md`

package/package-assets/shared/skills/lab/references/paper-writing/examples/conclusion/conservative-claim-boundary.md

@@ -0,0 +1,27 @@
+# Conservative Claim-Boundary LaTeX Example
+
+Use this example to close with the strongest supported claim while keeping the
+boundary explicit.
+
+```tex
+\section{Conclusion}
+
+This paper shows that adding a structured ranking backbone together with a
+post-hoc calibration stage improves uplift ranking under the frozen benchmark
+protocol. Across the three benchmark families used in this work, the full model
+consistently matches or exceeds the strongest baselines and remains stronger
+than the key ablated variants. This makes the main claim narrower than a
+universal superiority claim but stronger than a single-dataset win.
+
+We do not claim that the current method solves uplift modeling in every domain
+or that every design choice helps equally on every benchmark. In particular, the
+calibration stage appears beneficial on some datasets and neutral on others,
+which means its value should be interpreted as setting-dependent rather than as
+a guaranteed gain. That boundary is consistent with recent benchmarking
+practice, which argues for claim discipline and protocol-specific interpretation
+rather than broad overgeneralization~\cite{carlini2019evaluating}.
+
+The most useful next step is to extend the evaluation to a broader set of
+benchmark slices and to test whether the same ranking-versus-calibration split
+remains useful when the label distribution shifts more aggressively.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/conclusion-examples.md

@@ -0,0 +1,16 @@
+# Conclusion Example Patterns
+
+Use these examples to end with a bounded claim, not a marketing recap. The
+referenced file is a complete LaTeX conclusion example with explicit claim
+boundary language.
+
+## Recommended Pattern
+
+1. Restate the narrow supported claim.
+2. Restate the strongest evidence in one compact sentence.
+3. State the main limitation or boundary.
+4. End with the next concrete direction, not generic future work.
+
+## Example Files
+
+- `examples/conclusion/conservative-claim-boundary.md`

package/package-assets/shared/skills/lab/references/paper-writing/examples/experiments/figure-placeholder-and-discussion.md

@@ -0,0 +1,44 @@
+# Figure Placeholder and Discussion Example
+
+Use complete figure placeholders when the visual asset is not finalized yet but
+the manuscript already needs a stable figure slot, caption, label, and prose
+attachment.
+
+## Method Figure Placeholder
+
+```tex
+\begin{figure}[t]
+\centering
+\fbox{\rule{0pt}{1.55in}\rule{0.92\linewidth}{0pt}}
+\caption{Method overview. Figure intent: show the full pipeline, highlight the
+boundary between the structured scoring module and the post-hoc calibration
+stage, and make the train-time versus inference-time data flow easy to inspect.}
+\label{fig:method-overview}
+\end{figure}
+```
+
+## Results Figure Placeholder
+
+```tex
+\begin{figure}[t]
+\centering
+\fbox{\rule{0pt}{1.55in}\rule{0.92\linewidth}{0pt}}
+\caption{Benchmark-level results overview. Figure intent: summarize the trend
+across datasets, show error bars or confidence intervals, and reveal whether the
+main gain is stable or dominated by one benchmark.}
+\label{fig:results-overview}
+\end{figure}
+```
+
+## Discussion Example
+
+```tex
+Figure~\ref{fig:method-overview} gives the reader the shortest path to the
+method's logic before the section moves into module details. The figure should
+make it obvious which component produces the structured signal and where the
+post-hoc calibration step changes the final ranking.
+
+Figure~\ref{fig:results-overview} should then complement the tables rather than
+repeat them. Its job is to show whether the gain is stable across datasets and
+seeds, not to claim a new effect that the tables do not already support.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/experiments/main-results-and-ablation-latex.md

@@ -0,0 +1,83 @@
+# Main Results and Ablation LaTeX Example
+
+This file is a complete paper-facing LaTeX example for the experiments section.
+Reuse the structure, caption logic, and prose-to-table linkage. Replace the
+placeholder methods, metrics, and values with the current project's evidence.
+
+Source inspiration:
+- full table/figure organization examples from
+  `guanyingc/latex_paper_writing_tips`
+- full paper-source organization from
+  `evaluating-adversarial-robustness/adv-eval-paper`
+
+## Main Results Table
+
+```tex
+\begin{table}[t]
+\caption{Main benchmark results under the frozen evaluation protocol. Higher is better on all metrics.}
+\label{tab:main-results}
+\centering
+\resizebox{0.92\linewidth}{!}{
+\begin{tabular}{lccc}
+\toprule
+Method & AUUC $\uparrow$ & Qini $\uparrow$ & Calibration Error $\downarrow$ \\
+\midrule
+Strongest baseline & 0.1421 & 0.0873 & 0.0612 \\
+Closest prior work & 0.1488 & 0.0915 & 0.0544 \\
+Ours & \textbf{0.1564} & \textbf{0.0987} & \textbf{0.0418} \\
+\bottomrule
+\end{tabular}
+}
+\end{table}
+```
+
+Table message:
+- `Does the proposed method beat the strongest baselines under the frozen protocol?`
+
+## Ablation Table
+
+```tex
+\begin{table}[t]
+\caption{Ablations that isolate which design choices create the gain.}
+\label{tab:ablations}
+\centering
+\begin{tabular}{lc}
+\toprule
+Variant & AUUC $\uparrow$ \\
+\midrule
+Ours & \textbf{0.1564} \\
+w/o structure module & 0.1497 \\
+w/o calibration stage & 0.1510 \\
+w/ shuffled auxiliary signal & 0.1458 \\
+\bottomrule
+\end{tabular}
+\end{table}
+```
+
+Table message:
+- `Which design choices create the gain, and which ones are neutral?`
+
+## Experiments Section Stitching Example
+
+```tex
+\section{Experiments}
+\label{sec:experiments}
+
+Table~\ref{tab:main-results} answers the main ranking question: whether the full
+method remains stronger than the closest prior work and the strongest practical
+baseline under the frozen protocol. Our method achieves the best AUUC and Qini
+while also reducing calibration error, which means the gain is not coming from
+trading ranking quality against stability.
+
+Table~\ref{tab:ablations} then asks a narrower mechanism question. Removing the
+structure module causes the largest drop, so the main gain is tied to structured
+signal modeling rather than to a generic increase in capacity. Removing the
+calibration stage leads to a smaller but still visible drop, which supports the
+claim that calibration improves final ranking quality without being the sole
+driver of the result. The shuffled-signal variant acts as a negative control and
+shows that the gain does not survive when the auxiliary information is broken.
+
+One caveat is that the calibration gain may remain neutral on some benchmarks,
+so the paper should not overclaim that every component helps equally on every
+dataset.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/experiments-examples.md

@@ -0,0 +1,17 @@
+# Experiments Example Patterns
+
+Use these examples when turning validated results into paper-facing LaTeX assets.
+The referenced files contain complete LaTeX environments and section-level prose
+glue, not just checklists.
+
+## Required Asset Pattern
+
+1. Main results should live in a real `table` environment.
+2. Ablations should live in a separate `table` environment.
+3. Method and experiments should each have at least one figure placeholder with an explicit `Figure intent`.
+4. Captions should explain the table or figure message briefly; longer interpretation belongs in prose.
+
+## Example Files
+
+- `examples/experiments/main-results-and-ablation-latex.md`
+- `examples/experiments/figure-placeholder-and-discussion.md`

package/package-assets/shared/skills/lab/references/paper-writing/examples/index.md

@@ -1,6 +1,7 @@
 # Example Bank Index
 
-Use this folder for concrete writing patterns and locally organized cite targets.
+Use this folder for concrete writing patterns, complete LaTeX snippets, and
+locally organized cite targets.
 
 ## Files
 
@@ -12,10 +13,18 @@ Use this folder for concrete writing patterns and locally organized cite targets
 6. Introduction pipeline files: `references/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.md`, `references/examples/introduction/pipeline-version-2-two-contributions.md`, `references/examples/introduction/pipeline-version-3-new-module-on-existing-pipeline.md`, `references/examples/introduction/pipeline-version-4-observation-driven.md`, `references/examples/introduction/pipeline-not-recommended-abstract-only.md`
 7. Method examples index: `references/examples/method-examples.md`
 8. Method detail files: `references/examples/method/pre-writing-questions.md`, `references/examples/method/module-triad-neural-body.md`, `references/examples/method/neural-body-annotated-figure-text.md`, `references/examples/method/module-design-instant-ngp.md`, `references/examples/method/module-motivation-patterns.md`, `references/examples/method/section-skeleton.md`, `references/examples/method/overview-template.md`, `references/examples/method/example-of-the-three-elements.md`, `references/examples/method/method-writing-common-issues-note.md`
+9. Related work examples index: `references/examples/related-work-examples.md`
+10. Related work files: `references/examples/related-work/closest-prior-gap-template.md`, `references/examples/related-work/topic-comparison-template.md`
+11. Experiments examples index: `references/examples/experiments-examples.md`
+12. Experiments files: `references/examples/experiments/main-results-and-ablation-latex.md`, `references/examples/experiments/figure-placeholder-and-discussion.md`
+13. Conclusion examples index: `references/examples/conclusion-examples.md`
+14. Conclusion files: `references/examples/conclusion/conservative-claim-boundary.md`
 
 ## Usage
 
 1. Pick one template from a section guide.
 2. Open the matching examples file.
-3. Reuse the sentence logic, not exact wording.
-4. Keep citation links in your notes for traceability.
+3. Prefer the complete LaTeX examples when the section needs tables, figures,
+   citations, or section-level stitching.
+4. Reuse the structure and command patterns, not exact wording.
+5. Keep citation links in your notes for traceability.

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work/closest-prior-gap-template.md

@@ -0,0 +1,20 @@
+# Closest Prior Then Gap LaTeX Example
+
+Use this example when one family of papers is the closest technical anchor and
+the paragraph needs to explain the gap precisely.
+
+```tex
+\paragraph{Closest prior work.}
+The closest prior line improves uplift ranking by sharpening the treatment-aware
+scoring objective rather than by changing the final decision rule
+itself~\cite{lee2021uplift,wang2022counterfactual}. These methods are strong
+references because they already optimize for ranking quality and outperform
+simple pointwise baselines on standard benchmarks. However, they still assume
+that the learned score can be used directly as the final ranking signal across
+datasets with different calibration behavior. That assumption is limiting in our
+setting, where the raw score often contains useful relative information but is
+not always aligned with the final protocol-level target. Our method keeps the
+ranking-focused backbone but changes the final stage by inserting a post-hoc
+calibration module, so the method can preserve the stronger internal signal
+while adapting the exposed score to the benchmark-specific decision scale.
+```

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work/topic-comparison-template.md

@@ -0,0 +1,24 @@
+# Topic Comparison LaTeX Example
+
+Use this example when the related-work section needs a compact, citation-driven
+comparison paragraph rather than a bullet list of papers.
+
+```tex
+\paragraph{Structure-aware ranking methods.}
+A second line of work improves ranking by injecting structured inductive bias
+into the scoring function~\cite{smith2021structured,lee2022pairwise}. These
+methods are attractive because they often stabilize training and can exploit
+known relationships among samples or treatment groups. However, they typically
+assume that the structured module alone is sufficient to produce well-calibrated
+scores at evaluation time. In our setting, that assumption is too strong: the
+raw ranking signal remains useful, but it is not always aligned with the final
+decision scale required by the frozen protocol. We therefore keep the
+structure-aware backbone but add a separate calibration stage, which lets us
+reuse the stronger signal while correcting its final score mapping.
+```
+
+What this paragraph does:
+1. groups one literature line by topic
+2. states why the line is attractive
+3. identifies the exact limitation that matters here
+4. positions the current method as a narrower, testable change

package/package-assets/shared/skills/lab/references/paper-writing/examples/related-work-examples.md

@@ -0,0 +1,17 @@
+# Related Work Example Patterns
+
+Use these examples to structure `related work` around technical gaps instead of
+citation dumping. The referenced files are complete citation-driven LaTeX
+paragraph examples.
+
+## Recommended Pattern
+
+1. Open with the topic line.
+2. Summarize 2-4 representative methods compactly.
+3. State the exact limitation that matters for the current problem.
+4. End with a transition sentence that positions the current method.
+
+## Example Files
+
+- `examples/related-work/closest-prior-gap-template.md`
+- `examples/related-work/topic-comparison-template.md`

package/package-assets/shared/skills/lab/references/paper-writing-integration.md

@@ -2,13 +2,13 @@
 
 `/lab:write` vendors the paper-writing references directly into `skills/lab/references/paper-writing/`.
 The goal is to keep the upstream writing discipline while removing brittle runtime dependence on a separately installed skill.
-It also vendors the upstream example bank for the sections that currently have curated examples, so drafting can reuse concrete structure rather than only abstract guidance.
+It also vendors the upstream example bank for the sections that currently have curated examples, and adds local manuscript-delivery examples for missing sections, so drafting can reuse concrete structure rather than only abstract guidance.
 
 ## Role Split
 
 - `lab` controls stage boundaries, evidence discipline, and durable artifacts.
 - the vendored paper-writing references control section structure, paragraph logic, and reviewer-facing polish.
-- the vendored example bank controls example-driven structure selection for `abstract`, `introduction`, and `method`.
+- the vendored example bank controls example-driven structure selection for section prose and paper-facing LaTeX assets.
 - `/lab:write` links evidence-backed research outputs to paper-ready text.
 
 ## Required Shared Constraints
@@ -41,26 +41,35 @@ It also vendors the upstream example bank for the sections that currently have c
 - `paper-writing/examples/abstract-examples.md`
 - `paper-writing/examples/introduction-examples.md`
 - `paper-writing/examples/method-examples.md`
+- `paper-writing/examples/related-work-examples.md`
+- `paper-writing/examples/experiments-examples.md`
+- `paper-writing/examples/conclusion-examples.md`
 - `paper-writing/examples/abstract/*`
 - `paper-writing/examples/introduction/*`
 - `paper-writing/examples/method/*`
+- `paper-writing/examples/related-work/*`
+- `paper-writing/examples/experiments/*`
+- `paper-writing/examples/conclusion/*`
 
 ## Write-Time Rule
 
-For `abstract`, `introduction`, and `method`:
+For `abstract`, `introduction`, `method`, `related work`, `experiments`, and `conclusion`:
 
 1. read the section guide first
-2. read the matching examples index
+2. if the section has a bundled examples index, read it
 3. read 1-2 concrete example files that match the intended structure
-4. reuse structure and sentence logic without copying wording
-
-For `related work`, `experiments`, and `conclusion`:
-
-1. use the section guide directly
-2. do not invent non-existent example-bank files
+4. reuse structure, sentence logic, and LaTeX asset patterns without copying wording
 
 ## Attribution
 
 These references are adapted from:
 
 - `https://github.com/Master-cai/Research-Paper-Writing-Skills/tree/main/research-paper-writing/references`
+
+The local manuscript-delivery examples for missing sections are additionally informed by public LaTeX guidance and real paper-source repositories, including:
+
+- `https://github.com/guanyingc/latex_paper_writing_tips`
+- `https://github.com/evaluating-adversarial-robustness/adv-eval-paper`
+- `https://github.com/lightningnetwork/paper`
+
+These sources are used as structure references for complete LaTeX snippets, table/figure organization, and manuscript assembly patterns, so `/lab:write` can enforce tables, figure placeholders, and bibliography-ready drafts rather than prose-only section text.

package/package-assets/shared/skills/lab/stages/write.md

@@ -45,6 +45,9 @@ When the current target has a bundled example bank, load the examples index and
 - abstract -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/abstract-examples.md`, plus one matching file under `skills/lab/references/paper-writing/examples/abstract/`
 - introduction -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/introduction-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/introduction/`
 - method -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/method-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/method/`
+- related work -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/related-work-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/related-work/`
+- experiments -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/experiments-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/experiments/`
+- conclusion -> `skills/lab/references/paper-writing/examples/index.md`, `skills/lab/references/paper-writing/examples/conclusion-examples.md`, plus 1-2 matching files under `skills/lab/references/paper-writing/examples/conclusion/`
 
 Run these on every round:
 
@@ -61,17 +64,45 @@ Run these on every round:
 - If the user chooses the default scaffold, persist that choice in `.lab/config/workflow.json` by setting `paper_template_decision` to `default-scaffold`.
 - If the user chooses to attach a template, stop the drafting loop and route to `superlab paper attach-template --path <dir>` instead of silently falling back.
 - If `paper_template_decision` is `default-scaffold`, use the managed default LaTeX scaffold under the deliverable paper directory.
+- When using the managed default scaffold, use the managed paper asset templates as the starting point for new manuscript assets:
+  - `.lab/.managed/templates/paper.tex`
+  - `.lab/.managed/templates/paper-section.tex`
+  - `.lab/.managed/templates/paper-table.tex`
+  - `.lab/.managed/templates/paper-figure.tex`
+  - `.lab/.managed/templates/paper-references.bib`
 - If the current round is a final manuscript export or final-draft pass, `paper_template_root` is still empty, `paper_template_decision` is `default-scaffold`, and `paper_template_final_reminder_acknowledged` is `false`, ask one final reminder question about switching to a template before finalizing.
 - If the user confirms staying on the default scaffold at that final reminder, persist `paper_template_final_reminder_acknowledged: true`.
 - Load only the current section guide. Do not load every section guide at once.
-- Reuse example-bank structure, paragraph roles, and sentence logic when examples are bundled, but never copy wording verbatim.
+- Reuse example-bank structure, paragraph roles, sentence logic, and paper-facing LaTeX asset patterns when examples are bundled, but never copy wording verbatim.
 - Treat example cites and example file names as writing references, not as evidence for the current paper.
 - Build a compact mini-outline before prose.
+- Build the paper asset plan before prose when the section carries experimental, method, related-work, or conclusion claims:
+  - record which table asset files the section needs, what each table should show, and which evidence supports it
+  - record which figure placeholder files the section needs, what each figure should show, and why the reader needs it
+  - record which citation anchors must appear in the section and why each anchor matters
+- Before drafting `method`, `experiments`, `related work`, or `conclusion`, run `.lab/.managed/scripts/validate_paper_plan.py --paper-plan .lab/writing/plan.md`.
+- If the paper-plan validator fails, stop and fill `.lab/writing/plan.md` first instead of drafting prose.
 - For each subsection, explicitly include motivation, design, and technical advantage when applicable.
 - Avoid a writing style that reads like incremental patching of a naive baseline.
 - Keep terminology stable across the full paper.
 - Tie every new or revised claim to explicit evidence.
 - If a claim cannot be supported by results, weaken or remove it.
+- Do not treat section prose alone as a completed manuscript round.
+- For paper-facing final drafts, maintain a non-empty `references.bib` with real citation keys instead of TODO placeholders.
+- Keep paper-facing LaTeX free of absolute local paths, shell logs, rerun ids, and workflow-only provenance.
+- Replace raw engineering notation such as `+/-` with proper LaTeX formatting such as `\pm`.
+- If the current paper contains experimental claims, materialize real LaTeX table assets instead of leaving all results in prose:
+  - `<deliverables_root>/paper/tables/main-results.tex`
+  - `<deliverables_root>/paper/tables/ablations.tex`
+- If the current paper contains method or experiments claims, materialize figure placeholders with captions, labels, and explicit figure intent:
+  - `<deliverables_root>/paper/figures/method-overview.tex`
+  - `<deliverables_root>/paper/figures/results-overview.tex`
+- Table assets must use paper-facing LaTeX structure with `booktabs`, caption, label, and consistent precision.
+- Figure placeholders must explain what the final figure should show and why the reader needs it.
+- Keep `.lab/writing/plan.md` synchronized with the current table plan, figure plan, citation plan, and section-to-asset map whenever manuscript assets change.
+- Run `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before accepting a final-draft or export round.
+- If the manuscript validator fails, keep editing and asset generation until it passes; do not stop at prose-only completion.
+- Run a LaTeX compile smoke test when a local LaTeX toolchain is available; if not available, record the missing verification in the write iteration artifact.
 - Record what changed and why in a write-iteration artifact.
 - Return paragraph-level roles for the revised prose when drafting.
 - Run the five-dimension self-review checklist before accepting a round.
@@ -85,7 +116,12 @@ Run these on every round:
 - `.lab/writing/plan.md`
 - `.lab/writing/iterations/<n>.md`
 - `<deliverables_root>/paper/main.tex`
+- `<deliverables_root>/paper/references.bib`
 - `<deliverables_root>/paper/sections/<section>.tex`
+- `<deliverables_root>/paper/tables/main-results.tex`
+- `<deliverables_root>/paper/tables/ablations.tex`
+- `<deliverables_root>/paper/figures/method-overview.tex`
+- `<deliverables_root>/paper/figures/results-overview.tex`
 
 ## Stop Conditions
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.25",
+  "version": "0.1.27",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",